search

amanchadha / iSeeBetter

iSeeBetter: Spatio-Temporal Video Super Resolution using Recurrent-Generative Back-Projection Networks | Python3 | PyTorch | GANs | CNNs | ResNets | RNNs | Published in Springer Journal of Computational Visual Media, September 2020, Tsinghua University Press
https://arxiv.org/abs/2006.11161
MIT License
363 stars 68 forks source link

About the loss again #18

Closed heiheihei-ops closed 4 years ago

heiheihei-ops commented 4 years ago

image Thank you for your answer, but I notice you have used .mean() in your code , and I think its usage is the same as to divide by the batchsize. By the way, if it is possible to see the loss curve when you train? Thank you so much!

amanchadha commented 4 years ago

Hi again @heiheihei-ops , any operations on the loss would still hold well and would leave the training process relatively unaffected since we only care for the relative value of the loss (and not its absolute value). Unfortunately, I do not have the loss curve handy :(

Hope this helps!