Open Night1099 opened 6 months ago
turned out to be problem when using torch dynamo
to fix
pip install vision_aided_loss
dont use torch dynamo
But I still get the same error (I didn't use torch dynamo when config eccelerate)
Traceback (most recent call last):
File "/mnt/hdd/haseong8012/GAN/img2img-turbo/src/train_cyclegan_turbo.py", line 18, in
Does this issue persist if you try install the vision_aided_loss
package?
default training script for pix2pix-turbo Fails
Traceback (most recent call last): File "/workspace/img2img-turbo/src/train_pix2pix_turbo.py", line 307, in
main(args)
File "/workspace/img2img-turbo/src/train_pix2pix_turbo.py", line 65, in main
import vision_aided_loss
ModuleNotFoundError: No module named 'vision_aided_loss'
Traceback (most recent call last):
File "/usr/local/bin/accelerate", line 8, in
sys.exit(main())
File "/usr/local/lib/python3.10/dist-packages/accelerate/commands/accelerate_cli.py", line 46, in main
args.func(args)
File "/usr/local/lib/python3.10/dist-packages/accelerate/commands/launch.py", line 1075, in launch_command
simple_launcher(args)
File "/usr/local/lib/python3.10/dist-packages/accelerate/commands/launch.py", line 681, in simple_launcher
raise subprocess.CalledProcessError(returncode=process.returncode, cmd=cmd)
subprocess.CalledProcessError: Command '['/usr/bin/python', 'train_pix2pix_turbo.py', '--pretrained_model_name_or_path=stabilityai/sd-turbo', '--output_dir=output/pix2pix_turbo/DiffuseToHeight', '--dataset_folder=data/DiffuseToHeight', '--resolution=512', '--train_batch_size=2', '--enable_xformers_memory_efficient_attention', '--viz_freq', '25', '--track_val_fid', '--report_to', 'wandb', '--tracker_project_name', 'DiffusetoHeight']' returned non-zero exit status 1.