修改代码实现，提高代码可读性和可维护性

README.md

@@ -1,5 +1,4 @@
 # PFCFuse: A Poolformer and CNN fusion network for Infrared-Visible Image Fusion
-Poolformer-cnn图像融合框架
 The implementation of our paper "PFCFuse: A Poolformer and CNN fusion network for Infrared-Visible Image Fusion".
 ## Recommended Environment:
 python=3.8\
@@ -26,3 +25,14 @@ Run
 ```
 python test_IVF.py
 ```
+
+## 相关工作
+```
+@inproceedings{zhao2023cddfuse,
+  title={Cddfuse: Correlation-driven dual-branch feature decomposition for multi-modality image fusion},
+  author={Zhao, Zixiang and Bai, Haowen and Zhang, Jiangshe and Zhang, Yulun and Xu, Shuang and Lin, Zudi and Timofte, Radu and Van Gool, Luc},
+  booktitle={Proceedings of the IEEE/CVF conference on computer vision and pattern recognition},
+  pages={5906--5916},
+  year={2023}
+}
+```

net.py

@@ -1,4 +1,3 @@
-# poolformer
 import torch
 import torch.nn as nn
 import math
@@ -9,14 +8,6 @@ from einops import rearrange
 
 
 def drop_path(x, drop_prob: float = 0., training: bool = False):
-    """
-    Drop paths (Stochastic Depth) per sample (when applied in main path of residual blocks).
-    This is the same as the DropConnect impl I created for EfficientNet, etc networks, however,
-    the original name is misleading as 'Drop Connect' is a different form of dropout in a separate paper...
-    See discussion: https://github.com/tensorflow/tpu/issues/494#issuecomment-532968956 ... I've opted for
-    changing the layer and argument names to 'drop path' rather than mix DropConnect as a layer name and use
-    'survival rate' as the argument.
-    """
     if drop_prob == 0. or not training:
         return x
     keep_prob = 1 - drop_prob
@@ -40,8 +31,7 @@ class DropPath(nn.Module):
 
     def forward(self, x):
         return drop_path(x, self.drop_prob, self.training)
-
+# 改点，使用Pooling替换AttentionBase
-
 class Pooling(nn.Module):
     def __init__(self, kernel_size=3):
         super().__init__()
@@ -54,8 +44,8 @@ class Pooling(nn.Module):
 
 class PoolMlp(nn.Module):
     """
-      Implementation of MLP with 1*1 convolutions.
+    实现基于1x1卷积的MLP模块。
-      Input: tensor with shape [B, C, H, W]
+    输入：形状为[B, C, H, W]的张量。
     """
 
     def __init__(self,
@@ -65,6 +55,17 @@ class PoolMlp(nn.Module):
                  act_layer=nn.GELU,
                  bias=False,
                  drop=0.):
+        """
+        初始化PoolMlp模块。
+
+        参数:
+            in_features (int): 输入特征的数量。
+            hidden_features (int, 可选): 隐藏层特征的数量。默认为None，设置为与in_features相同。
+            out_features (int, 可选): 输出特征的数量。默认为None，设置为与in_features相同。
+            act_layer (nn.Module, 可选): 使用的激活层。默认为nn.GELU。
+            bias (bool, 可选): 是否在卷积层中包含偏置项。默认为False。
+            drop (float, 可选): Dropout比率。默认为0。
+        """
         super().__init__()
         out_features = out_features or in_features
         hidden_features = hidden_features or in_features
@@ -72,15 +73,17 @@ class PoolMlp(nn.Module):
         self.act = act_layer()
         self.fc2 = nn.Conv2d(hidden_features, out_features, 1, bias=bias)
         self.drop = nn.Dropout(drop)
-        # self.apply(self._init_weights)
-
-    # def _init_weights(self, m):
-    #     if isinstance(m, nn.Conv2D):
-    #         trunc_normal_(m.weight)
-    #         if m.bias is not None:
-    #             zeros_(m.bias)
 
