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

📚 A collection of all the Deep Learning Metrics that I came across which are not accuracy/loss.

Multi-tool reverse engineering collaboration solution.

Official Implementation of "Third Time's the Charm? Image and Video Editing with StyleGAN3" https://arxiv.org/abs/2201.13433

Open source Python implementation of the HDR+ photography pipeline

EdiBERT is a generative model based on a bi-directional transformer, suited for image manipulation

This is an official implementation of the paper "Distance-aware Quantization", accepted to ICCV2021.

Implementation for "Domain-Specific Bias Filtering for Single Labeled Domain Generalization"

Reimplement of SimSwap training code

Arch-Net: Model Distillation for Architecture Agnostic Model Deployment

[ICCV 2021 Oral] Deep Evidential Action Recognition

A deep-learning pipeline for segmentation of ambiguous microscopic images.

Repository for scripts and notebooks from the book: Programming PyTorch for Deep Learning

Implementation EfficientDet: Scalable and Efficient Object Detection in PyTorch

Caffe-like explicit model constructor. C(onfig)Model

Official codebase for Decision Transformer: Reinforcement Learning via Sequence Modeling.

This repository contains the code used to quantitatively evaluate counterfactual examples in the associated paper.

A unet implementation for Image semantic segmentation

Pytorch reimplementation of the Vision Transformer (An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale)

Resco: A simple python package that report the effect of deep residual learning

🔮 Execution time predictions for deep neural network training iterations across different GPUs.