Add table det

main.py

@@ -7,11 +7,11 @@ import torch
 
 print('Loading model...')
 device = 'gpu' if torch.cuda.is_available() else 'cpu'
-# table_det = init_detector('model/table-det/config.py',
-#                           'model/table-det/model.pth', device=device)
+table_det = init_detector('model/table-det/config.py',
+                          'model/table-det/model.pth', device=device)
 
-ocr = MMOCRInferencer(det='model/det/config.py',
-            det_weights='model/det/model.pth',
+ocr = MMOCRInferencer(det='model/text-det/config.py',
+            det_weights='model/text-det/model.pth',
             device=device)
 
 def get_rec(points):

model/table-det/config.py

@@ -0,0 +1,283 @@
+model = dict(
+    type='MaskRCNN',
+    data_preprocessor=dict(
+        type='DetDataPreprocessor',
+        mean=[103.53, 116.28, 123.675],
+        std=[1.0, 1.0, 1.0],
+        bgr_to_rgb=False,
+        pad_mask=True,
+        pad_size_divisor=32),
+    backbone=dict(
+        type='ResNet',
+        depth=50,
+        num_stages=4,
+        out_indices=(0, 1, 2, 3),
+        frozen_stages=1,
+        norm_cfg=dict(type='BN', requires_grad=False),
+        norm_eval=True,
+        style='caffe',
+        init_cfg=dict(
+            type='Pretrained',
+            checkpoint='open-mmlab://detectron2/resnet50_caffe')),
+    neck=dict(
+        type='FPN',
+        in_channels=[256, 512, 1024, 2048],
+        out_channels=256,
+        num_outs=5),
+    rpn_head=dict(
+        type='RPNHead',
+        in_channels=256,
+        feat_channels=256,
+        anchor_generator=dict(
+            type='AnchorGenerator',
+            scales=[8],
+            ratios=[0.5, 1.0, 2.0],
+            strides=[4, 8, 16, 32, 64]),
+        bbox_coder=dict(
+            type='DeltaXYWHBBoxCoder',
+            target_means=[0.0, 0.0, 0.0, 0.0],
+            target_stds=[1.0, 1.0, 1.0, 1.0]),
+        loss_cls=dict(
+            type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0),
+        loss_bbox=dict(type='L1Loss', loss_weight=1.0)),
+    roi_head=dict(
+        type='StandardRoIHead',
+        bbox_roi_extractor=dict(
+            type='SingleRoIExtractor',
+            roi_layer=dict(type='RoIAlign', output_size=7, sampling_ratio=0),
+            out_channels=256,
+            featmap_strides=[4, 8, 16, 32]),
+        bbox_head=dict(
+            type='Shared2FCBBoxHead',
+            in_channels=256,
+            fc_out_channels=1024,
+            roi_feat_size=7,
+            num_classes=1,
+            bbox_coder=dict(
+                type='DeltaXYWHBBoxCoder',
+                target_means=[0.0, 0.0, 0.0, 0.0],
+                target_stds=[0.1, 0.1, 0.2, 0.2]),
+            reg_class_agnostic=False,
+            loss_cls=dict(
+                type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
+            loss_bbox=dict(type='L1Loss', loss_weight=1.0)),
+        mask_roi_extractor=dict(
+            type='SingleRoIExtractor',
+            roi_layer=dict(type='RoIAlign', output_size=14, sampling_ratio=0),
+            out_channels=256,
+            featmap_strides=[4, 8, 16, 32]),
+        mask_head=dict(
+            type='FCNMaskHead',
+            num_convs=4,
+            in_channels=256,
+            conv_out_channels=256,
+            num_classes=1,
+            loss_mask=dict(
+                type='CrossEntropyLoss', use_mask=True, loss_weight=1.0))),
+    train_cfg=dict(
+        rpn=dict(
+            assigner=dict(
+                type='MaxIoUAssigner',
+                pos_iou_thr=0.7,
+                neg_iou_thr=0.3,
+                min_pos_iou=0.3,
+                match_low_quality=True,
+                ignore_iof_thr=-1),
+            sampler=dict(
+                type='RandomSampler',
+                num=256,
+                pos_fraction=0.5,
+                neg_pos_ub=-1,
+                add_gt_as_proposals=False),
+            allowed_border=-1,
+            pos_weight=-1,
+            debug=False),
+        rpn_proposal=dict(
+            nms_pre=2000,
+            max_per_img=1000,
+            nms=dict(type='nms', iou_threshold=0.7),
+            min_bbox_size=0),
+        rcnn=dict(
+            assigner=dict(
+                type='MaxIoUAssigner',
+                pos_iou_thr=0.5,
+                neg_iou_thr=0.5,
+                min_pos_iou=0.5,
+                match_low_quality=True,
+                ignore_iof_thr=-1),
+            sampler=dict(
+                type='RandomSampler',
+                num=512,
+                pos_fraction=0.25,
+                neg_pos_ub=-1,
+                add_gt_as_proposals=True),
+            mask_size=28,
+            pos_weight=-1,
+            debug=False)),
+    test_cfg=dict(
+        rpn=dict(
+            nms_pre=1000,
+            max_per_img=1000,
+            nms=dict(type='nms', iou_threshold=0.7),
+            min_bbox_size=0),
+        rcnn=dict(
+            score_thr=0.05,
+            nms=dict(type='nms', iou_threshold=0.5),
+            max_per_img=100,
+            mask_thr_binary=0.5)))
+dataset_type = 'CocoDataset'
+data_root = 'data/table-det-740/'
+backend_args = None
+train_pipeline = [
+    dict(type='LoadImageFromFile', backend_args=None),
+    dict(
+        type='LoadAnnotations',
