htwang14

I can't even unzip the file using `unzip test_lmbd.zip`

> > I can't even unzip the file using `unzip test_lmbd.zip` > > Have you solved this? Not really. But I found some other repos providing directly downloadable (resized) LSUN...

Thanks!

Just run `mv deeplab-resnet.pth.tar deeplab-resnet.pth` to remove the `.tar` extension in the file name. The file is not even a `tar` file at all, just a simple PyTorch checkpoint file.

Hi, thanks for your interest in our work! I have released the horse2zebra models compressed by GS32 and GS8. Please kindly check our GoogleDrive link. On horse2zebra dataset, it is...

The FID of the released models should match the ones reported in the paper. When you run the finetune script, a file named FID_log.txt will be generated, in which the...

Thanks for your interest in our work. GAN training is unstable due to the minimax optimization process, and combining it with model compression makes it even more unstable due to...

> if i use gs.py for other network,whether i need change model? Yes, you will need to replace CycleGAN (the model currently used) with your own network.

For example, if the minimum and maximum activation values are 0 and 4 respectively, then the activation values can be 4n/256, where n=0,1,...,255. In this case, you can express 0...

Our pretrained ATMC 8bit models are available at https://drive.google.com/drive/folders/1HDGkz8BKQGn6SFRPzaTt13hFOC8JbtUD?usp=sharing The files are names as `quant_closest__atmc_.pth`. For example, the file `quant_closest_svhn_atmc_0.005.pth` is the ATMC 8-bit model on SVHN dataset with 0.005...