Results
3
issues of
cocoman
In view of the inability to converge in the loss of training, I made the following changes to the FCN.py file: 1 The initial learning rate is 1e-4, and the...
hello, could I use Deformable-ConvNets-caffe by pycaffe to write the python conv code, and then generate the *.prototxt?
Dear Senior: Last time I use you code of hifi v2 to train on SK-Large,and test it on test set(including 750 images).I got the score 0.68477,which is far away from...