     def forward(self, x):
+        """
+        通过PoolMlp模块的前向传播。
+
+        参数:
+            x (torch.Tensor): 形状为[B, C, H, W]的输入张量。
+
+        返回:
+            torch.Tensor: 形状为[B, C, H, W]的输出张量。
+        """
         x = self.fc1(x)  # (B, C, H, W) --> (B, C, H, W)
         x = self.act(x)
         x = self.drop(x)
@@ -126,7 +129,7 @@ class BaseFeatureExtraction(nn.Module):
                 self.layer_scale_2.unsqueeze(-1).unsqueeze(-1)
                 * self.poolmlp(self.norm2(x)))
         else:
-            x = x + self.drop_path(self.token_mixer(self.norm1(x)))
+            x = x + self.drop_path(self.token_mixer(self.norm1(x))) # 匹配cddfuse
             x = x + self.drop_path(self.poolmlp(self.norm2(x)))
         return x
 
@@ -149,11 +152,9 @@ class InvertedResidualBlock(nn.Module):
             nn.Conv2d(hidden_dim, oup, 1, bias=False),
             # nn.BatchNorm2d(oup),
         )
-
     def forward(self, x):
         return self.bottleneckBlock(x)
 
-
 class DetailNode(nn.Module):
     def __init__(self):
         super(DetailNode, self).__init__()
@@ -181,14 +182,12 @@ class DetailFeatureExtraction(nn.Module):
         super(DetailFeatureExtraction, self).__init__()
         INNmodules = [DetailNode() for _ in range(num_layers)]
         self.net = nn.Sequential(*INNmodules)
-
     def forward(self, x):
         z1, z2 = x[:, :x.shape[1] // 2], x[:, x.shape[1] // 2:x.shape[1]]
         for layer in self.net:
             z1, z2 = layer(z1, z2)
         return torch.cat((z1, z2), dim=1)
 
-
 # =============================================================================
 
 # =============================================================================
@@ -369,7 +368,6 @@ class Restormer_Encoder(nn.Module):
         self.encoder_level1 = nn.Sequential(
             *[TransformerBlock(dim=dim, num_heads=heads[0], ffn_expansion_factor=ffn_expansion_factor,
                                bias=bias, LayerNorm_type=LayerNorm_type) for i in range(num_blocks[0])])
-
         self.baseFeature = BaseFeatureExtraction(dim=dim)
 
         self.detailFeature = DetailFeatureExtraction()
@@ -424,4 +422,3 @@ if __name__ == '__main__':
     window_size = 8
     modelE = Restormer_Encoder().cuda()
     modelD = Restormer_Decoder().cuda()
-

requirement.txt

@@ -0,0 +1,5 @@
+
+scipy==1.9.3
+scikit-image==0.19.2
+scikit-learn==1.1.3
+tqdm==4.62.0

test_IVF.py

@@ -8,25 +8,23 @@ import torch.nn as nn
 from utils.img_read_save import img_save,image_read_cv2
 import warnings
 import logging
-# 增加
 warnings.filterwarnings("ignore")
 logging.basicConfig(level=logging.CRITICAL)
 
 
 os.environ["CUDA_VISIBLE_DEVICES"] = "0"
-ckpt_path= r"models/PFCFuse.pth"
+ckpt_path= r"/home/star/whaiDir/PFCFuse/models/PFCFusion10-05-18-13.pth"
 
-for dataset_name in ["MSRS","TNO","RoadScene"]:
+for dataset_name in ["TNO"]:
     print("\n"*2+"="*80)
     model_name="PFCFuse    "
     print("The test result of "+dataset_name+' :')
-    test_folder=os.path.join('test_img',dataset_name) 
+    test_folder=os.path.join('/home/star/whaiDir/CDDFuse/test_img/',dataset_name)
     test_out_folder=os.path.join('test_result',dataset_name)
 
     device = 'cuda' if torch.cuda.is_available() else 'cpu'
     Encoder = nn.DataParallel(Restormer_Encoder()).to(device)
     Decoder = nn.DataParallel(Restormer_Decoder()).to(device)
-    # BaseFuseLayer = nn.DataParallel(BaseFeatureExtraction(dim=64, num_heads=8)).to(device)
     BaseFuseLayer = nn.DataParallel(BaseFeatureExtraction(dim=64)).to(device)
     DetailFuseLayer = nn.DataParallel(DetailFeatureExtraction(num_layers=1)).to(device)
 
