stylegan2-pytorch

stylegan2-pytorch copied to clipboard

can not set GPU ids when DDP

2

I tried: CUDA_VISIBLE_DEVICES=4,5,6,7 python -m torch.distributed.launch --nproc_per_node=4 --master_port=PORT train.py --batch BATCH_SIZE LMDB_PATH But the ids are always 0,1,2,3. I don't wha't the reason. Anybody konw this?

fido20160817

nan loss

8

Hi, Thanks for sharing your code. I used your code to train on FFHQ dataset. The resolution is 128X128. All losses become NaN after few training iterations. The training losses...

SenHe

Can you convert weights with stylegan1 tensorflow

1

Hello, you can convert the weight from the official nvidia stylegan2 implementation. Is it also possible for stylegan1 tensorflow implementation? Thanks!

MationPlays

This PR fixes two subtle bugs: 1. In the current code, when `resid` (equals to `n_sample % batch_size`) is 0, the program exits in the last iteration throwing just "Floating...

shionhonda

subprocess.CalledProcessError: Command '['C:\Users\USERNAME\anaconda3\envs\stylegan-rosinality\python.exe', '-u', 'train.py', '--local_rank=0', '--batch', '5', 'C:\Users\USERNAME\LMBD_PATH']' returned non-zero exit status 1

2

I get this issue when training: subprocess.CalledProcessError: Command '['C:\Users\USERNAME\anaconda3\envs\stylegan-rosinality\python.exe', '-u', 'train.py', '--local_rank=0', '--batch', '5', 'C:\Users\USERNAME\LMBD_PATH']' returned non-zero exit status 1.

MationPlays

TypeError: upfirdn2d(): incompatible function arguments.

1

Thanks for your great project! I meet with a problem when running this command: `python generate.py --ckpt ./checkpoint/550000.pt` the detailed errors as follow: `Traceback (most recent call last): File "generate.py",...

lavitaaaa

subprocess.CalledProcessError: Command '[××]' died with <Signals.SIGSEGV: 11>.

1

Traceback (most recent call last): File "/public/home/anaconda3/envs/stylegan/lib/python3.6/runpy.py", line 193, in _run_module_as_main "__main__", mod_spec) File "/public/home/anaconda3/envs/stylegan/lib/python3.6/runpy.py", line 85, in _run_code exec(code, run_globals) File "/public/home/anaconda3/envs/stylegan/lib/python3.6/site-packages/torch/distributed/launch.py", line 253, in main() File "/public/home/anaconda3/envs/stylegan/lib/python3.6/site-packages/torch/distributed/launch.py", line...

zju-lyf

Working code for CPU inference?

4

Hi, I want to run inference on the CPU on Colab but I think I will have issues with the .cu CUDA extensions since there is no nvcc avaliable on...

JohnnyRacer

ImportError: No module named 'fused'

3

Hi I run the following command: ``` python -m torch.distributed.launch --nproc_per_node=8 --master_port=5433 train.py --batch 16 ./dataset/stylegan2/bag_texture_mdb ``` I'm getting the following error: ``` ***************************************** Setting OMP_NUM_THREADS environment variable for each...

leonel-os

Has someone used this code in a Notebook? Would be someone willing to share the colab? I find it hard to do it. Thanks

MationPlays