fix

README.md

@@ -55,16 +55,16 @@ python cifar.py [--baseline]
 
 ### SE-ResNet50/ImageNet
 
-*The initial learning rate and mini-batch size are different from the original version because of my computational resource* (0.6 to 0.1 and 1024 to 128 respectively).
+*The initial learning rate and mini-batch size are different from the original version because of my computational resource* .
 
 |                  | ResNet         | SE-ResNet      |
 |:-------------    | :------------- | :------------- |
-|max. test accuracy(top1)|  79.26 %(*)             | 71.66 %(**)          |
+|max. test accuracy(top1)|  76.15 %(*)             | -- (**)          |
 
 
-+ (*): He, K., Zhang, X., Ren, S., & Sun, J. (2015). Deep Residual Learning for Image Recognition.
++ (*): [ResNet-50 in torchvision](https://pytorch.org/docs/stable/torchvision/models.html)
 
-+ (**): I share [this weight (training after 100 epochs)](https://drive.google.com/file/d/1WhBKRKIRtd-Fsrj3hx_WNycdsZSbC9Ep).
++ (**): When using `imagenet.py` in the `--distributed` setting on 8 GPUs. The weight will be available soon.
 
 ```python
 senet = se_resnet50(num_classes=1000)

senet/se_module.py

@@ -6,14 +6,14 @@ def __init__(self, channel, reduction=16):
         super(SELayer, self).__init__()
         self.avg_pool = nn.AdaptiveAvgPool2d(1)
         self.fc = nn.Sequential(
-                nn.Linear(channel, channel // reduction),
-                nn.ReLU(inplace=True),
-                nn.Linear(channel // reduction, channel),
-                nn.Sigmoid()
+            nn.Linear(channel, channel // reduction, bias=False),
+            nn.ReLU(inplace=True),
+            nn.Linear(channel // reduction, channel, bias=False),
+            nn.Sigmoid()
         )
 
     def forward(self, x):
         b, c, _, _ = x.size()
         y = self.avg_pool(x).view(b, c)
         y = self.fc(y).view(b, c, 1, 1)
-        return x * y
+        return x * y.expand_as(x)