yulunzhang / RNAN

PyTorch code for our ICLR 2019 paper "Residual Non-local Attention Networks for Image Restoration"
338 stars 53 forks source link

training time and number of GPUs #8

Open Marshall-yao opened 5 years ago

Marshall-yao commented 5 years ago

Hi, thanks for your wonderful work and opening source. Could you please tell me how long did you train the model , the kind of GPU and number of GPUs?

Best regards

yulunzhang commented 5 years ago

Hi, The whole time to train a model is about 3 days. I used 1 Titan Xp GPU for training.

Marshall-yao commented 5 years ago

@yulunzhang Thanks very much for your patient reply.

Is the training time same for super-resolution trained? and what about GPU memory used?

Besides, why not use DIV2K dataset to train SR model?

Best regards.