search

ckkelvinchan / RealBasicVSR

Official repository of "Investigating Tradeoffs in Real-World Video Super-Resolution"
Apache License 2.0
900 stars 134 forks source link

model training problem #51

Open RavenKang opened 2 years ago

RavenKang commented 2 years ago

When trying to train on multiple GPUs the error:

ValueError: You may use too small dataset and our distributed sampler cannot pad your dataset correctly. We highly recommend you to use fewer GPUs to finish your work

I follow the instructions below: Put the original REDS dataset in ./data Run the following command: python crop_sub_images.py --data-root ./data/REDS --scales 4

and training model follow the instructions mim train mmedit configs/realbasicvsr_wogan_c64b20_2x30x8_lr1e-4_300k_reds.py --gpus 2 --launcher pytorch

ckkelvinchan commented 2 years ago

How many GPUs are you using?

RavenKang commented 2 years ago

How many GPUs are you using?

I use 2 GPUs

zlu1994 commented 2 years ago

I also encountered the same problem and solved it in the following ways Modify code in realbasicvsr_wogan_c64b20_2x30x8_lr1e-4_300k_reds.py workers_per_gpu=4, num_input_frames=8,