Input 3 and 1 channel input to the network in pytorch?

1

My dataset consists mostly of 3 channel images, but i also have a few 1 channel images,Is it possible to train a network that takes in both 3 channels and 1 channels as inputs?

Any suggestions are welcome,Thanks in advance,

2

You could check for the number of channels and based on this chose a separate model input layer.
However, I wouldn’t apply this method.

The straightforward solution would be to load your images and convert them to RGB:

image = Image.open(path).convert('RGB')

You can add this line to your Dataset's __getitem__ method.

3

Thanks for the reply ptrblck!
Hmmm,So this converts the grayscale image to RGB?

4

Yes. It converts grayscale images to RGB and just keeps color images as RGB.

5

Thanks you for your time

6

No worries! Let me know, it that works for you!