diff --git a/.idea/.gitignore b/.idea/.gitignore
new file mode 100644
index 0000000000000000000000000000000000000000..13566b81b018ad684f3a35fee301741b2734c8f4
--- /dev/null
+++ b/.idea/.gitignore
@@ -0,0 +1,8 @@
+# Default ignored files
+/shelf/
+/workspace.xml
+# Editor-based HTTP Client requests
+/httpRequests/
+# Datasource local storage ignored files
+/dataSources/
+/dataSources.local.xml
diff --git a/.idea/Forecast4Muses.iml b/.idea/Forecast4Muses.iml
new file mode 100644
index 0000000000000000000000000000000000000000..269e1a84d959a26b80a7f728e00800bc44277d27
--- /dev/null
+++ b/.idea/Forecast4Muses.iml
@@ -0,0 +1,14 @@
+
+
+
+
+
+
+
+
+
+
+
+
+
+
\ No newline at end of file
diff --git a/.idea/deployment.xml b/.idea/deployment.xml
new file mode 100644
index 0000000000000000000000000000000000000000..f4d6e87b2bc20994698b49ef1bc8b0089aaf2d0d
--- /dev/null
+++ b/.idea/deployment.xml
@@ -0,0 +1,21 @@
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
\ No newline at end of file
diff --git a/.idea/inspectionProfiles/Project_Default.xml b/.idea/inspectionProfiles/Project_Default.xml
new file mode 100644
index 0000000000000000000000000000000000000000..9e1663500ff92ff5a2ab2e8f2a2abec29acc3096
--- /dev/null
+++ b/.idea/inspectionProfiles/Project_Default.xml
@@ -0,0 +1,75 @@
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
\ No newline at end of file
diff --git a/.idea/inspectionProfiles/profiles_settings.xml b/.idea/inspectionProfiles/profiles_settings.xml
new file mode 100644
index 0000000000000000000000000000000000000000..105ce2da2d6447d11dfe32bfb846c3d5b199fc99
--- /dev/null
+++ b/.idea/inspectionProfiles/profiles_settings.xml
@@ -0,0 +1,6 @@
+
+
+
+
+
+
\ No newline at end of file
diff --git a/.idea/misc.xml b/.idea/misc.xml
new file mode 100644
index 0000000000000000000000000000000000000000..af76f0a1c477c472913e9a914334df79a54619e9
--- /dev/null
+++ b/.idea/misc.xml
@@ -0,0 +1,4 @@
+
+
+
+
\ No newline at end of file
diff --git a/.idea/modules.xml b/.idea/modules.xml
new file mode 100644
index 0000000000000000000000000000000000000000..e8d711dca622db8318b3d955fa1d28ff1ad3553b
--- /dev/null
+++ b/.idea/modules.xml
@@ -0,0 +1,8 @@
+
+
+
+
+
+
+
+
\ No newline at end of file
diff --git a/.idea/vcs.xml b/.idea/vcs.xml
new file mode 100644
index 0000000000000000000000000000000000000000..35eb1ddfbbc029bcab630581847471d7f238ec53
--- /dev/null
+++ b/.idea/vcs.xml
@@ -0,0 +1,6 @@
+
+
+
+
+
+
\ No newline at end of file
diff --git a/Model/Model6/Model6_0_ClothesDetection/__init__.py b/Model/Model6/Model6_0_ClothesDetection/__init__.py
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/Model/Model6/Model6_0_ClothesDetection/mmyolo/configs/__init__.py b/Model/Model6/Model6_0_ClothesDetection/mmyolo/configs/__init__.py
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/Model/Model6/Model6_0_ClothesDetection/mmyolo/configs/_base_/__init__.py b/Model/Model6/Model6_0_ClothesDetection/mmyolo/configs/_base_/__init__.py
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/Model/Model6/Model6_0_ClothesDetection/mmyolo/configs/_base_/default_runtime.py b/Model/Model6/Model6_0_ClothesDetection/mmyolo/configs/_base_/default_runtime.py
new file mode 100644
index 0000000000000000000000000000000000000000..2f0db2e3d303e6d245c36610aab5b6fcb3193480
--- /dev/null
+++ b/Model/Model6/Model6_0_ClothesDetection/mmyolo/configs/_base_/default_runtime.py
@@ -0,0 +1,34 @@
+default_scope = 'mmyolo'
+
+default_hooks = dict(
+ timer=dict(type='IterTimerHook'),
+ logger=dict(type='LoggerHook', interval=50),
+ param_scheduler=dict(type='ParamSchedulerHook'),
+ checkpoint=dict(type='CheckpointHook', interval=1),
+ sampler_seed=dict(type='DistSamplerSeedHook'),
+ visualization=dict(type='mmdet.DetVisualizationHook'))
+
+env_cfg = dict(
+ cudnn_benchmark=False,
+ mp_cfg=dict(mp_start_method='fork', opencv_num_threads=0),
+ dist_cfg=dict(backend='nccl'),
+)
+
+vis_backends = [dict(type='LocalVisBackend')]
+visualizer = dict(
+ type='mmdet.DetLocalVisualizer',
+ vis_backends=vis_backends,
+ name='visualizer')
+log_processor = dict(type='LogProcessor', window_size=50, by_epoch=True)
+
+log_level = 'INFO'
+load_from = None
+resume = False
+
+# file_client_args = dict(
+# backend='petrel',
+# path_mapping=dict({
+# './data/': 's3://openmmlab/datasets/detection/',
+# 'data/': 's3://openmmlab/datasets/detection/'
+# }))
+file_client_args = dict(backend='disk')
diff --git a/Model/Model6/Model6_0_ClothesDetection/mmyolo/configs/_base_/det_p5_tta.py b/Model/Model6/Model6_0_ClothesDetection/mmyolo/configs/_base_/det_p5_tta.py
new file mode 100644
index 0000000000000000000000000000000000000000..cbbaf2e68ac7a0707f8fd40a0adfcb8de7189e97
--- /dev/null
+++ b/Model/Model6/Model6_0_ClothesDetection/mmyolo/configs/_base_/det_p5_tta.py
@@ -0,0 +1,57 @@
+# TODO: Need to solve the problem of multiple file_client_args parameters
+# _file_client_args = dict(
+# backend='petrel',
+# path_mapping=dict({
+# './data/': 's3://openmmlab/datasets/detection/',
+# 'data/': 's3://openmmlab/datasets/detection/'
+# }))
+_file_client_args = dict(backend='disk')
+
+tta_model = dict(
+ type='mmdet.DetTTAModel',
+ tta_cfg=dict(nms=dict(type='nms', iou_threshold=0.65), max_per_img=300))
+
+img_scales = [(640, 640), (320, 320), (960, 960)]
+
+# LoadImageFromFile
+# / | \
+# (RatioResize,LetterResize) (RatioResize,LetterResize) (RatioResize,LetterResize) # noqa
+# / \ / \ / \
+# RandomFlip RandomFlip RandomFlip RandomFlip RandomFlip RandomFlip # noqa
+# | | | | | |
+# LoadAnn LoadAnn LoadAnn LoadAnn LoadAnn LoadAnn
+# | | | | | |
+# PackDetIn PackDetIn PackDetIn PackDetIn PackDetIn PackDetIn # noqa
+
+_multiscale_resize_transforms = [
+ dict(
+ type='Compose',
+ transforms=[
+ dict(type='YOLOv5KeepRatioResize', scale=s),
+ dict(
+ type='LetterResize',
+ scale=s,
+ allow_scale_up=False,
+ pad_val=dict(img=114))
+ ]) for s in img_scales
+]
+
+tta_pipeline = [
+ dict(type='LoadImageFromFile', file_client_args=_file_client_args),
+ dict(
+ type='TestTimeAug',
+ transforms=[
+ _multiscale_resize_transforms,
+ [
+ dict(type='mmdet.RandomFlip', prob=1.),
+ dict(type='mmdet.RandomFlip', prob=0.)
+ ], [dict(type='mmdet.LoadAnnotations', with_bbox=True)],
+ [
+ dict(
+ type='mmdet.PackDetInputs',
+ meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
+ 'scale_factor', 'pad_param', 'flip',
+ 'flip_direction'))
+ ]
+ ])
+]
diff --git a/Model/Model6/Model6_0_ClothesDetection/mmyolo/configs/custom_dataset/.ipynb_checkpoints/__init__.py b/Model/Model6/Model6_0_ClothesDetection/mmyolo/configs/custom_dataset/.ipynb_checkpoints/__init__.py
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/Model/Model6/Model6_0_ClothesDetection/mmyolo/configs/custom_dataset/.ipynb_checkpoints/yolov5_s-v61_syncbn_fast_1xb32-100e_cat-checkpoint.py b/Model/Model6/Model6_0_ClothesDetection/mmyolo/configs/custom_dataset/.ipynb_checkpoints/yolov5_s-v61_syncbn_fast_1xb32-100e_cat-checkpoint.py
new file mode 100644
index 0000000000000000000000000000000000000000..c24cab973dbbededbd98f0d42444e689d7158695
--- /dev/null
+++ b/Model/Model6/Model6_0_ClothesDetection/mmyolo/configs/custom_dataset/.ipynb_checkpoints/yolov5_s-v61_syncbn_fast_1xb32-100e_cat-checkpoint.py
@@ -0,0 +1,135 @@
+_base_ = '../yolov5/yolov5_s-v61_syncbn_fast_8xb16-300e_coco.py'
+
+max_epochs = 100 # 训练的最大 epoch
+data_root = './data-df2/' # 数据集目录的绝对路径
+# data_root = '/root/workspace/mmyolo/data/cat/' # Docker 容器里面数据集目录的绝对路径
+
+# 结果保存的路径，可以省略，省略保存的文件名位于 work_dirs 下 config 同名的文件夹中
+# 如果某个 config 只是修改了部分参数，修改这个变量就可以将新的训练文件保存到其他地方
+work_dir = './work_dirs/yolov5_s_df2'
+
+# load_from 可以指定本地路径或者 URL，设置了 URL 会自动进行下载，因为上面已经下载过，我们这里设置本地路径
+# 因为本教程是在 cat 数据集上微调，故这里需要使用 `load_from` 来加载 MMYOLO 中的预训练模型，这样可以在加快收敛速度的同时保证精度
+# load_from = './work_dirs/yolov5_s-v61_syncbn_fast_8xb16-300e_coco_20220918_084700-86e02187.pth' # noqa
+
+# 根据自己的 GPU 情况，修改 batch size，YOLOv5-s 默认为 8卡 x 16bs
+train_batch_size_per_gpu = 32
+train_num_workers = 4 # 推荐使用 train_num_workers = nGPU x 4
+
+save_epoch_intervals = 2 # 每 interval 轮迭代进行一次保存一次权重
+
+# 根据自己的 GPU 情况，修改 base_lr，修改的比例是 base_lr_default * (your_bs / default_bs)
+base_lr = _base_.base_lr / 4
+
+anchors = [ # 此处已经根据数据集特点更新了 anchor，关于 anchor 的生成，后面小节会讲解
+ [(68, 69), (154, 91), (143, 162)], # P3/8
+ [(242, 160), (189, 287), (391, 207)], # P4/16
+ [(353, 337), (539, 341), (443, 432)] # P5/32
+]
+
+class_name = ('short_sleeved_shirt',
+ 'long_sleeved_shirt',
+ 'short_sleeved_outwear',
+ 'long_sleeved_outwear',
+ 'vest',
+ 'sling',
+ 'shorts',
+ 'trousers',
+ 'skirt',
+ 'short_sleeved_dress',
+ 'long_sleeved_dress',
+ 'vest_dress',
+ 'sling_dress') # 根据 class_with_id.txt 类别信息，设置 class_name
+
+num_classes = len(class_name)
+metainfo = dict(
+ classes=class_name,
+ palette=[(255, 0, 0),
+ (255, 128, 0),
+ (255, 255, 0),
+ (128, 255, 0),
+ (0, 255, 0),
+ (0, 255, 128),
+ (0, 255, 255),
+ (0, 128, 255),
+ (0, 0, 255),
+ (127, 0, 255),
+ (255, 0, 255),
+ (255, 0, 127),
+ (128, 128, 128)] # 画图时候的颜色，随便设置即可
+)
+
+train_cfg = dict(
+ max_epochs=max_epochs,
+ val_begin=20, # 第几个 epoch 后验证，这里设置 20 是因为前 20 个 epoch 精度不高，测试意义不大，故跳过
+ val_interval=save_epoch_intervals # 每 val_interval 轮迭代进行一次测试评估
+ # dynamic_intervals=[(max_epochs-_base_.num_last_epochs, 1)]
+)
+
+model = dict(
+ bbox_head=dict(
+ head_module=dict(num_classes=num_classes),
+ prior_generator=dict(base_sizes=anchors),
+
+ # loss_cls 会根据 num_classes 动态调整，但是 num_classes = 1 的时候，loss_cls 恒为 0
+ loss_cls=dict(loss_weight=0.5 *
+ (num_classes / 80 * 3 / _base_.num_det_layers))))
+
+train_dataloader = dict(
+ batch_size=train_batch_size_per_gpu,
+ num_workers=train_num_workers,
+ dataset=dict(
+ _delete_=True,
+ type='RepeatDataset',
+ # 数据量太少的话，可以使用 RepeatDataset ，在每个 epoch 内重复当前数据集 n 次，这里设置 5 是重复 5 次
+ times=2,
+ dataset=dict(
+ type=_base_.dataset_type,
+ data_root=data_root,
+ metainfo=metainfo,
+ ann_file='annotations/trainval.json',
+ data_prefix=dict(img='smaller-dataset/'),
+ filter_cfg=dict(filter_empty_gt=False, min_size=32),
+ pipeline=_base_.train_pipeline)))
+
+val_dataloader = dict(
+ dataset=dict(
+ metainfo=metainfo,
+ data_root=data_root,
+ ann_file='annotations/trainval.json',
+ data_prefix=dict(img='smaller-dataset/')))
+
+test_dataloader = val_dataloader
+
+val_evaluator = dict(ann_file=data_root + 'annotations/trainval.json')
+test_evaluator = val_evaluator
+
+optim_wrapper = dict(optimizer=dict(lr=base_lr))
+
+default_hooks = dict(
+ # 设置间隔多少个 epoch 保存模型，以及保存模型最多几个，`save_best` 是另外保存最佳模型（推荐）
+ checkpoint=dict(
+ type='CheckpointHook',
+ interval=save_epoch_intervals,
+ max_keep_ckpts=5,
+ save_best='auto'),
+ param_scheduler=dict(max_epochs=max_epochs, warmup_mim_iter=10),
+ # logger 输出的间隔
+ logger=dict(type='LoggerHook', interval=10))
+
+# custom_hooks = [
+# dict(
+# type="EMAHook",
+# ema_type="ExpMomentumEMA",
+# momentum=0.0001,
+# update_buffers=True,
+# strict_load=False,
+# priority=49),
+# dict(
+# type="mmdet.PipelineSwitchHook",
+# switch_epoch=max_epochs-max_epochs-_base_.num_last_epochs,
+# switch_pipeline=_base_.train_pipeline_stage2
+# )
+# ]
+
+visualizer = dict(vis_backends=[dict(type='LocalVisBackend'), dict(type='WandbVisBackend')])
\ No newline at end of file
diff --git a/Model/Model6/Model6_0_ClothesDetection/mmyolo/configs/custom_dataset/.ipynb_checkpoints/yolov6_s_fast-checkpoint.py b/Model/Model6/Model6_0_ClothesDetection/mmyolo/configs/custom_dataset/.ipynb_checkpoints/yolov6_s_fast-checkpoint.py
new file mode 100644
index 0000000000000000000000000000000000000000..5e04123bb59ed5b29bbea891f3456a81a5ed4a9f
--- /dev/null
+++ b/Model/Model6/Model6_0_ClothesDetection/mmyolo/configs/custom_dataset/.ipynb_checkpoints/yolov6_s_fast-checkpoint.py
@@ -0,0 +1,124 @@
+_base_ = '../yolov6/yolov6_s_syncbn_fast_8xb32-400e_coco.py'
+
+max_epochs = 100 # 训练的最大 epoch
+data_root = './data-df2/' # 数据集目录的绝对路径
+
+# 结果保存的路径，可以省略，省略保存的文件名位于 work_dirs 下 config 同名的文件夹中
+# 如果某个 config 只是修改了部分参数，修改这个变量就可以将新的训练文件保存到其他地方
+work_dir = './work_dirs/yolov6_s_df2'
+
+# 根据自己的 GPU 情况，修改 batch size，YOLOv5-s 默认为 8卡 x 16bs
+train_batch_size_per_gpu = 32
+train_num_workers = 4 # 推荐使用 train_num_workers = nGPU x 4
+
+save_epoch_intervals = 2 # 每 interval 轮迭代进行一次保存一次权重
+
+# 根据自己的 GPU 情况，修改 base_lr，修改的比例是 base_lr_default * (your_bs / default_bs)
+base_lr = _base_.base_lr / 4
+
+class_name = ('short_sleeved_shirt',
+ 'long_sleeved_shirt',
+ 'short_sleeved_outwear',
+ 'long_sleeved_outwear',
+ 'vest',
+ 'sling',
+ 'shorts',
+ 'trousers',
+ 'skirt',
+ 'short_sleeved_dress',
+ 'long_sleeved_dress',
+ 'vest_dress',
+ 'sling_dress') # 根据 class_with_id.txt 类别信息，设置 class_name
+
+num_classes = len(class_name)
+metainfo = dict(
+ classes=class_name,
+ palette=[(255, 0, 0),
+ (255, 128, 0),
+ (255, 255, 0),
+ (128, 255, 0),
+ (0, 255, 0),
+ (0, 255, 128),
+ (0, 255, 255),
+ (0, 128, 255),
+ (0, 0, 255),
+ (127, 0, 255),
+ (255, 0, 255),
+ (255, 0, 127),
+ (128, 128, 128)] # 画图时候的颜色，随便设置即可
+)
+
+train_cfg = dict(
+ max_epochs=max_epochs,
+ val_begin=20, # 第几个 epoch 后验证，这里设置 20 是因为前 20 个 epoch 精度不高，测试意义不大，故跳过
+ val_interval=save_epoch_intervals, # 每 val_interval 轮迭代进行一次测试评估
+ dynamic_intervals=[(max_epochs-_base_.num_last_epochs, 1)]
+)
+
+model = dict(
+ bbox_head=dict(
+ head_module=dict(num_classes=num_classes)),
+ train_cfg=dict(
+ initial_assigner=dict(num_classes=num_classes),
+ assigner=dict(num_classes=num_classes)
+ )
+)
+
+train_dataloader = dict(
+ batch_size=train_batch_size_per_gpu,
+ num_workers=train_num_workers,
+ dataset=dict(
+ _delete_=True,
+ type='RepeatDataset',
+ # 数据量太少的话，可以使用 RepeatDataset ，在每个 epoch 内重复当前数据集 n 次，这里设置 5 是重复 5 次
+ times=2,
+ dataset=dict(
+ type=_base_.dataset_type,
+ data_root=data_root,
+ metainfo=metainfo,
+ ann_file='annotations/trainval.json',
+ data_prefix=dict(img='smaller-dataset/'),
+ filter_cfg=dict(filter_empty_gt=False, min_size=32),
+ pipeline=_base_.train_pipeline)))
+
+val_dataloader = dict(
+ dataset=dict(
+ metainfo=metainfo,
+ data_root=data_root,
+ ann_file='annotations/trainval.json',
+ data_prefix=dict(img='smaller-dataset/')))
+
+test_dataloader = val_dataloader
+
+val_evaluator = dict(ann_file=data_root + 'annotations/trainval.json')
+test_evaluator = val_evaluator
+
+optim_wrapper = dict(optimizer=dict(lr=base_lr))
+
+default_hooks = dict(
+ # 设置间隔多少个 epoch 保存模型，以及保存模型最多几个，`save_best` 是另外保存最佳模型（推荐）
+ checkpoint=dict(
+ type='CheckpointHook',
+ interval=save_epoch_intervals,
+ max_keep_ckpts=5,
+ save_best='auto'),
+ param_scheduler=dict(max_epochs=max_epochs),
+ # logger 输出的间隔
+ logger=dict(type='LoggerHook', interval=10))
+
+custom_hooks = [
+ dict(
+ type="EMAHook",
+ ema_type="ExpMomentumEMA",
+ momentum=0.0001,
+ update_buffers=True,
+ strict_load=False,
+ priority=49),
+ dict(
+ type="mmdet.PipelineSwitchHook",
+ switch_epoch=max_epochs-max_epochs-_base_.num_last_epochs,
+ switch_pipeline=_base_.train_pipeline_stage2
+ )
+]
+
+visualizer = dict(vis_backends=[dict(type='LocalVisBackend'), dict(type='WandbVisBackend')])
\ No newline at end of file
diff --git a/Model/Model6/Model6_0_ClothesDetection/mmyolo/configs/custom_dataset/[A]dataset_split.sh b/Model/Model6/Model6_0_ClothesDetection/mmyolo/configs/custom_dataset/[A]dataset_split.sh
new file mode 100644
index 0000000000000000000000000000000000000000..84c460a5e635a5cbe180760cc56b2f92664be191
--- /dev/null
+++ b/Model/Model6/Model6_0_ClothesDetection/mmyolo/configs/custom_dataset/[A]dataset_split.sh
@@ -0,0 +1,5 @@
+cd ..