@@ -41,14 +39,12 @@ for dataset_name in ["MSRS","TNO","RoadScene"]:
 
     with torch.no_grad():
         for img_name in os.listdir(os.path.join(test_folder,"ir")):
+            print(img_name)
 
             data_IR=image_read_cv2(os.path.join(test_folder,"ir",img_name),mode='GRAY')[np.newaxis,np.newaxis, ...]/255.0
-            # 改
             data_VIS = cv2.split(image_read_cv2(os.path.join(test_folder, "vi", img_name), mode='YCrCb'))[0][np.newaxis, np.newaxis, ...] / 255.0
-            # ycrcb, uint8
             data_VIS_BGR = cv2.imread(os.path.join(test_folder, "vi", img_name))
             _, data_VIS_Cr, data_VIS_Cb = cv2.split(cv2.cvtColor(data_VIS_BGR, cv2.COLOR_BGR2YCrCb))
-            # 改
 
             data_IR,data_VIS = torch.FloatTensor(data_IR),torch.FloatTensor(data_VIS)
             data_VIS, data_IR = data_VIS.cuda(), data_IR.cuda()
@@ -60,15 +56,12 @@ for dataset_name in ["MSRS","TNO","RoadScene"]:
             data_Fuse, _ = Decoder(data_VIS, feature_F_B, feature_F_D)
             data_Fuse=(data_Fuse-torch.min(data_Fuse))/(torch.max(data_Fuse)-torch.min(data_Fuse))
             fi = np.squeeze((data_Fuse * 255).cpu().numpy())
-            # 改
-            # float32 to uint8
             fi = fi.astype(np.uint8)
             ycrcb_fi = np.dstack((fi, data_VIS_Cr, data_VIS_Cb))
             rgb_fi = cv2.cvtColor(ycrcb_fi, cv2.COLOR_YCrCb2RGB)
             img_save(rgb_fi, img_name.split(sep='.')[0], test_out_folder)
-            # 改
 
-    eval_folder=test_out_folder  
+    eval_folder=test_out_folder
     ori_img_folder=test_folder
 
     metric_result = np.zeros((8))
@@ -92,4 +85,4 @@ for dataset_name in ["MSRS","TNO","RoadScene"]:
             +str(np.round(metric_result[6], 2))+'\t'
             +str(np.round(metric_result[7], 2))
             )
-    print("="*80)
+    print("="*80)

train.py

@@ -87,7 +87,7 @@ Loss_ssim = kornia.losses.SSIM(11, reduction='mean')
 HuberLoss = nn.HuberLoss()
 
 # data loader
-trainloader = DataLoader(H5Dataset(r"data/MSRS_train_imgsize_128_stride_200.h5"),
+trainloader = DataLoader(H5Dataset(r"/home/star/whaiDir/CDDFuse/data/MSRS_train_imgsize_128_stride_200.h5"),
                          batch_size=batch_size,
                          shuffle=True,
                          num_workers=0)
@@ -201,13 +201,14 @@ for epoch in range(num_epochs):
         epoch_time = time.time() - prev_time
         prev_time = time.time()
         sys.stdout.write(
-            "\r[Epoch %d/%d] [Batch %d/%d] [loss: %f]"
+            "\r[Epoch %d/%d] [Batch %d/%d] [loss: %f] ETA: %.10s"
             % (
                 epoch,
                 num_epochs,
                 i,
                 len(loader['train']),
                 loss.item(),
+                time_left,
             )
         )