Justin-Tan / high-fidelity-generative-compression

Pytorch implementation of High-Fidelity Generative Image Compression + Routines for neural image compression
Apache License 2.0
411 stars 77 forks source link

’ train.py --model_type compression_gan --regime low --n_steps 1e6 --warmstart --ckpt path/to/base/checkpoint‘ did not work #34

Closed cheng-linkai closed 2 years ago

cheng-linkai commented 2 years ago

Train using full generator-discriminator loss

python3 train.py --model_type compression_gan --regime low --n_steps 1e6 --warmstart --ckpt path/to/base/checkpoint this command did not work for me ,after i changed it to 'python3 train.py --model_type compression_gan --regime low --n_steps 1e6 --warmstart -ckpt path/to/base/checkpoint' (--ckpt to -ckpt),it worked maybe this can help somebody

mepeichun commented 1 year ago

Same problem. Thanks for your help.