Abdelrahman (Ogail) Elogeel
Abdelrahman (Ogail) Elogeel
- I think you mean line 189 which is: net.load(args.restore_from, sess) I tried and it results in loss being ‘nan’ - i also tried to load from a saved checkpoint...
The dataset has 2 class obstacles (0) and non-obstacles (255) in a binary format. Here is an example of raw image  This is an example of label image (similar...
@hellochick I finally got it working, here are steps I did: - commenting `net.load` line - Setting number of classes to 2 - Setting IGNORE_LABEL to arbitrary number not 0...
@bhadresh74 is there a specific question you have?
@bhadresh74 Here are some suggestions: 1- getting loss to `0.6` is good indication, pushing it more will require some tinkering like: - increasing number of training steps - increasing batch...
@BCJuan excuse me for late reply. Yes I did both changes as well.
Yes, you will have to train from scratch
@BCJuan did fine-tuning from pretrained model boosted on your custom task? Have u tried to compare that vs training from scratch?
@BCJuan what's `mIoU` before and after using cityecapes pretrained model?
@BCJuan I did load the pretrained model however didn't see much diff between fine-tuning vs training from scratch.