DynamicReLU
DynamicReLU copied to clipboard
Implementation of Dynamic ReLU on Pytorch
conv3d
Hello, can I ask how to operate with conv_type='3d'? about the code 'theta = torch.mean(theta, axis=-1)' when conv_type = '2d'? Do somebody know?Thanks a lot.
Excuse me,could you please share the code of DynamicReluC,which is mentioned in the paper?
Excuse me,could you please share the code of DynamicReluC,which is mentioned in the paper?
def get_relu_coefs(self, x): print(x.shape) # axis? theta = torch.mean(x, dim=-1) if self.conv_type == '2d': # axis? theta = torch.mean(theta, dim=-1) theta = self.fc1(theta) theta = self.relu(theta) theta = self.fc2(theta) theta...
Thanks for your working! I have some questions: 1. That reduction ratios R=8 is the best trade-off in the paper , but the code defaults to 4, so why? 2....
Hi, have you ever reimplemented the results as the paper reported, such as MobileNet or ResNet?