#
drn
Here are 3 public repositories matching this topic...
常用的语义分割架构结构综述以及代码复现
deep-learning
pytorch
enet
fcn
image-segmentation
segnet
semantic-segmentation
gcn
deeplab
lrn
shufflenet
erfnet
frrn
drn
label-refinement-network
segmentation-networks
segmentation-models
bisenet
future-semantic-segmentation
-
Updated
Jul 13, 2019 - Python
PyTorch implementation of Dilated Residual Networks for semantic image segmentation
-
Updated
Dec 31, 2018 - Python
Improve this page
Add a description, image, and links to the drn topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the drn topic, visit your repo's landing page and select "manage topics."
When training, the augmentation
RandomScaleCropmay downscale the image and the target label image. It then pads the image and the label with [self.fill][1] which is ZERO.This is in contrast to the "ignore value" of the loss [that is set to 255][2].
This way the loss treats the padded region as valid "class 0" pixels and compute loss for it.
self.fillof the augmentation functions