Skip to content
#

xception

Star

Here are 52 public repositories matching this topic...

Language: All
Filter by language
All 52 Python 25 Jupyter Notebook 21 HTML 4
Sort: Best match
Sort options
Best match Most stars Fewest stars Most forks Fewest forks Recently updated Least recently updated

jfzhang95 / pytorch-deeplab-xception

Star
Open

Wrong padding of "label"

shaibagon
shaibagon commented Jan 7, 2019

When training, the augmentation RandomScaleCrop may 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.fill of the augmentation functions

Read more

weiaicunzai / pytorch-cifar100

Star

Practice on cifar100(ResNet, DenseNet, VGG, GoogleNet, InceptionV3, InceptionV4, Inception-ResNetv2, Xception, Resnet In Resnet, ResNext,ShuffleNet, ShuffleNetv2, MobileNet, MobileNetv2, SqueezeNet, NasNet, Residual Attention Network, SENet)

deep-learning pytorch image-classification densenet resnet squeezenet inceptionv3 googlenet resnext cifar100 mobilenet inceptionv4 shufflenet xception nasnet inception-resnet-v2
  • Updated Aug 27, 2019
  • Python

Improve this page

Add a description, image, and links to the xception topic page so that developers can more easily learn about it.

Curate this topic

Add this topic to your repo

To associate your repository with the xception topic, visit your repo's landing page and select "manage topics."

Learn more

You can’t perform that action at this time.