更新了kappamask模型

.netrc

@@ -1,3 +1,3 @@
-machine api.wandb.ai
-  login user
-  password 76211aa17d75da9ddab7b8cba5743454194fe1d5
+machine api.wandb.ai
+  login user
+  password 76211aa17d75da9ddab7b8cba5743454194fe1d5

app.py

@@ -18,6 +18,7 @@ from src.models.components.cdnetv1 import CDnetV1
 from src.models.components.cdnetv2 import CDnetV2
 from src.models.components.dbnet import DBNet
 from src.models.components.hrcloudnet import HRCloudNet
+from src.models.components.kappamask import KappaMask
 from src.models.components.mcdnet import MCDNet
 from src.models.components.scnn import SCNN
 from src.models.components.unetmobv2 import UNetMobV2
@@ -36,11 +37,13 @@ class Application:
                 self.device
             ),
             "unetmobv2": UNetMobV2(num_classes=2).to(self.device),
+            "kappamask":KappaMask(num_classes=2,in_channels=3).to(self.device)
         }
         self.__load_weight()
         self.transform = albu.Compose(
             [
                 albu.Resize(256, 256, always_apply=True),
+                albu.ToFloat(),
                 ToTensorV2(),
             ]
         )
@@ -119,7 +122,7 @@ class Application:
             [
                 gr.Image(sources=["clipboard", "upload"], type="pil"),
                 gr.Radio(
-                    ["cdnetv1", "cdnetv2", "hrcloudnet", "mcdnet", "scnn", "dbnet", "unetmobv2"],
+                    ["cdnetv1", "cdnetv2", "hrcloudnet", "mcdnet", "scnn", "dbnet", "unetmobv2","kappamask"],
                     label="model_name",
                     info="选择使用的模型",
                 ),

configs/data/hrcwhu/hrcwhu.yaml

@@ -46,7 +46,6 @@ train_pipeline:
     _target_: albumentations.Compose
     transforms:
       - _target_: albumentations.ToFloat
-        max_value: 255.0
       - _target_: albumentations.pytorch.transforms.ToTensorV2
 
   ann_transform: null
@@ -62,7 +61,6 @@ val_pipeline:
     _target_: albumentations.Compose
     transforms:
       - _target_: albumentations.ToFloat
-        max_value: 255.0
       - _target_: albumentations.pytorch.transforms.ToTensorV2
   ann_transform: null
 
@@ -78,7 +76,6 @@ test_pipeline:
     _target_: albumentations.Compose
     transforms:
       - _target_: albumentations.ToFloat
-        max_value: 255.0
       - _target_: albumentations.pytorch.transforms.ToTensorV2
   ann_transform: null
 

configs/experiment/cnn.yaml

@@ -1,56 +1,56 @@
-# @package _global_
-
-# to execute this experiment run:
-# python train.py experiment=example
-
-defaults:
-  - override /trainer: gpu
-  - override /data: mnist
-  - override /model: cnn
-  - override /logger: wandb
-  - override /callbacks: default
-
-# all parameters below will be merged with parameters from default configurations set above
-# this allows you to overwrite only specified parameters
-
-tags: ["mnist", "cnn"]
-
-seed: 42
-
-trainer:
-  min_epochs: 10
-  max_epochs: 10
-  gradient_clip_val: 0.5
-  devices: 1
-
-data:
-  batch_size: 128
-  train_val_test_split: [55_000, 5_000, 10_000]
-  num_workers: 31
-  pin_memory: False
-  persistent_workers: False
-
-model:
-  net:
-    dim: 32
-
-logger:
-  wandb:
-    project: "mnist"
-    name: "cnn"
-  aim:
-    experiment: "cnn"
-
-callbacks:
-  model_checkpoint:
-    dirpath: ${paths.output_dir}/checkpoints
-    filename: "epoch_{epoch:03d}"
-    monitor: "val/acc"
-    mode: "max"
-    save_last: True
-    auto_insert_metric_name: False
-
-  early_stopping:
-    monitor: "val/acc"
-    patience: 100
+# @package _global_
+
+# to execute this experiment run:
+# python train.py experiment=example
+
+defaults:
+  - override /trainer: gpu
+  - override /data: mnist
+  - override /model: cnn
+  - override /logger: wandb
+  - override /callbacks: default
+
+# all parameters below will be merged with parameters from default configurations set above
+# this allows you to overwrite only specified parameters
+
+tags: ["mnist", "cnn"]
+
+seed: 42
+
+trainer:
+  min_epochs: 10
+  max_epochs: 10
+  gradient_clip_val: 0.5
+  devices: 1
+
+data:
+  batch_size: 128
+  train_val_test_split: [55_000, 5_000, 10_000]
+  num_workers: 31
+  pin_memory: False
+  persistent_workers: False
+
+model:
+  net:
+    dim: 32
+
+logger:
+  wandb:
+    project: "mnist"
+    name: "cnn"
+  aim:
+    experiment: "cnn"
+
+callbacks:
+  model_checkpoint:
+    dirpath: ${paths.output_dir}/checkpoints
+    filename: "epoch_{epoch:03d}"
+    monitor: "val/acc"
+    mode: "max"
+    save_last: True
+    auto_insert_metric_name: False
+
+  early_stopping:
+    monitor: "val/acc"
+    patience: 100
     mode: "max"

