Pan-zhaoyu
Pan-zhaoyu
When I try to test the model on my own dataset, I got the results like the picture. Do you have any ideas why? Thanks.  
Caused by op u'block5_fc6/truncated_normal/TruncatedNormal', defined at: File "/home/robotics/keras-fcn/FCN-16.py", line 2, in fcn_vgg16 = FCN(input_shape=(500, 500, 3), classes=21, weights='imagenet', trainable_encoder=True) File "/home/robotics/keras-fcn/keras_fcn/models.py", line 29, in FCN return FCN_VGG16(*args, **kwargs) File "/home/robotics/keras-fcn/keras_fcn/models.py",...
Hi, I wonder to know your accuracy of the predicted results. How did you calculate the testing results? IoU or other methods? Because I apply this program to my own...
Hi,this is what I get when I run the server.py file. Where can I download this file and weight file together? Thank you guys.