Decent

Decent copied to clipboard

Error while training the network

1

Minimal steps for error replication: Training on Nvida A6000 GPU OS: Ubuntu 20.04 Cuda version: 12.0 Pip list: absl-py 1.4.0 cachetools 4.2.4 certifi 2021.5.30 cffi 1.14.6 charset-normalizer 2.0.12 cycler 0.11.0...

Manjuphoenix

Thanks for your work! I would like to know how to train your model for paired iamge to image translation label to rgb image?

Mahmood-Hussain

Very cool work! Wanted to see how much it has improved from previous methods but wondering what settings you are recommending. Did you use the default options or something else?...

samedii

Multi GPU Training Issue

1

Hello, authors! Thanks for your excellent work. I have trouble with multi-GPU training. My command line looks like this: ``` python train.py --dataroot $dataset_path--name $model_name--gpu 0,1,2,3 --batch_size 1 ``` And...

ShenZheng2000

Hi, I try to re-construct your code with DDP for faster multi-GPU training. However, I encountered some issue. ``` File "/data2/liurzh/Decent_parallel/train.py", line 243, in main() File "/data2/liurzh/Decent_parallel/train.py", line 109, in...

RuizhouLiu