colorization-pytorch icon indicating copy to clipboard operation
colorization-pytorch copied to clipboard

Published 20 hours ago • verified publisher icon richzhang

Model training Loss graph

Open Ugness opened this issue 6 years ago • 6 comments

newplot

Plot.ly Link: https://plot.ly/~Ugness/1/

I am training the model with ILSVRC2012 training set and same options as your implementation and my loss graph looks like above.
I am afraid that my model's loss reduces correctly. Can you check this loss graph or share your loss graph?
Thanks.

Ugness avatar Oct 04 '18 01:10 Ugness

Thanks for the message. I'll look into it in the next week or so.

richzhang avatar Oct 04 '18 02:10 richzhang

My apologies for the delay. I'm caught up with a few things and will have to look into this more after CVPR deadline (mid-Nov).

richzhang avatar Nov 06 '18 19:11 richzhang

Thanks.

Ugness avatar Nov 07 '18 08:11 Ugness

Hello author, I have the same problem above, what is the solution? Thanks in advance.

Samir55 avatar Dec 25 '18 16:12 Samir55

I believe I did not do the initialization properly. I am looking into it. Thanks for your patience!

richzhang avatar Dec 27 '18 21:12 richzhang

The problem was with the initialization. In the original paper, I used k-means initialization, but didn't have the code for pytorch.

I just pushed a change. If you rerun python make_ilsvrc_dataset.py, it will make a directory dataset/ilsvrc2012/train_small/, which contains 10 imagenet classes. Then rerun bash scripts/train_siggraph.sh again. It will first run 100 epochs on this small training set as "initialization", before training on the full training set.

It does still train quite slowly. Better networks/loss functions would be a good update to the project.

Thanks for your patience.

richzhang avatar Jan 05 '19 00:01 richzhang