Results 8 comments of smm

I do it in the code ![2018-02-01 11-17-59](https://user-images.githubusercontent.com/10106222/35659853-9642e8dc-0743-11e8-814f-c74127936b9f.png) This is mine. You should make sure that the four files(as the follow picture) are in the path of SNAPSHOT_DIR, that's your...

![2017-12-14 16-00-49](https://user-images.githubusercontent.com/10106222/33981521-32218efc-e0e8-11e7-9563-5bfd3f838227.png) @hellochick @zhoufengbuaa This is my evaluation result, the mIoU is gradually increasing, only 0.502 at the beginning , is it right or normal?

@hellochick , I find a problem that the same model, the first evaluation result is different from the second evaluation result and the third and so on, and their value...

@hellochick , oh I see, I do the test, you are right.

@zhoufengbuaa I want to get the mIoU of each category, such as yours, can you tell me how to get that?

Thank you, @hellochick I'll try

I do only modify the input_size to 512*512,because my gpu just has 6GB memory,and my train result is very bad too,nothing can be predictd right.I don't know where is wrong,can...

I have met a question and spent a afternoon trying to solve it,but I failed.could you tell me what is "parser.add_argument('--frequent', help='frequency of logging', default=config.default.frequent, type=int)" need,I run the code,and...