search

gwang-kim / DiffusionCLIP

[CVPR 2022] Official PyTorch Implementation for DiffusionCLIP: Text-guided Image Manipulation Using Diffusion Models
Other
785 stars 113 forks source link

Error trying to train #3

Closed corranmac closed 2 years ago

corranmac commented 2 years ago

Hi there, Im trying to finetune your FFHQ model but get this error:

Loading ResNet ArcFace Prepare identity latent precomputed/CelebA_HQ_train_t500_nim100_ninv40_pairs.pth ERROR - main.py - 2022-04-05 01:37:56,717 - Traceback (most recent call last): File "main.py", line 211, in main runner.clip_finetune() File "/content/DiffusionCLIP/diffusionclip.py", line 143, in clip_finetune train_dataset, test_dataset = get_dataset(self.config.data.dataset, DATASET_PATHS, self.config) File "/content/DiffusionCLIP/datasets/data_utils.py", line 13, in get_dataset train_dataset, test_dataset = get_celeba_dataset(dataset_paths['CelebA_HQ'], config) File "/content/DiffusionCLIP/datasets/CelebA_HQ_dataset.py", line 55, in get_celeba_dataset train_transform, config.data.image_size) File "/content/DiffusionCLIP/datasets/CelebA_HQ_dataset.py", line 16, in init meminit=False, lmdb.Error: /data/DiffusionCLIP/celeba_hq/LMDB_train: No such file or directory

gwang-kim commented 2 years ago

Thanks for your interest in our work, @corranmac. CelebA-HQ and AFHQ-Dog datasets are required to be preprocessed in LMDB format. I updated the codes for this and the instructions in the Dataset section of README. 

# CelebA-HQ 256x256
bash data_download.sh celeba_hq .
Hayeon-kimm commented 1 year ago

I downloaded it. However, I can't see data.mdb. I can only see the raw_images folder. How can get it?