Open Vietsol-AnhHaiLe opened 1 week ago
Hi.
I solved this problem by creating quantize.py
in ./anomalydiffusion/taming/modules/vqvae/
and using the code from here.
Hope this solution works for you as well.
it work but i have this next fault (Anomalydiffusion) haianh@admin:~/anomalydiffusion$ CUDA_VISIBLE_DEVICES=$gpu_id python main.py --spatial_encoder_embedding --data_enhance --base configs/latent-diffusion/txt2img-1p4B-finetune-encoder+embedding.yaml -t --actual_resume models/ldm/text2img-large/model.ckpt -n test --gpus 0 --init_word anomaly --mvtec_path=/home/haianh/anomalydiffusion/mvtec Global seed set to 23 Running on GPUs 0 Loading model from models/ldm/text2img-large/model.ckpt LatentDiffusion: Running in eps-prediction mode Killed
ModuleNotFoundError: No module named 'imgaug'
Traceback (most recent call last):
File "generate_with_mask.py", line 15, in
This should resolve the error.
pip install imgaug
i have pip install imgaug
(Anomalydiffusion) haianh@admin:~/anomalydiffusion$ CUDA_VISIBLE_DEVICES=$gpu_id python run-mvtec.py --data_path=/home/haianh/anomalydiffusion/mvtec
Global seed set to 23
Running on GPUs 0,
Loading model from ./models/ldm/text2img-large/model.ckpt
LatentDiffusion: Running in eps-prediction mode
Killed
Traceback (most recent call last):
File "generate_mask.py", line 13, in
(Anomalydiffusion) haianh@admin:~/anomalydiffusion$ python main.py --spatial_encoder_embedding --data_enhance --base configs/latent-diffusion/txt2img-1p4B-finetune-encoder+embedding.yaml -t --actual_resume models/ldm/text2img-large/model.ckpt -n test --gpus 0 --init_word anomaly --mvtec_path=/home/haianh/anomalydiffusion/mvtec Global seed set to 23 Running on GPUs 0 Loading model from models/ldm/text2img-large/model.ckpt Traceback (most recent call last): File "main.py", line 644, in
model = load_model_from_config(config, opt.actual_resume)
File "main.py", line 30, in load_model_from_config
model = instantiate_from_config(config.model)
File "/home/haianh/anomalydiffusion/ldm/util.py", line 86, in instantiate_from_config
return get_obj_from_str(config["target"])(config.get("params", dict()), kwargs)
File "/home/haianh/anomalydiffusion/ldm/util.py", line 94, in get_obj_from_str
return getattr(importlib.import_module(module, package=None), cls)
File "/home/haianh/miniconda3/envs/Anomalydiffusion/lib/python3.8/importlib/init.py", line 127, in import_module
return _bootstrap._gcd_import(name[level:], package, level)
File "", line 1014, in _gcd_import
File "", line 991, in _find_and_load
File "", line 975, in _find_and_load_unlocked
File "", line 671, in _load_unlocked
File "", line 783, in exec_module
File "", line 219, in _call_with_frames_removed
File "/home/haianh/anomalydiffusion/ldm/models/diffusion/ddpm.py", line 26, in
from ldm.models.autoencoder import VQModelInterface, IdentityFirstStage, AutoencoderKL
File "/home/haianh/anomalydiffusion/ldm/models/autoencoder.py", line 5, in
from taming.modules.vqvae.quantize import VectorQuantizer2 as VectorQuantizer
ModuleNotFoundError: No module named 'taming.modules.vqvae'
During handling of the above exception, another exception occurred:
Traceback (most recent call last): File "main.py", line 887, in
if trainer.global_rank == 0:
NameError: name 'trainer' is not defined