masa-su / pixyzoo Goto Github PK

GQN/dataset/convert2torch.py generate data files compressed by gzip.
But GQNDataset class expect uncompressed files.

The following error occurred when I executed GAN/train.py with the directory generated by convert2torch.py.

Traceback (most recent call last):
  File "train.py", line 94, in <module>
    x_data_test, v_data_test = next(iter(test_loader))
  File "/home/hoge/venv/pytorch-py36-cuda9/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 615, in __next__
    batch = self.collate_fn([self.dataset[i] for i in indices])
  File "/home/hoge/venv/pytorch-py36-cuda9/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 615, in <listcomp>
    batch = self.collate_fn([self.dataset[i] for i in indices])
  File "/home/hoge/work/pixyzoo/GQN/gqn_dataset.py", line 32, in __getitem__
    data = torch.load(scene_path)
  File "/home/hoge/venv/pytorch-py36-cuda9/lib/python3.6/site-packages/torch/serialization.py", line 365, in load
    f = open(f, 'rb')
FileNotFoundError: [Errno 2] No such file or directory: 'dataset/rooms_ring_camera-torch/train/1414.pt'

I am trying to reproduce the results and couldn't find the GQN/dataset/convert2torch.py file. I believe it wasn't added to the repository?
Thanks

need modifying from entropy to analytical entropy
https://github.com/masa-su/pixyzoo/blob/master/TD-VAE/model.py#L58-L59

Hi,

Many thanks for your contribution on implementing GQN.

Recently, I implemented GQN. After the training on rooms_ring_camera, I found that the loss will converge to around 6950 after 200K iterations, which means after the sigma decrease to 0.7, the loss will maintain at a stable level. But in their original paper, the final loss is just 6.1. I don’t understand the where is the problem. Do you have the same problem? Many thanks in advance!

Looking forward to your reply!

• pytorch implementation: https://github.com/alexis-jacq/Pytorch-Sketch-RNN
• paper: https://arxiv.org/abs/1704.03477