1- <div align =" center " ><img src =" assets/logo.png " width =" 600 " ></div >
2-
1+ <div align =" center " ><img src =" assets/logo.png " width =" 350 " ></div >
32<img src =" assets/demo.png " >
43
5- ## < div align = " center " > Introduction</ div >
4+ ## Introduction
65YOLOX is an anchor-free version of YOLO, with a simpler design but better performance! It aims to bridge the gap between research and industrial communities.
76
7+ <img src =" assets/git_fig.png " width =" 1000 " >
88
9- ## <div align =" center " >Why YOLOX?</div >
10-
11- <div align =" center " ><img src =" assets/fig1.png " width =" 400 " ><img src =" assets/fig2.png " width =" 400 " ></div >
12-
13- ## <div align =" center " >News!!</div >
14- * 【2020/07/19】 We have released our technical report on [ Arxiv] ( xxx ) !!
9+ ## Updates!!
10+ * 【2020/07/19】 We have released our technical report on Arxiv.
1511
16- ## < div align = " center " > Benchmark</ div >
12+ ## Benchmark
1713
18- ### Standard Models.
14+ #### Standard Models.
1915| Model | size | mAP<sup >test<br >0.5:0.95 | Speed V100<br >(ms) | Params<br >(M) | FLOPs<br >(B)| weights |
2016| ------ | :---: | :---: | :---: | :---: | :---: | :----: |
21- | [ YOLOX-s] ( ) | 640 | 39.6 | 9.8 | 9.0 | 26.8 | - |
22- | [ YOLOX-m] ( ) | 640 | 46.4 | 12.3 | 25.3 | 73.8| - |
23- | [ YOLOX-l] ( ) | 640 | 50.0 | 14.5 | 54.2| 155.6 | - |
24- | [ YOLOX-x] ( ) | 640 | ** 51.2** | 17.3 | 99.1 | 281.9 | - |
17+ | [ YOLOX-s] ( ./exps/yolox_s.py ) | 640 | 39.6 | 9.8 | 9.0 | 26.8 | [ Download] ( https://megvii-my.sharepoint.cn/:u:/g/personal/gezheng_megvii_com/EW62gmO2vnNNs5npxjzunVwB9p307qqygaCkXdTO88BLUg?e=NMTQYw ) |
18+ | [ YOLOX-m] ( ./exps/yolox_m.py ) | 640 | 46.4 | 12.3 | 25.3 | 73.8| [ Download] ( https://megvii-my.sharepoint.cn/:u:/g/personal/gezheng_megvii_com/ERMTP7VFqrVBrXKMU7Vl4TcBQs0SUeCT7kvc-JdIbej4tQ?e=1MDo9y ) |
19+ | [ YOLOX-l] ( ./exps/yolox_l.py ) | 640 | 50.0 | 14.5 | 54.2| 155.6 | [ Download] ( https://megvii-my.sharepoint.cn/:u:/g/personal/gezheng_megvii_com/EWA8w_IEOzBKvuueBqfaZh0BeoG5sVzR-XYbOJO4YlOkRw?e=wHWOBE ) |
20+ | [ YOLOX-x] ( ./exps/yolox_x.py ) | 640 | ** 51.2** | 17.3 | 99.1 | 281.9 | [ Download] ( https://megvii-my.sharepoint.cn/:u:/g/personal/gezheng_megvii_com/EdgVPHBziOVBtGAXHfeHI5kBza0q9yyueMGdT0wXZfI1rQ?e=tABO5u ) |
21+ | [ YOLOX-Darknet53] ( ./exps/yolov3.py ) | 640 | 47.4 | 11.1 | 63.7 | 185.3 | [ Download] ( https://megvii-my.sharepoint.cn/:u:/g/personal/gezheng_megvii_com/EZ-MV1r_fMFPkPrNjvbJEMoBLOLAnXH-XKEB77w8LhXL6Q?e=mf6wOc ) |
2522
26- ### Light Models.
27- | Model | size | mAP<sup >val<br >0.5:0.95 | Speed V100< br >(ms) | Params<br >(M) | FLOPs<br >(B)| weights |
28- | ------ | :---: | :---: | :---: | :---: | :---: | :----: |
29- | [ YOLOX-Nano] ( ) | 416 | 25.3 | - | 0.91 | 1.08 | - |
30- | [ YOLOX-Tiny] ( ) | 416 | 31.7 | - | 5.06 | 6.45 | - |
23+ #### Light Models.
24+ | Model | size | mAP<sup >val<br >0.5:0.95 | Params<br >(M) | FLOPs<br >(B)| weights |
25+ | ------ | :---: | :---: | :---: | :---: | :---: |
26+ | [ YOLOX-Nano] ( ./exps/nano.py ) | 416 | 25.3 | 0.91 | 1.08 | [ Download ] ( https://megvii-my.sharepoint.cn/:u:/g/personal/gezheng_megvii_com/EdcREey-krhLtdtSnxolxiUBjWMy6EFdiaO9bdOwZ5ygCQ?e=yQpdds ) |
27+ | [ YOLOX-Tiny] ( ./exps/yolox_tiny.py ) | 416 | 31.7 | 5.06 | 6.45 | [ Download ] ( https://megvii-my.sharepoint.cn/:u:/g/personal/gezheng_megvii_com/EYtjNFPqvZBBrQ-VowLcSr4B6Z5TdTflUsr_gO2CwhC3bQ?e=SBTwXj ) |
3128
32- ## < div align = " center " > Quick Start</ div >
29+ ## Quick Start
3330
34- ### Installation
31+ <details >
32+ <summary >Installation</summary >
3533
3634Step1. Install [ apex] ( https://github.com/NVIDIA/apex ) .
