Results are similar to the original deeplab v2 paper? about deeplab-v2--resnet-101--tensorflow

[zhengyang-wang]

Compared to the original deeplabv2 paper, two things were not implemented:

1. MSC: Employing mutli-scale inputs with max fusion.
2. CRF

My mIoU on val is 75.1, which is reasonable.

[dyz-zju]

Hello, I just run your code on augmented pascalvoc datasets, and not change anything.
After iter 20000, I test just get mIoU 68.8%, do you know why? Thanks!

[dyz-zju]

And more, the loss just shocks, after iter 20000, the final loss is aroud 1.3.

[zhengyang-wang]

Which pre-trained model did you use?

[zhengyang-wang]

And you may notice that you need to change 'valid_step' in main.py for testing/validation.

[dyz-zju]

I use deeplab_resnet_init.ckpt as my pertained model，and valid step is changed to 20000.

[zhengyang-wang]

Your final loss is correct. I cannot figure out what happened in your case without more information. I tested the code for several runs, the mIoU results for val are consistently around 75.

[licaizi]

@dyz-zju 您好，我也只跑出了0.68，请问后来您的结果怎么样了

[zhengyang-wang]

Please check #7

[dyz-zju]

@CaiziLee you need to use another dataset processed by author, the url can be found in somewhere.