+python tools/misc/coco_split.py --json data-df2/deepfashion2-smaller-dataset.json \
+ --out-dir data-df2/annotations/ \
+ --ratios 8 2 \
+ --shuffle --seed 10
diff --git a/Model/Model6/Model6_0_ClothesDetection/mmyolo/configs/custom_dataset/__init__.py b/Model/Model6/Model6_0_ClothesDetection/mmyolo/configs/custom_dataset/__init__.py
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/Model/Model6/Model6_0_ClothesDetection/mmyolo/configs/custom_dataset/yolov5_s-v61_syncbn_fast_1xb32-100e_cat.py b/Model/Model6/Model6_0_ClothesDetection/mmyolo/configs/custom_dataset/yolov5_s-v61_syncbn_fast_1xb32-100e_cat.py
new file mode 100644
index 0000000000000000000000000000000000000000..c24cab973dbbededbd98f0d42444e689d7158695
--- /dev/null
+++ b/Model/Model6/Model6_0_ClothesDetection/mmyolo/configs/custom_dataset/yolov5_s-v61_syncbn_fast_1xb32-100e_cat.py
@@ -0,0 +1,135 @@
+_base_ = '../yolov5/yolov5_s-v61_syncbn_fast_8xb16-300e_coco.py'
+
+max_epochs = 100 # 训练的最大 epoch
+data_root = './data-df2/' # 数据集目录的绝对路径
+# data_root = '/root/workspace/mmyolo/data/cat/' # Docker 容器里面数据集目录的绝对路径
+
+# 结果保存的路径，可以省略，省略保存的文件名位于 work_dirs 下 config 同名的文件夹中
+# 如果某个 config 只是修改了部分参数，修改这个变量就可以将新的训练文件保存到其他地方
+work_dir = './work_dirs/yolov5_s_df2'
+
+# load_from 可以指定本地路径或者 URL，设置了 URL 会自动进行下载，因为上面已经下载过，我们这里设置本地路径
+# 因为本教程是在 cat 数据集上微调，故这里需要使用 `load_from` 来加载 MMYOLO 中的预训练模型，这样可以在加快收敛速度的同时保证精度
+# load_from = './work_dirs/yolov5_s-v61_syncbn_fast_8xb16-300e_coco_20220918_084700-86e02187.pth' # noqa
+
+# 根据自己的 GPU 情况，修改 batch size，YOLOv5-s 默认为 8卡 x 16bs
+train_batch_size_per_gpu = 32
+train_num_workers = 4 # 推荐使用 train_num_workers = nGPU x 4
+
+save_epoch_intervals = 2 # 每 interval 轮迭代进行一次保存一次权重
+
+# 根据自己的 GPU 情况，修改 base_lr，修改的比例是 base_lr_default * (your_bs / default_bs)
+base_lr = _base_.base_lr / 4
+
+anchors = [ # 此处已经根据数据集特点更新了 anchor，关于 anchor 的生成，后面小节会讲解
+ [(68, 69), (154, 91), (143, 162)], # P3/8
+ [(242, 160), (189, 287), (391, 207)], # P4/16
+ [(353, 337), (539, 341), (443, 432)] # P5/32
+]
+
+class_name = ('short_sleeved_shirt',
+ 'long_sleeved_shirt',
+ 'short_sleeved_outwear',
+ 'long_sleeved_outwear',
+ 'vest',
+ 'sling',
+ 'shorts',
+ 'trousers',
+ 'skirt',
+ 'short_sleeved_dress',
+ 'long_sleeved_dress',
+ 'vest_dress',
+ 'sling_dress') # 根据 class_with_id.txt 类别信息，设置 class_name
+
+num_classes = len(class_name)
+metainfo = dict(
+ classes=class_name,
+ palette=[(255, 0, 0),
+ (255, 128, 0),
+ (255, 255, 0),
+ (128, 255, 0),
+ (0, 255, 0),
+ (0, 255, 128),
+ (0, 255, 255),
+ (0, 128, 255),
+ (0, 0, 255),
+ (127, 0, 255),
+ (255, 0, 255),
+ (255, 0, 127),
+ (128, 128, 128)] # 画图时候的颜色，随便设置即可
+)
+
+train_cfg = dict(
+ max_epochs=max_epochs,
+ val_begin=20, # 第几个 epoch 后验证，这里设置 20 是因为前 20 个 epoch 精度不高，测试意义不大，故跳过
+ val_interval=save_epoch_intervals # 每 val_interval 轮迭代进行一次测试评估
+ # dynamic_intervals=[(max_epochs-_base_.num_last_epochs, 1)]
+)
+
+model = dict(
+ bbox_head=dict(
+ head_module=dict(num_classes=num_classes),
+ prior_generator=dict(base_sizes=anchors),
+
+ # loss_cls 会根据 num_classes 动态调整，但是 num_classes = 1 的时候，loss_cls 恒为 0
+ loss_cls=dict(loss_weight=0.5 *
+ (num_classes / 80 * 3 / _base_.num_det_layers))))
+
+train_dataloader = dict(
+ batch_size=train_batch_size_per_gpu,
+ num_workers=train_num_workers,
+ dataset=dict(
+ _delete_=True,
+ type='RepeatDataset',
+ # 数据量太少的话，可以使用 RepeatDataset ，在每个 epoch 内重复当前数据集 n 次，这里设置 5 是重复 5 次
+ times=2,
+ dataset=dict(
+ type=_base_.dataset_type,
+ data_root=data_root,
+ metainfo=metainfo,
+ ann_file='annotations/trainval.json',
+ data_prefix=dict(img='smaller-dataset/'),
+ filter_cfg=dict(filter_empty_gt=False, min_size=32),
+ pipeline=_base_.train_pipeline)))
+
+val_dataloader = dict(
+ dataset=dict(
+ metainfo=metainfo,
+ data_root=data_root,
+ ann_file='annotations/trainval.json',
+ data_prefix=dict(img='smaller-dataset/')))
+
+test_dataloader = val_dataloader
+
+val_evaluator = dict(ann_file=data_root + 'annotations/trainval.json')
+test_evaluator = val_evaluator
+
+optim_wrapper = dict(optimizer=dict(lr=base_lr))
+
+default_hooks = dict(
+ # 设置间隔多少个 epoch 保存模型，以及保存模型最多几个，`save_best` 是另外保存最佳模型（推荐）
+ checkpoint=dict(
+ type='CheckpointHook',
+ interval=save_epoch_intervals,
+ max_keep_ckpts=5,
+ save_best='auto'),
+ param_scheduler=dict(max_epochs=max_epochs, warmup_mim_iter=10),
+ # logger 输出的间隔
+ logger=dict(type='LoggerHook', interval=10))
+
+# custom_hooks = [
+# dict(
+# type="EMAHook",
+# ema_type="ExpMomentumEMA",
+# momentum=0.0001,
+# update_buffers=True,
+# strict_load=False,
+# priority=49),
+# dict(
+# type="mmdet.PipelineSwitchHook",
+# switch_epoch=max_epochs-max_epochs-_base_.num_last_epochs,
+# switch_pipeline=_base_.train_pipeline_stage2
+# )
+# ]
+
+visualizer = dict(vis_backends=[dict(type='LocalVisBackend'), dict(type='WandbVisBackend')])
\ No newline at end of file
diff --git a/Model/Model6/Model6_0_ClothesDetection/mmyolo/configs/custom_dataset/yolov6_s_fast.py b/Model/Model6/Model6_0_ClothesDetection/mmyolo/configs/custom_dataset/yolov6_s_fast.py
new file mode 100644
index 0000000000000000000000000000000000000000..89381edf04db13b4456ce2f27f402e96ca7042e3
--- /dev/null
+++ b/Model/Model6/Model6_0_ClothesDetection/mmyolo/configs/custom_dataset/yolov6_s_fast.py
@@ -0,0 +1,124 @@
+_base_ = '../yolov6/yolov6_s_syncbn_fast_8xb32-400e_coco.py'
+
+max_epochs = 100 # 训练的最大 epoch
+data_root = './data-df2/' # 数据集目录的绝对路径
+
+# 结果保存的路径，可以省略，省略保存的文件名位于 work_dirs 下 config 同名的文件夹中
+# 如果某个 config 只是修改了部分参数，修改这个变量就可以将新的训练文件保存到其他地方
+work_dir = './work_dirs/yolov6_s_df2'
+
+# 根据自己的 GPU 情况，修改 batch size，YOLOv5-s 默认为 8卡 x 16bs
+train_batch_size_per_gpu = 32
+train_num_workers = 4 # 推荐使用 train_num_workers = nGPU x 4
+
+save_epoch_intervals = 2
+
+# 根据自己的 GPU 情况，修改 base_lr，修改的比例是 base_lr_default * (your_bs / default_bs)
+base_lr = _base_.base_lr / 4
+
+class_name = ('short_sleeved_shirt',
+ 'long_sleeved_shirt',
+ 'short_sleeved_outwear',
+ 'long_sleeved_outwear',
+ 'vest',
+ 'sling',
+ 'shorts',
+ 'trousers',
+ 'skirt',
+ 'short_sleeved_dress',
+ 'long_sleeved_dress',
+ 'vest_dress',
+ 'sling_dress') # 根据 class_with_id.txt 类别信息，设置 class_name
+
+num_classes = len(class_name)
+metainfo = dict(
+ classes=class_name,
+ palette=[(255, 0, 0),
+ (255, 128, 0),
+ (255, 255, 0),
+ (128, 255, 0),
+ (0, 255, 0),
+ (0, 255, 128),
+ (0, 255, 255),
+ (0, 128, 255),
+ (0, 0, 255),
+ (127, 0, 255),
+ (255, 0, 255),
+ (255, 0, 127),
+ (128, 128, 128)] # 画图时候的颜色，随便设置即可
+)
+
+train_cfg = dict(
+ max_epochs=max_epochs,
+ val_begin=20, # 第几个 epoch 后验证，这里设置 20 是因为前 20 个 epoch 精度不高，测试意义不大，故跳过
+ val_interval=save_epoch_intervals, # 每 val_interval 轮迭代进行一次测试评估
+ dynamic_intervals=[(max_epochs-_base_.num_last_epochs, 1)]
+)
+
+model = dict(
+ bbox_head=dict(
+ head_module=dict(num_classes=num_classes)),
+ train_cfg=dict(
+ initial_assigner=dict(num_classes=num_classes),
+ assigner=dict(num_classes=num_classes)
+ )
+)
+
+train_dataloader = dict(
+ batch_size=train_batch_size_per_gpu,
+ num_workers=train_num_workers,
+ dataset=dict(
+ _delete_=True,
+ type='RepeatDataset',
+ # 数据量太少的话，可以使用 RepeatDataset ，在每个 epoch 内重复当前数据集 n 次，这里设置 5 是重复 5 次
+ times=2,
+ dataset=dict(
+ type=_base_.dataset_type,
+ data_root=data_root,
+ metainfo=metainfo,
+ ann_file='annotations/trainval.json',
+ data_prefix=dict(img='smaller-dataset/'),
+ filter_cfg=dict(filter_empty_gt=False, min_size=32),
+ pipeline=_base_.train_pipeline)))
+
+val_dataloader = dict(
+ dataset=dict(
+ metainfo=metainfo,
+ data_root=data_root,
+ ann_file='annotations/trainval.json',
+ data_prefix=dict(img='smaller-dataset/')))
+
+test_dataloader = val_dataloader
+
+val_evaluator = dict(ann_file=data_root + 'annotations/trainval.json')
+test_evaluator = val_evaluator
+
+optim_wrapper = dict(optimizer=dict(lr=base_lr))
+
+default_hooks = dict(
+ # 设置间隔多少个 epoch 保存模型，以及保存模型最多几个，`save_best` 是另外保存最佳模型（推荐）
+ checkpoint=dict(
+ type='CheckpointHook',
+ interval=save_epoch_intervals,
+ max_keep_ckpts=5,
+ save_best='auto'),
+ param_scheduler=dict(max_epochs=max_epochs),
+ # logger 输出的间隔
+ logger=dict(type='LoggerHook', interval=10))
+
+custom_hooks = [
+ dict(
+ type="EMAHook",
+ ema_type="ExpMomentumEMA",
+ momentum=0.0001,
+ update_buffers=True,
+ strict_load=False,
+ priority=49),
+ dict(
+ type="mmdet.PipelineSwitchHook",
+ switch_epoch=max_epochs-max_epochs-_base_.num_last_epochs,
+ switch_pipeline=_base_.train_pipeline_stage2
+ )
+]
+
+visualizer = dict(vis_backends=[dict(type='LocalVisBackend'), dict(type='WandbVisBackend')])
\ No newline at end of file
diff --git a/Model/Model6/Model6_0_ClothesDetection/mmyolo/configs/custom_dataset/yolov7_l_syncbn_fast_6x16b-100e_coco.py b/Model/Model6/Model6_0_ClothesDetection/mmyolo/configs/custom_dataset/yolov7_l_syncbn_fast_6x16b-100e_coco.py
new file mode 100644
index 0000000000000000000000000000000000000000..a005c28eb78d101354650a20b1ff7212e24d0743
--- /dev/null
+++ b/Model/Model6/Model6_0_ClothesDetection/mmyolo/configs/custom_dataset/yolov7_l_syncbn_fast_6x16b-100e_coco.py
@@ -0,0 +1,489 @@
+_base_ = ['../_base_/default_runtime.py', '../_base_/det_p5_tta.py']
+
+data_root = './data-df2/'
+train_ann_file = 'annotations/train.json'
+train_data_prefix = 'smaller-dataset/'
+val_ann_file = 'annotations/val.json'
+val_data_prefix = 'smaller-dataset/'
+test_ann_file = 'annotations/test.json'
+test_data_prefix = 'smaller-dataset/'
+# num_classes = 13
+train_batch_size_per_gpu = 32
+train_num_workers = 4
+persistent_workers = True
+
+vis_backends = [
+ dict(type='LocalVisBackend'),
+]
+visualizer = dict(
+ type='mmdet.DetLocalVisualizer',
+ vis_backends=[
+ dict(type='LocalVisBackend'),
+ # dict(type='WandbVisBackend'),
+ dict(type='TensorboardVisBackend')
+ ],
+ name='visualizer')
+log_processor = dict(type='LogProcessor', window_size=50, by_epoch=True)
+log_level = 'INFO'
+load_from = None
+resume = False
+
+anchors = [
+ [(12, 16), (19, 36), (40, 28)], # P3/8
+ [(36, 75), (76, 55), (72, 146)], # P4/16
+ [(142, 110), (192, 243), (459, 401)] # P5/32
+]
+
+base_lr = 0.01
+max_epochs = 100
+
+num_epoch_stage2 = 10 # The last 10 epochs switch evaluation interval
+val_interval_stage2 = 1
+
+model_test_cfg = dict(
+ multi_label=True,
+ nms_pre=30000,
+ score_thr=0.001,
+ nms=dict(type='nms', iou_threshold=0.65),
+ max_per_img=300)
+
+img_scale = (640, 640)
+dataset_type = 'YOLOv5CocoDataset'
+classes=('short_sleeved_shirt', 'long_sleeved_shirt',
+ 'short_sleeved_outwear', 'long_sleeved_outwear',
+ 'vest', 'sling', 'shorts', 'trousers', 'skirt',
+ 'short_sleeved_dress', 'long_sleeved_dress',
+ 'vest_dress', 'sling_dress')
+num_classes = len(classes)
+palette=[(255, 0, 0), (255, 128, 0), (255, 255, 0),
+ (128, 255, 0), (0, 255, 0), (0, 255, 128),
+ (0, 255, 255), (0, 128, 255), (0, 0, 255),
+ (127, 0, 255), (255, 0, 255), (255, 0, 127),
+ (128, 128, 128)]
+metainfo = dict(
+ classes=classes,
+ palette=palette
+)
+val_batch_size_per_gpu = 1
+val_num_workers = 2
+batch_shapes_cfg = dict(
+ type='BatchShapePolicy',
+ batch_size=val_batch_size_per_gpu,
+ img_size=img_scale[0],
+ size_divisor=32,
+ extra_pad_ratio=0.5)
+strides = [8, 16, 32] # Strides of multi-scale prior box
+num_det_layers = 3
+norm_cfg = dict(type='BN', momentum=0.03, eps=0.001)
+
+# Data augmentation
+max_translate_ratio = 0.2 # YOLOv5RandomAffine
+scaling_ratio_range = (0.1, 2.0) # YOLOv5RandomAffine
+mixup_prob = 0.15 # YOLOv5MixUp
+randchoice_mosaic_prob = [0.8, 0.2]
+mixup_alpha = 8.0 # YOLOv5MixUp
+mixup_beta = 8.0 # YOLOv5MixUp
+
+# -----train val related-----
+loss_cls_weight = 0.3
+loss_bbox_weight = 0.05
+loss_obj_weight = 0.7
+# BatchYOLOv7Assigner params
+simota_candidate_topk = 10
+simota_iou_weight = 3.0
+simota_cls_weight = 1.0
+prior_match_thr = 4. # Priori box matching threshold
+obj_level_weights = [4., 1.,
+ 0.4] # The obj loss weights of the three output layers
+
+lr_factor = 0.1 # Learning rate scaling factor
+weight_decay = 0.0005
+save_epoch_intervals = 1
+max_keep_ckpts = 5
+
+env_cfg = dict(
+ cudnn_benchmark=True,
+ mp_cfg=dict(mp_start_method='fork', opencv_num_threads=0),
+ dist_cfg=dict(backend='nccl'))
+
+# ===============================Unmodified in most cases====================
+model = dict(
+ type='YOLODetector',
+ data_preprocessor=dict(
+ type='YOLOv5DetDataPreprocessor',
+ mean=[0., 0., 0.],
+ std=[255., 255., 255.],
+ bgr_to_rgb=True),
+ backbone=dict(
+ type='YOLOv7Backbone',
+ arch='L',
+ norm_cfg=norm_cfg,
+ act_cfg=dict(type='SiLU', inplace=True)),
+ neck=dict(
+ type='YOLOv7PAFPN',
+ block_cfg=dict(
+ type='ELANBlock',
+ middle_ratio=0.5,
+ block_ratio=0.25,
+ num_blocks=4,
+ num_convs_in_block=1),
+ upsample_feats_cat_first=False,
+ in_channels=[512, 1024, 1024],
+ # The real output channel will be multiplied by 2
+ out_channels=[128, 256, 512],
+ norm_cfg=norm_cfg,
+ act_cfg=dict(type='SiLU', inplace=True)),
+ bbox_head=dict(
+ type='YOLOv7Head',
+ head_module=dict(
+ type='YOLOv7HeadModule',
+ num_classes=num_classes,
+ in_channels=[256, 512, 1024],
+ featmap_strides=strides,
+ num_base_priors=3),
+ prior_generator=dict(
+ type='mmdet.YOLOAnchorGenerator',
+ base_sizes=anchors,
+ strides=strides),
+ # scaled based on number of detection layers
+ loss_cls=dict(
+ type='mmdet.CrossEntropyLoss',
+ use_sigmoid=True,
+ reduction='mean',
+ loss_weight=loss_cls_weight *
+ (num_classes / 80 * 3 / num_det_layers)),
+ loss_bbox=dict(
+ type='IoULoss',
+ iou_mode='ciou',
+ bbox_format='xyxy',
+ reduction='mean',
+ loss_weight=loss_bbox_weight * (3 / num_det_layers),
+ return_iou=True),
+ loss_obj=dict(
+ type='mmdet.CrossEntropyLoss',
+ use_sigmoid=True,
+ reduction='mean',
+ loss_weight=loss_obj_weight *
+ ((img_scale[0] / 640)**2 * 3 / num_det_layers)),
+ prior_match_thr=prior_match_thr,
+ obj_level_weights=obj_level_weights,
+ # BatchYOLOv7Assigner params
+ simota_candidate_topk=simota_candidate_topk,
+ simota_iou_weight=simota_iou_weight,
+ simota_cls_weight=simota_cls_weight),
+ test_cfg=model_test_cfg)
+
+pre_transform = [
+ dict(type='LoadImageFromFile', file_client_args=_base_.file_client_args),
+ dict(type='LoadAnnotations', with_bbox=True)
+]
+
+mosiac4_pipeline = [
+ dict(
+ type='Mosaic',
+ img_scale=img_scale,
+ pad_val=114.0,
+ pre_transform=pre_transform),
+ dict(
+ type='YOLOv5RandomAffine',
+ max_rotate_degree=0.0,
+ max_shear_degree=0.0,
+ max_translate_ratio=max_translate_ratio, # note
+ scaling_ratio_range=scaling_ratio_range, # note
+ # img_scale is (width, height)
+ border=(-img_scale[0] // 2, -img_scale[1] // 2),
+ border_val=(114, 114, 114)),
+]
+
+mosiac9_pipeline = [
+ dict(
+ type='Mosaic9',
+ img_scale=img_scale,
+ pad_val=114.0,
+ pre_transform=pre_transform),
+ dict(
+ type='YOLOv5RandomAffine',
+ max_rotate_degree=0.0,
+ max_shear_degree=0.0,
+ max_translate_ratio=max_translate_ratio, # note
+ scaling_ratio_range=scaling_ratio_range, # note
+ # img_scale is (width, height)
+ border=(-img_scale[0] // 2, -img_scale[1] // 2),
+ border_val=(114, 114, 114)),
+]
+
+randchoice_mosaic_pipeline = dict(
+ type='RandomChoice',
+ transforms=[mosiac4_pipeline, mosiac9_pipeline],
+ prob=randchoice_mosaic_prob)
+
+train_pipeline = [
+ *pre_transform,
+ randchoice_mosaic_pipeline,
+ dict(
+ type='YOLOv5MixUp',
+ alpha=mixup_alpha, # note
+ beta=mixup_beta, # note
+ prob=mixup_prob,
+ pre_transform=[*pre_transform, randchoice_mosaic_pipeline]),
+ dict(type='YOLOv5HSVRandomAug'),
+ dict(type='mmdet.RandomFlip', prob=0.5),
+ dict(
+ type='mmdet.PackDetInputs',
+ meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape', 'flip',
+ 'flip_direction'))
+]
+
+test_pipeline = [
+ dict(type='LoadImageFromFile', file_client_args=_base_.file_client_args),
+ dict(type='YOLOv5KeepRatioResize', scale=img_scale),
+ dict(
+ type='LetterResize',
+ scale=img_scale,
+ allow_scale_up=False,
+ pad_val=dict(img=114)),
+ dict(type='LoadAnnotations', with_bbox=True, _scope_='mmdet'),
+ dict(
+ type='mmdet.PackDetInputs',
+ meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
+ 'scale_factor', 'pad_param'))
+]
+
+train_dataloader = dict(
+ batch_size=train_batch_size_per_gpu,
+ num_workers=train_num_workers,
+ persistent_workers=persistent_workers,
+ pin_memory=True,
+ sampler=dict(type='DefaultSampler', shuffle=True),
+ collate_fn=dict(type='yolov5_collate'), # FASTER
+ dataset=dict(
+ type='RepeatDataset',
+ times=2,
+ dataset=dict(
+ type=dataset_type,
+ data_root=data_root,
+ metainfo=metainfo,
+ ann_file=val_ann_file,
+ data_prefix=dict(img=train_data_prefix),
+ filter_cfg=dict(filter_empty_gt=False, min_size=32),
+ pipeline=train_pipeline)
+ )
+ )
+
+val_dataloader = dict(
+ dataset=dict(
+ metainfo=metainfo,
+ data_root=data_root,
+ ann_file=val_ann_file,
+ data_prefix=dict(img=val_data_prefix)))
+
+val_evaluator = dict(ann_file=data_root + val_ann_file)
+
+test_dataloader = dict(
+ dataset=dict(
+ metainfo=metainfo,
+ data_root=data_root,
+ ann_file=test_ann_file,
+ data_prefix=dict(img=test_data_prefix)))
+test_evaluator = dict(ann_file=data_root + test_ann_file)
+
+train_cfg = dict(
+ type='EpochBasedTrainLoop',
+ max_epochs=max_epochs,
+ val_interval=save_epoch_intervals,
+ dynamic_intervals=[(max_epochs - num_epoch_stage2, val_interval_stage2)])
+val_cfg = dict(type='ValLoop')
+test_cfg = dict(type='TestLoop')
+
+param_scheduler = None
+optim_wrapper = dict(
+ type='OptimWrapper',
+ optimizer=dict(
+ type='SGD',
+ lr=base_lr,
+ momentum=0.937,
+ weight_decay=weight_decay,
+ nesterov=True,
+ batch_size_per_gpu=train_batch_size_per_gpu),
+ constructor='YOLOv7OptimWrapperConstructor')
+
+# TO DO: change param_scheduler type to StepLR, refer to mobilenet
+default_scope = 'mmyolo'
+default_hooks = dict(
+ timer=dict(type='IterTimerHook'),
+ logger=dict(type='LoggerHook', interval=10),
+ param_scheduler=dict(
+ type='YOLOv5ParamSchedulerHook',
+ scheduler_type='cosine',
+ lr_factor=lr_factor, # note
+ max_epochs=max_epochs),
+ checkpoint=dict(
+ type='CheckpointHook',
+ save_param_scheduler=False,
+ interval=save_epoch_intervals,
+ save_best='auto',
+ max_keep_ckpts=max_keep_ckpts),
+ sampler_seed=dict(type='DistSamplerSeedHook'),
+ visualization=dict(type='mmdet.DetVisualizationHook'))
+
+custom_hooks = [
+ dict(
+ type='EMAHook',
+ ema_type='ExpMomentumEMA',
+ momentum=0.001,
+ update_buffers=True,
+ strict_load=False,
+ priority=49)
+]
+
+# ============================
+
+file_client_args = dict(backend='disk')
+_file_client_args = dict(backend='disk')
+tta_model = dict(
+ type='mmdet.DetTTAModel',
+ tta_cfg=dict(nms=dict(type='nms', iou_threshold=0.65), max_per_img=300))
+img_scales = [
+ (
+ 640,
+ 640,
+ ),
+ (
+ 320,
+ 320,
+ ),
+ (
+ 960,
+ 960,
+ ),
+]
+_multiscale_resize_transforms = [
+ dict(
+ type='Compose',
+ transforms=[
+ dict(type='YOLOv5KeepRatioResize', scale=(
+ 640,
+ 640,
+ )),
+ dict(
+ type='LetterResize',
+ scale=(
+ 640,
+ 640,
+ ),
+ allow_scale_up=False,
+ pad_val=dict(img=114)),
+ ]),
+ dict(
+ type='Compose',
+ transforms=[
+ dict(type='YOLOv5KeepRatioResize', scale=(
+ 320,
+ 320,
+ )),
+ dict(
+ type='LetterResize',
+ scale=(
+ 320,
+ 320,
+ ),
+ allow_scale_up=False,
+ pad_val=dict(img=114)),
+ ]),
+ dict(
+ type='Compose',
+ transforms=[
+ dict(type='YOLOv5KeepRatioResize', scale=(
+ 960,
+ 960,
+ )),
+ dict(
+ type='LetterResize',
+ scale=(
+ 960,
+ 960,
+ ),
+ allow_scale_up=False,
+ pad_val=dict(img=114)),
+ ]),
+]
+tta_pipeline = [
+ dict(type='LoadImageFromFile', file_client_args=dict(backend='disk')),
+ dict(
+ type='TestTimeAug',
+ transforms=[
+ [
+ dict(
+ type='Compose',
+ transforms=[
+ dict(type='YOLOv5KeepRatioResize', scale=(
+ 640,
+ 640,
+ )),
+ dict(
+ type='LetterResize',
+ scale=(
+ 640,
+ 640,
+ ),
+ allow_scale_up=False,
+ pad_val=dict(img=114)),
+ ]),
+ dict(
+ type='Compose',
+ transforms=[
+ dict(type='YOLOv5KeepRatioResize', scale=(
+ 320,
+ 320,
+ )),
+ dict(
+ type='LetterResize',
+ scale=(
+ 320,
+ 320,
+ ),
+ allow_scale_up=False,
+ pad_val=dict(img=114)),
+ ]),
+ dict(
+ type='Compose',
+ transforms=[
+ dict(type='YOLOv5KeepRatioResize', scale=(
+ 960,
+ 960,
+ )),
+ dict(
+ type='LetterResize',
+ scale=(
+ 960,
+ 960,
+ ),
+ allow_scale_up=False,
+ pad_val=dict(img=114)),
+ ]),
+ ],
+ [
+ dict(type='mmdet.RandomFlip', prob=1.0),
+ dict(type='mmdet.RandomFlip', prob=0.0),
+ ],
+ [
+ dict(type='mmdet.LoadAnnotations', with_bbox=True),
+ ],
+ [
+ dict(
+ type='mmdet.PackDetInputs',
+ meta_keys=(
+ 'img_id',
+ 'img_path',
+ 'ori_shape',
+ 'img_shape',
+ 'scale_factor',
+ 'pad_param',
+ 'flip',
+ 'flip_direction',
+ )),
+ ],
+ ]),
+]
+
+launcher = 'none'
diff --git a/Model/Model6/Model6_0_ClothesDetection/mmyolo/configs/custom_dataset/yolov7_l_syncbn_fast_6x32b-100e_coco.py b/Model/Model6/Model6_0_ClothesDetection/mmyolo/configs/custom_dataset/yolov7_l_syncbn_fast_6x32b-100e_coco.py
new file mode 100644
index 0000000000000000000000000000000000000000..9a7a722e74a6b446c58e748d802511ae5fdab2d3
--- /dev/null
+++ b/Model/Model6/Model6_0_ClothesDetection/mmyolo/configs/custom_dataset/yolov7_l_syncbn_fast_6x32b-100e_coco.py
@@ -0,0 +1,554 @@
+_base_ = ['../_base_/default_runtime.py', '../_base_/det_p5_tta.py']
+
+data_root = './data-df2/'
+train_ann_file = 'annotations/train.json'
+train_data_prefix = 'smaller-dataset/'
+val_ann_file = 'annotations/val.json'
+val_data_prefix = 'smaller-dataset/'
+test_ann_file = 'annotations/test.json'
+test_data_prefix = 'smaller-dataset/'
+num_classes = 13
+train_batch_size_per_gpu = 32
+train_num_workers = 24
+persistent_workers = True
+
+vis_backends = [
+ dict(type='LocalVisBackend'),
+]
+visualizer = dict(
+ type='mmdet.DetLocalVisualizer',
+ vis_backends=[
+ dict(type='LocalVisBackend'),
+ dict(type='WandbVisBackend'),
+ # dict(type='TensorboardVisBackend')
+ ],
+ name='visualizer')
+log_processor = dict(type='LogProcessor', window_size=50, by_epoch=True)
+log_level = 'INFO'
+load_from = None
+resume = False
+
+anchors = [
+ [(12, 16), (19, 36), (40, 28)], # P3/8
+ [(36, 75), (76, 55), (72, 146)], # P4/16
+ [(142, 110), (192, 243), (459, 401)] # P5/32
+]
+
+base_lr = 0.01
+max_epochs = 100
+
+num_epoch_stage2 = 10 # The last 10 epochs switch evaluation interval
+val_interval_stage2 = 1
+
+model_test_cfg = dict(
+ multi_label=True,
+ nms_pre=30000,
+ score_thr=0.001,
+ nms=dict(type='nms', iou_threshold=0.65),
+ max_per_img=300)
+
+img_scale = (640, 640)
+dataset_type = 'YOLOv5CocoDataset'
+metainfo = dict(
+ classes=(
+ 'short_sleeved_shirt', 'long_sleeved_shirt',
+ 'short_sleeved_outwear', 'long_sleeved_outwear',
+ 'vest', 'sling', 'shorts', 'trousers', 'skirt',
+ 'short_sleeved_dress', 'long_sleeved_dress',
+ 'vest_dress', 'sling_dress'),
+ palette=[
+ (255, 0, 0),
+ (
+ 255,
+ 128,
+ 0,
+ ),
+ (
+ 255,
+ 255,
+ 0,
+ ),
+ (
+ 128,
+ 255,
+ 0,
+ ),
+ (
+ 0,
+ 255,
+ 0,
+ ),
+ (
+ 0,
+ 255,
+ 128,
+ ),
+ (
+ 0,
+ 255,
+ 255,
+ ),
+ (
+ 0,
+ 128,
+ 255,
+ ),
+ (
+ 0,
+ 0,
+ 255,
+ ),
+ (
+ 127,
+ 0,
+ 255,
+ ),
+ (
+ 255,
+ 0,
+ 255,
+ ),
+ (
+ 255,
+ 0,
+ 127,
+ ),
+ (
+ 128,
+ 128,
+ 128,
+ ),
+ ])
+
+val_batch_size_per_gpu = 1
+val_num_workers = 2
+batch_shapes_cfg = dict(
+ type='BatchShapePolicy',
+ batch_size=val_batch_size_per_gpu,
+ img_size=img_scale[0],
+ size_divisor=32,
+ extra_pad_ratio=0.5)
+strides = [8, 16, 32] # Strides of multi-scale prior box
+num_det_layers = 3
+norm_cfg = dict(type='BN', momentum=0.03, eps=0.001)
+
+# Data augmentation
+max_translate_ratio = 0.2 # YOLOv5RandomAffine
+scaling_ratio_range = (0.1, 2.0) # YOLOv5RandomAffine
+mixup_prob = 0.15 # YOLOv5MixUp
+randchoice_mosaic_prob = [0.8, 0.2]
+mixup_alpha = 8.0 # YOLOv5MixUp
+mixup_beta = 8.0 # YOLOv5MixUp
+
+# -----train val related-----
+loss_cls_weight = 0.3
+loss_bbox_weight = 0.05
+loss_obj_weight = 0.7
+# BatchYOLOv7Assigner params
+simota_candidate_topk = 10
+simota_iou_weight = 3.0
+simota_cls_weight = 1.0
+prior_match_thr = 4. # Priori box matching threshold
+obj_level_weights = [4., 1.,
+ 0.4] # The obj loss weights of the three output layers
+
+lr_factor = 0.1 # Learning rate scaling factor
+weight_decay = 0.0005
+save_epoch_intervals = 1
+max_keep_ckpts = 5
+
+env_cfg = dict(
+ cudnn_benchmark=True,
+ mp_cfg=dict(mp_start_method='fork', opencv_num_threads=0),
+ dist_cfg=dict(backend='nccl'))
+
+# ===============================Unmodified in most cases====================
+model = dict(
+ type='YOLODetector',
+ data_preprocessor=dict(
+ type='YOLOv5DetDataPreprocessor',
+ mean=[0., 0., 0.],
+ std=[255., 255., 255.],
+ bgr_to_rgb=True),
+ backbone=dict(
+ type='YOLOv7Backbone',
+ arch='L',
+ norm_cfg=norm_cfg,
+ act_cfg=dict(type='SiLU', inplace=True)),
+ neck=dict(
+ type='YOLOv7PAFPN',
+ block_cfg=dict(
+ type='ELANBlock',
+ middle_ratio=0.5,
+ block_ratio=0.25,
+ num_blocks=4,
+ num_convs_in_block=1),
+ upsample_feats_cat_first=False,
+ in_channels=[512, 1024, 1024],
+ # The real output channel will be multiplied by 2
+ out_channels=[128, 256, 512],
+ norm_cfg=norm_cfg,
+ act_cfg=dict(type='SiLU', inplace=True)),
+ bbox_head=dict(
+ type='YOLOv7Head',
+ head_module=dict(
+ type='YOLOv7HeadModule',
+ num_classes=num_classes,
+ in_channels=[256, 512, 1024],
+ featmap_strides=strides,
+ num_base_priors=3),
+ prior_generator=dict(
+ type='mmdet.YOLOAnchorGenerator',
+ base_sizes=anchors,
+ strides=strides),
+ # scaled based on number of detection layers
+ loss_cls=dict(
+ type='mmdet.CrossEntropyLoss',
+ use_sigmoid=True,
+ reduction='mean',
+ loss_weight=loss_cls_weight *
+ (num_classes / 80 * 3 / num_det_layers)),
+ loss_bbox=dict(
+ type='IoULoss',
+ iou_mode='ciou',
+ bbox_format='xyxy',
+ reduction='mean',
+ loss_weight=loss_bbox_weight * (3 / num_det_layers),
+ return_iou=True),
+ loss_obj=dict(
+ type='mmdet.CrossEntropyLoss',
+ use_sigmoid=True,
+ reduction='mean',
+ loss_weight=loss_obj_weight *
+ ((img_scale[0] / 640)**2 * 3 / num_det_layers)),
+ prior_match_thr=prior_match_thr,
+ obj_level_weights=obj_level_weights,
+ # BatchYOLOv7Assigner params
+ simota_candidate_topk=simota_candidate_topk,
+ simota_iou_weight=simota_iou_weight,
+ simota_cls_weight=simota_cls_weight),
+ test_cfg=model_test_cfg)
+
+pre_transform = [
+ dict(type='LoadImageFromFile', file_client_args=_base_.file_client_args),
+ dict(type='LoadAnnotations', with_bbox=True)
+]
+
+mosiac4_pipeline = [
+ dict(
+ type='Mosaic',
+ img_scale=img_scale,
+ pad_val=114.0,
+ pre_transform=pre_transform),
+ dict(
+ type='YOLOv5RandomAffine',
+ max_rotate_degree=0.0,
+ max_shear_degree=0.0,
+ max_translate_ratio=max_translate_ratio, # note
+ scaling_ratio_range=scaling_ratio_range, # note
+ # img_scale is (width, height)
+ border=(-img_scale[0] // 2, -img_scale[1] // 2),
+ border_val=(114, 114, 114)),
+]
+
+mosiac9_pipeline = [
+ dict(
+ type='Mosaic9',
+ img_scale=img_scale,
+ pad_val=114.0,
+ pre_transform=pre_transform),
+ dict(
+ type='YOLOv5RandomAffine',
+ max_rotate_degree=0.0,
+ max_shear_degree=0.0,
+ max_translate_ratio=max_translate_ratio, # note
+ scaling_ratio_range=scaling_ratio_range, # note
+ # img_scale is (width, height)
+ border=(-img_scale[0] // 2, -img_scale[1] // 2),
+ border_val=(114, 114, 114)),
+]
+
+randchoice_mosaic_pipeline = dict(
+ type='RandomChoice',
+ transforms=[mosiac4_pipeline, mosiac9_pipeline],
+ prob=randchoice_mosaic_prob)
+
+train_pipeline = [
+ *pre_transform,
+ randchoice_mosaic_pipeline,
+ dict(
+ type='YOLOv5MixUp',
+ alpha=mixup_alpha, # note
+ beta=mixup_beta, # note
+ prob=mixup_prob,
+ pre_transform=[*pre_transform, randchoice_mosaic_pipeline]),
+ dict(type='YOLOv5HSVRandomAug'),
+ dict(type='mmdet.RandomFlip', prob=0.5),
+ dict(
+ type='mmdet.PackDetInputs',
+ meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape', 'flip',
+ 'flip_direction'))
+]
+
+test_pipeline = [
+ dict(type='LoadImageFromFile', file_client_args=_base_.file_client_args),
+ dict(type='YOLOv5KeepRatioResize', scale=img_scale),
+ dict(
+ type='LetterResize',
+ scale=img_scale,
+ allow_scale_up=False,
+ pad_val=dict(img=114)),
+ dict(type='LoadAnnotations', with_bbox=True, _scope_='mmdet'),
+ dict(
+ type='mmdet.PackDetInputs',
+ meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
+ 'scale_factor', 'pad_param'))
+]
+
+train_dataloader = dict(
+ batch_size=train_batch_size_per_gpu,
+ num_workers=train_num_workers,
+ persistent_workers=persistent_workers,
+ pin_memory=True,
+ sampler=dict(type='DefaultSampler', shuffle=True),
+ collate_fn=dict(type='yolov5_collate'), # FASTER
+ dataset=dict(
+ type='RepeatDataset',
+ times=2,
+ dataset=dict(
+ type=dataset_type,
+ metainfo=metainfo,
+ data_root=data_root,
+ ann_file=val_ann_file,
+ data_prefix=dict(img=train_data_prefix),
+ filter_cfg=dict(filter_empty_gt=False, min_size=32),
+ pipeline=train_pipeline
+ )
+ )
+)
+val_dataloader = dict(
+ dataset=dict(
+ type=dataset_type,
+ metainfo=metainfo,
+ data_root=data_root,
+ ann_file=val_ann_file,
+ data_prefix=dict(img=val_data_prefix)))
+
+val_evaluator = dict(
+ type='mmdet.CocoMetric',
+ proposal_nums=(100, 1, 10),
+ ann_file=data_root + val_ann_file,
+ metric='bbox')
+
+test_dataloader = dict(
+ dataset=dict(
+ metainfo=metainfo,
+ data_root=data_root,
+ ann_file=test_ann_file,
+ data_prefix=dict(img=test_data_prefix)))
+test_evaluator = dict(
+ type='mmdet.CocoMetric',
+ proposal_nums=(100, 1, 10),
+ ann_file=data_root + test_ann_file,
+ metric='bbox')
+
+train_cfg = dict(
+ type='EpochBasedTrainLoop',
+ max_epochs=max_epochs,
+ val_interval=save_epoch_intervals,
+ dynamic_intervals=[(max_epochs - num_epoch_stage2, val_interval_stage2)])
+val_cfg = dict(type='ValLoop')
+test_cfg = dict(type='TestLoop')
+
+param_scheduler = None
+optim_wrapper = dict(
+ type='OptimWrapper',
+ optimizer=dict(
+ type='SGD',
+ lr=base_lr,
+ momentum=0.937,
+ weight_decay=weight_decay,
+ nesterov=True,
+ batch_size_per_gpu=train_batch_size_per_gpu),
+ constructor='YOLOv7OptimWrapperConstructor')
+
+# TO DO: change param_scheduler type to StepLR, refer to mobilenet
+default_scope = 'mmyolo'
+default_hooks = dict(
+ timer=dict(type='IterTimerHook'),
+ logger=dict(type='LoggerHook', interval=10),
+ param_scheduler=dict(
+ type='YOLOv5ParamSchedulerHook',
+ scheduler_type='cosine',
+ lr_factor=lr_factor, # note
+ max_epochs=max_epochs),
+ checkpoint=dict(
+ type='CheckpointHook',
+ save_param_scheduler=False,
+ interval=save_epoch_intervals,
+ save_best='auto',
+ max_keep_ckpts=max_keep_ckpts),
+ sampler_seed=dict(type='DistSamplerSeedHook'),
+ visualization=dict(type='mmdet.DetVisualizationHook'))
+
+custom_hooks = [
+ dict(
+ type='EMAHook',
+ ema_type='ExpMomentumEMA',
+ momentum=0.001,
+ update_buffers=True,
+ strict_load=False,
+ priority=49)
+]
+
+# ============================
+
+file_client_args = dict(backend='disk')
+_file_client_args = dict(backend='disk')
+tta_model = dict(
+ type='mmdet.DetTTAModel',
+ tta_cfg=dict(nms=dict(type='nms', iou_threshold=0.65), max_per_img=300))
+img_scales = [
+ (
+ 640,
+ 640,
+ ),
+ (
+ 320,
+ 320,
+ ),
+ (
+ 960,
+ 960,
+ ),
+]
+_multiscale_resize_transforms = [
+ dict(
+ type='Compose',
+ transforms=[
+ dict(type='YOLOv5KeepRatioResize', scale=(
+ 640,
+ 640,
+ )),
+ dict(
+ type='LetterResize',
+ scale=(
+ 640,
+ 640,
+ ),
+ allow_scale_up=False,
+ pad_val=dict(img=114)),
+ ]),
+ dict(
+ type='Compose',
+ transforms=[
+ dict(type='YOLOv5KeepRatioResize', scale=(
+ 320,
+ 320,
+ )),
+ dict(
+ type='LetterResize',
+ scale=(
+ 320,
+ 320,
+ ),
+ allow_scale_up=False,
+ pad_val=dict(img=114)),
+ ]),
+ dict(
+ type='Compose',
+ transforms=[
+ dict(type='YOLOv5KeepRatioResize', scale=(
+ 960,
+ 960,
+ )),
+ dict(
+ type='LetterResize',
+ scale=(
+ 960,
+ 960,
+ ),
+ allow_scale_up=False,
+ pad_val=dict(img=114)),
+ ]),
+]
+tta_pipeline = [
+ dict(type='LoadImageFromFile', file_client_args=dict(backend='disk')),
+ dict(
+ type='TestTimeAug',
+ transforms=[
+ [
+ dict(
+ type='Compose',
+ transforms=[
+ dict(type='YOLOv5KeepRatioResize', scale=(
+ 640,
+ 640,
+ )),
+ dict(
+ type='LetterResize',
+ scale=(
+ 640,
+ 640,
+ ),
+ allow_scale_up=False,
+ pad_val=dict(img=114)),
+ ]),
+ dict(
+ type='Compose',
+ transforms=[
+ dict(type='YOLOv5KeepRatioResize', scale=(
+ 320,
+ 320,
+ )),
+ dict(
+ type='LetterResize',
+ scale=(
+ 320,
+ 320,
+ ),
+ allow_scale_up=False,
+ pad_val=dict(img=114)),
+ ]),
+ dict(
+ type='Compose',
+ transforms=[
+ dict(type='YOLOv5KeepRatioResize', scale=(
+ 960,
+ 960,
+ )),
+ dict(
+ type='LetterResize',
+ scale=(
+ 960,
+ 960,
+ ),
+ allow_scale_up=False,
+ pad_val=dict(img=114)),
+ ]),
+ ],
+ [
+ dict(type='mmdet.RandomFlip', prob=1.0),
+ dict(type='mmdet.RandomFlip', prob=0.0),
+ ],
+ [
+ dict(type='mmdet.LoadAnnotations', with_bbox=True),
+ ],
+ [
+ dict(
+ type='mmdet.PackDetInputs',
+ meta_keys=(
+ 'img_id',
+ 'img_path',
+ 'ori_shape',
+ 'img_shape',
+ 'scale_factor',
+ 'pad_param',
+ 'flip',
+ 'flip_direction',
+ )),
+ ],
+ ]),
+]
+
+launcher = 'none'
diff --git a/Model/Model6/Model6_0_ClothesDetection/mmyolo/configs/custom_dataset/yolov7_l_syncbn_fast_8x16b-300e_coco.py b/Model/Model6/Model6_0_ClothesDetection/mmyolo/configs/custom_dataset/yolov7_l_syncbn_fast_8x16b-300e_coco.py
new file mode 100644
index 0000000000000000000000000000000000000000..c3c11c5ea042db35e7a73032a9b945522e3d7b21
--- /dev/null
+++ b/Model/Model6/Model6_0_ClothesDetection/mmyolo/configs/custom_dataset/yolov7_l_syncbn_fast_8x16b-300e_coco.py
@@ -0,0 +1,472 @@
+_base_ = ['../_base_/default_runtime.py', '../_base_/det_p5_tta.py']
+
+data_root = './data-df2/'
+train_ann_file = 'annotations/instances_train2017.json'
+train_data_prefix = 'train2017/'
+val_ann_file = 'annotations/instances_val2017.json'
+val_data_prefix = 'val2017/'
+num_classes = 13
+train_batch_size_per_gpu = 16
+train_num_workers = 8
+persistent_workers = True
+
+vis_backends = [
+ dict(type='LocalVisBackend'),
+]
+visualizer = dict(
+ type='mmdet.DetLocalVisualizer',
+ vis_backends=[
+ dict(type='LocalVisBackend'),
+ dict(type='WandbVisBackend')
+ ],
+ name='visualizer')
+log_processor = dict(type='LogProcessor', window_size=50, by_epoch=True)
+log_level = 'INFO'
+load_from = None
+resume = False
+
+anchors = [
+ [(12, 16), (19, 36), (40, 28)], # P3/8
+ [(36, 75), (76, 55), (72, 146)], # P4/16
+ [(142, 110), (192, 243), (459, 401)] # P5/32
+]
+
+base_lr = 0.01
+max_epochs = 100
+
+num_epoch_stage2 = 10 # The last 10 epochs switch evaluation interval
+val_interval_stage2 = 1
+
+model_test_cfg = dict(
+ multi_label=True,
+ nms_pre=30000,
+ score_thr=0.001,
+ nms=dict(type='nms', iou_threshold=0.65),
+ max_per_img=300)
+
+img_scale = (640, 640)
+dataset_type = 'YOLOv5CocoDataset'
+val_batch_size_per_gpu = 1
+val_num_workers = 2
+batch_shapes_cfg = dict(
+ type='BatchShapePolicy',
+ batch_size=val_batch_size_per_gpu,
+ img_size=img_scale[0],
+ size_divisor=32,
+ extra_pad_ratio=0.5)
+strides = [8, 16, 32] # Strides of multi-scale prior box
+num_det_layers = 3
+norm_cfg = dict(type='BN', momentum=0.03, eps=0.001)
+
+# Data augmentation
+max_translate_ratio = 0.2 # YOLOv5RandomAffine
+scaling_ratio_range = (0.1, 2.0) # YOLOv5RandomAffine
+mixup_prob = 0.15 # YOLOv5MixUp
+randchoice_mosaic_prob = [0.8, 0.2]
+mixup_alpha = 8.0 # YOLOv5MixUp
+mixup_beta = 8.0 # YOLOv5MixUp
+
+# -----train val related-----
+loss_cls_weight = 0.3
+loss_bbox_weight = 0.05
+loss_obj_weight = 0.7
+# BatchYOLOv7Assigner params
+simota_candidate_topk = 10
+simota_iou_weight = 3.0
+simota_cls_weight = 1.0
+prior_match_thr = 4. # Priori box matching threshold
+obj_level_weights = [4., 1.,
+ 0.4] # The obj loss weights of the three output layers
+
+lr_factor = 0.1 # Learning rate scaling factor
+weight_decay = 0.0005
+save_epoch_intervals = 2
+max_keep_ckpts = 5
+
+env_cfg = dict(
+ cudnn_benchmark=True,
+ mp_cfg=dict(mp_start_method='fork', opencv_num_threads=0),
+ dist_cfg=dict(backend='nccl'))
+
+# ===============================Unmodified in most cases====================
+model = dict(
+ type='YOLODetector',
+ data_preprocessor=dict(
+ type='YOLOv5DetDataPreprocessor',
+ mean=[0., 0., 0.],
+ std=[255., 255., 255.],
+ bgr_to_rgb=True),
+ backbone=dict(
+ type='YOLOv7Backbone',
+ arch='L',
+ norm_cfg=norm_cfg,
+ act_cfg=dict(type='SiLU', inplace=True)),
+ neck=dict(
+ type='YOLOv7PAFPN',
+ block_cfg=dict(
+ type='ELANBlock',
+ middle_ratio=0.5,
+ block_ratio=0.25,
+ num_blocks=4,
+ num_convs_in_block=1),
+ upsample_feats_cat_first=False,
+ in_channels=[512, 1024, 1024],
+ # The real output channel will be multiplied by 2
+ out_channels=[128, 256, 512],
+ norm_cfg=norm_cfg,
+ act_cfg=dict(type='SiLU', inplace=True)),
+ bbox_head=dict(
+ type='YOLOv7Head',
+ head_module=dict(
+ type='YOLOv7HeadModule',
+ num_classes=num_classes,
+ in_channels=[256, 512, 1024],
+ featmap_strides=strides,
+ num_base_priors=3),
+ prior_generator=dict(
+ type='mmdet.YOLOAnchorGenerator',
+ base_sizes=anchors,
+ strides=strides),
+ # scaled based on number of detection layers
+ loss_cls=dict(
+ type='mmdet.CrossEntropyLoss',
+ use_sigmoid=True,
+ reduction='mean',
+ loss_weight=loss_cls_weight *
+ (num_classes / 80 * 3 / num_det_layers)),
+ loss_bbox=dict(
+ type='IoULoss',
+ iou_mode='ciou',
+ bbox_format='xywh',
+ reduction='mean',
+ loss_weight=loss_bbox_weight * (3 / num_det_layers),
+ return_iou=True),
+ loss_obj=dict(
+ type='mmdet.CrossEntropyLoss',
+ use_sigmoid=True,
+ reduction='mean',
+ loss_weight=loss_obj_weight *
+ ((img_scale[0] / 640)**2 * 3 / num_det_layers)),
+ prior_match_thr=prior_match_thr,
+ obj_level_weights=obj_level_weights,
+ # BatchYOLOv7Assigner params
+ simota_candidate_topk=simota_candidate_topk,
+ simota_iou_weight=simota_iou_weight,
+ simota_cls_weight=simota_cls_weight),
+ test_cfg=model_test_cfg)
+
+pre_transform = [
+ dict(type='LoadImageFromFile', file_client_args=_base_.file_client_args),
+ dict(type='LoadAnnotations', with_bbox=True)
+]
+
+mosiac4_pipeline = [
+ dict(
+ type='Mosaic',
+ img_scale=img_scale,
+ pad_val=114.0,
+ pre_transform=pre_transform),
+ dict(
+ type='YOLOv5RandomAffine',
+ max_rotate_degree=0.0,
+ max_shear_degree=0.0,
+ max_translate_ratio=max_translate_ratio, # note
+ scaling_ratio_range=scaling_ratio_range, # note
+ # img_scale is (width, height)
+ border=(-img_scale[0] // 2, -img_scale[1] // 2),
+ border_val=(114, 114, 114)),
+]
+
+mosiac9_pipeline = [
+ dict(
+ type='Mosaic9',
+ img_scale=img_scale,
+ pad_val=114.0,
+ pre_transform=pre_transform),
+ dict(
+ type='YOLOv5RandomAffine',
+ max_rotate_degree=0.0,
+ max_shear_degree=0.0,
+ max_translate_ratio=max_translate_ratio, # note
+ scaling_ratio_range=scaling_ratio_range, # note
+ # img_scale is (width, height)
+ border=(-img_scale[0] // 2, -img_scale[1] // 2),
+ border_val=(114, 114, 114)),
+]
+
+randchoice_mosaic_pipeline = dict(
+ type='RandomChoice',
+ transforms=[mosiac4_pipeline, mosiac9_pipeline],
+ prob=randchoice_mosaic_prob)
+
+train_pipeline = [
+ *pre_transform,
+ randchoice_mosaic_pipeline,
+ dict(
+ type='YOLOv5MixUp',
+ alpha=mixup_alpha, # note
+ beta=mixup_beta, # note
+ prob=mixup_prob,
+ pre_transform=[*pre_transform, randchoice_mosaic_pipeline]),
+ dict(type='YOLOv5HSVRandomAug'),
+ dict(type='mmdet.RandomFlip', prob=0.5),
+ dict(
+ type='mmdet.PackDetInputs',
+ meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape', 'flip',
+ 'flip_direction'))
+]
+
+train_dataloader = dict(
+ batch_size=train_batch_size_per_gpu,
+ num_workers=train_num_workers,
+ persistent_workers=persistent_workers,
+ pin_memory=True,
+ sampler=dict(type='DefaultSampler', shuffle=True),
+ collate_fn=dict(type='yolov5_collate'), # FASTER
+ dataset=dict(
+ type=dataset_type,
+ data_root=data_root,
+ ann_file=train_ann_file,
+ data_prefix=dict(img=train_data_prefix),
+ filter_cfg=dict(filter_empty_gt=False, min_size=32),
+ pipeline=train_pipeline))
+
+test_pipeline = [
+ dict(type='LoadImageFromFile', file_client_args=_base_.file_client_args),
+ dict(type='YOLOv5KeepRatioResize', scale=img_scale),
+ dict(
+ type='LetterResize',
+ scale=img_scale,
+ allow_scale_up=False,
+ pad_val=dict(img=114)),
+ dict(type='LoadAnnotations', with_bbox=True, _scope_='mmdet'),
+ dict(
+ type='mmdet.PackDetInputs',
+ meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
+ 'scale_factor', 'pad_param'))
+]
+
+val_dataloader = dict(
+ batch_size=val_batch_size_per_gpu,
+ num_workers=val_num_workers,
+ persistent_workers=persistent_workers,
+ pin_memory=True,
+ drop_last=False,
+ sampler=dict(type='DefaultSampler', shuffle=False),
+ dataset=dict(
+ type=dataset_type,
+ data_root=data_root,
+ test_mode=True,
+ data_prefix=dict(img=val_data_prefix),
+ ann_file=val_ann_file,
+ pipeline=test_pipeline,
+ batch_shapes_cfg=batch_shapes_cfg))
+
+test_dataloader = val_dataloader
+
+param_scheduler = None
+optim_wrapper = dict(
+ type='OptimWrapper',
+ optimizer=dict(
+ type='SGD',
+ lr=base_lr,
+ momentum=0.937,
+ weight_decay=weight_decay,
+ nesterov=True,
+ batch_size_per_gpu=train_batch_size_per_gpu),
+ constructor='YOLOv7OptimWrapperConstructor')
+
+default_scope = 'mmyolo'
+default_hooks = dict(
+ timer=dict(type='IterTimerHook'),
+ logger=dict(type='LoggerHook', interval=2),
+ param_scheduler=dict(
+ type='YOLOv5ParamSchedulerHook',
+ scheduler_type='cosine',
+ lr_factor=lr_factor, # note
+ max_epochs=max_epochs),
+ checkpoint=dict(
+ type='CheckpointHook',
+ save_param_scheduler=False,
+ interval=save_epoch_intervals,
+ save_best='auto',
+ max_keep_ckpts=max_keep_ckpts),
+ sampler_seed=dict(type='DistSamplerSeedHook'),
+ visualization=dict(type='mmdet.DetVisualizationHook'))
+
+custom_hooks = [
+ dict(
+ type='EMAHook',
+ ema_type='ExpMomentumEMA',
+ momentum=0.0001,
+ update_buffers=True,
+ strict_load=False,
+ priority=49)
+]
+
+val_evaluator = dict(
+ type='mmdet.CocoMetric',
+ proposal_nums=(100, 1, 10), # Can be accelerated
+ ann_file=data_root + val_ann_file,
+ metric='bbox')
+test_evaluator = val_evaluator
+
+train_cfg = dict(
+ type='EpochBasedTrainLoop',
+ max_epochs=max_epochs,
+ val_interval=save_epoch_intervals,
+ dynamic_intervals=[(max_epochs - num_epoch_stage2, val_interval_stage2)])
+val_cfg = dict(type='ValLoop')
+test_cfg = dict(type='TestLoop')
+
+# ============================
+
+file_client_args = dict(backend='disk')
+_file_client_args = dict(backend='disk')
+tta_model = dict(
+ type='mmdet.DetTTAModel',
+ tta_cfg=dict(nms=dict(type='nms', iou_threshold=0.65), max_per_img=300))
+img_scales = [
+ (
+ 640,
+ 640,
+ ),
+ (
+ 320,
+ 320,
+ ),
+ (
+ 960,
+ 960,
+ ),
+]
+_multiscale_resize_transforms = [
+ dict(
+ type='Compose',
+ transforms=[
+ dict(type='YOLOv5KeepRatioResize', scale=(
+ 640,
+ 640,
+ )),
+ dict(
+ type='LetterResize',
+ scale=(
+ 640,
+ 640,
+ ),
+ allow_scale_up=False,
+ pad_val=dict(img=114)),
+ ]),
+ dict(
+ type='Compose',
+ transforms=[
+ dict(type='YOLOv5KeepRatioResize', scale=(
+ 320,
+ 320,
+ )),
+ dict(
+ type='LetterResize',
+ scale=(
+ 320,
+ 320,
+ ),
+ allow_scale_up=False,
+ pad_val=dict(img=114)),
+ ]),
+ dict(
+ type='Compose',
+ transforms=[
+ dict(type='YOLOv5KeepRatioResize', scale=(
+ 960,
+ 960,
+ )),
+ dict(
+ type='LetterResize',
+ scale=(
+ 960,
+ 960,
+ ),
+ allow_scale_up=False,
+ pad_val=dict(img=114)),
+ ]),
+]
+tta_pipeline = [
+ dict(type='LoadImageFromFile', file_client_args=dict(backend='disk')),
+ dict(
+ type='TestTimeAug',
+ transforms=[
+ [
+ dict(
+ type='Compose',
+ transforms=[
+ dict(type='YOLOv5KeepRatioResize', scale=(
+ 640,
+ 640,
+ )),
+ dict(
+ type='LetterResize',
+ scale=(
+ 640,
+ 640,
+ ),
+ allow_scale_up=False,
+ pad_val=dict(img=114)),
+ ]),
+ dict(
+ type='Compose',
+ transforms=[
+ dict(type='YOLOv5KeepRatioResize', scale=(
+ 320,
+ 320,
+ )),
+ dict(
+ type='LetterResize',
+ scale=(
+ 320,
+ 320,
+ ),
+ allow_scale_up=False,
+ pad_val=dict(img=114)),
+ ]),
+ dict(
+ type='Compose',
+ transforms=[
+ dict(type='YOLOv5KeepRatioResize', scale=(
+ 960,
+ 960,
+ )),
+ dict(
+ type='LetterResize',
+ scale=(
+ 960,
+ 960,
+ ),
+ allow_scale_up=False,
+ pad_val=dict(img=114)),
+ ]),
+ ],
+ [
+ dict(type='mmdet.RandomFlip', prob=1.0),
+ dict(type='mmdet.RandomFlip', prob=0.0),
+ ],
+ [
+ dict(type='mmdet.LoadAnnotations', with_bbox=True),
+ ],
+ [
+ dict(
+ type='mmdet.PackDetInputs',
+ meta_keys=(
+ 'img_id',
+ 'img_path',
+ 'ori_shape',
+ 'img_shape',
+ 'scale_factor',
+ 'pad_param',
+ 'flip',
+ 'flip_direction',
+ )),
+ ],
+ ]),
+]
+
+launcher = 'none'
\ No newline at end of file
diff --git a/Model/Model6/Model6_0_ClothesDetection/mmyolo/configs/yolov5/README.md b/Model/Model6/Model6_0_ClothesDetection/mmyolo/configs/yolov5/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..b22d880fc54f1638860a2783547229a9afd2fd2c
--- /dev/null
+++ b/Model/Model6/Model6_0_ClothesDetection/mmyolo/configs/yolov5/README.md
@@ -0,0 +1,118 @@
+# YOLOv5
+
+
+
+## Abstract
+
+YOLOv5 is a family of object detection architectures and models pretrained on the COCO dataset, and represents Ultralytics open-source research into future vision AI methods, incorporating lessons learned and best practices evolved over thousands of hours of research and development.
+
+
+
+YOLOv5-l-P5 model structure
+
+
+YOLOv5-l-P6 model structure
+
+
+
+
+YOLOv6-s model structure
+
+
+YOLOv6-l model structure
+
+
+
+
+YOLOv7-l-P5 model structure
+
+
+
+
+Show the paper's abstract
+
+
+Deeper neural networks are more difficult to train. We present a residual learning framework to ease the training of networks that are substantially deeper than those used previously. We explicitly reformulate the layers as learning residual functions with reference to the layer inputs, instead of learning unreferenced functions. We provide comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth. On the ImageNet dataset we evaluate residual nets with a depth of up to 152 layers---8x deeper than VGG nets but still having lower complexity. An ensemble of these residual nets achieves 3.57% error on the ImageNet test set. This result won the 1st place on the ILSVRC 2015 classification task. We also present analysis on CIFAR-10 with 100 and 1000 layers.
+
+The depth of representations is of central importance for many visual recognition tasks. Solely due to our extremely deep representations, we obtain a 28% relative improvement on the COCO object detection dataset. Deep residual nets are foundations of our submissions to ILSVRC & COCO 2015 competitions, where we also won the 1st places on the tasks of ImageNet detection, ImageNet localization, COCO detection, and COCO segmentation.
+
+
+
+
+## How to use it?
+
+
+
+**Predict image**
+
+```python
+from mmpretrain import inference_model
+
+predict = inference_model('resnet18_8xb16_cifar10', 'demo/bird.JPEG')
+print(predict['pred_class'])
+print(predict['pred_score'])
+```
+
+**Use the model**
+
+```python
+import torch
+from mmpretrain import get_model
+
+model = get_model('resnet18_8xb16_cifar10', pretrained=True)
+inputs = torch.rand(1, 3, 224, 224)
+out = model(inputs)
+print(type(out))
+# To extract features.
