loss is nan

[zlu1994]

"loss_pix" and "loss_clean" is nan every time I train for a while 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

[zhu2bowen]

have you tried a smaller lr?