configs/experiment/hrcwhu_hrcloud.yaml

@@ -1,47 +1,47 @@
-# @package _global_
-
-# to execute this experiment run:
-# python train.py experiment=example
-
-defaults:
-  - override /trainer: gpu
-  - override /data: hrcwhu/hrcwhu
-  - override /model: hrcloudnet/hrcloudnet
-  - override /logger: wandb
-  - override /callbacks: default
-
-# all parameters below will be merged with parameters from default configurations set above
-# this allows you to overwrite only specified parameters
-
-tags: ["hrcWhu", "hrcloud"]
-
-seed: 42
-
-
-  # scheduler:
-  #   _target_: torch.optim.lr_scheduler.ReduceLROnPlateau
-  #   _partial_: true
-  #   mode: min
-  #   factor: 0.1
-  #   patience: 10
-
-logger:
-  wandb:
-    project: "hrcWhu"
-    name: "hrcloud"
-  aim:
-    experiment: "hrcwhu_hrcloud"
-
-callbacks:
-  model_checkpoint:
-    dirpath: ${paths.output_dir}/checkpoints
-    filename: "epoch_{epoch:03d}"
-    monitor: "val/loss"
-    mode: "min"
-    save_last: True
-    auto_insert_metric_name: False
-
-  early_stopping:
-    monitor: "val/loss"
-    patience: 10
+# @package _global_
+
+# to execute this experiment run:
+# python train.py experiment=example
+
+defaults:
+  - override /trainer: gpu
+  - override /data: hrcwhu/hrcwhu
+  - override /model: hrcloudnet/hrcloudnet
+  - override /logger: wandb
+  - override /callbacks: default
+
+# all parameters below will be merged with parameters from default configurations set above
+# this allows you to overwrite only specified parameters
+
+tags: ["hrcWhu", "hrcloud"]
+
+seed: 42
+
+
+  # scheduler:
+  #   _target_: torch.optim.lr_scheduler.ReduceLROnPlateau
+  #   _partial_: true
+  #   mode: min
+  #   factor: 0.1
+  #   patience: 10
+
+logger:
+  wandb:
+    project: "hrcWhu"
+    name: "hrcloud"
+  aim:
+    experiment: "hrcwhu_hrcloud"
+
+callbacks:
+  model_checkpoint:
+    dirpath: ${paths.output_dir}/checkpoints
+    filename: "epoch_{epoch:03d}"
+    monitor: "val/loss"
+    mode: "min"
+    save_last: True
+    auto_insert_metric_name: False
+
+  early_stopping:
+    monitor: "val/loss"
+    patience: 10
     mode: "min"