+feats = model.extract_feat(inputs)
+print(type(feats))
+```
+
+**Train/Test Command**
+
+Prepare your dataset according to the [docs](https://mmpretrain.readthedocs.io/en/latest/user_guides/dataset_prepare.html#prepare-dataset).
+
+Train:
+
+```shell
+python tools/train.py configs/resnet/resnet18_8xb16_cifar10.py
+```
+
+Test:
+
+```shell
+python tools/test.py configs/resnet/resnet18_8xb16_cifar10.py https://download.openmmlab.com/mmclassification/v0/resnet/resnet18_b16x8_cifar10_20210528-bd6371c8.pth
+```
+
+
+
+## Models and results
+
+### Image Classification on ImageNet-1k
+
+| Model | Pretrain | Params (M) | Flops (G) | Top-1 (%) | Top-5 (%) | Config | Download |
+| :--------------------------------- | :----------: | :--------: | :-------: | :-------: | :-------: | :-------------------------------------------: | :----------------------------------------------------------------------: |
+| `resnet18_8xb32_in1k` | From scratch | 11.69 | 1.82 | 69.90 | 89.43 | [config](resnet18_8xb32_in1k.py) | [model](https://download.openmmlab.com/mmclassification/v0/resnet/resnet18_8xb32_in1k_20210831-fbbb1da6.pth) \| [log](https://download.openmmlab.com/mmclassification/v0/resnet/resnet18_8xb32_in1k_20210831-fbbb1da6.json) |
+| `resnet34_8xb32_in1k` | From scratch | 2.18 | 3.68 | 73.62 | 91.59 | [config](resnet34_8xb32_in1k.py) | [model](https://download.openmmlab.com/mmclassification/v0/resnet/resnet34_8xb32_in1k_20210831-f257d4e6.pth) \| [log](https://download.openmmlab.com/mmclassification/v0/resnet/resnet34_8xb32_in1k_20210831-f257d4e6.json) |
+| `resnet50_8xb32_in1k` | From scratch | 25.56 | 4.12 | 76.55 | 93.06 | [config](resnet50_8xb32_in1k.py) | [model](https://download.openmmlab.com/mmclassification/v0/resnet/resnet50_8xb32_in1k_20210831-ea4938fc.pth) \| [log](https://download.openmmlab.com/mmclassification/v0/resnet/resnet50_8xb32_in1k_20210831-ea4938fc.json) |
+| `resnet101_8xb32_in1k` | From scratch | 44.55 | 7.85 | 77.97 | 94.06 | [config](resnet101_8xb32_in1k.py) | [model](https://download.openmmlab.com/mmclassification/v0/resnet/resnet101_8xb32_in1k_20210831-539c63f8.pth) \| [log](https://download.openmmlab.com/mmclassification/v0/resnet/resnet101_8xb32_in1k_20210831-539c63f8.json) |
+| `resnet152_8xb32_in1k` | From scratch | 60.19 | 11.58 | 78.48 | 94.13 | [config](resnet152_8xb32_in1k.py) | [model](https://download.openmmlab.com/mmclassification/v0/resnet/resnet152_8xb32_in1k_20210901-4d7582fa.pth) \| [log](https://download.openmmlab.com/mmclassification/v0/resnet/resnet152_8xb32_in1k_20210901-4d7582fa.json) |
+| `resnetv1d50_8xb32_in1k` | From scratch | 25.58 | 4.36 | 77.54 | 93.57 | [config](resnetv1d50_8xb32_in1k.py) | [model](https://download.openmmlab.com/mmclassification/v0/resnet/resnetv1d50_b32x8_imagenet_20210531-db14775a.pth) \| [log](https://download.openmmlab.com/mmclassification/v0/resnet/resnetv1d50_b32x8_imagenet_20210531-db14775a.json) |
+| `resnetv1d101_8xb32_in1k` | From scratch | 44.57 | 8.09 | 78.93 | 94.48 | [config](resnetv1d101_8xb32_in1k.py) | [model](https://download.openmmlab.com/mmclassification/v0/resnet/resnetv1d101_b32x8_imagenet_20210531-6e13bcd3.pth) \| [log](https://download.openmmlab.com/mmclassification/v0/resnet/resnetv1d101_b32x8_imagenet_20210531-6e13bcd3.json) |
+| `resnetv1d152_8xb32_in1k` | From scratch | 60.21 | 11.82 | 79.41 | 94.70 | [config](resnetv1d152_8xb32_in1k.py) | [model](https://download.openmmlab.com/mmclassification/v0/resnet/resnetv1d152_b32x8_imagenet_20210531-278cf22a.pth) \| [log](https://download.openmmlab.com/mmclassification/v0/resnet/resnetv1d152_b32x8_imagenet_20210531-278cf22a.json) |
+| `resnet50_8xb32-fp16_in1k` | From scratch | 25.56 | 4.12 | 76.30 | 93.07 | [config](resnet50_8xb32-fp16_in1k.py) | [model](https://download.openmmlab.com/mmclassification/v0/fp16/resnet50_batch256_fp16_imagenet_20210320-b3964210.pth) \| [log](https://download.openmmlab.com/mmclassification/v0/fp16/resnet50_batch256_fp16_imagenet_20210320-b3964210.json) |
+| `resnet50_8xb256-rsb-a1-600e_in1k` | From scratch | 25.56 | 4.12 | 80.12 | 94.78 | [config](resnet50_8xb256-rsb-a1-600e_in1k.py) | [model](https://download.openmmlab.com/mmclassification/v0/resnet/resnet50_8xb256-rsb-a1-600e_in1k_20211228-20e21305.pth) \| [log](https://download.openmmlab.com/mmclassification/v0/resnet/resnet50_8xb256-rsb-a1-600e_in1k_20211228-20e21305.json) |
+| `resnet50_8xb256-rsb-a2-300e_in1k` | From scratch | 25.56 | 4.12 | 79.55 | 94.37 | [config](resnet50_8xb256-rsb-a2-300e_in1k.py) | [model](https://download.openmmlab.com/mmclassification/v0/resnet/resnet50_8xb256-rsb-a2-300e_in1k_20211228-0fd8be6e.pth) \| [log](https://download.openmmlab.com/mmclassification/v0/resnet/resnet50_8xb256-rsb-a2-300e_in1k_20211228-0fd8be6e.json) |
+| `resnet50_8xb256-rsb-a3-100e_in1k` | From scratch | 25.56 | 4.12 | 78.30 | 93.80 | [config](resnet50_8xb256-rsb-a3-100e_in1k.py) | [model](https://download.openmmlab.com/mmclassification/v0/resnet/resnet50_8xb256-rsb-a3-100e_in1k_20211228-3493673c.pth) \| [log](https://download.openmmlab.com/mmclassification/v0/resnet/resnet50_8xb256-rsb-a3-100e_in1k_20211228-3493673c.json) |
+| `resnetv1c50_8xb32_in1k` | From scratch | 25.58 | 4.36 | 77.01 | 93.58 | [config](resnetv1c50_8xb32_in1k.py) | [model](https://download.openmmlab.com/mmclassification/v0/resnet/resnetv1c50_8xb32_in1k_20220214-3343eccd.pth) \| [log](https://download.openmmlab.com/mmclassification/v0/resnet/resnetv1c50_8xb32_in1k_20220214-3343eccd.json) |
+| `resnetv1c101_8xb32_in1k` | From scratch | 44.57 | 8.09 | 78.30 | 94.27 | [config](resnetv1c101_8xb32_in1k.py) | [model](https://download.openmmlab.com/mmclassification/v0/resnet/resnetv1c101_8xb32_in1k_20220214-434fe45f.pth) \| [log](https://download.openmmlab.com/mmclassification/v0/resnet/resnetv1c101_8xb32_in1k_20220214-434fe45f.json) |
+| `resnetv1c152_8xb32_in1k` | From scratch | 60.21 | 11.82 | 78.76 | 94.41 | [config](resnetv1c152_8xb32_in1k.py) | [model](https://download.openmmlab.com/mmclassification/v0/resnet/resnetv1c152_8xb32_in1k_20220214-c013291f.pth) \| [log](https://download.openmmlab.com/mmclassification/v0/resnet/resnetv1c152_8xb32_in1k_20220214-c013291f.json) |
+
+### Image Classification on CIFAR-10
+
+| Model | Pretrain | Params (M) | Flops (G) | Top-1 (%) | Config | Download |
+| :------------------------ | :----------: | :--------: | :-------: | :-------: | :----------------------------------: | :-------------------------------------------------------------------------------------------------: |
+| `resnet18_8xb16_cifar10` | From scratch | 11.17 | 0.56 | 94.82 | [config](resnet18_8xb16_cifar10.py) | [model](https://download.openmmlab.com/mmclassification/v0/resnet/resnet18_b16x8_cifar10_20210528-bd6371c8.pth) \| [log](https://download.openmmlab.com/mmclassification/v0/resnet/resnet18_b16x8_cifar10_20210528-bd6371c8.json) |
+| `resnet34_8xb16_cifar10` | From scratch | 21.28 | 1.16 | 95.34 | [config](resnet34_8xb16_cifar10.py) | [model](https://download.openmmlab.com/mmclassification/v0/resnet/resnet34_b16x8_cifar10_20210528-a8aa36a6.pth) \| [log](https://download.openmmlab.com/mmclassification/v0/resnet/resnet34_b16x8_cifar10_20210528-a8aa36a6.json) |
+| `resnet50_8xb16_cifar10` | From scratch | 23.52 | 1.31 | 95.55 | [config](resnet50_8xb16_cifar10.py) | [model](https://download.openmmlab.com/mmclassification/v0/resnet/resnet50_b16x8_cifar10_20210528-f54bfad9.pth) \| [log](https://download.openmmlab.com/mmclassification/v0/resnet/resnet50_b16x8_cifar10_20210528-f54bfad9.json) |
+| `resnet101_8xb16_cifar10` | From scratch | 42.51 | 2.52 | 95.58 | [config](resnet101_8xb16_cifar10.py) | [model](https://download.openmmlab.com/mmclassification/v0/resnet/resnet101_b16x8_cifar10_20210528-2d29e936.pth) \| [log](https://download.openmmlab.com/mmclassification/v0/resnet/resnet101_b16x8_cifar10_20210528-2d29e936.json) |
+| `resnet152_8xb16_cifar10` | From scratch | 58.16 | 3.74 | 95.76 | [config](resnet152_8xb16_cifar10.py) | [model](https://download.openmmlab.com/mmclassification/v0/resnet/resnet152_b16x8_cifar10_20210528-3e8e9178.pth) \| [log](https://download.openmmlab.com/mmclassification/v0/resnet/resnet152_b16x8_cifar10_20210528-3e8e9178.json) |
+
+### Image Classification on CIFAR-100
+
+| Model | Pretrain | Params (M) | Flops (G) | Top-1 (%) | Top-5 (%) | Config | Download |
+| :------------------------ | :----------: | :--------: | :-------: | :-------: | :-------: | :----------------------------------: | :----------------------------------------------------------------------------------------: |
+| `resnet50_8xb16_cifar100` | From scratch | 23.71 | 1.31 | 79.90 | 95.19 | [config](resnet50_8xb16_cifar100.py) | [model](https://download.openmmlab.com/mmclassification/v0/resnet/resnet50_b16x8_cifar100_20210528-67b58a1b.pth) \| [log](https://download.openmmlab.com/mmclassification/v0/resnet/resnet50_b16x8_cifar100_20210528-67b58a1b.json) |
+
+### Image Classification on CUB-200-2011
+
+| Model | Pretrain | Params (M) | Flops (G) | Top-1 (%) | Config | Download |
+| :------------------ | :----------: | :--------: | :-------: | :-------: | :----------------------------: | :-------------------------------------------------------------------------------------------------------------: |
+| `resnet50_8xb8_cub` | From scratch | 23.92 | 16.48 | 88.45 | [config](resnet50_8xb8_cub.py) | [model](https://download.openmmlab.com/mmclassification/v0/resnet/resnet50_8xb8_cub_20220307-57840e60.pth) \| [log](https://download.openmmlab.com/mmclassification/v0/resnet/resnet50_8xb8_cub_20220307-57840e60.json) |
+
+## Citation
+
+```bibtex
+@inproceedings{he2016deep,
+ title={Deep residual learning for image recognition},
+ author={He, Kaiming and Zhang, Xiangyu and Ren, Shaoqing and Sun, Jian},
+ booktitle={Proceedings of the IEEE conference on computer vision and pattern recognition},
+ pages={770--778},
+ year={2016}
+}
+```
diff --git a/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/configs/resnet/__init__.py b/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/configs/resnet/__init__.py
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/configs/resnet/metafile.yml b/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/configs/resnet/metafile.yml
new file mode 100644
index 0000000000000000000000000000000000000000..16387248c43aea59c5563b4c6c98df8dd8effead
--- /dev/null
+++ b/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/configs/resnet/metafile.yml
@@ -0,0 +1,352 @@
+Collections:
+ - Name: ResNet
+ Metadata:
+ Training Data: ImageNet-1k
+ Training Techniques:
+ - SGD with Momentum
+ - Weight Decay
+ Training Resources: 8x V100 GPUs
+ Epochs: 100
+ Batch Size: 256
+ Architecture:
+ - ResNet
+ Paper:
+ URL: https://openaccess.thecvf.com/content_cvpr_2016/html/He_Deep_Residual_Learning_CVPR_2016_paper.html
+ Title: "Deep Residual Learning for Image Recognition"
+ README: configs/resnet/README.md
+ Code:
+ URL: https://github.com/open-mmlab/mmpretrain/blob/v0.15.0/mmcls/models/backbones/resnet.py#L383
+ Version: v0.15.0
+
+Models:
+ - Name: resnet18_8xb16_cifar10
+ Metadata:
+ Training Data: CIFAR-10
+ Epochs: 200
+ Batch Size: 128
+ FLOPs: 560000000
+ Parameters: 11170000
+ In Collection: ResNet
+ Results:
+ - Dataset: CIFAR-10
+ Metrics:
+ Top 1 Accuracy: 94.82
+ Task: Image Classification
+ Weights: https://download.openmmlab.com/mmclassification/v0/resnet/resnet18_b16x8_cifar10_20210528-bd6371c8.pth
+ Config: configs/resnet/resnet18_8xb16_cifar10.py
+ - Name: resnet34_8xb16_cifar10
+ Metadata:
+ Training Data: CIFAR-10
+ Epochs: 200
+ Batch Size: 128
+ FLOPs: 1160000000
+ Parameters: 21280000
+ In Collection: ResNet
+ Results:
+ - Dataset: CIFAR-10
+ Metrics:
+ Top 1 Accuracy: 95.34
+ Task: Image Classification
+ Weights: https://download.openmmlab.com/mmclassification/v0/resnet/resnet34_b16x8_cifar10_20210528-a8aa36a6.pth
+ Config: configs/resnet/resnet34_8xb16_cifar10.py
+ - Name: resnet50_8xb16_cifar10
+ Metadata:
+ Training Data: CIFAR-10
+ Epochs: 200
+ Batch Size: 128
+ FLOPs: 1310000000
+ Parameters: 23520000
+ In Collection: ResNet
+ Results:
+ - Dataset: CIFAR-10
+ Metrics:
+ Top 1 Accuracy: 95.55
+ Task: Image Classification
+ Weights: https://download.openmmlab.com/mmclassification/v0/resnet/resnet50_b16x8_cifar10_20210528-f54bfad9.pth
+ Config: configs/resnet/resnet50_8xb16_cifar10.py
+ - Name: resnet101_8xb16_cifar10
+ Metadata:
+ Training Data: CIFAR-10
+ Epochs: 200
+ Batch Size: 128
+ FLOPs: 2520000000
+ Parameters: 42510000
+ In Collection: ResNet
+ Results:
+ - Dataset: CIFAR-10
+ Metrics:
+ Top 1 Accuracy: 95.58
+ Task: Image Classification
+ Weights: https://download.openmmlab.com/mmclassification/v0/resnet/resnet101_b16x8_cifar10_20210528-2d29e936.pth
+ Config: configs/resnet/resnet101_8xb16_cifar10.py
+ - Name: resnet152_8xb16_cifar10
+ Metadata:
+ Training Data: CIFAR-10
+ Epochs: 200
+ Batch Size: 128
+ FLOPs: 3740000000
+ Parameters: 58160000
+ In Collection: ResNet
+ Results:
+ - Dataset: CIFAR-10
+ Metrics:
+ Top 1 Accuracy: 95.76
+ Task: Image Classification
+ Weights: https://download.openmmlab.com/mmclassification/v0/resnet/resnet152_b16x8_cifar10_20210528-3e8e9178.pth
+ Config: configs/resnet/resnet152_8xb16_cifar10.py
+ - Name: resnet50_8xb16_cifar100
+ Metadata:
+ Training Data: CIFAR-100
+ Epochs: 200
+ Batch Size: 128
+ FLOPs: 1310000000
+ Parameters: 23710000
+ In Collection: ResNet
+ Results:
+ - Dataset: CIFAR-100
+ Metrics:
+ Top 1 Accuracy: 79.90
+ Top 5 Accuracy: 95.19
+ Task: Image Classification
+ Weights: https://download.openmmlab.com/mmclassification/v0/resnet/resnet50_b16x8_cifar100_20210528-67b58a1b.pth
+ Config: configs/resnet/resnet50_8xb16_cifar100.py
+ - Name: resnet18_8xb32_in1k
+ Metadata:
+ FLOPs: 1820000000
+ Parameters: 11690000
+ In Collection: ResNet
+ Results:
+ - Dataset: ImageNet-1k
+ Metrics:
+ Top 1 Accuracy: 69.90
+ Top 5 Accuracy: 89.43
+ Task: Image Classification
+ Weights: https://download.openmmlab.com/mmclassification/v0/resnet/resnet18_8xb32_in1k_20210831-fbbb1da6.pth
+ Config: configs/resnet/resnet18_8xb32_in1k.py
+ - Name: resnet34_8xb32_in1k
+ Metadata:
+ FLOPs: 3680000000
+ Parameters: 2180000
+ In Collection: ResNet
+ Results:
+ - Dataset: ImageNet-1k
+ Metrics:
+ Top 1 Accuracy: 73.62
+ Top 5 Accuracy: 91.59
+ Task: Image Classification
+ Weights: https://download.openmmlab.com/mmclassification/v0/resnet/resnet34_8xb32_in1k_20210831-f257d4e6.pth
+ Config: configs/resnet/resnet34_8xb32_in1k.py
+ - Name: resnet50_8xb32_in1k
+ Metadata:
+ FLOPs: 4120000000
+ Parameters: 25560000
+ In Collection: ResNet
+ Results:
+ - Dataset: ImageNet-1k
+ Metrics:
+ Top 1 Accuracy: 76.55
+ Top 5 Accuracy: 93.06
+ Task: Image Classification
+ Weights: https://download.openmmlab.com/mmclassification/v0/resnet/resnet50_8xb32_in1k_20210831-ea4938fc.pth
+ Config: configs/resnet/resnet50_8xb32_in1k.py
+ - Name: resnet101_8xb32_in1k
+ Metadata:
+ FLOPs: 7850000000
+ Parameters: 44550000
+ In Collection: ResNet
+ Results:
+ - Dataset: ImageNet-1k
+ Metrics:
+ Top 1 Accuracy: 77.97
+ Top 5 Accuracy: 94.06
+ Task: Image Classification
+ Weights: https://download.openmmlab.com/mmclassification/v0/resnet/resnet101_8xb32_in1k_20210831-539c63f8.pth
+ Config: configs/resnet/resnet101_8xb32_in1k.py
+ - Name: resnet152_8xb32_in1k
+ Metadata:
+ FLOPs: 11580000000
+ Parameters: 60190000
+ In Collection: ResNet
+ Results:
+ - Dataset: ImageNet-1k
+ Metrics:
+ Top 1 Accuracy: 78.48
+ Top 5 Accuracy: 94.13
+ Task: Image Classification
+ Weights: https://download.openmmlab.com/mmclassification/v0/resnet/resnet152_8xb32_in1k_20210901-4d7582fa.pth
+ Config: configs/resnet/resnet152_8xb32_in1k.py
+ - Name: resnetv1d50_8xb32_in1k
+ Metadata:
+ FLOPs: 4360000000
+ Parameters: 25580000
+ In Collection: ResNet
+ Results:
+ - Dataset: ImageNet-1k
+ Metrics:
+ Top 1 Accuracy: 77.54
+ Top 5 Accuracy: 93.57
+ Task: Image Classification
+ Weights: https://download.openmmlab.com/mmclassification/v0/resnet/resnetv1d50_b32x8_imagenet_20210531-db14775a.pth
+ Config: configs/resnet/resnetv1d50_8xb32_in1k.py
+ - Name: resnetv1d101_8xb32_in1k
+ Metadata:
+ FLOPs: 8090000000
+ Parameters: 44570000
+ In Collection: ResNet
+ Results:
+ - Dataset: ImageNet-1k
+ Metrics:
+ Top 1 Accuracy: 78.93
+ Top 5 Accuracy: 94.48
+ Task: Image Classification
+ Weights: https://download.openmmlab.com/mmclassification/v0/resnet/resnetv1d101_b32x8_imagenet_20210531-6e13bcd3.pth
+ Config: configs/resnet/resnetv1d101_8xb32_in1k.py
+ - Name: resnetv1d152_8xb32_in1k
+ Metadata:
+ FLOPs: 11820000000
+ Parameters: 60210000
+ In Collection: ResNet
+ Results:
+ - Dataset: ImageNet-1k
+ Metrics:
+ Top 1 Accuracy: 79.41
+ Top 5 Accuracy: 94.70
+ Task: Image Classification
+ Weights: https://download.openmmlab.com/mmclassification/v0/resnet/resnetv1d152_b32x8_imagenet_20210531-278cf22a.pth
+ Config: configs/resnet/resnetv1d152_8xb32_in1k.py
+ - Name: resnet50_8xb32-fp16_in1k
+ Metadata:
+ FLOPs: 4120000000
+ Parameters: 25560000
+ Training Techniques:
+ - SGD with Momentum
+ - Weight Decay
+ - Mixed Precision Training
+ In Collection: ResNet
+ Results:
+ - Task: Image Classification
+ Dataset: ImageNet-1k
+ Metrics:
+ Top 1 Accuracy: 76.30
+ Top 5 Accuracy: 93.07
+ Weights: https://download.openmmlab.com/mmclassification/v0/fp16/resnet50_batch256_fp16_imagenet_20210320-b3964210.pth
+ Config: configs/resnet/resnet50_8xb32-fp16_in1k.py
+ - Name: resnet50_8xb256-rsb-a1-600e_in1k
+ Metadata:
+ FLOPs: 4120000000
+ Parameters: 25560000
+ Training Techniques:
+ - LAMB
+ - Weight Decay
+ - Cosine Annealing
+ - Mixup
+ - CutMix
+ - RepeatAugSampler
+ - RandAugment
+ Epochs: 600
+ Batch Size: 2048
+ In Collection: ResNet
+ Results:
+ - Task: Image Classification
+ Dataset: ImageNet-1k
+ Metrics:
+ Top 1 Accuracy: 80.12
+ Top 5 Accuracy: 94.78
+ Weights: https://download.openmmlab.com/mmclassification/v0/resnet/resnet50_8xb256-rsb-a1-600e_in1k_20211228-20e21305.pth
+ Config: configs/resnet/resnet50_8xb256-rsb-a1-600e_in1k.py
+ - Name: resnet50_8xb256-rsb-a2-300e_in1k
+ Metadata:
+ FLOPs: 4120000000
+ Parameters: 25560000
+ Training Techniques:
+ - LAMB
+ - Weight Decay
+ - Cosine Annealing
+ - Mixup
+ - CutMix
+ - RepeatAugSampler
+ - RandAugment
+ Epochs: 300
+ Batch Size: 2048
+ In Collection: ResNet
+ Results:
+ - Task: Image Classification
+ Dataset: ImageNet-1k
+ Metrics:
+ Top 1 Accuracy: 79.55
+ Top 5 Accuracy: 94.37
+ Weights: https://download.openmmlab.com/mmclassification/v0/resnet/resnet50_8xb256-rsb-a2-300e_in1k_20211228-0fd8be6e.pth
+ Config: configs/resnet/resnet50_8xb256-rsb-a2-300e_in1k.py
+ - Name: resnet50_8xb256-rsb-a3-100e_in1k
+ Metadata:
+ FLOPs: 4120000000
+ Parameters: 25560000
+ Training Techniques:
+ - LAMB
+ - Weight Decay
+ - Cosine Annealing
+ - Mixup
+ - CutMix
+ - RandAugment
+ Batch Size: 2048
+ In Collection: ResNet
+ Results:
+ - Task: Image Classification
+ Dataset: ImageNet-1k
+ Metrics:
+ Top 1 Accuracy: 78.30
+ Top 5 Accuracy: 93.80
+ Weights: https://download.openmmlab.com/mmclassification/v0/resnet/resnet50_8xb256-rsb-a3-100e_in1k_20211228-3493673c.pth
+ Config: configs/resnet/resnet50_8xb256-rsb-a3-100e_in1k.py
+ - Name: resnetv1c50_8xb32_in1k
+ Metadata:
+ FLOPs: 4360000000
+ Parameters: 25580000
+ In Collection: ResNet
+ Results:
+ - Dataset: ImageNet-1k
+ Metrics:
+ Top 1 Accuracy: 77.01
+ Top 5 Accuracy: 93.58
+ Task: Image Classification
+ Weights: https://download.openmmlab.com/mmclassification/v0/resnet/resnetv1c50_8xb32_in1k_20220214-3343eccd.pth
+ Config: configs/resnet/resnetv1c50_8xb32_in1k.py
+ - Name: resnetv1c101_8xb32_in1k
+ Metadata:
+ FLOPs: 8090000000
+ Parameters: 44570000
+ In Collection: ResNet
+ Results:
+ - Dataset: ImageNet-1k
+ Metrics:
+ Top 1 Accuracy: 78.30
+ Top 5 Accuracy: 94.27
+ Task: Image Classification
+ Weights: https://download.openmmlab.com/mmclassification/v0/resnet/resnetv1c101_8xb32_in1k_20220214-434fe45f.pth
+ Config: configs/resnet/resnetv1c101_8xb32_in1k.py
+ - Name: resnetv1c152_8xb32_in1k
+ Metadata:
+ FLOPs: 11820000000
+ Parameters: 60210000
+ In Collection: ResNet
+ Results:
+ - Dataset: ImageNet-1k
+ Metrics:
+ Top 1 Accuracy: 78.76
+ Top 5 Accuracy: 94.41
+ Task: Image Classification
+ Weights: https://download.openmmlab.com/mmclassification/v0/resnet/resnetv1c152_8xb32_in1k_20220214-c013291f.pth
+ Config: configs/resnet/resnetv1c152_8xb32_in1k.py
+ - Name: resnet50_8xb8_cub
+ Metadata:
+ FLOPs: 16480000000
+ Parameters: 23920000
+ In Collection: ResNet
+ Results:
+ - Dataset: CUB-200-2011
+ Metrics:
+ Top 1 Accuracy: 88.45
+ Task: Image Classification
+ Pretrain: https://download.openmmlab.com/mmclassification/v0/resnet/resnet50_3rdparty-mill_in21k_20220331-faac000b.pth
+ Weights: https://download.openmmlab.com/mmclassification/v0/resnet/resnet50_8xb8_cub_20220307-57840e60.pth
+ Config: configs/resnet/resnet50_8xb8_cub.py
diff --git a/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/configs/resnet/resnet101_8xb16_cifar10.py b/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/configs/resnet/resnet101_8xb16_cifar10.py
new file mode 100644
index 0000000000000000000000000000000000000000..166a1740b09c5fb74462a0672cd5fef54caae8f7
--- /dev/null
+++ b/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/configs/resnet/resnet101_8xb16_cifar10.py
@@ -0,0 +1,5 @@
+_base_ = [
+ '../_base_/models/resnet101_cifar.py',
+ '../_base_/datasets/cifar10_bs16.py',
+ '../_base_/schedules/cifar10_bs128.py', '../_base_/default_runtime.py'
+]
diff --git a/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/configs/resnet/resnet101_8xb32_in1k.py b/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/configs/resnet/resnet101_8xb32_in1k.py
new file mode 100644
index 0000000000000000000000000000000000000000..388d2cd918ab75ec46346faa0448ef9cf2893fc8
--- /dev/null
+++ b/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/configs/resnet/resnet101_8xb32_in1k.py
@@ -0,0 +1,4 @@
+_base_ = [
+ '../_base_/models/resnet101.py', '../_base_/datasets/imagenet_bs32.py',
+ '../_base_/schedules/imagenet_bs256.py', '../_base_/default_runtime.py'
+]
diff --git a/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/configs/resnet/resnet152_8xb16_cifar10.py b/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/configs/resnet/resnet152_8xb16_cifar10.py
new file mode 100644
index 0000000000000000000000000000000000000000..3f307b6aa81661558b8308094de6e8327d08c830
--- /dev/null
+++ b/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/configs/resnet/resnet152_8xb16_cifar10.py
@@ -0,0 +1,5 @@
+_base_ = [
+ '../_base_/models/resnet152_cifar.py',
+ '../_base_/datasets/cifar10_bs16.py',
+ '../_base_/schedules/cifar10_bs128.py', '../_base_/default_runtime.py'
+]
diff --git a/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/configs/resnet/resnet152_8xb32_in1k.py b/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/configs/resnet/resnet152_8xb32_in1k.py
new file mode 100644
index 0000000000000000000000000000000000000000..cc9dc2cee4a0fd8a9d47d461b2d5d00bf9962bf5
--- /dev/null
+++ b/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/configs/resnet/resnet152_8xb32_in1k.py
@@ -0,0 +1,4 @@
+_base_ = [
+ '../_base_/models/resnet152.py', '../_base_/datasets/imagenet_bs32.py',
+ '../_base_/schedules/imagenet_bs256.py', '../_base_/default_runtime.py'
+]
diff --git a/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/configs/resnet/resnet18_8xb16_cifar10.py b/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/configs/resnet/resnet18_8xb16_cifar10.py
new file mode 100644
index 0000000000000000000000000000000000000000..c7afa397b7b6a01decd0a010816ebe3678ca44aa
--- /dev/null
+++ b/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/configs/resnet/resnet18_8xb16_cifar10.py
@@ -0,0 +1,4 @@
+_base_ = [
+ '../_base_/models/resnet18_cifar.py', '../_base_/datasets/cifar10_bs16.py',
+ '../_base_/schedules/cifar10_bs128.py', '../_base_/default_runtime.py'
+]
diff --git a/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/configs/resnet/resnet18_8xb32_in1k.py b/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/configs/resnet/resnet18_8xb32_in1k.py
new file mode 100644
index 0000000000000000000000000000000000000000..ac452ff75602464eba84a3eea150b30748122c69
--- /dev/null
+++ b/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/configs/resnet/resnet18_8xb32_in1k.py
@@ -0,0 +1,4 @@
