Closed aleksandrmelnyk closed 7 years ago
Seems like annotations on output image doesn't correspond input one...? After run test_fcn32_vgg.py I got:
The model is not trained. The weights are just initialized from classification finetuning. Train the model to get better results.
Seems like annotations on output image doesn't correspond input one...? After run test_fcn32_vgg.py I got: