Giters
thomasjpfan
/
pytorch_refinenet
Pytorch Implementation of Refinenet
Geek Repo:
Geek Repo
Github PK Tool:
Github PK Tool
Stargazers:
160
Watchers:
7
Issues:
6
Forks:
33
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 ago
Comments count
9
how to apply it on non-square image?
Updated
5 years ago
ValueError: optimizing a parameter that doesn't require gradients
Updated
6 years ago
Comments count
3
accuracy on Pascal VOC
Updated
6 years ago
Comments count
2
number of channel mismatch
Updated
6 years ago
Comments count
3
one of the variables needed for gradient computation has been modified by an inplace operation
Updated
7 years ago
Comments count
4