+_base_ = [
+ '../_base_/models/resnet18.py', '../_base_/datasets/imagenet_bs32.py',
+ '../_base_/schedules/imagenet_bs256.py', '../_base_/default_runtime.py'
+]
diff --git a/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/configs/resnet/resnet34_8xb16_cifar10.py b/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/configs/resnet/resnet34_8xb16_cifar10.py
new file mode 100644
index 0000000000000000000000000000000000000000..7f5cd517d505ea479b506b6e4756c117c392dabd
--- /dev/null
+++ b/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/configs/resnet/resnet34_8xb16_cifar10.py
@@ -0,0 +1,4 @@
+_base_ = [
+ '../_base_/models/resnet34_cifar.py', '../_base_/datasets/cifar10_bs16.py',
+ '../_base_/schedules/cifar10_bs128.py', '../_base_/default_runtime.py'
+]
diff --git a/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/configs/resnet/resnet34_8xb32_in1k.py b/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/configs/resnet/resnet34_8xb32_in1k.py
new file mode 100644
index 0000000000000000000000000000000000000000..7749261c80defef7cbf94c4e1284c26382246dc6
--- /dev/null
+++ b/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/configs/resnet/resnet34_8xb32_in1k.py
@@ -0,0 +1,4 @@
+_base_ = [
+ '../_base_/models/resnet34.py', '../_base_/datasets/imagenet_bs32.py',
+ '../_base_/schedules/imagenet_bs256.py', '../_base_/default_runtime.py'
+]
diff --git a/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/configs/resnet/resnet50_32xb64-warmup-coslr_in1k.py b/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/configs/resnet/resnet50_32xb64-warmup-coslr_in1k.py
new file mode 100644
index 0000000000000000000000000000000000000000..c26245ef53a736c22c0ef7d4e9d8b7876509fe2e
--- /dev/null
+++ b/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/configs/resnet/resnet50_32xb64-warmup-coslr_in1k.py
@@ -0,0 +1,5 @@
+_base_ = [
+ '../_base_/models/resnet50.py', '../_base_/datasets/imagenet_bs64.py',
+ '../_base_/schedules/imagenet_bs2048_coslr.py',
+ '../_base_/default_runtime.py'
+]
diff --git a/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/configs/resnet/resnet50_32xb64-warmup-lbs_in1k.py b/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/configs/resnet/resnet50_32xb64-warmup-lbs_in1k.py
new file mode 100644
index 0000000000000000000000000000000000000000..2f24f9a0f2c54a2bb634c1f374bc1b534d63697f
--- /dev/null
+++ b/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/configs/resnet/resnet50_32xb64-warmup-lbs_in1k.py
@@ -0,0 +1,12 @@
+_base_ = ['./resnet50_32xb64-warmup_in1k.py']
+model = dict(
+ head=dict(
+ type='LinearClsHead',
+ num_classes=1000,
+ in_channels=2048,
+ loss=dict(
+ type='LabelSmoothLoss',
+ loss_weight=1.0,
+ label_smooth_val=0.1,
+ num_classes=1000),
+ ))
diff --git a/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/configs/resnet/resnet50_32xb64-warmup_in1k.py b/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/configs/resnet/resnet50_32xb64-warmup_in1k.py
new file mode 100644
index 0000000000000000000000000000000000000000..34d5288b9d3f9fcf3f0b409dc1c17906654c2170
--- /dev/null
+++ b/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/configs/resnet/resnet50_32xb64-warmup_in1k.py
@@ -0,0 +1,4 @@
+_base_ = [
+ '../_base_/models/resnet50.py', '../_base_/datasets/imagenet_bs64.py',
+ '../_base_/schedules/imagenet_bs2048.py', '../_base_/default_runtime.py'
+]
diff --git a/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/configs/resnet/resnet50_8xb128_coslr-90e_in21k.py b/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/configs/resnet/resnet50_8xb128_coslr-90e_in21k.py
new file mode 100644
index 0000000000000000000000000000000000000000..d2cc1ee2830661998505310d8c7074d8ae5da6b4
--- /dev/null
+++ b/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/configs/resnet/resnet50_8xb128_coslr-90e_in21k.py
@@ -0,0 +1,11 @@
+_base_ = [
+ '../_base_/models/resnet50.py', '../_base_/datasets/imagenet21k_bs128.py',
+ '../_base_/schedules/imagenet_bs1024_coslr.py',
+ '../_base_/default_runtime.py'
+]
+
+# model settings
+model = dict(head=dict(num_classes=21843))
+
+# runtime settings
+train_cfg = dict(by_epoch=True, max_epochs=90)
diff --git a/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/configs/resnet/resnet50_8xb16-mixup_cifar10.py b/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/configs/resnet/resnet50_8xb16-mixup_cifar10.py
new file mode 100644
index 0000000000000000000000000000000000000000..2420ebfeb0a34675a4b1b2a69c0b8a39e197ce35
--- /dev/null
+++ b/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/configs/resnet/resnet50_8xb16-mixup_cifar10.py
@@ -0,0 +1,5 @@
+_base_ = [
+ '../_base_/models/resnet50_cifar_mixup.py',
+ '../_base_/datasets/cifar10_bs16.py',
+ '../_base_/schedules/cifar10_bs128.py', '../_base_/default_runtime.py'
+]
diff --git a/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/configs/resnet/resnet50_8xb16_cifar10.py b/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/configs/resnet/resnet50_8xb16_cifar10.py
new file mode 100644
index 0000000000000000000000000000000000000000..669e5de27e526dd46d9f06c99e478dce16f0ac9a
--- /dev/null
+++ b/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/configs/resnet/resnet50_8xb16_cifar10.py
@@ -0,0 +1,4 @@
+_base_ = [
+ '../_base_/models/resnet50_cifar.py', '../_base_/datasets/cifar10_bs16.py',
+ '../_base_/schedules/cifar10_bs128.py', '../_base_/default_runtime.py'
+]
diff --git a/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/configs/resnet/resnet50_8xb16_cifar100.py b/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/configs/resnet/resnet50_8xb16_cifar100.py
new file mode 100644
index 0000000000000000000000000000000000000000..ebde6c76ecca6d23b58edfb85ebc3b72ce15a2b2
--- /dev/null
+++ b/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/configs/resnet/resnet50_8xb16_cifar100.py
@@ -0,0 +1,19 @@
+_base_ = [
+ '../_base_/models/resnet50_cifar.py',
+ '../_base_/datasets/cifar100_bs16.py',
+ '../_base_/schedules/cifar10_bs128.py',
+ '../_base_/default_runtime.py',
+]
+
+# model settings
+model = dict(head=dict(num_classes=100))
+
+# schedule settings
+optim_wrapper = dict(optimizer=dict(weight_decay=0.0005))
+
+param_scheduler = dict(
+ type='MultiStepLR',
+ by_epoch=True,
+ milestones=[60, 120, 160],
+ gamma=0.2,
+)
diff --git a/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/configs/resnet/resnet50_8xb256-rsb-a1-600e_in1k.py b/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/configs/resnet/resnet50_8xb256-rsb-a1-600e_in1k.py
new file mode 100644
index 0000000000000000000000000000000000000000..a4ea15984a0063c06e09eb5063d49b2cf90371cf
--- /dev/null
+++ b/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/configs/resnet/resnet50_8xb256-rsb-a1-600e_in1k.py
@@ -0,0 +1,56 @@
+_base_ = [
+ '../_base_/models/resnet50.py',
+ '../_base_/datasets/imagenet_bs256_rsb_a12.py',
+ '../_base_/schedules/imagenet_bs2048_rsb.py',
+ '../_base_/default_runtime.py'
+]
+
+# model settings
+model = dict(
+ backbone=dict(
+ norm_cfg=dict(type='SyncBN', requires_grad=True),
+ drop_path_rate=0.05,
+ ),
+ head=dict(
+ loss=dict(
+ type='LabelSmoothLoss',
+ label_smooth_val=0.1,
+ mode='original',
+ use_sigmoid=True,
+ )),
+ train_cfg=dict(augments=[
+ dict(type='Mixup', alpha=0.2),
+ dict(type='CutMix', alpha=1.0)
+ ]),
+)
+
+# dataset settings
+train_dataloader = dict(sampler=dict(type='RepeatAugSampler', shuffle=True))
+
+# schedule settings
+optim_wrapper = dict(
+ optimizer=dict(weight_decay=0.01),
+ paramwise_cfg=dict(bias_decay_mult=0., norm_decay_mult=0.),
+)
+
+param_scheduler = [
+ # warm up learning rate scheduler
+ dict(
+ type='LinearLR',
+ start_factor=0.0001,
+ by_epoch=True,
+ begin=0,
+ end=5,
+ # update by iter
+ convert_to_iter_based=True),
+ # main learning rate scheduler
+ dict(
+ type='CosineAnnealingLR',
+ T_max=595,
+ eta_min=1.0e-6,
+ by_epoch=True,
+ begin=5,
+ end=600)
+]
+
+train_cfg = dict(by_epoch=True, max_epochs=600)
diff --git a/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/configs/resnet/resnet50_8xb256-rsb-a2-300e_in1k.py b/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/configs/resnet/resnet50_8xb256-rsb-a2-300e_in1k.py
new file mode 100644
index 0000000000000000000000000000000000000000..df8edc0370400a3f3985c33bffae2d04afc55772
--- /dev/null
+++ b/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/configs/resnet/resnet50_8xb256-rsb-a2-300e_in1k.py
@@ -0,0 +1,46 @@
+_base_ = [
+ '../_base_/models/resnet50.py',
+ '../_base_/datasets/imagenet_bs256_rsb_a12.py',
+ '../_base_/schedules/imagenet_bs2048_rsb.py',
+ '../_base_/default_runtime.py'
+]
+
+# model settings
+model = dict(
+ backbone=dict(
+ norm_cfg=dict(type='SyncBN', requires_grad=True),
+ drop_path_rate=0.05,
+ ),
+ head=dict(loss=dict(use_sigmoid=True)),
+ train_cfg=dict(augments=[
+ dict(type='Mixup', alpha=0.1),
+ dict(type='CutMix', alpha=1.0)
+ ]))
+
+# dataset settings
+train_dataloader = dict(sampler=dict(type='RepeatAugSampler', shuffle=True))
+
+# schedule settings
+optim_wrapper = dict(
+ paramwise_cfg=dict(bias_decay_mult=0., norm_decay_mult=0.))
+
+param_scheduler = [
+ # warm up learning rate scheduler
+ dict(
+ type='LinearLR',
+ start_factor=0.0001,
+ by_epoch=True,
+ begin=0,
+ end=5,
+ # update by iter
+ convert_to_iter_based=True),
+ # main learning rate scheduler
+ dict(
+ type='CosineAnnealingLR',
+ T_max=295,
+ eta_min=1.0e-6,
+ by_epoch=True,
+ begin=5,
+ end=300)
+]
+train_cfg = dict(by_epoch=True, max_epochs=300)
diff --git a/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/configs/resnet/resnet50_8xb256-rsb-a3-100e_in1k.py b/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/configs/resnet/resnet50_8xb256-rsb-a3-100e_in1k.py
new file mode 100644
index 0000000000000000000000000000000000000000..3a36c5843a69aea20fdb9287561e5c2a96459852
--- /dev/null
+++ b/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/configs/resnet/resnet50_8xb256-rsb-a3-100e_in1k.py
@@ -0,0 +1,22 @@
+_base_ = [
+ '../_base_/models/resnet50.py',
+ '../_base_/datasets/imagenet_bs256_rsb_a3.py',
+ '../_base_/schedules/imagenet_bs2048_rsb.py',
+ '../_base_/default_runtime.py'
+]
+
+# model settings
+model = dict(
+ backbone=dict(norm_cfg=dict(type='SyncBN', requires_grad=True)),
+ head=dict(loss=dict(use_sigmoid=True)),
+ train_cfg=dict(augments=[
+ dict(type='Mixup', alpha=0.1),
+ dict(type='CutMix', alpha=1.0)
+ ]),
+)
+
+# schedule settings
+optim_wrapper = dict(
+ optimizer=dict(lr=0.008),
+ paramwise_cfg=dict(bias_decay_mult=0., norm_decay_mult=0.),
+)
diff --git a/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/configs/resnet/resnet50_8xb32-coslr-preciseBN_in1k.py b/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/configs/resnet/resnet50_8xb32-coslr-preciseBN_in1k.py
new file mode 100644
index 0000000000000000000000000000000000000000..01fefbbf2852eeceddb0ad026fb5098e763e0710
--- /dev/null
+++ b/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/configs/resnet/resnet50_8xb32-coslr-preciseBN_in1k.py
@@ -0,0 +1,13 @@
+_base_ = 'resnet50_8xb32-coslr_in1k.py'
+
+# Precise BN hook will update the bn stats, so this hook should be executed
+# before CheckpointHook(priority of 'VERY_LOW') and
+# EMAHook(priority of 'NORMAL') So set the priority of PreciseBNHook to
+# 'ABOVENORMAL' here.
+custom_hooks = [
+ dict(
+ type='PreciseBNHook',
+ num_samples=8192,
+ interval=1,
+ priority='ABOVE_NORMAL')
+]
diff --git a/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/configs/resnet/resnet50_8xb32-coslr_in1k.py b/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/configs/resnet/resnet50_8xb32-coslr_in1k.py
new file mode 100644
index 0000000000000000000000000000000000000000..938a114b79696b5ad3442c1dd2a7aea33342b679
--- /dev/null
+++ b/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/configs/resnet/resnet50_8xb32-coslr_in1k.py
@@ -0,0 +1,5 @@
+_base_ = [
+ '../_base_/models/resnet50.py', '../_base_/datasets/imagenet_bs32.py',
+ '../_base_/schedules/imagenet_bs256_coslr.py',
+ '../_base_/default_runtime.py'
+]
diff --git a/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/configs/resnet/resnet50_8xb32-cutmix_in1k.py b/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/configs/resnet/resnet50_8xb32-cutmix_in1k.py
new file mode 100644
index 0000000000000000000000000000000000000000..2f8d0ca9f3a500344c18b669f25f3cb78393d7dd
--- /dev/null
+++ b/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/configs/resnet/resnet50_8xb32-cutmix_in1k.py
@@ -0,0 +1,5 @@
+_base_ = [
+ '../_base_/models/resnet50_cutmix.py',
+ '../_base_/datasets/imagenet_bs32.py',
+ '../_base_/schedules/imagenet_bs256.py', '../_base_/default_runtime.py'
+]
diff --git a/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/configs/resnet/resnet50_8xb32-fp16-dynamic_in1k.py b/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/configs/resnet/resnet50_8xb32-fp16-dynamic_in1k.py
new file mode 100644
index 0000000000000000000000000000000000000000..58f6fe4cf25e8f0b3d321a7aab4b746552aa4163
--- /dev/null
+++ b/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/configs/resnet/resnet50_8xb32-fp16-dynamic_in1k.py
@@ -0,0 +1,4 @@
+_base_ = ['./resnet50_8xb32_in1k.py']
+
+# schedule settings
+optim_wrapper = dict(type='AmpOptimWrapper', loss_scale='dynamic')
diff --git a/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/configs/resnet/resnet50_8xb32-fp16_in1k.py b/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/configs/resnet/resnet50_8xb32-fp16_in1k.py
new file mode 100644
index 0000000000000000000000000000000000000000..19ee6ee4f82ec02f34628bdf8dd74a379798cc67
--- /dev/null
+++ b/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/configs/resnet/resnet50_8xb32-fp16_in1k.py
@@ -0,0 +1,4 @@
+_base_ = ['./resnet50_8xb32_in1k.py']
+
+# schedule settings
+optim_wrapper = dict(type='AmpOptimWrapper', loss_scale=512.)
diff --git a/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/configs/resnet/resnet50_8xb32-lbs_in1k.py b/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/configs/resnet/resnet50_8xb32-lbs_in1k.py
new file mode 100644
index 0000000000000000000000000000000000000000..1c1aa5a2c4eee10c10159175224d9b77ea57e57b
--- /dev/null
+++ b/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/configs/resnet/resnet50_8xb32-lbs_in1k.py
@@ -0,0 +1,5 @@
+_base_ = [
+ '../_base_/models/resnet50_label_smooth.py',
+ '../_base_/datasets/imagenet_bs32.py',
+ '../_base_/schedules/imagenet_bs256.py', '../_base_/default_runtime.py'
+]
diff --git a/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/configs/resnet/resnet50_8xb32-mixup_in1k.py b/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/configs/resnet/resnet50_8xb32-mixup_in1k.py
new file mode 100644
index 0000000000000000000000000000000000000000..2a153d0e18f521f72b8beaf4cbea36d41f5b3300
--- /dev/null
+++ b/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/configs/resnet/resnet50_8xb32-mixup_in1k.py
@@ -0,0 +1,5 @@
+_base_ = [
+ '../_base_/models/resnet50_mixup.py',
+ '../_base_/datasets/imagenet_bs32.py',
+ '../_base_/schedules/imagenet_bs256.py', '../_base_/default_runtime.py'
+]
diff --git a/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/configs/resnet/resnet50_8xb32_in1k.py b/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/configs/resnet/resnet50_8xb32_in1k.py
new file mode 100644
index 0000000000000000000000000000000000000000..c32f333b67c255c6101469323636bf242eebb8da
--- /dev/null
+++ b/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/configs/resnet/resnet50_8xb32_in1k.py
@@ -0,0 +1,4 @@
+_base_ = [
+ '../_base_/models/resnet50.py', '../_base_/datasets/imagenet_bs32.py',
+ '../_base_/schedules/imagenet_bs256.py', '../_base_/default_runtime.py'
+]
diff --git a/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/configs/resnet/resnet50_8xb8_cub.py b/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/configs/resnet/resnet50_8xb8_cub.py
new file mode 100644
index 0000000000000000000000000000000000000000..17054ef536930d74136897f8f25637321a364ce7
--- /dev/null
+++ b/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/configs/resnet/resnet50_8xb8_cub.py
@@ -0,0 +1,20 @@
+_base_ = [
+ '../_base_/models/resnet50.py',
+ '../_base_/datasets/cub_bs8_448.py',
+ '../_base_/schedules/cub_bs64.py',
+ '../_base_/default_runtime.py',
+]
+
+# model settings
+# use pre-train weight converted from https://github.com/Alibaba-MIIL/ImageNet21K # noqa
+pretrained = 'https://download.openmmlab.com/mmclassification/v0/resnet/resnet50_3rdparty-mill_in21k_20220331-faac000b.pth' # noqa
+
+model = dict(
+ type='ImageClassifier',
+ backbone=dict(
+ init_cfg=dict(
+ type='Pretrained', checkpoint=pretrained, prefix='backbone')),
+ head=dict(num_classes=200, ))
+
+# runtime settings
+default_hooks = dict(logger=dict(type='LoggerHook', interval=20))
diff --git a/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/configs/resnet/resnetv1c101_8xb32_in1k.py b/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/configs/resnet/resnetv1c101_8xb32_in1k.py
new file mode 100644
index 0000000000000000000000000000000000000000..441aff591851f402a176c142c93dc866a77b82c2
--- /dev/null
+++ b/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/configs/resnet/resnetv1c101_8xb32_in1k.py
@@ -0,0 +1,7 @@
+_base_ = [
+ '../_base_/models/resnetv1c50.py',
+ '../_base_/datasets/imagenet_bs32_pil_resize.py',
+ '../_base_/schedules/imagenet_bs256.py', '../_base_/default_runtime.py'
+]
+
+model = dict(backbone=dict(depth=101))
diff --git a/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/configs/resnet/resnetv1c152_8xb32_in1k.py b/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/configs/resnet/resnetv1c152_8xb32_in1k.py
new file mode 100644
index 0000000000000000000000000000000000000000..b9f466f85c8e8c89fb78f53c27eca1d5acaf5221
--- /dev/null
+++ b/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/configs/resnet/resnetv1c152_8xb32_in1k.py
@@ -0,0 +1,7 @@
+_base_ = [
+ '../_base_/models/resnetv1c50.py',
+ '../_base_/datasets/imagenet_bs32_pil_resize.py',
+ '../_base_/schedules/imagenet_bs256.py', '../_base_/default_runtime.py'
+]
+
+model = dict(backbone=dict(depth=152))
diff --git a/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/configs/resnet/resnetv1c50_8xb32_in1k.py b/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/configs/resnet/resnetv1c50_8xb32_in1k.py
new file mode 100644
index 0000000000000000000000000000000000000000..aa1c8b6475ce373f4a35123a72e31419b87027c0
--- /dev/null
+++ b/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/configs/resnet/resnetv1c50_8xb32_in1k.py
@@ -0,0 +1,5 @@
+_base_ = [
+ '../_base_/models/resnetv1c50.py',
+ '../_base_/datasets/imagenet_bs32_pil_resize.py',
+ '../_base_/schedules/imagenet_bs256.py', '../_base_/default_runtime.py'
+]
diff --git a/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/configs/resnet/resnetv1d101_8xb32_in1k.py b/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/configs/resnet/resnetv1d101_8xb32_in1k.py
new file mode 100644
index 0000000000000000000000000000000000000000..b16ca863db2c50267764b1b37aa8b2db891ad2c9
--- /dev/null
+++ b/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/configs/resnet/resnetv1d101_8xb32_in1k.py
@@ -0,0 +1,5 @@
+_base_ = [
+ '../_base_/models/resnetv1d101.py',
+ '../_base_/datasets/imagenet_bs32_pil_resize.py',
+ '../_base_/schedules/imagenet_bs256.py', '../_base_/default_runtime.py'
+]
diff --git a/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/configs/resnet/resnetv1d152_8xb32_in1k.py b/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/configs/resnet/resnetv1d152_8xb32_in1k.py
new file mode 100644
index 0000000000000000000000000000000000000000..76926ddbb661029b8cff86ad0d98028531235fa1
--- /dev/null
+++ b/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/configs/resnet/resnetv1d152_8xb32_in1k.py
@@ -0,0 +1,5 @@
+_base_ = [
+ '../_base_/models/resnetv1d152.py',
+ '../_base_/datasets/imagenet_bs32_pil_resize.py',
+ '../_base_/schedules/imagenet_bs256.py', '../_base_/default_runtime.py'
+]
diff --git a/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/configs/resnet/resnetv1d50_8xb32_in1k.py b/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/configs/resnet/resnetv1d50_8xb32_in1k.py
new file mode 100644
index 0000000000000000000000000000000000000000..208bde470ad12407d7e56eddeddfc88529e3708b
--- /dev/null
+++ b/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/configs/resnet/resnetv1d50_8xb32_in1k.py
@@ -0,0 +1,5 @@
+_base_ = [
+ '../_base_/models/resnetv1d50.py',
+ '../_base_/datasets/imagenet_bs32_pil_resize.py',
+ '../_base_/schedules/imagenet_bs256.py', '../_base_/default_runtime.py'
+]
diff --git a/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/configs/resnext101_4xb16_1024e_4channel.py b/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/configs/resnext101_4xb16_1024e_4channel.py
new file mode 100644
index 0000000000000000000000000000000000000000..0de71f68d6705b3fc1000419ca705be2b839d425
--- /dev/null
+++ b/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/configs/resnext101_4xb16_1024e_4channel.py
@@ -0,0 +1,88 @@
+_base_ = [ # 此配置文件将继承所有 `_base_` 中的配置
+ '../configs/_base_/schedules/custom_schedule.py', # 训练策略配置
+ '../configs/_base_/default_runtime.py' # 默认运行设置
+]
+
+default_hooks = dict(
+ # print log every 50 iterations.
+ logger=dict(type='LoggerHook', interval=25),
+ # save checkpoint per 8 epochs.
+ checkpoint=dict(save_best='auto', interval=16)
+)
+
+visualizer = dict(
+ vis_backends=[dict(type='LocalVisBackend'),
+ dict(type='WandbVisBackend')])
+
+dataset_type = 'CustomDataset'
+
+# config of pipline
+train_pipeline = [
+ dict(type='LoadImageFromFile', imdecode_backend='pillow', color_type='unchanged'), # 读取图像
+ dict(type='RandomResizedCrop', scale=224), # 随机放缩裁剪
+ dict(type='RandomFlip', prob=0.5, direction='horizontal'), # 随机水平翻转
+ dict(type='PackInputs'), # 准备图像以及标签
+]
+
+test_pipeline = [
+ dict(type='LoadImageFromFile', imdecode_backend='pillow', color_type='unchanged'), # 读取图像
+ dict(type='ResizeEdge', scale=256, edge='short'), # 缩放短边尺寸至 256px
+ dict(type='CenterCrop', crop_size=224), # 中心裁剪
+ dict(type='PackInputs'), # 准备图像以及标签
+]
+
+# config of dataloader
+train_dataloader = dict(
+ batch_size=16, # 每张 GPU 的 batchsize
+ num_workers=5, # 每个 GPU 的线程数
+ dataset=dict( # 训练数据集
+ type=dataset_type,
+ data_root='../2_preprocess_data_3000',
+ with_label=True,
+ ann_file='',
+ data_prefix='train',
+ pipeline=train_pipeline),
+ sampler=dict(type='DefaultSampler', shuffle=True), # 默认采样器
+ persistent_workers=True, # 是否保持进程，可以缩短每个 epoch 的准备时间
+)
+
+# 构造验证集 dataloader
+val_dataloader = dict(
+ batch_size=16,
+ num_workers=5,
+ dataset=dict(
+ type=dataset_type,
+ data_root='../2_preprocess_data_3000',
+ with_label=True,
+ ann_file='',
+ data_prefix='val',
+ pipeline=test_pipeline),
+ sampler=dict(type='DefaultSampler', shuffle=False),
+ persistent_workers=True,
+)
+
+# set evaluator of validation dataset. Here uses top1 and top3 accuracy
+val_evaluator = dict(type='Accuracy', topk=(1, 3))
+
+test_dataloader = val_dataloader
+test_evaluator = val_evaluator
+
+model = dict(
+ type='ImageClassifier', # 主模型类型（对于图像分类任务，使用 `ImageClassifier`）
+ backbone=dict(
+ type='ResNeXt', # 主干网络类型
+ depth=101,
+ in_channels=4, # 输入通道数
+ ),
+ neck=dict(type='GlobalAveragePooling'), # 颈网络类型
+ head=dict(
+ type='LinearClsHead', # 分类颈网络类型
+ # 除了 `type` 之外的所有字段都来自 `LinearClsHead` 类的 __init__ 方法
+ # 可查阅 https://mmpretrain.readthedocs.io/zh_CN/latest/api/generated/mmpretrain.models.heads.LinearClsHead.html
+ num_classes=7, # 分类类别数
+ in_channels=2048,
+ loss=dict(type='CrossEntropyLoss', loss_weight=1.0), # 损失函数配置信息
+ topk=(1, 3), # 评估指标，Top-k 准确率
+ ))
+
+
diff --git a/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/configs/resnext101_4xb32_1024e_4channel.py b/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/configs/resnext101_4xb32_1024e_4channel.py
new file mode 100644
index 0000000000000000000000000000000000000000..0f0c5dafbd8475a8b0dec583a871eb23c9e79bdd
--- /dev/null
+++ b/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/configs/resnext101_4xb32_1024e_4channel.py
@@ -0,0 +1,114 @@
+_base_ = [ # 此配置文件将继承所有 `_base_` 中的配置
+ '../configs/_base_/schedules/custom_schedule.py', # 训练策略配置
+ '../configs/_base_/default_runtime.py' # 默认运行设置
+]
+
+default_hooks = dict(
+ # print log every 50 iterations.
