Yang Zou
> Maybe you should set align_corners=True for Upsample for Pytroch > 0.4. Thanks for your prompt reply. Actually the evaluate.py I used, which is your up-to-dated implementation, already set align_corners=True....
> Do you evaluate the VOC_scenes_20000.pth I provided? I just evaluated the provided VOC_scenes_20000.pth. It can only get 70.4 which is slightly worse than the model fine-tuned in my computer....
I have figured the scale problem in data preprocessing. But I still do not know why the model do not use std in the normalization? Any help will be appreciated!
1) 505 is for train set and 500 is for val set of cityscapes. 2) We also observe this phenomenon. My guess is that the pseudo-labels do not change to...
It's the number of images... On Mon, Jul 13, 2020 at 12:11 PM xuebingbing121 wrote: > Yes, i know 505 is for train set and 500 is for val set of...
The iterations and epochs should be in the training log part, not the validation/testing part. On Mon, Jul 13, 2020 at 12:17 PM xuebingbing121 wrote: > OK i see😂It's a...
It's in the log file.... 
You may want to debug it out. For the training data, if you want to keep the GTA2Cityscapes benchmark, the val set cannot be changed. But the training set of...
Usually segmentation papers use miou for the whole dataset/images already been seen for evaluation and comparison...
Line 757 the class ScoreUpdater in CRST_seg.py defines how to evaluate the results.