Skip to content

PyTorch implementation of PSPNet segmentation network

Notifications You must be signed in to change notification settings

ScienTechYD/pspnet-pytorch

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

17 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

pspnet-pytorch

PyTorch implementation of PSPNet segmentation network

Original paper

Pyramid Scene Parsing Network

Details

This is a slightly different version - instead of direct 8x upsampling at the end I use three consequitive upsamplings for stability.

Feature extraction

Using pretrained weights for extractors - improved quality and convergence dramatically.

Currently supported:

  • SqueezeNet
  • DenseNet-121
  • ResNet-18
  • ResNet-34
  • ResNet-50
  • ResNet-101
  • ResNet-152

Planned:

  • DenseNet-169
  • DenseNet-201

Usage

To follow the training routine in train.py you need a DataLoader that yields the tuples of the following format:

(Bx3xHxW FloatTensor x, BxHxW LongTensor y, BxN LongTensor y_cls) where

x - batch of input images,

y - batch of groung truth seg maps,

y_cls - batch of 1D tensors of dimensionality N: N total number of classes,

y_cls[i, T] = 1 if class T is present in image i, 0 otherwise

About

PyTorch implementation of PSPNet segmentation network

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 100.0%