Hi everyone, I am working on an encoder model based on resnet50. And whenever I pass the images into the encoder, the RuntimeError occurs:
---------------------------------------------------------------------------
RuntimeError Traceback (most recent call last)
<ipython-input-67-bfcd094ef931> in <module>()
23 '''
24 # input EncoderEps, train DF
---> 25 fL = EncoderEps(LRimg)
26 fH = EncoderEps(HRimg)
27 f_size = fL.size(0)
4 frames
/usr/local/lib/python3.7/dist-packages/torch/nn/modules/module.py in _call_impl(self, *input, **kwargs)
887 result = self._slow_forward(*input, **kwargs)
888 else:
--> 889 result = self.forward(*input, **kwargs)
890 for hook in itertools.chain(
891 _global_forward_hooks.values(),
<ipython-input-64-952baa4092a1> in forward(self, x)
30
31 def forward(self,x):
---> 32 x = self.model.conv1(x)
33 print("Success with conv1")
34 x = self.model.bn1(x)
/usr/local/lib/python3.7/dist-packages/torch/nn/modules/module.py in _call_impl(self, *input, **kwargs)
887 result = self._slow_forward(*input, **kwargs)
888 else:
--> 889 result = self.forward(*input, **kwargs)
890 for hook in itertools.chain(
891 _global_forward_hooks.values(),
/usr/local/lib/python3.7/dist-packages/torch/nn/modules/conv.py in forward(self, input)
397
398 def forward(self, input: Tensor) -> Tensor:
--> 399 return self._conv_forward(input, self.weight, self.bias)
400
401 class Conv3d(_ConvNd):
/usr/local/lib/python3.7/dist-packages/torch/nn/modules/conv.py in _conv_forward(self, input, weight, bias)
394 _pair(0), self.dilation, self.groups)
395 return F.conv2d(input, weight, bias, self.stride,
--> 396 self.padding, self.dilation, self.groups)
397
398 def forward(self, input: Tensor) -> Tensor:
RuntimeError: expected scalar type Byte but found Float
It is shown that the error occur in the conv1 layer when it is calling the Conv2d and something related with the padding, dilation parameters. But I don’t know how to deal with it.
My encoder model code is like this:
def weights_init_kaiming(m):
classname = m.__class__.__name__
if classname.find('Conv') != -1:
init.kaiming_normal_(m.weight.data, a=0, mode='fan_in') # For old pytorch, you may use kaiming_normal.
elif classname.find('Linear') != -1:
init.kaiming_normal_(m.weight.data, a=0, mode='fan_out')
init.constant_(m.bias.data, 0.0)
elif classname.find('BatchNorm1d') != -1:
init.normal_(m.weight.data, 1.0, 0.02)
init.constant_(m.bias.data, 0.0)
def weights_init_normal(m):
classname = m.__class__.__name__
if classname.find('Linear') != -1:
init.normal_(m.weight.data, std=0.001)
init.constant_(m.bias.data, 0.0)
class encoder(nn.Module):
def __init__(self, reduced_dim=256):
super(encoder, self).__init__()
Resnet_50 = models.resnet50(pretrained=True)
#base_model = Resnet_50
base_model = nn.Sequential(*(list(Resnet_50.children())[:-2]))
self.model = base_model
add_block = nn.Sequential(nn.Conv2d(2048, reduced_dim, kernel_size=1, stride=1, padding=0),
nn.BatchNorm2d(reduced_dim))
add_block.apply(weights_init_kaiming) # 为什么在原resnet结构中添加模块需要初始化参数呢？
self.add_block = add_block
def forward(self,x):
x = self.model(x)
f = self.add_block(x)
print("Success with addblock")
return f
Maybe something is run with my data? my trainning dataloader is built with the transform like this:
trndata_trans = transforms.Compose([transforms.ToPILImage(),
transforms.Resize((256,128)),
transforms.RandomHorizontalFlip(),
transforms.RandomVerticalFlip(),
transforms.ToTensor(),
transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])])
Can anyone help me out with this plz?