Tramac / Fast Scnn Pytorch
Licence: apache-2.0
A PyTorch Implementation of Fast-SCNN: Fast Semantic Segmentation Network
Stars: β 239
Programming Languages
python
139335 projects - #7 most used programming language
Projects that are alternatives of or similar to Fast Scnn Pytorch
Fastseg
πΈ PyTorch implementation of MobileNetV3 for real-time semantic segmentation, with pretrained weights & state-of-the-art performance
Stars: β 202 (-15.48%)
Mutual labels: semantic-segmentation
Fcn
Chainer Implementation of Fully Convolutional Networks. (Training code to reproduce the original result is available.)
Stars: β 211 (-11.72%)
Mutual labels: semantic-segmentation
Cylinder3d
Rank 1st in the leaderboard of SemanticKITTI semantic segmentation (both single-scan and multi-scan) (Nov. 2020) (CVPR2021 Oral)
Stars: β 221 (-7.53%)
Mutual labels: semantic-segmentation
Fast Semantic Segmentation
ICNet and PSPNet-50 in Tensorflow for real-time semantic segmentation
Stars: β 203 (-15.06%)
Mutual labels: semantic-segmentation
Lightnetplusplus
LightNet++: Boosted Light-weighted Networks for Real-time Semantic Segmentation
Stars: β 218 (-8.79%)
Mutual labels: semantic-segmentation
Pixelnet
The repository contains source code and models to use PixelNet architecture used for various pixel-level tasks. More details can be accessed at <http://www.cs.cmu.edu/~aayushb/pixelNet/>.
Stars: β 194 (-18.83%)
Mutual labels: semantic-segmentation
Unet Pytorch
U-Net implementation for PyTorch based on https://arxiv.org/abs/1505.04597
Stars: β 229 (-4.18%)
Mutual labels: semantic-segmentation
Intrada
Unsupervised Intra-domain Adaptation for Semantic Segmentation through Self-Supervision (CVPR 2020 Oral)
Stars: β 211 (-11.72%)
Mutual labels: semantic-segmentation
Nncf
PyTorch*-based Neural Network Compression Framework for enhanced OpenVINOβ’ inference
Stars: β 218 (-8.79%)
Mutual labels: semantic-segmentation
Semantic Segmentation Suite
Semantic Segmentation Suite in TensorFlow. Implement, train, and test new Semantic Segmentation models easily!
Stars: β 2,395 (+902.09%)
Mutual labels: semantic-segmentation
Cagnet Zero Shot Semantic Segmentation
Code for our ACMMM2020 paper "Context-aware Feature Generation for Zero-shot Semantic Segmentation".
Stars: β 208 (-12.97%)
Mutual labels: semantic-segmentation
Tensorflow Deeplab Lfov
DeepLab-LargeFOV implemented in tensorflow
Stars: β 218 (-8.79%)
Mutual labels: semantic-segmentation
Seg Uncertainty
IJCAI2020 & IJCV 2020 π Unsupervised Scene Adaptation with Memory Regularization in vivo
Stars: β 202 (-15.48%)
Mutual labels: semantic-segmentation
Deep Learning In Production
Develop production ready deep learning code, deploy it and scale it
Stars: β 216 (-9.62%)
Mutual labels: semantic-segmentation
Keras Unet
Helper package with multiple U-Net implementations in Keras as well as useful utility tools helpful when working with image semantic segmentation tasks. This library and underlying tools come from multiple projects I performed working on semantic segmentation tasks
Stars: β 196 (-17.99%)
Mutual labels: semantic-segmentation
Deeplabv3.pytorch
PyTorch implementation of DeepLabv3
Stars: β 211 (-11.72%)
Mutual labels: semantic-segmentation
Decouplesegnets
Implementation of Our ECCV2020-work: Improving Semantic Segmentation via Decoupled Body and Edge Supervision
Stars: β 232 (-2.93%)
Mutual labels: semantic-segmentation
Asis
Associatively Segmenting Instances and Semantics in Point Clouds, CVPR 2019
Stars: β 228 (-4.6%)
Mutual labels: semantic-segmentation
Smoothly Blend Image Patches
Using a U-Net for image segmentation, blending predicted patches smoothly is a must to please the human eye.
Stars: β 218 (-8.79%)
Mutual labels: semantic-segmentation
Fast-SCNN: Fast Semantic Segmentation Network
A PyTorch implementation of Fast-SCNN: Fast Semantic Segmentation Network from the paper by Rudra PK Poudel, Stephan Liwicki.
Table of Contents
Installation
- Python 3.x. Recommended using Anaconda3
-
PyTorch 1.0. Install PyTorch by selecting your environment on the website and running the appropriate command. Such as:
conda install pytorch torchvision cudatoolkit=9.0 -c pytorch
- Clone this repository.
- Download the dataset by following the instructions below.
- Note: For training, we currently support cityscapes, and aim to add VOC and ADE20K.
Datasets
- You can download cityscapes from here. Note: please download leftImg8bit_trainvaltest.zip(11GB) and gtFine_trainvaltest(241MB).
Training-Fast-SCNN
- By default, we assume you have downloaded the cityscapes dataset in the
./datasets/citys
dir. - To train Fast-SCNN using the train script the parameters listed in
train.py
as a flag or manually change them.
python train.py --model fast_scnn --dataset citys
Evaluation
To evaluate a trained network:
python eval.py
Demo
Running a demo:
python demo.py --model fast_scnn --input-pic './png/berlin_000000_000019_leftImg8bit.png'
Results
Method | Dataset | crop_size | mIoU | pixAcc |
---|---|---|---|---|
Fast-SCNN(paper) | cityscapes | |||
Fast-SCNN(ours) | cityscapes | 768 | 54.84% | 92.37% |
Note: The result based on crop_size=768, which is different with paper.
ββββββββββ(a) test image βββββββββββ(b) ground truth ββββββββββ(c) predicted result
TODO
- [ ] add distributed training
- [ ] Support for the VOC, ADE20K dataset
- [ ] Support TensorBoard
- [x] save the best model
- [x] add Ohem Loss
Authors
References
- Rudra PK Poudel. et al. "Fast-SCNN: Fast Semantic Segmentation Network".
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].