BiSeNet based on pytorch

Last update: Dec 26, 2022

Related tags

Deep Learning BiSeNet

Overview

BiSeNet

BiSeNet based on pytorch 0.4.1 and python 3.6

Dataset

Download CamVid dataset from Google Drive or Baidu Yun(6xw4).

Pretrained model

Download best_dice_loss_miou_0.655.pth in Google Drive or in Baidu Yun(6y3e) and put it in ./checkpoints

Demo

python demo.py

Result

Original	GT	Predict

Train

python train.py

Use tensorboard to see the real-time loss and accuracy

loss on train

pixel precision on val

miou on val

Test

python test.py

Result

class	Bicyclist	Building	Car	Pole	Fence	Pedestrian	Road	Sidewalk	SignSymbol	Sky	Tree	miou
iou	0.61	0.80	0.86	0.35	0.37	0.59	0.88	0.81	0.28	0.91	0.73	0.655

This time I train the model with dice loss and get better result than cross entropy loss. I did not use lots special training strategy, you can get much better result than this repo if using task-specific strategy.
This repo is mainly for proving the effeciveness of the model.
I also tried some simplified version of bisenet but it seems does not preform very well in CamVid dataset.

Speed

Method	640×320	1280×720	1920×1080
Paper	129.4	47.9	23
This Repo	126.8	53.7	23.6

This shows the speed comparison between paper and my implementation.

The number in first row means input image resolution.
The number in second and third row means FPS.
The result is based on resnet-18.

Future work

Finish real-time segmentation with camera or pre-load video

BiSeNet based on pytorch

Related tags

Overview

BiSeNet

Dataset

Pretrained model

Demo

Result

Train

loss on train

pixel precision on val

miou on val

Test

Result

Speed

Future work

Reference

Owner

Hierarchical Memory Matching Network for Video Object Segmentation (ICCV 2021)

This repository contains the official implementation code of the paper Improving Multimodal Fusion with Hierarchical Mutual Information Maximization for Multimodal Sentiment Analysis, accepted at EMNLP 2021.

Independent and minimal implementations of some reinforcement learning algorithms using PyTorch (including PPO, A3C, A2C, ...).

Code accompanying "Evolving spiking neuron cellular automata and networks to emulate in vitro neuronal activity," accepted to IEEE SSCI ICES 2021

Unofficial implementation of Alias-Free Generative Adversarial Networks. (https://arxiv.org/abs/2106.12423) in PyTorch

OpenVisionAPI server

Code for NeurIPS 2020 article "Contrastive learning of global and local features for medical image segmentation with limited annotations"

The lightweight PyTorch wrapper for high-performance AI research. Scale your models, not the boilerplate.

Pretrained SOTA Deep Learning models, callbacks and more for research and production with PyTorch Lightning and PyTorch

A PyTorch implementation of "SimGNN: A Neural Network Approach to Fast Graph Similarity Computation" (WSDM 2019).

Attention-based Transformation from Latent Features to Point Clouds (AAAI 2022)

Code for our paper A Transformer-Based Feature Segmentation and Region Alignment Method For UAV-View Geo-Localization,

This repository contains a pytorch implementation of "StereoPIFu: Depth Aware Clothed Human Digitization via Stereo Vision".

Code for "Finding Regions of Heterogeneity in Decision-Making via Expected Conditional Covariance" at NeurIPS 2021

🤗 Transformers: State-of-the-art Natural Language Processing for Pytorch, TensorFlow, and JAX.

Cweqgen - The CW Equation Generator

Implementation for paper "Towards the Generalization of Contrastive Self-Supervised Learning"

FinRL-Meta: A Universe for Data-Driven Financial Reinforcement Learning. 🔥

PyTorch implementation of probabilistic deep forecast applied to air quality.

The undersampled DWI image using Slice-Interleaved Diffusion Encoding (SIDE) method can be reconstructed by the UNet network.

BiSeNet based on pytorch

Related tags

Overview

BiSeNet

Dataset

Pretrained model

Demo

Result

Train

loss on train

pixel precision on val

miou on val

Test

Result

Speed

Future work

Reference

Owner

Hierarchical Memory Matching Network for Video Object Segmentation (ICCV 2021)

This repository contains the official implementation code of the paper Improving Multimodal Fusion with Hierarchical Mutual Information Maximization for Multimodal Sentiment Analysis, accepted at EMNLP 2021.

Independent and minimal implementations of some reinforcement learning algorithms using PyTorch (including PPO, A3C, A2C, ...).

Code accompanying "Evolving spiking neuron cellular automata and networks to emulate in vitro neuronal activity," accepted to IEEE SSCI ICES 2021

Unofficial implementation of Alias-Free Generative Adversarial Networks. (https://arxiv.org/abs/2106.12423) in PyTorch

OpenVisionAPI server

Code for NeurIPS 2020 article "Contrastive learning of global and local features for medical image segmentation with limited annotations"

The lightweight PyTorch wrapper for high-performance AI research. Scale your models, not the boilerplate.

Pretrained SOTA Deep Learning models, callbacks and more for research and production with PyTorch Lightning and PyTorch

A PyTorch implementation of "SimGNN: A Neural Network Approach to Fast Graph Similarity Computation" (WSDM 2019).

Attention-based Transformation from Latent Features to Point Clouds (AAAI 2022)

Code for our paper A Transformer-Based Feature Segmentation and Region Alignment Method For UAV-View Geo-Localization,

This repository contains a pytorch implementation of "StereoPIFu: Depth Aware Clothed Human Digitization via Stereo Vision".

Code for "Finding Regions of Heterogeneity in Decision-Making via Expected Conditional Covariance" at NeurIPS 2021

🤗 Transformers: State-of-the-art Natural Language Processing for Pytorch, TensorFlow, and JAX.

Cweqgen - The CW Equation Generator

Implementation for paper "Towards the Generalization of Contrastive Self-Supervised Learning"

FinRL­-Meta: A Universe for Data­-Driven Financial Reinforcement Learning. 🔥

PyTorch implementation of probabilistic deep forecast applied to air quality.

The undersampled DWI image using Slice-Interleaved Diffusion Encoding (SIDE) method can be reconstructed by the UNet network.

FinRL-Meta: A Universe for Data-Driven Financial Reinforcement Learning. 🔥