Closed dyz-zju closed 6 years ago
Compared to the original deeplabv2 paper, two things were not implemented:
My mIoU on val is 75.1, which is reasonable.
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!
And more, the loss just shocks, after iter 20000, the final loss is aroud 1.3.
Which pre-trained model did you use?
And you may notice that you need to change 'valid_step' in main.py for testing/validation.
I use deeplab_resnet_init.ckpt as my pertained model,and valid step is changed to 20000.
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.
@dyz-zju 您好,我也只跑出了0.68,请问后来您的结果怎么样了
@CaiziLee you need to use another dataset processed by author, the url can be found in somewhere.
Hello, your implementation has achive the results compared to the original paper? I want to known,thanks!