Training Logs

[alexriedel1]

Dear Sanghyun Jo,
I was wondering if you were able to share training logs with your final parameters, losses and mious?
Thanks, Alex

EDIT:
Also I would like to ask you, if you think its reasonable for training and validation if I rely entirely on the loss, as I have no ground truth masks for validation. For this purpose I calculate the "raw loss" additionally without multiplying RE loss with alpha, both on the train and validation set (because otherwise my loss metric would be influenced by the number of epochs).

[shjo-april]

Hello Alex,
thanks for question.

I will update training logs and weights this week.

I already put up my ground-truth mask on my github page.
So, you can refer to that.

If you want to check mIoU using the model, you have to make pseudo-labels using inference_* python files.

Best,
Sanghyun