search

hellochick / ICNet-tensorflow

TensorFlow-based implementation of "ICNet for Real-Time Semantic Segmentation on High-Resolution Images".
406 stars 153 forks source link

label indices mismatch between evaluation and gt data #10

Closed olive0206 closed 6 years ago

olive0206 commented 6 years ago

Hello~,

I recently downloaded the cityscape dataset from the official website.

and I tried to run evaluation.py code with cityscape eval & gt data.

Fortunately, I produce the the prediction result from the evaluation code using your trained model provided on GoogleDrive.

But Badly, I found the label indices generated from evaluation and those from ground-truth are mismatched. For example, the index for class person is 11 in your dataset, but it is 24 in cityscape dataset. so the final mIOU is extremely low like 0.00XX...

I guess, you trained the model with old version of cityscape dataset or something different from mine.

Am I right?? could you confirm my opinion??

hellochick commented 6 years ago

Hey, @olive0206 , since I have converted the dataset into trainID format. You can take a look at following repo, especially this code: https://github.com/mcordts/cityscapesScripts/blob/master/cityscapesscripts/helpers/labels.py It define the mapping between classes !

olive0206 commented 6 years ago

Thanks a lot, @hellochick !! ;)