search

hyao1 / GLAD

The official code of "GLAD: Towards Better Reconstruction with Global and Local Adaptive Diffusion Models for Unsupervised Anomaly Detection"
35 stars 2 forks source link

有关scheduler_config.json文件 #1

Closed houruixiang-1024 closed 2 months ago

houruixiang-1024 commented 2 months ago

Traceback (most recent call last): File "main.py", line 522, in dino_model, val_pipe = load_test_model(args, torch.float16) File "main.py", line 393, in load_test_model scheduler=DDIMScheduler.from_pretrained(args.pretrained_model_name_or_path, subfolder="scheduler"), File "/data/greatwall13/anaconda3/envs/unsup/lib/python3.8/site-packages/diffusers/schedulers/scheduling_utils.py", line 140, in from_pretrained config, kwargs, commit_hash = cls.load_config( File "/data/greatwall13/anaconda3/envs/unsup/lib/python3.8/site-packages/diffusers/configuration_utils.py", line 397, in load_config raise EnvironmentError( OSError: CompVis/stable-diffusion-v1-4 does not appear to have a file named scheduler_config.json.

hyao1 commented 2 months ago

CompVis/stable-diffusion-v1-4 is pretrained stable diffusion model. You need to download it before training. If you can not download it becasue of network, we provide it in our onedrive. After downloading it, please modify the args.pretrained_model_name_or_path into your downloaded file path.