+ logger=dict(type='LoggerHook', interval=25),
+ # save checkpoint per 8 epochs.
+ checkpoint=dict(save_best='auto', interval=16)
+)
+
+visualizer = dict(
+ vis_backends=[dict(type='LocalVisBackend'),
+ dict(type='WandbVisBackend')])
+
+dataset_type = 'CustomDataset'
+
+# config of pipline
+train_pipeline = [
+ dict(type='LoadImageFromFile', imdecode_backend='pillow', flag='unchanged'), # 读取图像
+ dict(type='RandomResizedCrop', scale=224), # 随机放缩裁剪
+ dict(type='RandomFlip', prob=0.5, direction='horizontal'), # 随机水平翻转
+ dict(type='PackInputs'), # 准备图像以及标签
+]
+
+test_pipeline = [
+ dict(type='LoadImageFromFile', imdecode_backend='pillow', flag='unchanged'), # 读取图像
+ dict(type='ResizeEdge', scale=256, edge='short'), # 缩放短边尺寸至 256px
+ dict(type='CenterCrop', crop_size=224), # 中心裁剪
+ dict(type='PackInputs'), # 准备图像以及标签
+]
+
+# config of dataloader
+train_dataloader = dict(
+ batch_size=32, # 每张 GPU 的 batchsize
+ num_workers=5, # 每个 GPU 的线程数
+ dataset=dict( # 训练数据集
+ type=dataset_type,
+ data_root='../2_preprocess_data_3000',
+ with_label=True,
+ ann_file='',
+ data_prefix='train',
+ pipeline=train_pipeline),
+ sampler=dict(type='DefaultSampler', shuffle=True), # 默认采样器
+ persistent_workers=True, # 是否保持进程，可以缩短每个 epoch 的准备时间
+)
+
+# 构造验证集 dataloader
+val_dataloader = dict(
+ batch_size=32,
+ num_workers=5,
+ dataset=dict(
+ type=dataset_type,
+ data_root='../2_preprocess_data_3000',
+ with_label=True,
+ ann_file='',
+ data_prefix='val',
+ pipeline=test_pipeline),
+ sampler=dict(type='DefaultSampler', shuffle=False),
+ persistent_workers=True,
+)
+
+# set evaluator of validation dataset. Here uses top1 and top3 accuracy
+val_evaluator = dict(type='Accuracy', topk=(1, 3))
+
+test_dataloader = val_dataloader
+test_evaluator = val_evaluator
+
+model = dict(
+ type='ImageClassifier', # 主模型类型（对于图像分类任务，使用 `ImageClassifier`）
+ backbone=dict(
+ type='HRNet', # 主干网络类型
+ arch='w32', # 主干网络架构
+ extra=dict(
+ stage1=dict(
+ num_modules=1,
+ num_branches=1,
+ block='BOTTLENECK',
+ num_blocks=(4, ),
+ num_channels=(64, )),
+ stage2=dict(
+ num_modules=1,
+ num_branches=2,
+ block='BASIC',
+ num_blocks=(4, 4),
+ num_channels=(32, 64)),
+ stage3=dict(
+ num_modules=4,
+ num_branches=3,
+ block='BASIC',
+ num_blocks=(4, 4, 4),
+ num_channels=(32, 64, 128)),
+ stage4=dict(
+ num_modules=3,
+ num_branches=4,
+ block='BASIC',
+ num_blocks=(4, 4, 4, 4),
+ num_channels=(32, 64, 128, 256))),
+ ),
+ neck=dict(type='GlobalAveragePooling'), # 颈网络类型
+ head=dict(
+ type='LinearClsHead', # 分类颈网络类型
+ # 除了 `type` 之外的所有字段都来自 `LinearClsHead` 类的 __init__ 方法
+ # 可查阅 https://mmpretrain.readthedocs.io/zh_CN/latest/api/generated/mmpretrain.models.heads.LinearClsHead.html
+ num_classes=7, # 分类类别数
+ in_channels=256,
+ loss=dict(type='CrossEntropyLoss', loss_weight=1.0), # 损失函数配置信息
+ topk=(1, 3), # 评估指标，Top-k 准确率
+ ))
+
+optim_wrapper = dict(
+ accumulative_counts=8
+)
diff --git a/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/configs/resnext101_4xb32_2048e_3c_noF.py b/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/configs/resnext101_4xb32_2048e_3c_noF.py
new file mode 100644
index 0000000000000000000000000000000000000000..5a75884d5bc715db4c86e429ebc4512dbab7c017
--- /dev/null
+++ b/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/configs/resnext101_4xb32_2048e_3c_noF.py
@@ -0,0 +1,108 @@
+_base_ = [ # 此配置文件将继承所有 `_base_` 中的配置
+ '../configs/_base_/schedules/custom_schedule.py', # 训练策略配置
+ '../configs/_base_/datasets/custom_ds.py',
+ '../configs/_base_/default_runtime.py' # 默认运行设置
+]
+
+default_hooks = dict(
+ # print log every 50 iterations.
+ logger=dict(type='LoggerHook', interval=10),
+ # save checkpoint per 8 epochs.
+ checkpoint=dict(save_best='auto', interval=16)
+)
+
+# visualizer = dict(
+# vis_backends=[dict(type='LocalVisBackend'),
+# dict(type='WandbVisBackend')])
+
+dataset_type = 'CustomDataset'
+
+# config of pipline
+train_pipeline = [
+ dict(type='LoadImageFromFile'), # 读取图像
+ dict(type='RandomResizedCrop', scale=224), # 随机放缩裁剪
+ dict(type='RandomFlip', prob=0.5, direction='horizontal'), # 随机水平翻转
+ dict(type='mmpretrain.PackInputs'), # 准备图像以及标签
+]
+
+test_pipeline = [
+ dict(type='LoadImageFromFile'), # 读取图像
+ dict(type='mmpretrain.ResizeEdge', scale=256, edge='short'), # 缩放短边尺寸至 256px
+ dict(type='CenterCrop', crop_size=224), # 中心裁剪
+ dict(type='mmpretrain.PackInputs'), # 准备图像以及标签
+]
+
+# config of dataloader
+train_dataloader = dict(
+ batch_size=32, # 每张 GPU 的 batchsize
+ num_workers=5, # 每个 GPU 的线程数
+ dataset=dict( # 训练数据集
+ type=dataset_type,
+ data_root='../2_preprocess_data_3000',
+ with_label=True,
+ ann_file='',
+ data_prefix='train',
+ pipeline=train_pipeline),
+ sampler=dict(type='DefaultSampler', shuffle=True), # 默认采样器
+ persistent_workers=True, # 是否保持进程，可以缩短每个 epoch 的准备时间
+)
+
+# 构造验证集 dataloader
+val_dataloader = dict(
+ batch_size=32,
+ num_workers=5,
+ dataset=dict(
+ type=dataset_type,
+ data_root='Model6_2/2_preprocess_data_3000',
+ with_label=True,
+ ann_file='',
+ data_prefix='val',
+ pipeline=test_pipeline),
+ sampler=dict(type='DefaultSampler', shuffle=False),
+ persistent_workers=True,
+)
+
+# set evaluator of validation dataset. Here uses top1 and top3 accuracy
+val_evaluator = dict(type='Accuracy', topk=(1, 3))
+
+test_dataloader = val_dataloader
+test_evaluator = val_evaluator
+
+model = dict(
+ type='ImageClassifier', # 主模型类型（对于图像分类任务，使用 `ImageClassifier`）
+ backbone=dict(
+ type='ResNeXt', # 主干网络类型
+ depth=101,
+ in_channels=3, # 输入通道数
+ ),
+ neck=dict(type='GlobalAveragePooling'), # 颈网络类型
+ head=dict(
+ type='LinearClsHead', # 分类颈网络类型
+ # 除了 `type` 之外的所有字段都来自 `LinearClsHead` 类的 __init__ 方法
+ # 可查阅 https://mmpretrain.readthedocs.io/zh_CN/latest/api/generated/mmpretrain.models.heads.LinearClsHead.html
+ num_classes=7, # 分类类别数
+ in_channels=2048,
+ loss=dict(type='CrossEntropyLoss', loss_weight=1.0), # 损失函数配置信息
+ topk=(1, 3), # 评估指标，Top-k 准确率
+ ))
+
+optim_wrapper = dict(
+ accumulative_counts=8
+)
+
+param_scheduler = [
+ # 在前10轮迭代中，逐迭代次数，线性预热
+ dict(type='LinearLR',
+ start_factor=0.00001,
+ by_epoch=True,
+ end=10,
+ convert_to_iter_based=True, # 逐迭代次数更新学习率.
+ ),
+ # 在 10 轮次后，通过余弦退火衰减
+ dict(type='MultiStepLR',
+ by_epoch=True, # 按轮次更新学习率
+ milestones=[30, 210, 390, 570, 750, 930, 1110, 1290, 1470, 1650, 1830],
+ gamma=0.9)
+]
+
+train_cfg = dict(by_epoch=True, max_epochs=2048, val_interval=16)
\ No newline at end of file
diff --git a/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/configs/resnext101_4xb32_2048e_4channel.py b/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/configs/resnext101_4xb32_2048e_4channel.py
new file mode 100644
index 0000000000000000000000000000000000000000..4e06572819b7798a43e71ea69d4b0131ef14c2d4
--- /dev/null
+++ b/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/configs/resnext101_4xb32_2048e_4channel.py
@@ -0,0 +1,107 @@
+_base_ = [ # 此配置文件将继承所有 `_base_` 中的配置
+ '../configs/_base_/schedules/custom_schedule.py', # 训练策略配置
+ '../configs/_base_/default_runtime.py' # 默认运行设置
+]
+
+default_hooks = dict(
+ # print log every 50 iterations.
+ logger=dict(type='LoggerHook', interval=10),
+ # save checkpoint per 8 epochs.
+ checkpoint=dict(save_best='auto', interval=16)
+)
+
+visualizer = dict(
+ vis_backends=[dict(type='LocalVisBackend'),
+ dict(type='WandbVisBackend')])
+
+dataset_type = 'CustomDataset'
+
+# config of pipline
+train_pipeline = [
+ dict(type='LoadImageFromFile', imdecode_backend='pillow', color_type='unchanged'), # 读取图像
+ dict(type='RandomResizedCrop', scale=224), # 随机放缩裁剪
+ dict(type='RandomFlip', prob=0.5, direction='horizontal'), # 随机水平翻转
+ dict(type='PackInputs'), # 准备图像以及标签
+]
+
+test_pipeline = [
+ dict(type='LoadImageFromFile', imdecode_backend='pillow', color_type='unchanged'), # 读取图像
+ dict(type='ResizeEdge', scale=256, edge='short'), # 缩放短边尺寸至 256px
+ dict(type='CenterCrop', crop_size=224), # 中心裁剪
+ dict(type='PackInputs'), # 准备图像以及标签
+]
+
+# config of dataloader
+train_dataloader = dict(
+ batch_size=32, # 每张 GPU 的 batchsize
+ num_workers=5, # 每个 GPU 的线程数
+ dataset=dict( # 训练数据集
+ type=dataset_type,
+ data_root='../2_preprocess_data_3000',
+ with_label=True,
+ ann_file='',
+ data_prefix='train',
+ pipeline=train_pipeline),
+ sampler=dict(type='DefaultSampler', shuffle=True), # 默认采样器
+ persistent_workers=True, # 是否保持进程，可以缩短每个 epoch 的准备时间
+)
+
+# 构造验证集 dataloader
+val_dataloader = dict(
+ batch_size=32,
+ num_workers=5,
+ dataset=dict(
+ type=dataset_type,
+ data_root='../2_preprocess_data_3000',
+ with_label=True,
+ ann_file='',
+ data_prefix='val',
+ pipeline=test_pipeline),
+ sampler=dict(type='DefaultSampler', shuffle=False),
+ persistent_workers=True,
+)
+
+# set evaluator of validation dataset. Here uses top1 and top3 accuracy
+val_evaluator = dict(type='Accuracy', topk=(1, 3))
+
+test_dataloader = val_dataloader
+test_evaluator = val_evaluator
+
+model = dict(
+ type='ImageClassifier', # 主模型类型（对于图像分类任务，使用 `ImageClassifier`）
+ backbone=dict(
+ type='ResNeXt', # 主干网络类型
+ depth=101,
+ in_channels=4, # 输入通道数
+ ),
+ neck=dict(type='GlobalAveragePooling'), # 颈网络类型
+ head=dict(
+ type='LinearClsHead', # 分类颈网络类型
+ # 除了 `type` 之外的所有字段都来自 `LinearClsHead` 类的 __init__ 方法
+ # 可查阅 https://mmpretrain.readthedocs.io/zh_CN/latest/api/generated/mmpretrain.models.heads.LinearClsHead.html
+ num_classes=7, # 分类类别数
+ in_channels=2048,
+ loss=dict(type='CrossEntropyLoss', loss_weight=1.0), # 损失函数配置信息
+ topk=(1, 3), # 评估指标，Top-k 准确率
+ ))
+
+optim_wrapper = dict(
+ accumulative_counts=8
+)
+
+param_scheduler = [
+ # 在前10轮迭代中，逐迭代次数，线性预热
+ dict(type='LinearLR',
+ start_factor=0.00001,
+ by_epoch=True,
+ end=10,
+ convert_to_iter_based=True, # 逐迭代次数更新学习率.
+ ),
+ # 在 10 轮次后，通过余弦退火衰减
+ dict(type='MultiStepLR',
+ by_epoch=True, # 按轮次更新学习率
+ milestones=[30, 210, 390, 570, 750, 930, 1110, 1290, 1470, 1650, 1830],
+ gamma=0.9)
+]
+
+train_cfg = dict(by_epoch=True, max_epochs=2048, val_interval=16)
\ No newline at end of file
diff --git a/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/work_dirs/__init__.py b/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/work_dirs/__init__.py
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/work_dirs/mobilenet-v2_4xb32_2000e_3c_noF/__init__.py b/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/work_dirs/mobilenet-v2_4xb32_2000e_3c_noF/__init__.py
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/work_dirs/mobilenet-v2_4xb32_2000e_3c_noF/best_accuracy_top1_epoch_1830.pth b/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/work_dirs/mobilenet-v2_4xb32_2000e_3c_noF/best_accuracy_top1_epoch_1830.pth
new file mode 100644
index 0000000000000000000000000000000000000000..30d65cf4d7684002b0b7699d77050f24c14d33ff
--- /dev/null
+++ b/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/work_dirs/mobilenet-v2_4xb32_2000e_3c_noF/best_accuracy_top1_epoch_1830.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f94fb49e0516357b263b86ecd5998ed689b7d9c1983cb2e5010a395eae741f5b
+size 11350925
diff --git a/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/work_dirs/mobilenet-v2_4xb32_2000e_3c_noF/best_accuracy_top1_epoch_510.pth b/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/work_dirs/mobilenet-v2_4xb32_2000e_3c_noF/best_accuracy_top1_epoch_510.pth
new file mode 100644
index 0000000000000000000000000000000000000000..fc3ca16d99ad6706cd8f563ed6840371ef88a129
--- /dev/null
+++ b/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/work_dirs/mobilenet-v2_4xb32_2000e_3c_noF/best_accuracy_top1_epoch_510.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:455e447e5e941875abf43f800a9e11348ba33d4b5bf5a9c1a78ca20f7833e044
+size 9791117
diff --git a/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/work_dirs/mobilenet-v2_4xb32_2000e_3c_noF/mobilenet-v2_1xb32_300e_3c_noF.py b/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/work_dirs/mobilenet-v2_4xb32_2000e_3c_noF/mobilenet-v2_1xb32_300e_3c_noF.py
new file mode 100644
index 0000000000000000000000000000000000000000..8fb558c161d85f81f3dc13d6551359f923e008c8
--- /dev/null
+++ b/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/work_dirs/mobilenet-v2_4xb32_2000e_3c_noF/mobilenet-v2_1xb32_300e_3c_noF.py
@@ -0,0 +1,140 @@
+model = dict(
+ type='ImageClassifier',
+ backbone=dict(type='MobileNetV2', widen_factor=1.0),
+ neck=dict(type='GlobalAveragePooling'),
+ head=dict(
+ type='LinearClsHead',
+ num_classes=7,
+ in_channels=1280,
+ loss=dict(type='CrossEntropyLoss', loss_weight=1.0),
+ topk=(
+ 1,
+ 3,
+ )))
+dataset_type = 'CustomDataset'
+data_preprocessor = dict(
+ num_classes=7,
+ mean=[
+ 123.675,
+ 116.28,
+ 103.53,
+ ],
+ std=[
+ 58.395,
+ 57.12,
+ 57.375,
+ ],
+ to_rgb=True)
+train_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='RandomResizedCrop', scale=224, backend='pillow'),
+ dict(type='RandomFlip', prob=0.5, direction='horizontal'),
+ dict(type='PackInputs'),
+]
+val_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='ResizeEdge', scale=256, edge='short', backend='pillow'),
+ dict(type='CenterCrop', crop_size=224),
+ dict(type='PackInputs'),
+]
+train_dataloader = dict(
+ pin_memory=True,
+ persistent_workers=True,
+ collate_fn=dict(type='default_collate'),
+ batch_size=32,
+ num_workers=5,
+ dataset=dict(
+ type='CustomDataset',
+ data_root='data',
+ with_label=True,
+ ann_file='',
+ data_prefix='train',
+ pipeline=[
+ dict(type='LoadImageFromFile'),
+ dict(type='RandomResizedCrop', scale=224, backend='pillow'),
+ dict(type='RandomFlip', prob=0.5, direction='horizontal'),
+ dict(type='PackInputs'),
+ ]),
+ sampler=dict(type='DefaultSampler', shuffle=True))
+val_dataloader = dict(
+ pin_memory=True,
+ persistent_workers=True,
+ collate_fn=dict(type='default_collate'),
+ batch_size=32,
+ num_workers=5,
+ dataset=dict(
+ type='CustomDataset',
+ data_root='data',
+ with_label=True,
+ ann_file='',
+ data_prefix='val',
+ pipeline=[
+ dict(type='LoadImageFromFile'),
+ dict(type='ResizeEdge', scale=256, edge='short', backend='pillow'),
+ dict(type='CenterCrop', crop_size=224),
+ dict(type='PackInputs'),
+ ]),
+ sampler=dict(type='DefaultSampler', shuffle=False))
+val_evaluator = dict(
+ type='Accuracy', topk=(
+ 1,
+ 3,
+ ))
+test_dataloader = dict(
+ pin_memory=True,
+ persistent_workers=True,
+ collate_fn=dict(type='default_collate'),
+ batch_size=32,
+ num_workers=5,
+ dataset=dict(
+ type='CustomDataset',
+ data_root='data',
+ with_label=True,
+ ann_file='',
+ data_prefix='val',
+ pipeline=[
+ dict(type='LoadImageFromFile'),
+ dict(type='ResizeEdge', scale=256, edge='short', backend='pillow'),
+ dict(type='CenterCrop', crop_size=224),
+ dict(type='PackInputs'),
+ ]),
+ sampler=dict(type='DefaultSampler', shuffle=False))
+test_evaluator = dict(
+ type='Accuracy', topk=(
+ 1,
+ 3,
+ ))
+optim_wrapper = dict(
+ optimizer=dict(type='SGD', lr=0.045, momentum=0.9, weight_decay=4e-05))
+param_scheduler = dict(type='StepLR', by_epoch=True, step_size=10, gamma=0.98)
+train_cfg = dict(by_epoch=True, max_epochs=2000, val_interval=10)
+val_cfg = dict()
+test_cfg = dict()
+auto_scale_lr = dict(base_batch_size=256)
+default_scope = 'mmpretrain'
+default_hooks = dict(
+ timer=dict(type='IterTimerHook'),
+ logger=dict(type='LoggerHook', interval=10),
+ param_scheduler=dict(type='ParamSchedulerHook'),
+ checkpoint=dict(type='CheckpointHook', save_best='auto', interval=10),
+ sampler_seed=dict(type='DistSamplerSeedHook'),
+ visualization=dict(type='VisualizationHook', enable=False))
+env_cfg = dict(
+ cudnn_benchmark=False,
+ mp_cfg=dict(mp_start_method='fork', opencv_num_threads=0),
+ dist_cfg=dict(backend='nccl'))
+vis_backends = [
+ dict(type='LocalVisBackend'),
+]
+visualizer = dict(
+ type='UniversalVisualizer',
+ vis_backends=[
+ dict(type='LocalVisBackend'),
+ dict(type='WandbVisBackend'),
+ ])
+log_level = 'INFO'
+load_from = None
+resume = False
+randomness = dict(seed=None, deterministic=False)
+launcher = 'pytorch'
+work_dir = 'work_dirs/mobilenet-v2_4xb32_2000e_3c_noF'
diff --git a/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/work_dirs/mobilevit-small_4xb32_2000e_3c_noF/__init__.py b/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/work_dirs/mobilevit-small_4xb32_2000e_3c_noF/__init__.py
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/work_dirs/mobilevit-small_4xb32_2000e_3c_noF/best_accuracy_top1_epoch_1820.pth b/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/work_dirs/mobilevit-small_4xb32_2000e_3c_noF/best_accuracy_top1_epoch_1820.pth
new file mode 100644
index 0000000000000000000000000000000000000000..09160917e4f58e48cf4b15becf7be70834295094
--- /dev/null
+++ b/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/work_dirs/mobilevit-small_4xb32_2000e_3c_noF/best_accuracy_top1_epoch_1820.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4aa448ed138b71c7d9d975ec4a973168d5ff1fdf344fa9b62ff3775c52cbe83
+size 22108115
diff --git a/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/work_dirs/mobilevit-small_4xb32_2000e_3c_noF/mobilevit-small_4xb32_2000e_3c_noF.py b/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/work_dirs/mobilevit-small_4xb32_2000e_3c_noF/mobilevit-small_4xb32_2000e_3c_noF.py
new file mode 100644
index 0000000000000000000000000000000000000000..1dd70453e6fedc075f30a51e736d7c99f36c584f
--- /dev/null
+++ b/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/work_dirs/mobilevit-small_4xb32_2000e_3c_noF/mobilevit-small_4xb32_2000e_3c_noF.py
@@ -0,0 +1,137 @@
+model = dict(
+ type='ImageClassifier',
+ backbone=dict(type='MobileViT', arch='small'),
+ neck=dict(type='GlobalAveragePooling'),
+ head=dict(
+ type='LinearClsHead',
+ num_classes=7,
+ in_channels=640,
+ loss=dict(type='CrossEntropyLoss', loss_weight=1.0),
+ topk=(
+ 1,
+ 3,
+ )))
+dataset_type = 'CustomDataset'
+data_preprocessor = dict(
+ num_classes=6, mean=[
+ 0,
+ 0,
+ 0,
+ ], std=[
+ 255,
+ 255,
+ 255,
+ ], to_rgb=False)
+train_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='RandomResizedCrop', scale=224),
+ dict(type='RandomFlip', prob=0.5, direction='horizontal'),
+ dict(type='PackInputs'),
+]
+test_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='ResizeEdge', scale=288, edge='short'),
+ dict(type='CenterCrop', crop_size=256),
+ dict(type='PackInputs'),
+]
+train_dataloader = dict(
+ pin_memory=True,
+ persistent_workers=True,
+ collate_fn=dict(type='default_collate'),
+ batch_size=32,
+ num_workers=5,
+ dataset=dict(
+ type='CustomDataset',
+ data_root='data',
+ with_label=True,
+ ann_file='',
+ data_prefix='train',
+ pipeline=[
+ dict(type='LoadImageFromFile'),
+ dict(type='RandomResizedCrop', scale=224),
+ dict(type='RandomFlip', prob=0.5, direction='horizontal'),
+ dict(type='PackInputs'),
+ ]),
+ sampler=dict(type='DefaultSampler', shuffle=True))
+val_dataloader = dict(
+ pin_memory=True,
+ persistent_workers=True,
+ collate_fn=dict(type='default_collate'),
+ batch_size=32,
+ num_workers=5,
+ dataset=dict(
+ type='CustomDataset',
+ data_root='data',
+ with_label=True,
+ ann_file='',
+ data_prefix='val',
+ pipeline=[
+ dict(type='LoadImageFromFile'),
+ dict(type='ResizeEdge', scale=288, edge='short'),
+ dict(type='CenterCrop', crop_size=256),
+ dict(type='PackInputs'),
+ ]),
+ sampler=dict(type='DefaultSampler', shuffle=False))
+val_evaluator = dict(
+ type='Accuracy', topk=(
+ 1,
+ 3,
+ ))
+test_dataloader = dict(
+ pin_memory=True,
+ persistent_workers=True,
+ collate_fn=dict(type='default_collate'),
+ batch_size=32,
+ num_workers=5,
+ dataset=dict(
+ type='CustomDataset',
+ data_root='data',
+ with_label=True,
+ ann_file='',
+ data_prefix='val',
+ pipeline=[
+ dict(type='LoadImageFromFile'),
+ dict(type='ResizeEdge', scale=288, edge='short'),
+ dict(type='CenterCrop', crop_size=256),
+ dict(type='PackInputs'),
+ ]),
+ sampler=dict(type='DefaultSampler', shuffle=False))
+test_evaluator = dict(
+ type='Accuracy', topk=(
+ 1,
+ 3,
+ ))
+default_scope = 'mmpretrain'
+default_hooks = dict(
+ timer=dict(type='IterTimerHook'),
+ logger=dict(type='LoggerHook', interval=10),
+ param_scheduler=dict(type='ParamSchedulerHook'),
+ checkpoint=dict(type='CheckpointHook', save_best='auto', interval=10),
+ sampler_seed=dict(type='DistSamplerSeedHook'),
+ visualization=dict(type='VisualizationHook', enable=False))
+env_cfg = dict(
+ cudnn_benchmark=False,
+ mp_cfg=dict(mp_start_method='fork', opencv_num_threads=0),
