search

taki0112 / UGATIT

Official Tensorflow implementation of U-GAT-IT: Unsupervised Generative Attentional Networks with Adaptive Layer-Instance Normalization for Image-to-Image Translation (ICLR 2020)
MIT License
6.17k stars 1.04k forks source link

problems about ptetrained models #72

Open ZoeSnow opened 4 years ago

ZoeSnow commented 4 years ago

All links to datasets and pretrained models are not available. Why can't I open these internet links? Thanks for your reply!

san-guy commented 4 years ago

The link to pre-trained model and dataset is available please check again. attaching the links here again:

  1. 50 epochs: https://drive.google.com/file/d/1V6GbSItG3HZKv3quYs7AP0rr1kOCT3QO/view
  2. 100 epochs: https://drive.google.com/file/d/19xQK2onIy-3S5W5K-XIh85pAg_RNvBVf/view
  3. dataset: https://drive.google.com/file/d/1xOWj1UVgp6NKMT3HbPhBbtq2A4EDkghF/view
ZoeSnow commented 4 years ago

@pnagasanthosh Thanks again! I found that I couldn't open these links just because of Google Drive.

Onr commented 4 years ago

after downloading the pre-trained models from google drive when i try to unzip them i get an error (CRC32 check failed) both for the 50 epoch and 100 epoch. dose anyone else encountered that problem? Thanks

Sxela commented 4 years ago

Okay, worked with windows 7zip - default linux unzip can't handle 7gb files. I suggest reuploading a tar.bz, which doesn't have this filesize limitation.

If extracting with unzip, files have about 700mb data in them when unzipped. Getting an error while using those file in a model: OP_REQUIRES failed at save_restore_v2_ops.cc:184 : Out of range: Read less bytes than requested