BigGAN-PyTorch
BigGAN-PyTorch copied to clipboard
ajbrock
The author's officially unofficial PyTorch BigGAN implementation.
Hi! I'd like to ask about pretrained models for Places365. In Readme, it says that Places365 pretrained models are coming soon. Is there still a plan to make them available...
Hi! Thanks for your great work! I have a question about the hinge loss of the generator(line 28 in losses.py). It seems that this may cause negative loss and it...
Hi, I was looking through this code for reimplementation for a separate task, but I noticed that the orthogonal regularization is implemented by adding the gradient of modified orthogonal regularization...
fine-tunning
Hi, Do anyone fine-tuning by means of the provided model(Source: Imagenet, target: tench (n01440764)) ? I use the same parameters to train. Before training, the result is as felloing: ...
Hi @ajbrock and team, thanks for making this codebase available for people to use, this is really amazing work! I'm currently doing a project on conditional medical image generation and...
Hello, I am using ImageNet 64x64 and run the code with the following command : `python train.py --dataset I64_hdf5 --shuffle --batch_size 128 --num_G_accumulations 1 --num_D_accumulations 1 --num_D_steps 1 --G_lr 1e-4...
Could you be so kind and either upload a requirements.txt file or comment on the exact versions of tqdm, numpy, scipy, and h5py that you used? I assume this might...
Hello, when i try to run the torchvision.utils.save_image() function inside the save_and_sample() function i get the error in the title. Can i get some help? This error is present in...
Hi guys, thank you for the amazing work! I have a trouble with FID. During the training, many times the log shows FID is nan. It does not happen all...
Hi, I am trying to train on a custom dataset using your algorithm. I try to increase batch size up to the point that my script doesn't break. I am...