configs/experiment/hrcwhu_kappamask.yaml

@@ -0,0 +1,47 @@
+# @package _global_
+
+# to execute this experiment run:
+# python train.py experiment=example
+
+defaults:
+  - override /trainer: gpu
+  - override /data: hrcwhu/hrcwhu
+  - override /model: kappamask/kappamask
+  - override /logger: wandb
+  - override /callbacks: default
+
+# all parameters below will be merged with parameters from default configurations set above
+# this allows you to overwrite only specified parameters
+
+tags: ["hrcWhu", "kappamask"]
+
+seed: 42
+
+
+  # scheduler:
+  #   _target_: torch.optim.lr_scheduler.ReduceLROnPlateau
+  #   _partial_: true
+  #   mode: min
+  #   factor: 0.1
+  #   patience: 10
+
+logger:
+  wandb:
+    project: "hrcWhu"
+    name: "kappamask"
+  aim:
+    experiment: "hrcwhu_kappamask"
+
+callbacks:
+  model_checkpoint:
+    dirpath: ${paths.output_dir}/checkpoints
+    filename: "epoch_{epoch:03d}"
+    monitor: "val/loss"
+    mode: "min"
+    save_last: True
+    auto_insert_metric_name: False
+
+  early_stopping:
+    monitor: "val/loss"
+    patience: 10
+    mode: "min"

configs/experiment/lnn.yaml

@@ -1,57 +1,57 @@
-# @package _global_
-
-# to execute this experiment run:
-# python train.py experiment=example
-
-defaults:
-  - override /trainer: gpu
-  - override /data: mnist
-  - override /model: lnn
-  - override /logger: wandb
-  - override /callbacks: default
-
-# all parameters below will be merged with parameters from default configurations set above
-# this allows you to overwrite only specified parameters
-
-tags: ["mnist", "lnn"]
-
-seed: 42
-
-trainer:
-  min_epochs: 10
-  max_epochs: 10
-  gradient_clip_val: 0.5
-  devices: 1
-
-data:
-  batch_size: 128
-  train_val_test_split: [55_000, 5_000, 10_000]
-  num_workers: 31
-  pin_memory: False
-  persistent_workers: False
-
-model:
-  net:
-    _target_: src.models.components.lnn.LNN
-    dim: 32
-
-logger:
-  wandb:
-    project: "mnist"
-    name: "lnn"
-  aim:
-    experiment: "lnn"
-
-callbacks:
-  model_checkpoint:
-    dirpath: ${paths.output_dir}/checkpoints
-    filename: "epoch_{epoch:03d}"
-    monitor: "val/acc"
-    mode: "max"
-    save_last: True
-    auto_insert_metric_name: False
-
-  early_stopping:
-    monitor: "val/acc"
-    patience: 100
+# @package _global_
+
+# to execute this experiment run:
+# python train.py experiment=example
+
+defaults:
+  - override /trainer: gpu
+  - override /data: mnist
+  - override /model: lnn
+  - override /logger: wandb
+  - override /callbacks: default
+
+# all parameters below will be merged with parameters from default configurations set above
+# this allows you to overwrite only specified parameters
+
+tags: ["mnist", "lnn"]
+
+seed: 42
+
+trainer:
+  min_epochs: 10
+  max_epochs: 10
+  gradient_clip_val: 0.5
+  devices: 1
+
+data:
+  batch_size: 128
+  train_val_test_split: [55_000, 5_000, 10_000]
+  num_workers: 31
+  pin_memory: False
+  persistent_workers: False
+
+model:
+  net:
+    _target_: src.models.components.lnn.LNN
+    dim: 32
+
+logger:
+  wandb:
+    project: "mnist"
+    name: "lnn"
+  aim:
+    experiment: "lnn"
+
+callbacks:
+  model_checkpoint:
+    dirpath: ${paths.output_dir}/checkpoints
+    filename: "epoch_{epoch:03d}"
+    monitor: "val/acc"
+    mode: "max"
+    save_last: True
+    auto_insert_metric_name: False
+
+  early_stopping:
+    monitor: "val/acc"
+    patience: 100
     mode: "max"

