Can anyone tell me how can i concatenate three greyscale images(1 channels each) into a 3 channel image so that it can be fed into standard convnets?
(i.e. the greyscale images are of dimesions[60,60,1] and i want them to be of [60,60,3])
If img is your image, then torch.cat((img, img, img), 2) will work. However, maybe this is not what you really want to do. If you could refit your model to receive greyscale images, it could improve the performance of your model.
1 Like
I did as you said but i am getting the following error.
TypeError: expected Tensor as element 0 in argument 0, but got tuple
You must be missing something. Could you send a snippet so that I can reproduce this error ?