thomasjpfan / pytorch_refinenet

Pytorch Implementation of Refinenet

thomasjpfan/pytorch_refinenet Issues

I have two questions:1) I train on my dataset for implement 2 classes when last layer sigmoid activate for binary cross entropy ,but the loss didn't convergence, 2) and the output shape is (N, C, 32, 32) when input shape is (N,C,128,128), can I unsample output to mask size（128,128）？
Updated 2 years ago9
how to apply it on non-square image?
Updated 5 years ago
ValueError: optimizing a parameter that doesn't require gradients
Updated 6 years ago3
accuracy on Pascal VOC
Updated 6 years ago2
number of channel mismatch
Updated 6 years ago3
one of the variables needed for gradient computation has been modified by an inplace operation
Updated 7 years ago4