search

rosinality / vq-vae-2-pytorch

Implementation of Generating Diverse High-Fidelity Images with VQ-VAE-2 in PyTorch
Other
1.61k stars 271 forks source link

[extract_code] error in lmdb #46

Open kimdn opened 4 years ago

kimdn commented 4 years ago

I ran python /people/kimd999/script/python/cryoEM/vq-vae-2-pytorch/train_vqvae.py /people/kimd999/MARScryo/dn/data/part/PDX_label_correct/exp_coexp/input --size 256

It seems to generate sample images and checkpoint files in checkpoint folder well.

However, python /people/kimd999/script/python/cryoEM/vq-vae-2-pytorch/extract_code.py --size 256 --ckpt checkpoint/vqvae_560.pt --name small256 /people/kimd999/MARScryo/dn/data/part/PDX_label_correct/exp_coexp/input

resulted in Traceback (most recent call last): File "/people/kimd999/script/python/cryoEM/vq-vae-2-pytorch/extract_code.py", line 66, in <module> env = lmdb.open(args.name, map_size=map_size) lmdb.Error: small256: Input/output error

In my same conda environment (conda activate pytorch), I already installed lmdb as pip install lmdb

Can I have some guess/advice please?

Thank you

rosinality commented 4 years ago

Could you check free disk spaces? If it is enough then you can try to reduce map_size.