+ dist_cfg=dict(backend='nccl'))
+vis_backends = [
+ dict(type='LocalVisBackend'),
+]
+visualizer = dict(
+ type='UniversalVisualizer',
+ vis_backends=[
+ dict(type='LocalVisBackend'),
+ dict(type='WandbVisBackend'),
+ ])
+log_level = 'INFO'
+load_from = None
+resume = False
+randomness = dict(seed=None, deterministic=False)
+optim_wrapper = dict(
+ optimizer=dict(type='SGD', lr=0.1, momentum=0.9, weight_decay=0.0001))
+param_scheduler = dict(type='StepLR', by_epoch=True, step_size=10, gamma=0.98)
+train_cfg = dict(by_epoch=True, max_epochs=2000, val_interval=10)
+val_cfg = dict()
+test_cfg = dict()
+auto_scale_lr = dict(base_batch_size=256)
+launcher = 'pytorch'
+work_dir = './work_dirs/mobilevit-small_4xb32_2000e_3c_noF'
diff --git a/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/work_dirs/resnext101_4xb32_2048e_3c_noF/best_accuracy_top1_epoch_1520.pth b/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/work_dirs/resnext101_4xb32_2048e_3c_noF/best_accuracy_top1_epoch_1520.pth
new file mode 100644
index 0000000000000000000000000000000000000000..acba4115d02bc506683cad7340f79eeaf6eb0989
--- /dev/null
+++ b/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/work_dirs/resnext101_4xb32_2048e_3c_noF/best_accuracy_top1_epoch_1520.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:502b0d646ba913bb0b5ceadf8c01e4fb4eec5b5204f0db12e6d7a70b5f427d06
+size 171110493
diff --git a/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/work_dirs/resnext101_4xb32_2048e_3c_noF/resnext101_4xb32_2048e_3c_noF.py b/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/work_dirs/resnext101_4xb32_2048e_3c_noF/resnext101_4xb32_2048e_3c_noF.py
new file mode 100644
index 0000000000000000000000000000000000000000..e2f977ca9e86a412a643dd45598753372c392b9c
--- /dev/null
+++ b/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/work_dirs/resnext101_4xb32_2048e_3c_noF/resnext101_4xb32_2048e_3c_noF.py
@@ -0,0 +1,131 @@
+optim_wrapper = dict(
+ type='OptimWrapper',
+ optimizer=dict(
+ type='Adam',
+ lr=0.0001,
+ betas=(0.9, 0.999),
+ eps=1e-08,
+ weight_decay=0,
+ amsgrad=False),
+ accumulative_counts=8)
+param_scheduler = [
+ dict(
+ type='LinearLR',
+ start_factor=1e-05,
+ by_epoch=True,
+ end=10,
+ convert_to_iter_based=True),
+ dict(
+ type='MultiStepLR',
+ by_epoch=True,
+ milestones=[30, 210, 390, 570, 750, 930, 1110, 1290, 1470, 1650, 1830],
+ gamma=0.9)
+]
+train_cfg = dict(by_epoch=True, max_epochs=2048, val_interval=16)
+val_cfg = dict()
+test_cfg = dict()
+default_scope = 'mmpretrain'
+default_hooks = dict(
+ timer=dict(type='IterTimerHook'),
+ logger=dict(type='LoggerHook', interval=10),
+ param_scheduler=dict(type='ParamSchedulerHook'),
+ checkpoint=dict(type='CheckpointHook', interval=16, save_best='auto'),
+ sampler_seed=dict(type='DistSamplerSeedHook'),
+ visualization=dict(type='VisualizationHook', enable=False))
+env_cfg = dict(
+ cudnn_benchmark=False,
+ mp_cfg=dict(mp_start_method='fork', opencv_num_threads=0),
+ dist_cfg=dict(backend='nccl'))
+vis_backends = [dict(type='LocalVisBackend')]
+visualizer = dict(
+ type='UniversalVisualizer',
+ vis_backends=[dict(type='LocalVisBackend'),
+ dict(type='WandbVisBackend')])
+log_level = 'INFO'
+load_from = None
+resume = False
+randomness = dict(seed=None, deterministic=False)
+dataset_type = 'CustomDataset'
+train_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='RandomResizedCrop', scale=224),
+ dict(type='RandomFlip', prob=0.5, direction='horizontal'),
+ dict(type='PackInputs')
+]
+test_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='ResizeEdge', scale=256, edge='short'),
+ dict(type='CenterCrop', crop_size=224),
+ dict(type='PackInputs')
+]
+train_dataloader = dict(
+ pin_memory=True,
+ persistent_workers=True,
+ collate_fn=dict(type='default_collate'),
+ batch_size=32,
+ num_workers=5,
+ dataset=dict(
+ type='CustomDataset',
+ data_root='../2_preprocess_data_3000',
+ with_label=True,
+ ann_file='',
+ data_prefix='train',
+ pipeline=[
+ dict(type='LoadImageFromFile'),
+ dict(type='RandomResizedCrop', scale=224),
+ dict(type='RandomFlip', prob=0.5, direction='horizontal'),
+ dict(type='PackInputs')
+ ]),
+ sampler=dict(type='DefaultSampler', shuffle=True))
+val_dataloader = dict(
+ pin_memory=True,
+ persistent_workers=True,
+ collate_fn=dict(type='default_collate'),
+ batch_size=32,
+ num_workers=5,
+ dataset=dict(
+ type='CustomDataset',
+ data_root='../2_preprocess_data_3000',
+ with_label=True,
+ ann_file='',
+ data_prefix='val',
+ pipeline=[
+ dict(type='LoadImageFromFile'),
+ dict(type='ResizeEdge', scale=256, edge='short'),
+ dict(type='CenterCrop', crop_size=224),
+ dict(type='PackInputs')
+ ]),
+ sampler=dict(type='DefaultSampler', shuffle=False))
+val_evaluator = dict(type='Accuracy', topk=(1, 3))
+test_dataloader = dict(
+ pin_memory=True,
+ persistent_workers=True,
+ collate_fn=dict(type='default_collate'),
+ batch_size=32,
+ num_workers=5,
+ dataset=dict(
+ type='CustomDataset',
+ data_root='../2_preprocess_data_3000',
+ with_label=True,
+ ann_file='',
+ data_prefix='val',
+ pipeline=[
+ dict(type='LoadImageFromFile'),
+ dict(type='ResizeEdge', scale=256, edge='short'),
+ dict(type='CenterCrop', crop_size=224),
+ dict(type='PackInputs')
+ ]),
+ sampler=dict(type='DefaultSampler', shuffle=False))
+test_evaluator = dict(type='Accuracy', topk=(1, 3))
+model = dict(
+ type='ImageClassifier',
+ backbone=dict(type='ResNeXt', depth=101, in_channels=3),
+ neck=dict(type='GlobalAveragePooling'),
+ head=dict(
+ type='LinearClsHead',
+ num_classes=7,
+ in_channels=2048,
+ loss=dict(type='CrossEntropyLoss', loss_weight=1.0),
+ topk=(1, 3)))
+launcher = 'pytorch'
+work_dir = './work_dirs/resnext101_4xb32_2048e_3c_noF'
diff --git a/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/work_dirs/shufflenet-v2-1x_4xb32_2000e_3c_noF/__init__.py b/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/work_dirs/shufflenet-v2-1x_4xb32_2000e_3c_noF/__init__.py
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/work_dirs/shufflenet-v2-1x_4xb32_2000e_3c_noF/best_accuracy_top1_epoch_1920.pth b/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/work_dirs/shufflenet-v2-1x_4xb32_2000e_3c_noF/best_accuracy_top1_epoch_1920.pth
new file mode 100644
index 0000000000000000000000000000000000000000..b12900cb9e1a73eb1f89858d04e0511217dac912
--- /dev/null
+++ b/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/work_dirs/shufflenet-v2-1x_4xb32_2000e_3c_noF/best_accuracy_top1_epoch_1920.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d20a545b5c67e17c12ae6acc8305bdf1042329774e7df1640ec5c85eca6565be
+size 8113501
diff --git a/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/work_dirs/shufflenet-v2-1x_4xb32_2000e_3c_noF/shufflenet-v2-1x_4xb32_2000e_3c_noF.py b/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/work_dirs/shufflenet-v2-1x_4xb32_2000e_3c_noF/shufflenet-v2-1x_4xb32_2000e_3c_noF.py
new file mode 100644
index 0000000000000000000000000000000000000000..498df9518f20b41383851a1253aba27bd9fdeca6
--- /dev/null
+++ b/Model/Model6/Model6_2_ProfileRecogition/mmpretrain/work_dirs/shufflenet-v2-1x_4xb32_2000e_3c_noF/shufflenet-v2-1x_4xb32_2000e_3c_noF.py
@@ -0,0 +1,155 @@
+model = dict(
+ type='ImageClassifier',
+ backbone=dict(type='ShuffleNetV2', widen_factor=1.0),
+ neck=dict(type='GlobalAveragePooling'),
+ head=dict(
+ type='LinearClsHead',
+ num_classes=7,
+ in_channels=1024,
+ loss=dict(type='CrossEntropyLoss', loss_weight=1.0),
+ topk=(
+ 1,
+ 3,
+ )))
+dataset_type = 'CustomDataset'
+data_preprocessor = dict(
+ num_classes=7,
+ mean=[
+ 123.675,
+ 116.28,
+ 103.53,
+ ],
+ std=[
+ 58.395,
+ 57.12,
+ 57.375,
+ ],
+ to_rgb=True)
+train_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='RandomResizedCrop', scale=224, backend='pillow'),
+ dict(type='RandomFlip', prob=0.5, direction='horizontal'),
+ dict(type='PackInputs'),
+]
+test_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='ResizeEdge', scale=256, edge='short', backend='pillow'),
+ dict(type='CenterCrop', crop_size=224),
+ dict(type='PackInputs'),
+]
+train_dataloader = dict(
+ pin_memory=True,
+ persistent_workers=True,
+ collate_fn=dict(type='default_collate'),
+ batch_size=32,
+ num_workers=5,
+ dataset=dict(
+ type='CustomDataset',
+ data_root='data',
+ with_label=True,
+ ann_file='',
+ data_prefix='train',
+ pipeline=[
+ dict(type='LoadImageFromFile'),
+ dict(type='RandomResizedCrop', scale=224, backend='pillow'),
+ dict(type='RandomFlip', prob=0.5, direction='horizontal'),
+ dict(type='PackInputs'),
+ ]),
+ sampler=dict(type='DefaultSampler', shuffle=True))
+val_dataloader = dict(
+ pin_memory=True,
+ persistent_workers=True,
+ collate_fn=dict(type='default_collate'),
+ batch_size=32,
+ num_workers=5,
+ dataset=dict(
+ type='CustomDataset',
+ data_root='data',
+ with_label=True,
+ ann_file='',
+ data_prefix='val',
+ pipeline=[
+ dict(type='LoadImageFromFile'),
+ dict(type='ResizeEdge', scale=256, edge='short', backend='pillow'),
+ dict(type='CenterCrop', crop_size=224),
+ dict(type='PackInputs'),
+ ]),
+ sampler=dict(type='DefaultSampler', shuffle=False))
+val_evaluator = dict(
+ type='Accuracy', topk=(
+ 1,
+ 3,
+ ))
+test_dataloader = dict(
+ pin_memory=True,
+ persistent_workers=True,
+ collate_fn=dict(type='default_collate'),
+ batch_size=32,
+ num_workers=5,
+ dataset=dict(
+ type='CustomDataset',
+ data_root='data',
+ with_label=True,
+ ann_file='',
+ data_prefix='val',
+ pipeline=[
+ dict(type='LoadImageFromFile'),
+ dict(type='ResizeEdge', scale=256, edge='short', backend='pillow'),
+ dict(type='CenterCrop', crop_size=224),
+ dict(type='PackInputs'),
+ ]),
+ sampler=dict(type='DefaultSampler', shuffle=False))
+test_evaluator = dict(
+ pin_memory=True,
+ persistent_workers=True,
+ collate_fn=dict(type='default_collate'),
+ batch_size=32,
+ num_workers=5,
+ dataset=dict(
+ type='CustomDataset',
+ data_root='data',
+ with_label=True,
+ ann_file='',
+ data_prefix='val',
+ pipeline=[
+ dict(type='LoadImageFromFile'),
+ dict(type='ResizeEdge', scale=256, edge='short', backend='pillow'),
+ dict(type='CenterCrop', crop_size=224),
+ dict(type='PackInputs'),
+ ]),
+ sampler=dict(type='DefaultSampler', shuffle=False))
+optim_wrapper = dict(
+ optimizer=dict(type='SGD', lr=0.1, momentum=0.9, weight_decay=0.0001),
+ paramwise_cfg=dict(norm_decay_mult=0))
+param_scheduler = dict(type='StepLR', by_epoch=True, step_size=10, gamma=0.98)
+train_cfg = dict(by_epoch=True, max_epochs=2000, val_interval=10)
+val_cfg = dict()
+test_cfg = dict()
+auto_scale_lr = dict(base_batch_size=1024)
+default_scope = 'mmpretrain'
+default_hooks = dict(
+ timer=dict(type='IterTimerHook'),
+ logger=dict(type='LoggerHook', interval=10),
+ param_scheduler=dict(type='ParamSchedulerHook'),
+ checkpoint=dict(type='CheckpointHook', save_best='auto', interval=10),
+ sampler_seed=dict(type='DistSamplerSeedHook'),
+ visualization=dict(type='VisualizationHook', enable=False))
+env_cfg = dict(
+ cudnn_benchmark=False,
+ mp_cfg=dict(mp_start_method='fork', opencv_num_threads=0),
+ dist_cfg=dict(backend='nccl'))
+vis_backends = [
+ dict(type='LocalVisBackend'),
+]
+visualizer = dict(
+ type='UniversalVisualizer',
+ vis_backends=[
+ dict(type='LocalVisBackend'),
+ dict(type='WandbVisBackend'),
+ ])
+log_level = 'INFO'
+load_from = None
+resume = False
+randomness = dict(seed=None, deterministic=False)
+launcher = 'pytorch'
+work_dir = './work_dirs/shufflenet-v2-1x_4xb32_2000e_3c_noF'
diff --git a/Model/Model6/__init__.py b/Model/Model6/__init__.py
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/Model/Model6/extensions/__init__.py b/Model/Model6/extensions/__init__.py
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/Model/Model6/extensions/dataset_info.py b/Model/Model6/extensions/dataset_info.py
new file mode 100644
index 0000000000000000000000000000000000000000..ef0d62e43089770797ef565d2153c8d42e4956c5
--- /dev/null
+++ b/Model/Model6/extensions/dataset_info.py
@@ -0,0 +1,104 @@
+# Copyright (c) OpenMMLab. All rights reserved.
+import numpy as np
+
+
+class DatasetInfo:
+
+ def __init__(self, dataset_info):
+ self._dataset_info = dataset_info
+ self.dataset_name = self._dataset_info['dataset_name']
+ self.paper_info = self._dataset_info['paper_info']
+ self.keypoint_info = self._dataset_info['keypoint_info']
+ self.skeleton_info = self._dataset_info['skeleton_info']
+ self.joint_weights = np.array(
+ self._dataset_info['joint_weights'], dtype=np.float32)[:, None]
+
+ self.sigmas = np.array(self._dataset_info['sigmas'])
+
+ self._parse_keypoint_info()
+ self._parse_skeleton_info()
+
+ def _parse_skeleton_info(self):
+ """Parse skeleton information.
+
+ - link_num (int): number of links.
+ - skeleton (list((2,))): list of links (id).
+ - skeleton_name (list((2,))): list of links (name).
+ - pose_link_color (np.ndarray): the color of the link for
+ visualization.
+ """
+ self.link_num = len(self.skeleton_info.keys())
+ self.pose_link_color = []
+
+ self.skeleton_name = []
+ self.skeleton = []
+ for skid in self.skeleton_info.keys():
+ link = self.skeleton_info[skid]['link']
+ self.skeleton_name.append(link)
+ self.skeleton.append([
+ self.keypoint_name2id[link[0]], self.keypoint_name2id[link[1]]
+ ])
+ self.pose_link_color.append(self.skeleton_info[skid].get(
+ 'color', [255, 128, 0]))
+ self.pose_link_color = np.array(self.pose_link_color)
+
+ def _parse_keypoint_info(self):
+ """Parse keypoint information.
+
+ - keypoint_num (int): number of keypoints.
+ - keypoint_id2name (dict): mapping keypoint id to keypoint name.
+ - keypoint_name2id (dict): mapping keypoint name to keypoint id.
+ - upper_body_ids (list): a list of keypoints that belong to the
+ upper body.
+ - lower_body_ids (list): a list of keypoints that belong to the
+ lower body.
+ - flip_index (list): list of flip index (id)
+ - flip_pairs (list((2,))): list of flip pairs (id)
+ - flip_index_name (list): list of flip index (name)
+ - flip_pairs_name (list((2,))): list of flip pairs (name)
+ - pose_kpt_color (np.ndarray): the color of the keypoint for
+ visualization.
+ """
+
+ self.keypoint_num = len(self.keypoint_info.keys())
+ self.keypoint_id2name = {}
+ self.keypoint_name2id = {}
+
+ self.pose_kpt_color = []
+ self.upper_body_ids = []
+ self.lower_body_ids = []
+
+ self.flip_index_name = []
+ self.flip_pairs_name = []
+
+ for kid in self.keypoint_info.keys():
+
+ keypoint_name = self.keypoint_info[kid]['name']
+ self.keypoint_id2name[kid] = keypoint_name
+ self.keypoint_name2id[keypoint_name] = kid
+ self.pose_kpt_color.append(self.keypoint_info[kid].get(
+ 'color', [255, 128, 0]))
+
+ type = self.keypoint_info[kid].get('type', '')
+ if type == 'upper':
+ self.upper_body_ids.append(kid)
+ elif type == 'lower':
+ self.lower_body_ids.append(kid)
+ else:
+ pass
+
+ swap_keypoint = self.keypoint_info[kid].get('swap', '')
+ if swap_keypoint == keypoint_name or swap_keypoint == '':
+ self.flip_index_name.append(keypoint_name)
+ else:
+ self.flip_index_name.append(swap_keypoint)
+ if [swap_keypoint, keypoint_name] not in self.flip_pairs_name:
+ self.flip_pairs_name.append([keypoint_name, swap_keypoint])
+
+ self.flip_pairs = [[
+ self.keypoint_name2id[pair[0]], self.keypoint_name2id[pair[1]]
+ ] for pair in self.flip_pairs_name]
+ self.flip_index = [
+ self.keypoint_name2id[name] for name in self.flip_index_name
+ ]
+ self.pose_kpt_color = np.array(self.pose_kpt_color)
diff --git a/Model/Model6/extensions/vis_pred_save.py b/Model/Model6/extensions/vis_pred_save.py
new file mode 100644
index 0000000000000000000000000000000000000000..000b7746bdfbb02cf29b09f5b4959a23b8ec3f7b
--- /dev/null
+++ b/Model/Model6/extensions/vis_pred_save.py
@@ -0,0 +1,209 @@
+from .dataset_info import DatasetInfo
+import cv2
+import mmcv
+import numpy as np
+import os
+from os import path as osp
+import json
+
+
+def save_result(img,
+ poses,
+ img_name=None,
+ radius=4,
+ thickness=1,
+ bbox_score_thr=None,
+ kpt_score_thr=0.3,
+ bbox_color='green',
+ dataset_info=None,
+ show=False,
+ out_dir=None,
+ vis_out_dir=None,
+ pred_out_dir=None,):
+ """Visualize the detection results on the image.
+
+ Args:
+ img (str | np.ndarray): Image filename or loaded image.
+ poses (dict[dict]): a dict which contains pose_model and pose_results of different classes.
+ And the pose_results contains bboxes, bbox_scores, keypoints and keypoint_scores.
+ img_name (str): Image name.
+ radius (int): Radius of circles.
+ thickness (int): Thickness of lines.
+ bbox_score_thr (float): The threshold to visualize the bounding boxes.
+ kpt_score_thr (float): The threshold to visualize the keypoints.
+ bbox_color (str | tuple[int]): Color of bounding boxes.
+ dataset_info (DatasetInfo): Dataset info.
+ show (bool): Whether to show the image. Default False.
+ out_dir (str): The output directory to save the visualizations and predictions results.
+ If vis_out_dir is None, visualizations will be saved in ${out_dir}/visualizations.
+ If pred_out_dir is None, predictions will be saved in ${out_dir}/predictions.
+ Default None.
+ vis_out_dir (str): The output directory to save the visualization results. Default None.
+ pred_out_dir (str): The output directory to save the predictions results. Default None.
+ """
+ # set flags
+ vis_out_flag = False if vis_out_dir is None else vis_out_dir
+ pred_out_flag = False if pred_out_dir is None else pred_out_dir
+ if out_dir:
+ if not vis_out_dir:
+ vis_out_flag = osp.join(out_dir, 'visualizations')
+ if not osp.exists(vis_out_flag):
+ os.mkdir(vis_out_flag)
+ if not pred_out_dir:
+ pred_out_flag = osp.join(out_dir, 'predictions')
+ if not osp.exists(pred_out_flag):
+ os.mkdir(pred_out_flag)
+
+ # read image
+ img_path = None
+ if isinstance(img, str):
+ img_path = img
+ img = mmcv.imread(img)
+ elif isinstance(img, np.ndarray):
+ img = img.copy()
+ else:
+ raise TypeError('img must be a filename or numpy array, '
+ f'but got {type(img)}')
+ bbox_list = []
+ label_list = []
+ class_name_list = []
+ bbox_score_list = []
+ idx = 0
+ for label, v in poses.items():
+ if len(v) == 0:
+ continue
+ pose_results = v['pose_results']
+ bbox = pose_results[0].gt_instances.bboxes
+ bbox_score = pose_results[0].gt_instances.bbox_scores
+ for bbox_idx in range(len(bbox)):
+ b = bbox[bbox_idx]
+ s = bbox_score[bbox_idx]
+ if bbox_score_thr is not None:
+ b = np.append(b, values=s) # switch to x1, y1, x2, y2, score
+ bbox_score_list.append(s.tolist())
+ bbox_list.append(b)
+ label_list.append(idx)
+ class_name_list.append(label)
+ idx += 1
+ bbox_list = np.array(bbox_list)
+ label_list = np.array(label_list)
+
+ # draw bbox
+ img = mmcv.imshow_det_bboxes(
+ img,
+ bbox_list,
+ label_list,
+ class_names=class_name_list,
+ score_thr=bbox_score_thr if bbox_score_thr is not None else 0,
+ bbox_color=bbox_color,
+ text_color='white',
+ show=False,
+ # out_file=out_file
+ )
+
+ keypoints_list = []
+ keypoint_scores_list = []
+ # draw pose of different classes
+ for label, v in poses.items():
+ if len(v) == 0:
+ continue
+ pose_model = v['pose_model']
+ pose_results = v['pose_results']
+ keypoints = pose_results[0].pred_instances.keypoints
+ for ks in keypoints:
+ keypoints_list.append(ks.tolist())
+ keypoint_scores = pose_results[0].pred_instances.keypoint_scores
+ for kss in keypoint_scores:
+ keypoint_scores_list.append(kss.tolist())
+
+ # get dataset info
+ if (dataset_info is None and hasattr(pose_model, 'cfg')
+ and 'dataset_info' in pose_model.cfg):
+ dataset_info = DatasetInfo(pose_model.cfg.dataset_info)
+
+ if dataset_info is not None:
+ skeleton = dataset_info.skeleton
+
+ pose_kpt_color = dataset_info.pose_kpt_color
+ pose_kpt_color_tmp = []
+ for color in pose_kpt_color:
+ pose_kpt_color_tmp.append(tuple([int(x) for x in color]))
+ pose_kpt_color = pose_kpt_color_tmp
+
+ pose_link_color = dataset_info.pose_link_color
+ pose_link_color_tmp = []
+ for color in pose_link_color:
+ pose_link_color_tmp.append(tuple([int(x) for x in color]))
+ pose_link_color = pose_link_color_tmp
+ else:
+ warnings.warn(
+ 'dataset is deprecated.'
+ 'Please set `dataset_info` in the config.'
+ 'Check https://github.com/open-mmlab/mmpose/pull/663 for details.',
+ DeprecationWarning)
+ raise ValueError('dataset_info is not specified or set in the config file.')
