BigGAN-PyTorch
BigGAN-PyTorch copied to clipboard
ajbrock
The author's officially unofficial PyTorch BigGAN implementation.
Run script `launch_cifar_ema.sh`. Got error: > File "/scratch/liu.shu/codesPool/BigGAN-PyTorch/inception_utils.py", line 279, in prepare_inception_metrics data_mu = np.load(dataset+'_inception_moments.npz')['mu'] ... fid = open(os_fspath(file), "rb") FileNotFoundError: [Errno 2] No such file or directory: 'C10_inception_moments.npz' Seems...
Dear author, I notice that you say the computed inception scores and FIDs in the inception_utils.py are not comparable with the original TF IS/FID code. what's the mainly difference between...
Hi ajbrock, I was running the training code on ImageNet by using default script ```launch_BigGAN_bs256x8.sh```. It has finished 134k iterations and here is the log file. Compare with the log...
Previously, the BigGAN-deep discriminator applied a ReLU to the input images, which range in [-1, 1]. This appeared to cripple the training process.
Hello ajbrock, I want to use CIFAR10 as training dataset to train BigGAN, but I don't know what parameters have a direct impact on the quality of generated image? Could...
Hey, I am a student trying to reproduce the training process using my own dataset. I got the following error right after the first Epoch of training is finished: ```...
Hi everyone, I implemented three TPU enabled PyTorch training repos for BigGAN-PyTorch, all of which are based on this repo. [BigGAN-PyTorch-TPU-Single](https://github.com/shizhediao/BigGAN-PyTorch-TPU-Single): Training BigGAN with a single TPU. [BigGAN-PyTorch-TPU-Parallel](https://github.com/shizhediao/BigGAN-PyTorch-TPU-Parallel): Parallel version...
Hello, I am trying to train a bigGan with a custom dataset, whose resolution is 512x512. I edited one of the provided scripts to launch the training, but I got...
In the test function in train_fns.py, when saving the best model based on best IS or FID, the best model is first saved, and then the state_dict is updated with...
The BigGAN-Deep generator in BigGANdeep.py deviates from the official biggan-deep-512 tfhub module in several important ways. After reverse engineering the Tensorflow graph, the following fixes were ascertained: - Specnorm the...
