search

pkuxmq / Invertible-Image-Rescaling

[ECCV 2020, IJCV 2022] Invertible Image Rescaling
Apache License 2.0
630 stars 86 forks source link

Training Details #7

Open wenbinTse opened 4 years ago

wenbinTse commented 4 years ago

Hi, thank for your amazing work. I want to reproduce your work using the config train_IRN_x2.yml, but the training is slow and will cost 4 days using the default config. Do I need to notice any detail? BTW, does the default config in yml file is the correct one to reproduce the paper results?

pkuxmq commented 4 years ago

Yes it will cost these time to train 500k iterations. The default config is the correct one.

toddwyl commented 3 years ago

Can you reproduce the DIV2k_val psnr? I train for 3 days and I think I cannot get the 44 psnr. image @wenbinTse @pkuxmq

toddwyl commented 3 years ago

Can you reproduce the DIV2k_val psnr? I train for 3 days and I think I cannot get the 44 psnr. image @wenbinTse @pkuxmq

Is that the tensorboard show the PSNR and the paper show the PSNR_Y? @pkuxmq

pkuxmq commented 3 years ago

@ManWingloeng Yes, the training code only calculates RGB PSNR, and the testing code will calculate both RGB PSNR and Y PSNR. We report Y PSNR in the paper following the setting of other works. For IRN_x2, the final RGB PSNR should be around 40.8dB.

toddwyl commented 3 years ago

@ManWingloeng Yes, the training code only calculates RGB PSNR, and the testing code will calculate both RGB PSNR and Y PSNR. We report Y PSNR in the paper following the setting of other works. For IRN_x2, the final RGB PSNR should be around 40.8dB.

Thanks your reply.