This project aims at providing a concise, easy-to-use, modifiable reference implementation for semantic segmentation models using PyTorch.

Last update: Jan 08, 2023

Overview

Semantic Segmentation on PyTorch

English | 简体中文

This project aims at providing a concise, easy-to-use, modifiable reference implementation for semantic segmentation models using PyTorch.

Installation

# semantic-segmentation-pytorch dependencies
pip install ninja tqdm

# follow PyTorch installation in https://pytorch.org/get-started/locally/
conda install pytorch torchvision -c pytorch

# install PyTorch Segmentation
git clone https://github.com/Tramac/awesome-semantic-segmentation-pytorch.git

Usage

Train

Single GPU training

# for example, train fcn32_vgg16_pascal_voc:
python train.py --model fcn32s --backbone vgg16 --dataset pascal_voc --lr 0.0001 --epochs 50

Multi-GPU training

# for example, train fcn32_vgg16_pascal_voc with 4 GPUs:
export NGPUS=4
python -m torch.distributed.launch --nproc_per_node=$NGPUS train.py --model fcn32s --backbone vgg16 --dataset pascal_voc --lr 0.0001 --epochs 50

Evaluation

Single GPU evaluating

# for example, evaluate fcn32_vgg16_pascal_voc
python eval.py --model fcn32s --backbone vgg16 --dataset pascal_voc

Multi-GPU evaluating

# for example, evaluate fcn32_vgg16_pascal_voc with 4 GPUs:
export NGPUS=4
python -m torch.distributed.launch --nproc_per_node=$NGPUS eval.py --model fcn32s --backbone vgg16 --dataset pascal_voc

Demo

cd ./scripts
#for new users:
python demo.py --model fcn32s_vgg16_voc --input-pic ../tests/test_img.jpg
#you should add 'test.jpg' by yourself
python demo.py --model fcn32s_vgg16_voc --input-pic ../datasets/test.jpg

.{SEG_ROOT}
├── scripts
│   ├── demo.py
│   ├── eval.py
│   └── train.py

Support

Model

DETAILS for model & backbone.

.{SEG_ROOT}
├── core
│   ├── models
│   │   ├── bisenet.py
│   │   ├── danet.py
│   │   ├── deeplabv3.py
│   │   ├── deeplabv3+.py
│   │   ├── denseaspp.py
│   │   ├── dunet.py
│   │   ├── encnet.py
│   │   ├── fcn.py
│   │   ├── pspnet.py
│   │   ├── icnet.py
│   │   ├── enet.py
│   │   ├── ocnet.py
│   │   ├── psanet.py
│   │   ├── cgnet.py
│   │   ├── espnet.py
│   │   ├── lednet.py
│   │   ├── dfanet.py
│   │   ├── ......

Dataset

You can run script to download dataset, such as:

cd ./core/data/downloader
python ade20k.py --download-dir ../datasets/ade

Dataset	training set	validation set	testing set
VOC2012	1464	1449	✘
VOCAug	11355	2857	✘
ADK20K	20210	2000	✘
Cityscapes	2975	500	✘
COCO
SBU-shadow	4085	638	✘
LIP(Look into Person)	30462	10000	10000

.{SEG_ROOT}
├── core
│   ├── data
│   │   ├── dataloader
│   │   │   ├── ade.py
│   │   │   ├── cityscapes.py
│   │   │   ├── mscoco.py
│   │   │   ├── pascal_aug.py
│   │   │   ├── pascal_voc.py
│   │   │   ├── sbu_shadow.py
│   │   └── downloader
│   │       ├── ade20k.py
│   │       ├── cityscapes.py
│   │       ├── mscoco.py
│   │       ├── pascal_voc.py
│   │       └── sbu_shadow.py

Result

PASCAL VOC 2012

Methods	Backbone	TrainSet	EvalSet	crops_size	epochs	JPU	Mean IoU	pixAcc
FCN32s	vgg16	train	val	480	60	✘	47.50	85.39
FCN16s	vgg16	train	val	480	60	✘	49.16	85.98
FCN8s	vgg16	train	val	480	60	✘	48.87	85.02
FCN32s	resnet50	train	val	480	50	✘	54.60	88.57
PSPNet	resnet50	train	val	480	60	✘	63.44	89.78
DeepLabv3	resnet50	train	val	480	60	✘	60.15	88.36

Note: lr=1e-4, batch_size=4, epochs=80.

Overfitting Test

See TEST for details.

.{SEG_ROOT}
├── tests
│   └── test_model.py

This project aims at providing a concise, easy-to-use, modifiable reference implementation for semantic segmentation models using PyTorch.

Related tags

Overview

Semantic Segmentation on PyTorch

Installation

Usage

Train

Evaluation

Demo

Support

Model

Dataset

Result

Overfitting Test

To Do

References

Owner

Demos of essentia classifiers hosted on replicate.ai

StyleGAN - Official TensorFlow Implementation

Keyword spotting on Arm Cortex-M Microcontrollers

Look Who’s Talking: Active Speaker Detection in the Wild

Fortuitous Forgetting in Connectionist Networks

This repository contains the code for using the H3DS dataset introduced in H3D-Net: Few-Shot High-Fidelity 3D Head Reconstruction

[NeurIPS 2021] Official implementation of paper "Learning to Simulate Self-driven Particles System with Coordinated Policy Optimization".

Implementation for Simple Spectral Graph Convolution in ICLR 2021

Pytorch implementation of

SCAAML is a deep learning framwork dedicated to side-channel attacks run on top of TensorFlow 2.x.

Competitive Programming Club, Clinify's Official repository for CP problems hosting by club members.

[CVPR'21] Projecting Your View Attentively: Monocular Road Scene Layout Estimation via Cross-view Transformation

House_prices_kaggle - Predict sales prices and practice feature engineering, RFs, and gradient boosting

Synthesizing Long-Term 3D Human Motion and Interaction in 3D in CVPR2021

code for "Self-supervised edge features for improved Graph Neural Network training",

Codes for TS-CAM: Token Semantic Coupled Attention Map for Weakly Supervised Object Localization.

Unifying Global-Local Representations in Salient Object Detection with Transformer

Generate text captions for images from their CLIP embeddings. Includes PyTorch model code and example training script.

Edge-oriented Convolution Block for Real-time Super Resolution on Mobile Devices, ACM Multimedia 2021

HashNeRF-pytorch - Pure PyTorch Implementation of NVIDIA paper on Instant Training of Neural Graphics primitives