RuntimeError: Given groups=1, weight of size [64, 3, 7, 7], expected input[3, 1, 224, 224] to have 3 channels, but got 1 channels instead

Question

In the code below:

    model_ft.eval()
    test_data, test_target = image_datasets['train'][idx]
    test_data = test_data.cuda()
    #test_target = test_target.cuda()
    test_target = torch.tensor(test_target)
    test_target = test_target.cuda()
    test_data.unsqueeze_(1)
    test_target.unsqueeze_(0)
    print(test_data.shape)
    output = model_ft(test_data)

I get the following error:

Traceback (most recent call last):
  File "test_loocv.py", line 245, in <module>
    output = model_ft(test_data)
  File "/scratch/sjn-p3/anaconda/anaconda3/lib/python3.6/site-packages/torch/nn/modules/module.py", line 477, in __call__
    result = self.forward(*input, **kwargs)
  File "/scratch/sjn-p3/anaconda/anaconda3/lib/python3.6/site-packages/torchvision-0.2.1-py3.6.egg/torchvision/models/resnet.py", line 139, in forward
  File "/scratch/sjn-p3/anaconda/anaconda3/lib/python3.6/site-packages/torch/nn/modules/module.py", line 477, in __call__
    result = self.forward(*input, **kwargs)
  File "/scratch/sjn-p3/anaconda/anaconda3/lib/python3.6/site-packages/torch/nn/modules/conv.py", line 301, in forward
    self.padding, self.dilation, self.groups)
RuntimeError: Given groups=1, weight of size [64, 3, 7, 7], expected input[3, 1, 224, 224] to have 3 channels, but got 1 channels instead

Also, test_data has the shape: torch.Size([3, 1, 224, 224]).

How should I fix this?

Solution

Here's the fix:

test_data, test_target = image_datasets['train'][idx]
test_data = test_data.cuda()
test_target = torch.tensor(test_target)
test_target = test_target.cuda()
test_data.unsqueeze_(0)
test_target.unsqueeze_(0)
output = model_ft(test_data)

I had to change test_data.unsqueeze_(1) to test_data.unsqueeze_(0)

Comments

[CodeBlooded]

Could you please explain a little further about this?