All Projects → kazuto1011 → Pspnet Pytorch

kazuto1011 / Pspnet Pytorch

Licence: mit
PyTorch implementation of PSPNet

Programming Languages

python
139335 projects - #7 most used programming language

Projects that are alternatives of or similar to Pspnet Pytorch

Semantic Segmentation Editor
Web labeling tool for bitmap images and point clouds
Stars: ✭ 894 (+1724.49%)
Mutual labels:  semantic-segmentation
Enet Sad pytorch
Pytorch implementation of "Learning Lightweight Lane Detection CNNs by Self Attention Distillation (ICCV 2019)"
Stars: ✭ 30 (-38.78%)
Mutual labels:  semantic-segmentation
Seg Mentor
TFslim based semantic segmentation models, modular&extensible boutique design
Stars: ✭ 43 (-12.24%)
Mutual labels:  semantic-segmentation
Medicaldetectiontoolkit
The Medical Detection Toolkit contains 2D + 3D implementations of prevalent object detectors such as Mask R-CNN, Retina Net, Retina U-Net, as well as a training and inference framework focused on dealing with medical images.
Stars: ✭ 917 (+1771.43%)
Mutual labels:  semantic-segmentation
Ssc
Semantic Scene Completion
Stars: ✭ 29 (-40.82%)
Mutual labels:  semantic-segmentation
Deeplabv3 Plus
Tensorflow 2.3.0 implementation of DeepLabV3-Plus
Stars: ✭ 32 (-34.69%)
Mutual labels:  semantic-segmentation
Sota Point Cloud
🔥Deep Learning for 3D Point Clouds (IEEE TPAMI, 2020)
Stars: ✭ 778 (+1487.76%)
Mutual labels:  semantic-segmentation
Fcn Googlenet
GoogLeNet implementation of Fully Convolutional Networks for Semantic Segmentation in TensorFlow
Stars: ✭ 45 (-8.16%)
Mutual labels:  semantic-segmentation
Tf Unet
tensorflow version of unet
Stars: ✭ 29 (-40.82%)
Mutual labels:  semantic-segmentation
Chainer Segnet
SegNet implementation & experiments in Chainer
Stars: ✭ 42 (-14.29%)
Mutual labels:  semantic-segmentation
Face Parsing.pytorch
Using modified BiSeNet for face parsing in PyTorch
Stars: ✭ 838 (+1610.2%)
Mutual labels:  semantic-segmentation
3d Semantic Segmentation For Scene Parsing
A new approach for the real time 3D semantic segmentation based on feature abstract and deep learning method
Stars: ✭ 13 (-73.47%)
Mutual labels:  semantic-segmentation
Pytorch Auto Drive
Segmentation models (ERFNet, ENet, DeepLab, FCN...) and Lane detection models (SCNN, SAD, PRNet, RESA, LSTR...) based on PyTorch 1.6 with mixed precision training
Stars: ✭ 32 (-34.69%)
Mutual labels:  semantic-segmentation
Efficientdet Pytorch
A PyTorch impl of EfficientDet faithful to the original Google impl w/ ported weights
Stars: ✭ 906 (+1748.98%)
Mutual labels:  semantic-segmentation
Vocal Melody Extraction
Source code for "Vocal melody extraction with semantic segmentation and audio-symbolic domain transfer learning".
Stars: ✭ 44 (-10.2%)
Mutual labels:  semantic-segmentation
Deeplab Pytorch
PyTorch implementation of DeepLab v2 on COCO-Stuff / PASCAL VOC
Stars: ✭ 787 (+1506.12%)
Mutual labels:  semantic-segmentation
Midv 500 Models
Model for document segmentation trained on the midv-500-models dataset.
Stars: ✭ 31 (-36.73%)
Mutual labels:  semantic-segmentation
Lung Segmentation
Segmentation of Lungs from Chest X-Rays using Fully Connected Networks
Stars: ✭ 47 (-4.08%)
Mutual labels:  semantic-segmentation
Unet Rgb
unet for rgb images semantic segmentation
Stars: ✭ 44 (-10.2%)
Mutual labels:  semantic-segmentation
Recurrent Scene Parsing With Perspective Understanding In The Loop
parsing scene images with understanding geometric perspective in the loop
Stars: ✭ 32 (-34.69%)
Mutual labels:  semantic-segmentation

PSPNet with PyTorch

Unofficial implementation of "Pyramid Scene Parsing Network" (https://arxiv.org/abs/1612.01105). This repository is just for caffe to pytorch model conversion and evaluation.

Requirements

  • pytorch
  • click
  • addict
  • pydensecrf
  • protobuf

Preparation

Instead of building the author's caffe implementation, you can convert off-the-shelf caffemodels to pytorch models via the caffe.proto.

1. Compile the caffe.proto for Python API

This step can be skipped. FYI.
Download the author's caffe.proto into the libs, not the one in the original caffe.

# For protoc command
pip install protobuf
# This generates ./caffe_pb2.py
protoc --python_out=. caffe.proto

2. Model conversion

  1. Find the caffemodels on the author's page (e.g. pspnet50_ADE20K.caffemodel) and store them to the data/models/ directory.
  2. Convert the caffemodels to .pth file.
python convert.py -c <PATH TO YAML>

Demo

python demo.py -c <PATH TO YAML> -i <PATH TO IMAGE>
  • With a --no-cuda option, this runs on CPU.
  • With a --crf option, you can perform a CRF postprocessing.

demo

Evaluation

PASCAL VOC2012 only. Please set the dataset path in config/voc12.yaml.

python eval.py -c config/voc12.yaml

88.1% mIoU (SS) and 88.6% mIoU (MS) on validation set.
NOTE: 3 points lower than caffe implementation. WIP

  • SS: averaged prediction with flipping (2x)
  • MS: averaged prediction with multi-scaling (6x) and flipping (2x)
  • Both: No CRF post-processing

References

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].