generate_images raise Value Error: not enough image data??

[huaikaimancheng]

I am using my owner datasets to train a model by the stylegan3 code. The datasets are gray images. I have trained a model and want to use the generate_images file to generate samples. But it can't work when I run the code. The information is followed.
error:
Loading networks from "../input/afhqv2model/network-snapshot-000270.pkl"...
Generating image for seed 0 (0/1) ...
Setting up PyTorch plugin "bias_act_plugin"... Done.
Setting up PyTorch plugin "filtered_lrelu_plugin"... Done.
Traceback (most recent call last):
File "../input/stylegan3pytorch/stylegan3-main/gen_images.py", line 143, in
generate_images() # pylint: disable=no-value-for-parameter
File "/opt/conda/lib/python3.7/site-packages/click/core.py", line 1128, in call
return self.main(*args, **kwargs)
File "/opt/conda/lib/python3.7/site-packages/click/core.py", line 1053, in main
rv = self.invoke(ctx)
File "/opt/conda/lib/python3.7/site-packages/click/core.py", line 1395, in invoke
return ctx.invoke(self.callback, **ctx.params)
File "/opt/conda/lib/python3.7/site-packages/click/core.py", line 754, in invoke
return __callback(*args, **kwargs)
File "../input/stylegan3pytorch/stylegan3-main/gen_images.py", line 137, in generate_images
PIL.Image.fromarray(img[0].cpu().numpy(), 'RGB').save(f'{outdir}/seed{seed:04d}.png')
File "/opt/conda/lib/python3.7/site-packages/PIL/Image.py", line 2949, in fromarray
return frombuffer(mode, size, obj, "raw", rawmode, 0, 1)
File "/opt/conda/lib/python3.7/site-packages/PIL/Image.py", line 2876, in frombuffer
return frombytes(mode, size, data, decoder_name, args)
File "/opt/conda/lib/python3.7/site-packages/PIL/Image.py", line 2822, in frombytes
im.frombytes(data, decoder_name, args)
File "/opt/conda/lib/python3.7/site-packages/PIL/Image.py", line 831, in frombytes
raise ValueError("not enough image data")
ValueError: not enough image data
What can I do about that? Thanks for helping me solve the problem.

[huaikaimancheng]

This problem has been done! The officially generate image code needs to be updated according to my own trained model. The following is my own modification.

#generate_images.py
…………………………………………………………………………………………
#img = (img.permute(0, 2, 3, 1) * 127.5 + 128).clamp(0, 255).to(torch.uint8)
#PIL.Image.fromarray(img[0].cpu().numpy(), 'RGB').save(f'{outdir}/seed{seed:04d}.png')
img = (img.permute(0, 1, 2, 3) * 127.5 + 128).clamp(0, 255).to(torch.uint8)
PIL.Image.fromarray(img[0].cpu().numpy()[0]).save(f'{outdir}/seed{seed:04d}.png