+        with_bbox=True,
+        with_mask=True,
+        poly2mask=False),
+    dict(
+        type='RandomChoiceResize',
+        scales=[(1333, 640), (1333, 672), (1333, 704), (1333, 736),
+                (1333, 768), (1333, 800)],
+        keep_ratio=True),
+    dict(type='RandomFlip', prob=0.5),
+    dict(type='PackDetInputs')
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile', backend_args=None),
+    dict(type='Resize', scale=(1333, 800), keep_ratio=True),
+    dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
+    dict(
+        type='PackDetInputs',
+        meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
+                   'scale_factor'))
+]
+train_dataloader = dict(
+    batch_size=4,
+    num_workers=2,
+    persistent_workers=True,
+    sampler=dict(type='DefaultSampler', shuffle=True),
+    batch_sampler=dict(type='AspectRatioBatchSampler'),
+    dataset=dict(
+        type='CocoDataset',
+        data_root='data/table-det-740/',
+        ann_file='train_coco.json',
+        data_prefix=dict(img=''),
+        filter_cfg=dict(filter_empty_gt=True, min_size=32),
+        pipeline=[
+            dict(type='LoadImageFromFile', backend_args=None),
+            dict(
+                type='LoadAnnotations',
+                with_bbox=True,
+                with_mask=True,
+                poly2mask=False),
+            dict(
+                type='RandomChoiceResize',
+                scales=[(1333, 640), (1333, 672), (1333, 704), (1333, 736),
+                        (1333, 768), (1333, 800)],
+                keep_ratio=True),
+            dict(type='RandomFlip', prob=0.5),
+            dict(type='PackDetInputs')
+        ],
+        backend_args=None,
+        metainfo=dict(classes=('Table', ), palette=[(220, 20, 60)])))
+val_dataloader = dict(
+    batch_size=1,
+    num_workers=2,
+    persistent_workers=True,
+    drop_last=False,
+    sampler=dict(type='DefaultSampler', shuffle=False),
+    dataset=dict(
+        type='CocoDataset',
+        data_root='data/table-det-740/',
+        ann_file='test_coco.json',
+        data_prefix=dict(img=''),
+        test_mode=True,
+        pipeline=[
+            dict(type='LoadImageFromFile', backend_args=None),
+            dict(type='Resize', scale=(1333, 800), keep_ratio=True),
+            dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
+            dict(
+                type='PackDetInputs',
+                meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
+                           'scale_factor'))
+        ],
+        backend_args=None,
+        metainfo=dict(classes=('Table', ), palette=[(220, 20, 60)])))
+test_dataloader = dict(
+    batch_size=1,
+    num_workers=2,
+    persistent_workers=True,
+    drop_last=False,
+    sampler=dict(type='DefaultSampler', shuffle=False),
+    dataset=dict(
+        type='CocoDataset',
+        data_root='data/table-det-740/',
+        ann_file='test_coco.json',
+        data_prefix=dict(img=''),
+        test_mode=True,
+        pipeline=[
+            dict(type='LoadImageFromFile', backend_args=None),
+            dict(type='Resize', scale=(1333, 800), keep_ratio=True),
+            dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
+            dict(
+                type='PackDetInputs',
+                meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
+                           'scale_factor'))
+        ],
+        backend_args=None,
+        metainfo=dict(classes=('Table', ), palette=[(220, 20, 60)])))
+val_evaluator = dict(
+    type='CocoMetric',
+    ann_file='data/table-det-740/test_coco.json',
+    metric=['bbox', 'segm'],
+    format_only=False,
+    backend_args=None)
+test_evaluator = dict(
+    type='CocoMetric',
+    ann_file='data/table-det-740/test_coco.json',
+    metric=['bbox', 'segm'],
+    format_only=False,
+    backend_args=None)
+train_cfg = dict(type='EpochBasedTrainLoop', max_epochs=12, val_interval=1)
+val_cfg = dict(type='ValLoop')
+test_cfg = dict(type='TestLoop')
+param_scheduler = [
+    dict(
+        type='LinearLR', start_factor=0.001, by_epoch=False, begin=0, end=500),
+    dict(
+        type='MultiStepLR',
+        begin=0,
+        end=12,
+        by_epoch=True,
+        milestones=[8, 11],
+        gamma=0.1)
+]
+optim_wrapper = dict(
+    type='OptimWrapper',
+    optimizer=dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001))
+auto_scale_lr = dict(enable=False, base_batch_size=16)
+default_scope = 'mmdet'
+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='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='DetLocalVisualizer',
+    vis_backends=[dict(type='LocalVisBackend')],
+    name='visualizer')
+log_processor = dict(type='LogProcessor', window_size=50, by_epoch=True)
+log_level = 'INFO'
+load_from = 'https://download.openmmlab.com/mmdetection/v2.0/mask_rcnn/mask_rcnn_r50_caffe_fpn_mstrain-poly_3x_coco/mask_rcnn_r50_caffe_fpn_mstrain-poly_3x_coco_bbox_mAP-0.408__segm_mAP-0.37_20200504_163245-42aa3d00.pth'
+resume = False
+metainfo = dict(classes=('Table', ), palette=[(220, 20, 60)])
+launcher = 'none'
+work_dir = './work_dirs/vote-config'

model/table-det/model.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:580befce0957f18f2dde80eafa744b5128d7ba1fbb08ea0a8ea18bcaab7d0b50
+size 351236105