NVlabs / stylegan2-ada-pytorch

StyleGAN2-ADA - Official PyTorch implementation
https://arxiv.org/abs/2006.06676
Other
4.13k stars 1.17k forks source link

Assertion Error in : images.ndim==4 is not true for the given dataset in github. #293

Open priyamp2309 opened 1 year ago

priyamp2309 commented 1 year ago

Created a dataset of size = 1 with image resolution (192, 320) Using the training regime with segmentation masks Created Generator with 5887448 parameters Created Discriminator (3+4 blocks) with 2443581 parameters Traceback (most recent call last): File "train.py", line 33, in out_G = diff_augment(out_G) File "/home/usd.local/priyam.pandey/priyam/code/one-shot-synthesis-master/one-shot-synthesis-master/core/differentiable_augmentation/diff_augm.py", line 12, in call return self.augment_func(batch) File "/home/usd.local/priyam.pandey/anaconda3/envs/osmis/lib/python3.8/site-packages/torch/nn/modules/module.py", line 722, in _call_impl result = self.forward(*input, **kwargs) File "/home/usd.local/priyam.pandey/priyam/code/one-shot-synthesis-master/one-shot-synthesis-master/core/differentiable_augmentation/augment.py", line 182, in forward assert isinstance(images, torch.Tensor) and images.ndim == 4 AssertionError

pietrobert3 commented 12 months ago

I have the same problem