stylegan2-pytorch
stylegan2-pytorch copied to clipboard
lucidrains
Simplest working implementation of Stylegan2, state of the art generative adversarial network, in Pytorch. Enabling everyone to experience disentanglement
Hi! I'm just playing around at the moment, but am having some performance issues when using an RTX 3090. As the 3090 needs CUDA 11, I've installed like this: pip...
A very handy feature, would be lovely to have it in this version as well :D
I tried the command suggested in the readme: ```bash > conda install pytorch torchvision -c python Collecting package metadata (current_repodata.json): done Solving environment: failed with initial frozen solve. Retrying with...
Hey there @lucidrains, Came across your incredible work and immediately tried it out on my RTX 2070! Since the training will take some time and require a lot of memory,...
I train my dataset by the following commands: ``` stylegan2_pytorch --data trees_128 ^ --name stylegan4trees_128_12_17 ^ --image_size 128 ^ --network_capacity 16 ^ --batch_size 8 ^ --gradient_accumulate_every 16 ^ --num_train_steps 100000...
hi @lucidrains i've a issue when try to train with image with size of 512. Run the following line: stylegan2_pytorch --data ./flowers --multi-gpus --image-size 512 Issue: ...
hi @lucidrains, congratulate for your work, it's amazing. In a previous issue you said that if i want to get a single image instead a grid i have to set...
Hello all! Does the `--gradient-accumulate-every` value determines the the number of batches used to accumulate the gradient (without zeroing it) before the model weights are updated and gradients zeroed? Also,...
I feel like this project should have a way to use a TPU instead of a GPU. One usage example would be on [Google Colab](https://colab.research.google.com/notebooks/tpu.ipynb).
Metadata
Owner
Metadata
Simplest working implementation of Stylegan2, state of the art generative adversarial network, in Pytorch. Enabling everyone to experience disentanglement