Hsuan

Yes, @zhoufengbuaa . I know the mean of image I used is for Pascal. But I think image mean is used for shifting the RGB value to -128~128. So the...

@zhoufengbuaa @John1231983 , Did you run the `evaluate.py` with `trainIdLabelImg` ? You should first transform the images using this script: https://github.com/mcordts/cityscapesScripts/blob/master/cityscapesscripts/preparation/createTrainIdLabelImgs.py Please tell me your evaluation procedure, thanks. Btw, I...

@smmdream , yes it's normal. Since not all objects appear in the beginning (One image may not contain 19 classes together), so the mIoU will gradually increase.

Hey, since you use different part of queue, the result will be different. But if you run the whole evaluation data, the result will be the same.

You can get the output from `raw_output_up` instead of `pred`.

Hey @smmdream , I think you should preprocess the color.png first, and let the pixel value range from 0~num_classes, just like gtFine_labelTrainIds.png. If you use RGB value to train, it...

Hey guys, maybe the problem is you need to update the moving mean/variance first. Then use the new moving mean/variance to train beta & gamma variable. I have successfully trained...

Hey @anqingjianke , Could you tell me how you process data into only 2 classes? Maybe the problems occurs here. Btw, after you update mean/var for a period of time,...

@anqingjianke , here is another advice, I think after you train for beta & gamma, you can fixed all of them and fine-tune the model, just do `train.py`. Maybe it...

Hey @manutdzou, I am not sure this code can re-produce the performance of original work or not. Because the author haven't provide the code of training phaze, I can only...