RuntimeError: Given groups=1, weight of size [64, 3, 3, 3], expected input[2, 224, 224, 3] to have 3 channels, but got 224 channels instead about contour-detection-pytorch

[captanlevi]

Hello, you need your images to be in the 3D shape.
As in not (224,224) but (1,224,224).
Reshaping can resolve your issue.

Other than that as there is a little interest in this project. I will be launching a new code with new features in the next few days.

[kulkarnikeerti]

@captanlevi Thanks, that helped.
And thanks for letting me know about the new features. I suppose the new features will be added in the same repository, or will there be a new repository for that?

And just one last question about this model. I am getting negative loss values. Do you have any suggestions for this? or is this a normal behavior?
Thanks

[captanlevi]

I will work in the same repo, for the negative loss perhaps you have not normalised the images ?

[kulkarnikeerti]

Yeah, I haven't normalized the images. I am using albumentations for augmentation and I tried to normalize it in the same way. But this didn't help.

Just to clarify, is this how you normalize the images in this code? or I missed that part of code? Because I use the same values for normalization in albumentations but that didn't help me.

Contour-Detection-Pytorch/train.py

Line 101 in e3e6c90

# image_res = norm_op(image_res)

[kulkarnikeerti]

Okay. I figured it out. Thanks:)