train-CRF-RNN icon indicating copy to clipboard operation
train-CRF-RNN copied to clipboard

How to output pixel_accuracy,mean_accuracy,mean_IU and frequency_weighted

Open ursular86 opened this issue 9 years ago • 0 comments

Thanks for this code, it is very helpful for me. I have no idea how to output pixel_accuracy,mean_accuracy,mean_IU and frequency_weighted.I saw these words in the "test_model.py" and "test_model.py" is called in "solve.py". But it seems that the code "subprocess.call(['python', 'test_model.py', str(i)], stderr=FNULL)" in "solve.py" has never been excecuted. Is there something wrong with my code? What's more, if we test the network by "test_model.py", how about the test code from caffe, does it also runs? I will be appreciated if you can help me .Thank you!

ursular86 avatar Oct 26 '16 14:10 ursular86