configs/model/kappamask/kappamask.yaml

@@ -0,0 +1,23 @@
+_target_: src.models.base_module.BaseLitModule
+
+net:
+  _target_: src.models.components.kappamask.KappaMask
+  num_classes: 2
+  in_channels: 3
+
+num_classes: 2
+
+criterion:
+  _target_: torch.nn.CrossEntropyLoss
+
+optimizer:
+  _target_: torch.optim.AdamW
+  _partial_: true
+  lr: 0.00001
+
+scheduler:
+  _target_: torch.optim.lr_scheduler.ReduceLROnPlateau
+  _partial_: true
+  mode: min
+  factor: 0.1
+  patience: 4

environment.yaml

@@ -24,4 +24,6 @@ dependencies:
       - aim
       - gradio
       - image-dehazer
-      - thop
+      - thop
+      - albumentations
+      - segmentation_models_pytorch

logs/train/runs/hrcwhu_kappamask/2024-08-07_16-34-34/checkpoints/epoch_015.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb7a77410abe75b5a66c9ec7d46f4203c8c41d70180174b0d0e2db2ff21b31ca
+size 372474542

logs/train/runs/hrcwhu_kappamask/2024-08-07_16-34-34/checkpoints/last.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2cdda7ab749f7a75c157da0cbe88cb379b712ab604294e8436e204748f5beb4
+size 372474606