+
+ # create circles_list
+ circles_list = []
+ for bbox_idx, circles in enumerate(keypoints):
+ c_dict = {}
+ for c_idx, c in enumerate(circles):
+ if keypoint_scores[bbox_idx][c_idx] >= kpt_score_thr:
+ c_dict[c_idx] = c
+ # else:
+ # c_dict[c_idx] = None
+ circles_list.append(c_dict)
+
+ # create lines_list
+ lines_list = []
+ for bbox_idx, _ in enumerate(keypoints):
+ s_dict = {}
+ for s_idx, s in enumerate(skeleton):
+ if s[0] in circles_list[bbox_idx].keys() and s[1] in circles_list[bbox_idx].keys():
+ s_dict[s_idx] = True
+ else:
+ s_dict[s_idx] = False
+ lines_list.append(s_dict)
+
+ # draw circle
+ for _, circles in enumerate(circles_list):
+ for c_idx, c in circles.items():
+ if c is not None:
+ cv2.circle(img, (int(c[0]), int(c[1])), radius, pose_kpt_color[c_idx], -1)
+
+ # draw line
+ for bbox_idx, lines in enumerate(lines_list):
+ for l_idx, l in lines.items():
+ if l:
+ s = skeleton[l_idx][0] # idx of start point
+ e = skeleton[l_idx][1] # idx of end point
+ cv2.line(img,
+ (int(circles_list[bbox_idx][s][0]), int(circles_list[bbox_idx][s][1])),
+ (int(circles_list[bbox_idx][e][0]), int(circles_list[bbox_idx][e][1])),
+ pose_link_color[l_idx], thickness)
+
+ if show:
+ mmcv.imshow(img, wait_time=0)
+ if img_path is None:
+ if img_name is not None:
+ img_path = img_name
+ else:
+ img_path = 'demo.jpg'
+ if vis_out_flag:
+ out_file = osp.join(vis_out_flag, osp.basename(img_path))
+ mmcv.imwrite(img, out_file)
+ if pred_out_flag:
+ pred_list = []
+ for bbox_idx in range(len(bbox_list)):
+ bbl = bbox_list[bbox_idx].tolist()
+ pred_list.append(dict(
+ keypoints=keypoints_list[bbox_idx],
+ keypoint_scores=keypoint_scores_list[bbox_idx],
+ bbox=[bbl],
+ bbox_score=bbox_score_list[bbox_idx],
+ ))
+ # replace .jpg or .png with .json
+ out_file = osp.join(pred_out_flag, osp.basename(img_path).rsplit('.', 1)[0] + '.json')
+ json.dump(pred_list, open(out_file, 'w'))
+
+ return img
diff --git a/Model/Model6/model6_inference.py b/Model/Model6/model6_inference.py
new file mode 100644
index 0000000000000000000000000000000000000000..4b2fd561e6f07e09b7cb9d6a962c60df7fe43e0d
--- /dev/null
+++ b/Model/Model6/model6_inference.py
@@ -0,0 +1,270 @@
+"""old name: test_runtime_model6.py"""
+
+import json
+import os
+import subprocess
+import sys
+import warnings
+from time import time
+from typing import Union, Tuple, Any
+
+import pandas as pd
+from mmdet.apis import inference_detector
+from mmdet.apis import init_detector as det_init_detector
+from mmpose.apis import inference_topdown
+from mmpose.apis import init_model as pose_init_model
+from mmpretrain import ImageClassificationInferencer
+from mmpretrain.utils import register_all_modules
+from .extensions.vis_pred_save import save_result
+
+register_all_modules()
+
+st = ist = time()
+# irt = time() - st
+# print(f'==Packages importing time is {irt}s==\n')
+
+print('==Start==')
+
+# DEVICE = 'cuda:0,1,2,3'
+DEVICE = 'cpu'
+abs_path = os.path.dirname(os.path.abspath(__file__))
+yolo_config = os.path.join(abs_path, 'Model6_0_ClothesDetection/mmyolo/configs/custom_dataset/yolov6_s_fast.py')
+yolo_checkpoint = os.path.join(abs_path, 'Model6_0_ClothesDetection/mmyolo/work_dirs/yolov6_s_df2_0.4/epoch_64.pth')
+pretrain_config = os.path.join(abs_path, 'Model6_2_ProfileRecogition/mmpretrain/configs/resnext101_4xb32_2048e_3c_noF.py')
+pretrain_checkpoint = os.path.join(abs_path, 'Model6_2_ProfileRecogition/mmpretrain/work_dirs/'
+ 'resnext101_4xb32_2048e_3c_noF/best_accuracy_top1_epoch_1520.pth')
+pose_configs = {
+ 'short_sleeved_shirt': 'Model/Model6/Model6_1_ClothesKeyPoint/mmpose_1_x/configs/fashion_2d_keypoint/topdown_heatmap/deepfashion2/td_hm_res50_4xb32-60e_deepfashion2_short_sleeved_shirt_256x192.py',
+ 'long_sleeved_shirt': 'Model/Model6/Model6_1_ClothesKeyPoint/mmpose_1_x/configs/fashion_2d_keypoint/topdown_heatmap/deepfashion2/td_hm_res50_4xb64-120e_deepfashion2_long_sleeved_shirt_256x192.py',
+ 'short_sleeved_outwear': 'Model/Model6/Model6_1_ClothesKeyPoint/mmpose_1_x/configs/fashion_2d_keypoint/topdown_heatmap/deepfashion2/td_hm_res50_4xb8-150e_deepfashion2_short_sleeved_outwear_256x192.py',
+ 'long_sleeved_outwear': 'Model/Model6/Model6_1_ClothesKeyPoint/mmpose_1_x/configs/fashion_2d_keypoint/topdown_heatmap/deepfashion2/td_hm_res50_4xb16-120e_deepfashion2_long_sleeved_outwear_256x192.py',
+ 'vest': 'Model/Model6/Model6_1_ClothesKeyPoint/mmpose_1_x/configs/fashion_2d_keypoint/topdown_heatmap/deepfashion2/td_hm_res50_4xb64-120e_deepfashion2_vest_256x192.py',
+ 'sling': 'Model/Model6/Model6_1_ClothesKeyPoint/mmpose_1_x/configs/fashion_2d_keypoint/topdown_heatmap/deepfashion2/td_hm_res50_4xb64-120e_deepfashion2_sling_256x192.py',
+ 'shorts': 'Model/Model6/Model6_1_ClothesKeyPoint/mmpose_1_x/configs/fashion_2d_keypoint/topdown_heatmap/deepfashion2/td_hm_res50_4xb64-210e_deepfashion2_shorts_256x192.py',
+ 'trousers': 'Model/Model6/Model6_1_ClothesKeyPoint/mmpose_1_x/configs/fashion_2d_keypoint/topdown_heatmap/deepfashion2/td_hm_res50_4xb64-60e_deepfashion2_trousers_256x192.py',
+ 'skirt': 'Model/Model6/Model6_1_ClothesKeyPoint/mmpose_1_x/configs/fashion_2d_keypoint/topdown_heatmap/deepfashion2/td_hm_res50_4xb64-120e_deepfashion2_skirt_256x192.py',
+ 'short_sleeved_dress': 'Model/Model6/Model6_1_ClothesKeyPoint/mmpose_1_x/configs/fashion_2d_keypoint/topdown_heatmap/deepfashion2/td_hm_res50_4xb64-150e_deepfashion2_short_sleeved_dress_256x192.py',
+ 'long_sleeved_dress': 'Model/Model6/Model6_1_ClothesKeyPoint/mmpose_1_x/configs/fashion_2d_keypoint/topdown_heatmap/deepfashion2/td_hm_res50_4xb16-150e_deepfashion2_long_sleeved_dress_256x192.py',
+ 'vest_dress': 'Model/Model6/Model6_1_ClothesKeyPoint/mmpose_1_x/configs/fashion_2d_keypoint/topdown_heatmap/deepfashion2/td_hm_res50_4xb64-150e_deepfashion2_vest_dress_256x192.py',
+ 'sling_dress': 'Model/Model6/Model6_1_ClothesKeyPoint/mmpose_1_x/configs/fashion_2d_keypoint/topdown_heatmap/deepfashion2/td_hm_res50_4xb64-210e_deepfashion2_sling_dress_256x192.py',
+}
+
+pose_checkpoints = {
+ 'short_sleeved_shirt': 'Model/Model6/Model6_1_ClothesKeyPoint/work_dirs_1-x/td_hm_res50_4xb32-60e_deepfashion2_short_sleeved_shirt_256x192/best_PCK_epoch_50.pth',
+ 'long_sleeved_shirt': 'Model/Model6/Model6_1_ClothesKeyPoint/work_dirs_1-x/td_hm_res50_4xb64-120e_deepfashion2_long_sleeved_shirt_256x192/best_PCK_epoch_60.pth',
+ 'short_sleeved_outwear': 'Model/Model6/Model6_1_ClothesKeyPoint/work_dirs_1-x/td_hm_res50_4xb8-150e_deepfashion2_short_sleeved_outwear_256x192/best_PCK_epoch_120.pth',
+ 'long_sleeved_outwear': 'Model/Model6/Model6_1_ClothesKeyPoint/work_dirs_1-x/td_hm_res50_4xb16-120e_deepfashion2_long_sleeved_outwear_256x192/best_PCK_epoch_100.pth',
+ 'vest': 'Model/Model6/Model6_1_ClothesKeyPoint/work_dirs_1-x/td_hm_res50_4xb64-120e_deepfashion2_vest_256x192/best_PCK_epoch_90.pth',
+ 'sling': 'Model/Model6/Model6_1_ClothesKeyPoint/work_dirs_1-x/td_hm_res50_4xb64-120e_deepfashion2_sling_256x192/best_PCK_epoch_60.pth',
+ 'shorts': 'Model/Model6/Model6_1_ClothesKeyPoint/work_dirs_1-x/td_hm_res50_4xb64-210e_deepfashion2_shorts_256x192/best_PCK_epoch_160.pth',
+ 'trousers': 'Model/Model6/Model6_1_ClothesKeyPoint/work_dirs_1-x/td_hm_res50_4xb64-60e_deepfashion2_trousers_256x192/best_PCK_epoch_30.pth',
+ 'skirt': 'Model/Model6/Model6_1_ClothesKeyPoint/work_dirs_1-x/td_hm_res50_4xb64-120e_deepfashion2_skirt_256x192/best_PCK_epoch_110.pth',
+ 'short_sleeved_dress': 'Model/Model6/Model6_1_ClothesKeyPoint/work_dirs_1-x/td_hm_res50_4xb64-150e_deepfashion2_short_sleeved_dress_256x192/best_PCK_epoch_100.pth',
+ 'long_sleeved_dress': 'Model/Model6/Model6_1_ClothesKeyPoint/work_dirs_1-x/td_hm_res50_4xb16-150e_deepfashion2_long_sleeved_dress_256x192/best_PCK_epoch_120.pth',
+ 'vest_dress': 'Model/Model6/Model6_1_ClothesKeyPoint/work_dirs_1-x/td_hm_res50_4xb64-150e_deepfashion2_vest_dress_256x192/best_PCK_epoch_80.pth',
+ 'sling_dress': 'Model/Model6/Model6_1_ClothesKeyPoint/work_dirs_1-x/td_hm_res50_4xb64-210e_deepfashion2_sling_dress_256x192/best_PCK_epoch_140.pth',
+}
+
+start_load = time()
+yolo_inferencer = det_init_detector(yolo_config, yolo_checkpoint, device=DEVICE)
+print('=' * 2 + 'The model loading time of MMYolo is {}s'.format(time() - start_load) + '=' * 2)
+
+start_load = time()
+pretrain_inferencer = ImageClassificationInferencer(model=pretrain_config,
+ pretrained=pretrain_checkpoint,
+ device=DEVICE)
+print('=' * 2 + 'The model loading time of MMPretrain is {}s'.format(time() - start_load) + '=' * 2)
+
+
+def get_bbox_results_by_classes(result) -> dict:
+ """
+ :param result: the result of mmyolo inference
+ :return: a dict of bbox results by classes
+ """
+ bbox_results_by_classes = {
+ 'short_sleeved_shirt': [],
+ 'long_sleeved_shirt': [],
+ 'short_sleeved_outwear': [],
+ 'long_sleeved_outwear': [],
+ 'vest': [],
+ 'sling': [],
+ 'shorts': [],
+ 'trousers': [],
+ 'skirt': [],
+ 'short_sleeved_dress': [],
+ 'long_sleeved_dress': [],
+ 'vest_dress': [],
+ 'sling_dress': [],
+ }
+ pred_instances = result.pred_instances
+ _bboxes = pred_instances.bboxes
+ _labels = pred_instances.labels
+ _scores = pred_instances.scores
+ labels = _labels[[_scores > 0.3]]
+ bboxes = _bboxes[[_scores > 0.3]]
+ # use enumerate to get index and value
+ for idx, value in enumerate(labels):
+ class_name = list(bbox_results_by_classes.keys())[value]
+ x1 = bboxes[idx][0]
+ y1 = bboxes[idx][1]
+ x2 = bboxes[idx][2]
+ y2 = bboxes[idx][3]
+ bbox_results_by_classes[class_name].append([x1, y1, x2, y2])
+ return bbox_results_by_classes
+
+
+def mmyolo_inference(img: Union[str, list], model) -> tuple:
+ mmyolo_st = time()
+ result = inference_detector(model, img)
+ mmyolo_et = time()
+
+ return result, (mmyolo_et - mmyolo_st)
+
+
+def mmpose_inference(person_results: dict, use_bbox: bool,
+ mmyolo_cfg_path: str, mmyolo_ckf_path: str,
+ img: str, output_path_root: str, save=True, device='cpu') -> float:
+ """
+ :param person_results: the result of mmyolo inference
+ :param use_bbox: whether to use bbox to inference the pose results
+ :param mmyolo_cfg_path: the file path of mmyolo config
+ :param mmyolo_ckf_path: the file path of mmyolo checkpoint
+ :param img: the path of the image to inference
+ :param output_path_root: the root path of the output
+ :param save: whether to save the inference result, including the image and the predicted json file.
+ If `save` is False, `output_path_root` will be invalid.
+ :param device: the device to inference
+ """
+ mmpose_st = time()
+ poses = {
+ 'short_sleeved_shirt': {},
+ 'long_sleeved_shirt': {},
+ 'short_sleeved_outwear': {},
+ 'long_sleeved_outwear': {},
+ 'vest': {},
+ 'sling': {},
+ 'shorts': {},
+ 'trousers': {},
+ 'skirt': {},
+ 'short_sleeved_dress': {},
+ 'long_sleeved_dress': {},
+ 'vest_dress': {},
+ 'sling_dress': {}
+ }
+ for label, person_result in person_results.items():
+ if len(person_result) == 0:
+ continue
+ pose_config = pose_configs[label]
+ pose_checkpoint = pose_checkpoints[label]
+ if not use_bbox:
+ from mmpose.apis import MMPoseInferencer
+
+ warnings.warn('use_bbox is False, '
+ 'which means using MMPoseInferencer to inference the pose results without use_bbox '
+ 'and may be wrong')
+ inferencer = MMPoseInferencer(
+ pose2d=pose_config,
+ pose2d_weights=pose_checkpoint,
+ det_model=mmyolo_cfg_path,
+ det_weights=mmyolo_ckf_path
+ )
+ result_generator = inferencer(img, out_dir='upload_to_web_tmp', return_vis=True)
+ result = next(result_generator)
+ # print(result)
+ else:
+ pose_model = pose_init_model(
+ pose_config,
+ pose_checkpoint,
+ device=device
+ )
+ pose_results = inference_topdown(pose_model, img, person_result, bbox_format='xyxy')
+ poses[label]['pose_results'] = pose_results
+ poses[label]['pose_model'] = pose_model
+ mmpose_et = time()
+ if save:
+
+ save_result(img, poses, out_dir=output_path_root)
+
+ return mmpose_et - mmpose_st
+
+
+def mmpretrain_inference(img: Union[str, list], model) -> tuple:
+ mmpretain_st = time()
+ cls_result = model(img)
+ mmpretain_et = time()
+ return cls_result, (mmpretain_et - mmpretain_st)
+
+
+def main(img_path: str, output_path_root='upload_to_web_tmp', use_bbox=True, device='cpu', test_runtime=False) -> dict:
+ """
+ :param img_path: the path of the image or the folder of images
+ :param output_path_root: the root path of the output
+ :param use_bbox: whether to use bbox to inference the pose results
+ :param device: the device to inference
+ :param test_runtime: whether to test the runtime
+
+ :return: the results of model6_2 in form of dictionary
+ """
+ if os.path.isdir(img_path):
+ img_names = os.listdir(img_path)
+ img_paths = [os.path.join(img_path, img_name) for img_name in img_names]
+ elif os.path.isfile(img_path):
+ img_paths = [img_path]
+ else:
+ print('==Img_path must be a path of an imgage or a folder!==')
+ raise ValueError()
+
+ runtimes = [['img_name',
+ 'runtime_mmyolo', 'percent1',
+ 'runtime_mmpose', 'percent2',
+ 'runtime_mmpretrain', 'percent3',
+ 'runtime_total']]
+
+ cls_results = {}
+
+ for img in img_paths:
+ print(f'==Start to inference {img}==')
+ yolo_result, runtime_mmyolo = mmyolo_inference(img, yolo_inferencer)
+ print(f'==mmyolo running time is {runtime_mmyolo}s==')
+
+ person_results = get_bbox_results_by_classes(yolo_result)
+
+ runtime_mmpose = mmpose_inference(
+ person_results=person_results,
+ use_bbox=use_bbox,
+ mmyolo_cfg_path=yolo_config,
+ mmyolo_ckf_path=yolo_checkpoint,
+ img=img,
+ output_path_root=output_path_root,
+ save=True,
+ device=device
+ )
+ print(f'mmpose running time is {runtime_mmpose}s')
+
+ cls_result, runtime_mmpretrain = mmpretrain_inference(img, pretrain_inferencer)
+ print(f'mmpretrain running time is {runtime_mmpretrain}s')
+ cls_results[os.path.basename(img)] = cls_result
+ if test_runtime:
+ runtime_total = runtime_mmyolo + runtime_mmpose + runtime_mmpretrain
+ percent1 = str(round(runtime_mmyolo / runtime_total * 100, 2)) + '%'
+ percent2 = str(round(runtime_mmpose / runtime_total * 100, 2)) + '%'
+ percent3 = str(round(runtime_mmpretrain / runtime_total * 100, 2)) + '%'
+ img_name = os.path.basename(img)
+ runtimes.append([img_name,
+ runtime_mmyolo, percent1,
+ runtime_mmpose, percent2,
+ runtime_mmpretrain, percent3,
+ runtime_total])
+ if test_runtime:
+ df = pd.DataFrame(runtimes, columns=runtimes[0])
+ df.to_csv('runtimes.csv', index=False)
+
+ return cls_results
+
+
+if __name__ == "__main__":
+ # main(1)
+ main('data-test/')
+ # main('data-test/000002.jpg')
+ rt = time() - st
+ print(f'==Totol time cost is {rt}s==')
diff --git a/Model/__init__.py b/Model/__init__.py
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/[gradio]model_display.py b/[gradio]model_display.py
new file mode 100644
index 0000000000000000000000000000000000000000..39efa4bbb1dc564fe5435904870656f5dddb6531
--- /dev/null
+++ b/[gradio]model_display.py
@@ -0,0 +1,323 @@
+import numpy as np
+import gradio as gr
+import requests
+import base64
+import pandas as pd
+import cv2
+from typing import Tuple
+from PIL import Image
+from io import BytesIO
+
+import os
+
+from Model.Model6.model6_inference import main as model6_inferencer
+from mmyolo.utils import register_all_modules
+
+register_all_modules()
+
+
+def get_access_token(refatch=False) -> str:
+ """获取百度AI的access_token
+ :param refatch:是否重新获取access_token
+ :return:返回access_token"""
+ if refatch:
+ # client_id 为官网获取的AK， client_secret 为官网获取的SK
+ client_id = '7OtH60uo01ZNYN4yPyahlRSx'
+ client_secret = 'D5AxcUpyQyIA7KgPplp7dnz5tM0UIljy'
+ host = 'https://aip.baidubce.com/oauth/2.0/token?' \
+ 'grant_type=client_credentials&client_id=%s&client_secret=%s' % (client_id, client_secret)
+ response = requests.get(host)
+ # print(response)
+ if response:
+ return response.json()['access_token']
+ else:
+ r"""
+ {"refresh_token":"25.24b9368ce91f9bd62c8dad38b3436800.315360000.2007815067.282335-30479502",
+ "expires_in":2592000,
+ "session_key":
+ "9mzdWT\/YmQ7oEi9WCRWbXd0YCcrSYQY6kKZjObKunlcKcZt95j9\/q1aJqbVXihpQOXK84o5WLJ8e7d4cXOi0VUJJcz5YEQ==",
+ "access_token":"24.becefee37aba38ea43c546fc154d3016.2592000.1695047067.282335-30479502",
+ "scope":"public brain_all_scope brain_body_analysis brain_body_attr brain_body_number brain_driver_behavior
+ brain_body_seg brain_gesture_detect brain_body_tracking brain_hand_analysis wise_adapt
+ lebo_resource_base lightservice_public hetu_basic lightcms_map_poi kaidian_kaidian
+ ApsMisTest_Test\u6743\u9650 vis-classify_flower lpq_\u5f00\u653e cop_helloScope
+ ApsMis_fangdi_permission smartapp_snsapi_base smartapp_mapp_dev_manage iop_autocar oauth_tp_app
+ smartapp_smart_game_openapi oauth_sessionkey smartapp_swanid_verify smartapp_opensource_openapi
+ smartapp_opensource_recapi fake_face_detect_\u5f00\u653eScope
+ vis-ocr_\u865a\u62df\u4eba\u7269\u52a9\u7406 idl-video_\u865a\u62df\u4eba\u7269\u52a9\u7406
+ smartapp_component smartapp_search_plugin avatar_video_test b2b_tp_openapi b2b_tp_openapi_online
+ smartapp_gov_aladin_to_xcx","session_secret":"5c8c3dbb80b04f58bb33aa8077758679"
+ }
+ """
+ access_token = "24.becefee37aba38ea43c546fc154d3016.2592000.1695047067.282335-30479502"
+ return access_token
+
+
+def resize_image(img, max_length=2048, min_length=50) -> Tuple[np.ndarray, bool]:
+ """Ensure that the longest side is shorter than 2048px and the shortest side is longer than 50px.
+ :param img: 前端传入的图片
+ :param max_length: 最长边像素
+ :param min_length: 最短边像素
+ :return: 返回处理后的图片和是否进行了resize的标志
+ """
+ flag = False
+ max_side = max(img.shape[0], img.shape[1])
+ min_side = min(img.shape[0], img.shape[1])
+ if max_side > max_length:
+ scale = max_length / max_side
+ img = cv2.resize(img, (int(img.shape[1] * scale), int(img.shape[0] * scale)))
+ flag = True
+ if min_side < min_length:
+ scale = min_length / min_side
+ img = cv2.resize(img, (int(img.shape[1] * scale), int(img.shape[0] * scale)))
+ flag = True
+ return img, flag
+
+
+def model1_det(x):
+ """人体检测与属性识别
+ :param x:前端传入的图片
+ :return:返回检测结果
+ """
+
+ def _Baidu_det(img):
+ """调用百度AI接口进行人体检测与属性识别
+ :param img:前端传入的图片，格式为numpy.ndarray
+ :return:返回检测结果
+ """
+ request_url = "https://aip.baidubce.com/rest/2.0/image-classify/v1/body_attr"
+ # 保存图片到本地
+ cv2.imwrite('test.jpg', img)
+ # 二进制方式打开图片文件
+ f = open('test.jpg', 'rb')
+ hex_image = base64.b64encode(f.read())
+ # 选择二进制图片和需要输出的属性（12个）
+ params = {
+ "image": hex_image,
+ "type": "gender,age,upper_wear,lower_wear,upper_color,lower_color,"
+ "orientation,upper_cut,lower_cut,side_cut,occlusion,is_human"
+ }
+ access_token = get_access_token()
+ request_url = request_url + "?access_token=" + access_token
+ headers = {'content-type': 'application/x-www-form-urlencoded'}
+ response = requests.post(request_url, data=params, headers=headers)
+ if response:
+ return response.json()
+
+ def _get_attributes_list(r) -> dict:
+ """获取人体属性列表
+ :param r:百度AI接口返回的json数据
+ :return:返回人体属性列表
+ """
+ all_humans_attributes_list = {}
+ person_num = r['person_num']
+ print('person_num:', person_num)
+ for human_idx in range(person_num):
+ attributes_dict = r['person_info'][human_idx]['attributes']
+ attributes_list = []
+ for key, value in attributes_dict.items():
+ attribute = [key, value['name'], value['score']]
+ attributes_list.append(attribute)
+ new_value = ['attribute', 'attribute_value', 'accuracy']
+ attributes_list.insert(0, new_value)
+ df = pd.DataFrame(attributes_list[1:], columns=attributes_list[0])
+ all_humans_attributes_list[human_idx] = df
+ return all_humans_attributes_list
+
+ def _show_img(img, bboxes):
+ """显示图片
+ :param img:前端传入的图片
+ :param bboxes:检测框坐标
+ :return:处理完成的图片 """
+ line_width = int(max(img.shape[1], img.shape[0]) / 400)
+ for bbox in bboxes:
+ left, top, width, height = bbox['left'], bbox['top'], bbox['width'], bbox['height']
+ right, bottom = left + width, top + height
+ for i in range(left, right):
+ img[top:top + line_width, i] = [255, 0, 0]
+ img[bottom - line_width:bottom, i] = [255, 0, 0]
+ for i in range(top, bottom):
+ img[i, left:left + line_width] = [255, 0, 0]
+ img[i, right - line_width:right] = [255, 0, 0]
+ return img
+
+ result = _Baidu_det(x)
+ HAs_list = _get_attributes_list(result)
+ locations = []
+ for i in range(len(result['person_info'])):
+ locations.append(result['person_info'][i]['location'])
+
+ return _show_img(x, locations), f"模型检测到的人数为：{result['person_num']}人"
+
+
+def model2_rem(x):
+ """背景消除
+ :param x: 前端传入的图片
+ :return: 返回处理后的图片
+ """
+
+ def _Baidu_rem(img):
+ """调用百度AI接口进行背景消除
+ :param img: 前端传入的图片，格式为numpy.ndarray
+ :return: 返回处理后的图片
+ """
+ request_url = "https://aip.baidubce.com/rest/2.0/image-classify/v1/body_seg"
+ bgr_image = cv2.cvtColor(img, cv2.COLOR_RGB2BGR)
+ cv2.imwrite('test.jpg', bgr_image)
+ f = open('test.jpg', 'rb')
+ hex_image = base64.b64encode(f.read())
+ params = {"image": hex_image}
+ access_token = get_access_token()
+ request_url = request_url + "?access_token=" + access_token
+ headers = {'content-type': 'application/x-www-form-urlencoded'}
+ response = requests.post(request_url, data=params, headers=headers)
+ if response:
+ encoded_image = response.json()["foreground"]
+ decoded_image = base64.b64decode(encoded_image)
+ image = Image.open(BytesIO(decoded_image))
+ image_array = np.array(image)
+ return image_array
+
+ resized_x, resized_f = resize_image(x)
+ new_img = _Baidu_rem(resized_x)
+ if resized_f:
+ resized_f = "图片尺寸已被修改至合适大小"
+ else:
+ resized_f = "图片尺寸无需修改"
+
+ return new_img, resized_f
+
+
+def model3_ext(x: np.ndarray, num_clusters=12):
+ """主色调提取
+ :param x: 前端传入的图片
+ :param num_clusters: 聚类的数量
+ :return: 返回主色调条形卡片"""
+
+ # TODO: 编写颜色名称匹配算法[most important]
+ # TODO: 修改颜色条形卡片呈现形式，要求呈现颜色名称和比例[important]
+ def _find_name(color):
+ """根据颜色值查找颜色名称
+ :param color:颜色值
+ :return:返回颜色名称
+ """
+ pass
+
+ def _cluster(img, NUM_CLUSTERS):
+ """K-means 聚类提取主色调
+ :param img: 前端传入的图片
+ :param NUM_CLUSTERS: 聚类的数量
+ :return: 返回聚类结果
+ """
+ h, w, ch = img.shape
+ reshaped_x = np.float32(img.reshape((-1, 4)))
+ new_data_list = []
+ for i in range(len(reshaped_x)):
+ if reshaped_x[i][3] < 100:
+ continue
+ else:
+ new_data_list.append(reshaped_x[i])
+ reshaped_x = np.array(new_data_list)
+ reshaped_x = np.delete(reshaped_x, 3, axis=1)
+ criteria = (cv2.TERM_CRITERIA_EPS + cv2.TERM_CRITERIA_MAX_ITER, 10, 1.0)
+ NUM_CLUSTERS = NUM_CLUSTERS
+ ret, label, center = cv2.kmeans(reshaped_x, NUM_CLUSTERS, None, criteria,
+ NUM_CLUSTERS, cv2.KMEANS_RANDOM_CENTERS)
+ clusters = np.zeros([NUM_CLUSTERS], dtype=np.int32)
+ for i in range(len(label)):
+ clusters[label[i][0]] += 1
+ clusters = np.float32(clusters) / float(len(reshaped_x))
+ center = np.int32(center)
+ x_offset = 0
+ card = np.zeros((50, w, 3), dtype=np.uint8)
+ for c in np.argsort(clusters)[::-1]:
+ dx = int(clusters[c] * w)
+ b = center[c][0]
+ g = center[c][1]
+ r = center[c][2]
+ cv2.rectangle(card, (x_offset, 0), (x_offset + dx, 50),
+ (int(b), int(g), int(r)), -1)
+ x_offset += dx
+
+ return card, resized_f
+
+ resized_x, resized_f = resize_image(x)
+ card, resized_f = _cluster(resized_x, num_clusters)
+ if resized_f:
+ resized_f = "图片尺寸已被修改至合适大小"
+ else:
+ resized_f = "图片尺寸无需修改"
+
+ return card, resized_f
+
+
+def model4_clo(x_path: str):
+ def _get_result(input_path: str, cls_results: dict) -> pd.DataFrame:
+ """convert the results of model6_2 to a dataframe
+ :param input_path: the (absolute) path of the image
+ :param cls_results: the results of model6_2
+
+ :return: a dataframe to display on the web
+ """
+ result_pd = []
+ img_name = os.path.basename(input_path)
+ pred_profile = cls_results[img_name][0]['pred_class']
+ pred_score = round(cls_results[img_name][0]['pred_score'], 2)
+ result_pd.append([img_name, pred_profile, pred_score])
+ df = pd.DataFrame(result_pd, columns=None)
+ return df
+
+ output_path_root = 'upload_to_web_tmp'
+ if not os.path.exists(output_path_root):
+ os.mkdir(output_path_root)
+ cls_result = model6_inferencer(x_path, output_path_root)
+
+ if cls_result:
+ # use np to read image·
+ x_name = os.path.basename(x_path)
+ pred_x = np.array(Image.open(os.path.join(output_path_root, 'visualizations', x_name)))
+
+ return pred_x, _get_result(x_path, cls_result), "识别成功!"
+ # TODO: 完善识别失败时的处理（model6_inference.py中）[important]
+ return x_path, pd.DataFrame(), "未检测到服装"
+
+
+with gr.Blocks() as demo:
+ gr.Markdown("# Flip text or image files using this demo.")
+ with gr.Tab("人体检测模型"):
+ with gr.Row():
+ model1_input = gr.Image(height=400)
+ model1_output_img = gr.Image(height=400)
+ # model1_output_df = gr.DataFrame()
+ model1_button = gr.Button("开始检测")
+ with gr.Tab("背景消除模型"):
+ with gr.Row():
+ model2_input = gr.Image(height=400)
+ model2_output_img = gr.Image(height=400)
+ model2_button = gr.Button("开始消除")
+ with gr.Tab('主色调提取'):
+ with gr.Row():
+ with gr.Column():
+ # TODO: 参照“蒙娜丽莎”尝试修改前端界面[not important]
+ # TODO: 修改布局，使其更美观[moderately important]
+ model3_input = gr.Image(height=400, image_mode='RGBA')
+ model3_slider = gr.Slider(minimum=1, maximum=20, step=1, value=12,
+ min_width=400, label="聚类数量")
+ model3_output_img = gr.Image(height=400)
+ model3_button = gr.Button("开始提取")
+ with gr.Tab("廓形识别"):
+ with gr.Row():
+ model4_input = gr.Image(height=400, type="filepath")
+ model4_output_img = gr.Image(height=400)
+ model4_output_df = gr.DataFrame(headers=['img_name', 'pred_profile', 'pred_score'],
+ datatype=['str', 'str', 'number'])
+ model4_button = gr.Button("开始识别")
+ # 设置折叠内容
+ with gr.Accordion("模型运行信息"):
+ running_info = gr.Markdown("等待输入和运行...")
+
+ model1_button.click(model1_det, inputs=model1_input, outputs=[model1_output_img, running_info])
+ model2_button.click(model2_rem, inputs=model2_input, outputs=[model2_output_img, running_info])
+ model3_button.click(model3_ext, inputs=[model3_input, model3_slider], outputs=[model3_output_img, running_info])
+ model4_button.click(model4_clo, inputs=model4_input, outputs=[model4_output_img, model4_output_df, running_info])
+demo.launch(share=True)
diff --git a/requirements.txt b/requirements.txt
new file mode 100644
index 0000000000000000000000000000000000000000..64fa7cb246a7694cc07b7d9e564f962a413a9c76
--- /dev/null
+++ b/requirements.txt
@@ -0,0 +1,14 @@
+mmcv==2.0.0
+mmdet==3.0.0
+mmengine==0.8.4
+mmpose==1.1.0
+mmpretrain==1.0.2
+mmyolo==0.6.0
+numpy==1.23.5
+opencv-python==4.7.0.72
+openmim==0.3.7
+pandas==2.0.0
+pillow==9.4.0
+pip==23.0.1
+pycocotools==2.0.7
+scipy==1.10.1