a Pytorch easy re-implement of "YOLOX: Exceeding YOLO Series in 2021"

Overview

A pytorch easy re-implement of "YOLOX: Exceeding YOLO Series in 2021"

1. Notes

This is a pytorch easy re-implement of "YOLOX: Exceeding YOLO Series in 2021" [https://arxiv.org/abs/2107.08430]
The repo is still under development

2. Environment

pytorch>=1.7.0, python>=3.6, Ubuntu/Windows, see more in 'requirements.txt'

cd /path/to/your/work
git clone https://github.com/zhangming8/yolox-pytorch.git
cd yolox-pytorch
download pre-train weights in Model Zoo to /path/to/your/work/weights

3. Object Detection

Model Zoo

All weights can be downloaded from GoogleDrive or BaiduDrive (code:bc72)

Model test size mAPval
0.5:0.95
mAPtest
0.5:0.95
Params
(M)
yolox-nano 416 25.4 25.7 0.91
yolox-tiny 416 33.1 33.2 5.06
yolox-s 640 39.3 39.6 9.0
yolox-m 640 46.2 46.4 25.3
yolox-l 640 49.5 50.0 54.2
yolox-x 640 50.5 51.1 99.1
yolox-x 800 51.2 51.9 99.1

mAP was reevaluated on COCO val2017 and test2017, and some results are slightly better than the official implement YOLOX. You can reproduce them by scripts in 'evaluate.sh'

Dataset

download COCO:
http://images.cocodataset.org/zips/train2017.zip
http://images.cocodataset.org/zips/val2017.zip
http://images.cocodataset.org/annotations/annotations_trainval2017.zip

unzip and put COCO dataset in following folders:
/path/to/dataset/annotations/instances_train2017.json
/path/to/dataset/annotations/instances_val2017.json
/path/to/dataset/images/train2017/*.jpg
/path/to/dataset/images/val2017/*.jpg

change opt.dataset_path = "/path/to/dataset" in 'config.py'

Train

See more example in 'train.sh'
a. Train from scratch:(backbone="CSPDarknet-s" means using yolox-s, and you can change it, eg: CSPDarknet-nano, tiny, s, m, l, x)
python train.py gpus='0' backbone="CSPDarknet-s" num_epochs=300 exp_id="coco_CSPDarknet-s_640x640" use_amp=True val_intervals=2 data_num_workers=6 batch_size=48

b. Finetune, download pre-trained weight on COCO and finetune on customer dataset:
python train.py gpus='0' backbone="CSPDarknet-s" num_epochs=300 exp_id="coco_CSPDarknet-s_640x640" use_amp=True val_intervals=2 data_num_workers=6 batch_size=48 load_model="../weights/yolox-s.pth"

c. Resume, you can use 'resume=True' when your training is accidentally stopped:
python train.py gpus='0' backbone="CSPDarknet-s" num_epochs=300 exp_id="coco_CSPDarknet-s_640x640" use_amp=True val_intervals=2 data_num_workers=6 batch_size=48 load_model="exp/coco_CSPDarknet-s_640x640/model_last.pth" resume=True

Some Tips:

a. You can also change params in 'train.sh'(these params will replace opt.xxx in config.py) and use 'nohup sh train.sh &' to train
b. Multi-gpu train: set opt.gpus = "3,5,6,7" in 'config.py' or set gpus="3,5,6,7" in 'train.sh'
c. If you want to close multi-size training, change opt.random_size = None in 'config.py' or set random_size=None in 'train.sh'
d. random_size = (14, 26) means: Randomly select an integer from interval (14,26) and multiply by 32 as the input size
e. Visualized log by tensorboard: 
    tensorboard --logdir exp/your_exp_id/logs_2021-08-xx-xx-xx and visit http://localhost:6006
   Your can also use the following shell scripts:
    (1) grep 'train epoch' exp/your_exp_id/logs_2021-08-xx-xx-xx/log.txt
    (2) grep 'val epoch' exp/your_exp_id/logs_2021-08-xx-xx-xx/log.txt

Evaluate

Module weights will be saved in './exp/your_exp_id/model_xx.pth'
change 'load_model'='weight/path/to/evaluate.pth' and backbone='backbone-type' in 'evaluate.sh'
sh evaluate.sh

Predict/Inference/Demo

a. Predict images, change img_dir and load_model
python predict.py gpus='0' backbone="CSPDarknet-s" vis_thresh=0.3 load_model="exp/coco_CSPDarknet-s_640x640/model_best.pth" img_dir='/path/to/dataset/images/val2017'

b. Predict video
python predict.py gpus='0' backbone="CSPDarknet-s" vis_thresh=0.3 load_model="exp/coco_CSPDarknet-s_640x640/model_best.pth" video_dir='/path/to/your/video.mp4'

You can also change params in 'predict.sh', and use 'sh predict.sh'

Train Customer Dataset(VOC format)

1. put your annotations(.xml) and images(.jpg) into:
    /path/to/voc_data/images/train2017/*.jpg  # train images
    /path/to/voc_data/images/train2017/*.xml  # train xml annotations
    /path/to/voc_data/images/val2017/*.jpg  # val images
    /path/to/voc_data/images/val2017/*.xml  # val xml annotations

2. change opt.label_name = ['your', 'dataset', 'label'] in 'config.py'
   change opt.dataset_path = '/path/to/voc_data' in 'config.py'

3. python tools/voc_to_coco.py
   Converted COCO format annotation will be saved into:
    /path/to/voc_data/annotations/instances_train2017.json
    /path/to/voc_data/annotations/instances_val2017.json

4. (Optional) you can visualize the converted annotations by:
    python tools/show_coco_anns.py
    Here is an analysis of the COCO annotation https://blog.csdn.net/u010397980/article/details/90341223?spm=1001.2014.3001.5501

5. run train.sh, evaluate.sh, predict.sh (are the same as COCO)

4. Multi/One-class Multi-object Tracking(MOT)

one-class/single-class MOT Dataset

DOING

Multi-class MOT Dataset

DOING

Train

DOING

Evaluate

DOING

Predict/Inference/Demo

DOING

5. Acknowledgement

https://github.com/Megvii-BaseDetection/YOLOX
https://github.com/PaddlePaddle/PaddleDetection
https://github.com/open-mmlab/mmdetection
https://github.com/xingyizhou/CenterNet
Segcache: a memory-efficient and scalable in-memory key-value cache for small objects

Segcache: a memory-efficient and scalable in-memory key-value cache for small objects This repo contains the code of Segcache described in the followi

TheSys Group @ CMU CS 78 Jan 07, 2023
Emulation and Feedback Fuzzing of Firmware with Memory Sanitization

BaseSAFE This repository contains the BaseSAFE Rust APIs, introduced by "BaseSAFE: Baseband SAnitized Fuzzing through Emulation". The example/ directo

Security in Telecommunications 138 Dec 16, 2022
Cascading Feature Extraction for Fast Point Cloud Registration (BMVC 2021)

Cascading Feature Extraction for Fast Point Cloud Registration This repository contains the source code for the paper [Arxive link comming soon]. Meth

7 May 26, 2022
A Python script that creates subtitles of a given length from text paragraphs that can be easily imported into any Video Editing software such as FinalCut Pro for further adjustments.

Text to Subtitles - Python This python file creates subtitles of a given length from text paragraphs that can be easily imported into any Video Editin

Dmytro North 9 Dec 24, 2022
Prefix-Tuning: Optimizing Continuous Prompts for Generation

Prefix Tuning Files: . ├── gpt2 # Code for GPT2 style autoregressive LM │ ├── train_e2e.py # high-level script

530 Jan 04, 2023
A Java implementation of the experiments for the paper "k-Center Clustering with Outliers in Sliding Windows"

OutliersSlidingWindows A Java implementation of the experiments for the paper "k-Center Clustering with Outliers in Sliding Windows" Dataset generatio

PaoloPellizzoni 0 Jan 05, 2022
TextBPN Adaptive Boundary Proposal Network for Arbitrary Shape Text Detection

TextBPN Adaptive Boundary Proposal Network for Arbitrary Shape Text Detection; Accepted by ICCV2021. Note: The complete code (including training and t

S.X.Zhang 84 Dec 13, 2022
Adaptive FNO transformer - official Pytorch implementation

Adaptive Fourier Neural Operators: Efficient Token Mixers for Transformers This repository contains PyTorch implementation of the Adaptive Fourier Neu

NVIDIA Research Projects 77 Dec 29, 2022
A FAIR dataset of TCV experimental results for validating edge/divertor turbulence models.

TCV-X21 validation for divertor turbulence simulations Quick links Intro Welcome to TCV-X21. We're glad you've found us! This repository is designed t

0 Dec 18, 2021
Lightweight plotting to the terminal. 4x resolution via Unicode.

Uniplot Lightweight plotting to the terminal. 4x resolution via Unicode. When working with production data science code it can be handy to have plotti

Olav Stetter 203 Dec 29, 2022
⚾🤖⚾ Automatic baseball pitching overlay in realtime

⚾ Automatically overlaying pitch motion and trajectory with machine learning! This project takes your baseball pitching clips and automatically genera

Tony Chou 240 Dec 05, 2022
Groceries ARL: Association Rules (Birliktelik Kuralı)

Groceries_ARL Association Rules (Birliktelik Kuralı) Birliktelik kuralları, mark

Şebnem 5 Feb 08, 2022
Styled Handwritten Text Generation with Transformers (ICCV 21)

⚡ Handwriting Transformers [PDF] Ankan Kumar Bhunia, Salman Khan, Hisham Cholakkal, Rao Muhammad Anwer, Fahad Shahbaz Khan & Mubarak Shah Abstract: We

Ankan Kumar Bhunia 85 Dec 22, 2022
PyTorch implementation for "Sharpness-aware Quantization for Deep Neural Networks".

Sharpness-aware Quantization for Deep Neural Networks Recent Update 2021.11.23: We release the source code of SAQ. Setup the environments Clone the re

Zhuang AI Group 30 Dec 19, 2022
FastFCN: Rethinking Dilated Convolution in the Backbone for Semantic Segmentation.

FastFCN: Rethinking Dilated Convolution in the Backbone for Semantic Segmentation [Project] [Paper] [arXiv] [Home] Official implementation of FastFCN:

Wu Huikai 815 Dec 29, 2022
This repository contains the code for our fast polygonal building extraction from overhead images pipeline.

Polygonal Building Segmentation by Frame Field Learning We add a frame field output to an image segmentation neural network to improve segmentation qu

Nicolas Girard 186 Jan 04, 2023
CCPD: a diverse and well-annotated dataset for license plate detection and recognition

CCPD (Chinese City Parking Dataset, ECCV) UPdate on 10/03/2019. CCPD Dataset is now updated. We are confident that images in subsets of CCPD is much m

detectRecog 1.8k Dec 30, 2022
Deep Learning for Morphological Profiling

Deep Learning for Morphological Profiling An end-to-end implementation of a ML System for morphological profiling using self-supervised learning to di

Danielh Carranza 0 Jan 20, 2022
Article Reranking by Memory-enhanced Key Sentence Matching for Detecting Previously Fact-checked Claims.

MTM This is the official repository of the paper: Article Reranking by Memory-enhanced Key Sentence Matching for Detecting Previously Fact-checked Cla

ICTMCG 13 Sep 17, 2022
Codes for ACL-IJCNLP 2021 Paper "Zero-shot Fact Verification by Claim Generation"

Zero-shot-Fact-Verification-by-Claim-Generation This repository contains code and models for the paper: Zero-shot Fact Verification by Claim Generatio

Liangming Pan 47 Jan 01, 2023