IndexError: list index out of range

[bsahil29]

I am trying to train the InstaGAN on a smaller dataset of around 40 images from both domains. But I am getting the following error :
File "/network/home/bansalsa/instagan/data/unaligned_seg_dataset.py", line 49, in read_segs
segs.append(-torch.ones(segs[0].size()))
IndexError: list index out of range

I have read the already available issues and double-checked that there is a mask for every image in the trainA and trainB folders but still I'm getting the same error. Also, the images are readable via PIL, I have checked that too.

This is the screenshot to the output that I'm getting :

What could be a reason for getting this error?

[sangwoomo]

Hi, it seems that the code fails to read the mask. You'd better to check for which image/mask the code fails to read exactly, e.g., by printing the ID of the image before the failure.
#5 (comment)

[bsahil29]

Yeah it worked. There was an issue with reading some of the masks. Thanks! :)

[kalai2033]

Hi @sangwoomo and @bsahil29 I face the same issue...

I have printed the seg_paths ... Every time it breaks at random point. But i have corresponding mask images in both the train and train_seg folder with same name and same dimensions. I cant understand why it fails.

Can you please help me fix it?

[sangwoomo]

I'm sorry but I have no idea since I had never encountered this problem.
Can you simply remove the problematic index?

[jdunkelheit]

In addition to missing masks, this issue can also happen when the masks have a wrong name. The mask cannot simply have the exact same name as the image.
Make sure the name of the masks is composed of "image name" + "_0". For example:

    ├── trainA
        ├── 1.png
        ├── 2.png
        └── ...
    ├── trainA_seg
        ├── 1_0.png
        ├── 2_0.png
        └── ...
    ├── trainB
        ├── 1.png
        ├── 2.png
        └── ...
    ├── trainB_seg
        ├── 1_0.png
        ├── 2_0.png
        └── ...

In case you have more than one mask for the same image, it will be like:

    ├── trainA
        ├── 1.png
        ├── 2.png
        └── ...
    ├── trainA_seg
        ├── 1_0.png
        ├── 1_1.png
        ├── 2_0.png
        ├── 2_1.png
        └── ...
    ├── trainB
        ├── 1.png
        ├── 2.png
        └── ...
    ├── trainB_seg
        ├── 1_0.png
        ├── 1_1.png
        ├── 2_0.png
        ├── 2_1.png
        └── ...