src/models/components/kappamask.py

@@ -0,0 +1,152 @@
+# -*- coding: utf-8 -*-
+# @Time    : 2024/8/7 下午3:51
+# @Author  : xiaoshun
+# @Email   : [email protected]
+# @File    : kappamask.py.py
+# @Software: PyCharm
+
+import torch
+from torch import nn as nn
+from torch.nn import functional as F
+
+
+class KappaMask(nn.Module):
+    def __init__(self, num_classes=2, in_channels=3):
+        super().__init__()
+        self.conv1 = nn.Sequential(
+            nn.Conv2d(in_channels, 64, 3, 1, 1),
+            nn.ReLU(inplace=True),
+            nn.Conv2d(64, 64, 3, 1, 1),
+            nn.ReLU(inplace=True),
+        )
+        self.conv2 = nn.Sequential(
+            nn.Conv2d(64, 128, 3, 1, 1),
+            nn.ReLU(inplace=True),
+            nn.Conv2d(128, 128, 3, 1, 1),
+            nn.ReLU(inplace=True),
+        )
+        self.conv3 = nn.Sequential(
+            nn.Conv2d(128, 256, 3, 1, 1),
+            nn.ReLU(inplace=True),
+            nn.Conv2d(256, 256, 3, 1, 1),
+            nn.ReLU(inplace=True),
+        )
+
+        self.conv4 = nn.Sequential(
+            nn.Conv2d(256, 512, 3, 1, 1),
+            nn.ReLU(inplace=True),
+            nn.Conv2d(512, 512, 3, 1, 1),
+            nn.ReLU(inplace=True),
+        )
+        self.drop4 = nn.Dropout(0.5)
+
+        self.conv5 = nn.Sequential(
+            nn.Conv2d(512, 1024, 3, 1, 1),
+            nn.ReLU(inplace=True),
+            nn.Conv2d(1024, 1024, 3, 1, 1),
+            nn.ReLU(inplace=True),
+        )
+        self.drop5 = nn.Dropout(0.5)
+
+        self.up6 = nn.Sequential(
+            nn.Upsample(scale_factor=2),
+            nn.ZeroPad2d((0, 1, 0, 1)),
+            nn.Conv2d(1024, 512, 2),
+            nn.ReLU(inplace=True)
+        )
+        self.conv6 = nn.Sequential(
+            nn.Conv2d(1024, 512, 3, 1, 1),
+            nn.ReLU(inplace=True),
+            nn.Conv2d(512, 512, 3, 1, 1),
+            nn.ReLU(inplace=True),
+        )
+        self.up7 = nn.Sequential(
+            nn.Upsample(scale_factor=2),
+            nn.ZeroPad2d((0, 1, 0, 1)),
+            nn.Conv2d(512, 256, 2),
+            nn.ReLU(inplace=True)
+        )
+        self.conv7 = nn.Sequential(
+            nn.Conv2d(512, 256, 3, 1, 1),
+            nn.ReLU(inplace=True),
+            nn.Conv2d(256, 256, 3, 1, 1),
+            nn.ReLU(inplace=True),
+        )
+
+        self.up8 = nn.Sequential(
+            nn.Upsample(scale_factor=2),
+            nn.ZeroPad2d((0, 1, 0, 1)),
+            nn.Conv2d(256, 128, 2),
+            nn.ReLU(inplace=True)
+        )
+        self.conv8 = nn.Sequential(
+            nn.Conv2d(256, 128, 3, 1, 1),
+            nn.ReLU(inplace=True),
+            nn.Conv2d(128, 128, 3, 1, 1),
+            nn.ReLU(inplace=True),
+        )
+
+        self.up9 = nn.Sequential(
+            nn.Upsample(scale_factor=2),
+            nn.ZeroPad2d((0, 1, 0, 1)),
+            nn.Conv2d(128, 64, 2),
+            nn.ReLU(inplace=True)
+        )
+        self.conv9 = nn.Sequential(
+            nn.Conv2d(128, 64, 3, 1, 1),
+            nn.ReLU(inplace=True),
+            nn.Conv2d(64, 64, 3, 1, 1),
+            nn.ReLU(inplace=True),
+            nn.Conv2d(64, 2, 3, 1, 1),
+            nn.ReLU(inplace=True),
+        )
+        self.conv10 = nn.Conv2d(2, num_classes, 1)
+        self.__init_weights()
+
+    def __init_weights(self):
+        for m in self.modules():
+            if isinstance(m, nn.Conv2d):
+                nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='relu')
+
+    def forward(self, x):
+        conv1 = self.conv1(x)
+        pool1 = F.max_pool2d(conv1, 2, 2)
+
+        conv2 = self.conv2(pool1)
+        pool2 = F.max_pool2d(conv2, 2, 2)
+
+        conv3 = self.conv3(pool2)
+        pool3 = F.max_pool2d(conv3, 2, 2)
+
+        conv4 = self.conv4(pool3)
+        drop4 = self.drop4(conv4)
+        pool4 = F.max_pool2d(drop4, 2, 2)
+
+        conv5 = self.conv5(pool4)
+        drop5 = self.drop5(conv5)
+
+        up6 = self.up6(drop5)
+        merge6 = torch.cat((drop4, up6), dim=1)
+        conv6 = self.conv6(merge6)
+
+        up7 = self.up7(conv6)
+        merge7 = torch.cat((conv3, up7), dim=1)
+        conv7 = self.conv7(merge7)
+
+        up8 = self.up8(conv7)
+        merge8 = torch.cat((conv2, up8), dim=1)
+        conv8 = self.conv8(merge8)
+
+        up9 = self.up9(conv8)
+        merge9 = torch.cat((conv1, up9), dim=1)
+        conv9 = self.conv9(merge9)
+
+        output = self.conv10(conv9)
+        return output
+
+
+if __name__ == '__main__':
+    model = KappaMask(num_classes=2, in_channels=3)
+    fake_data = torch.rand(2, 3, 256, 256)
+    output = model(fake_data)
+    print(output.shape)

wandb_vis.py

@@ -25,6 +25,7 @@ from src.models.components.cdnetv1 import CDnetV1
 from src.models.components.cdnetv2 import CDnetV2
 from src.models.components.dbnet import DBNet
 from src.models.components.hrcloudnet import HRCloudNet
+from src.models.components.kappamask import KappaMask
 from src.models.components.mcdnet import MCDNet
 from src.models.components.scnn import SCNN
 from src.models.components.unetmobv2 import UNetMobV2
@@ -69,6 +70,9 @@ class WandbVis:
         if self.model_name == "unetmobv2":
             return UNetMobV2(num_classes=2).to(self.device)
 
+        if self.model_name == "kappamask":
+            return KappaMask(num_classes=2, in_channels=3).to(self.device)
+
         raise ValueError(f"{self.model_name}模型不存在")
 
     def load_model(self):
@@ -91,7 +95,7 @@ class WandbVis:
             ]
         )
         img_transform = albu.Compose([
-            albu.ToFloat(255.0),
+            albu.ToFloat(),
             ToTensorV2()
         ])
         ann_transform = None