3735
@@ -47,38 +45,53 @@ $ cd yolox
4745$ pip3 install -v -e . # or "python3 setup.py develop
4846```
4947
50- ### Demo
48+ </details >
49+
50+ <details >
51+ <summary >Demo</summary >
52+
53+ Step1. Download a pretrained model from the benchmark table.
5154
52- You can use either -n or -f to specify your detector's config:
55+ Step2. Use either -n or -f to specify your detector's config. For example :
5356
5457``` shell
55- python tools/demo.py -n yolox-s -c < MODEL_PATH > --conf 0.3 --nms 0.65 --tsize 640
58+ python tools/demo.py image -n yolox-s -c /path/to/your/yolox_s.pth.tar --path assets/dog.jpg -- conf 0.3 --nms 0.65 --tsize 640 --save_result
5659```
5760or
5861``` shell
59- python tools/demo.py -f exps/base/yolox_s.py -c < MODEL_PATH> --conf 0.3 --nms 0.65 --tsize 640
62+ python tools/demo.py image -f exps/yolox_s.py -c /path/to/your/yolox_s.pth.tar --path assets/dog.jpg --conf 0.3 --nms 0.65 --tsize 640 --save_result
63+ ```
64+ Demo for video:
65+ ``` shell
66+ python tools/demo.py video -n yolox-s -c /path/to/your/yolox_s.pth.tar --path /path/to/your/video --conf 0.3 --nms 0.65 --tsize 640 --save_result
6067```
6168
6269
63- <details open >
70+ </details >
71+
72+ <details >
6473<summary >Reproduce our results on COCO</summary >
6574
66- Step1.
75+ Step1. Prepare dataset
76+ ``` shell
77+ cd < YOLOX_HOME>
78+ mkdir datasets
79+ ln -s /path/to/your/COCO ./datasets/COCO
80+ ```
6781
68- * Reproduce our results on COCO by specifying -n:
82+ Step2. Reproduce our results on COCO by specifying -n:
6983
7084``` shell
7185python tools/train.py -n yolox-s -d 8 -b 64 --fp16 -o
7286 yolox-m
7387 yolox-l
7488 yolox-x
7589```
76- Notes:
7790* -d: number of gpu devices
78- * -b: total batch size, the recommended number for -b equals to num_gpu * 8
91+ * -b: total batch size, the recommended number for -b is num_gpu * 8
7992* --fp16: mixed precision training
8093
81- The above commands are equivalent to:
94+ When using -f, the above commands are equivalent to:
8295
8396``` shell
8497python tools/train.py -f exps/base/yolox-s.py -d 8 -b 64 --fp16 -o
@@ -87,42 +100,49 @@ python tools/train.py -f exps/base/yolox-s.py -d 8 -b 64 --fp16 -o
87100 exps/base/yolox-x.py
88101```
89102
90- * Customize your training.
91-
92- * Finetune your datset on COCO pretrained models.
93103</details >
94104
95- <details open >
105+
106+ <details >
96107<summary >Evaluation</summary >
108+
97109We support batch testing for fast evaluation:
98110
99111``` shell
100- python tools/eval.py -n yolox-s -b 64 -- conf 0.001 --fp16 (optional) --fuse (optional) --test (for test-dev set)
112+ python tools/eval.py -n yolox-s -c yolox_s.pth.tar - b 64 -d 8 -- conf 0.001 [ --fp16] [ --fuse]
101113 yolox-m
102114 yolox-l
103115 yolox-x
104116```
117+ * --fuse: fuse conv and bn
118+ * -d: number of GPUs used for evaluation. DEFAULT: All GPUs available will be used.
119+ * -b: total batch size across on all GPUs
105120
106121To reproduce speed test, we use the following command:
107122``` shell
108- python tools/eval.py -n yolox-s -b 1 -d 0 --conf 0.001 --fp16 --fuse --test (for test-dev set)
123+ python tools/eval.py -n yolox-s -c yolox_s.pth.tar - b 1 -d 1 --conf 0.001 --fp16 --fuse
109124 yolox-m
110125 yolox-l
111126 yolox-x
112127```
113128
114- ## <div align =" center " >Deployment</div >
115-
116129</details >
117130
118- 1 . [ ONNX: Including ONNX export and an ONNXRuntime demo.] ( )
119- 2 . [ TensorRT in both C++ and Python] ( )
120- 3 . [ NCNN in C++] ( )
121- 4 . [ OpenVINO in both C++ and Python] ( )
122131
123- ## <div align =" center " >Cite Our Work</div >
132+ <details open >
133+ <summary >Toturials</summary >
134+
135+ * [ Training on custom data] ( docs/train_custom_data.md ) .
136+
137+ </details >
138+
139+ ## Deployment
124140
125141
126- If you find this project useful for you, please use the following BibTeX entry.
142+ 1 . [ ONNX: Including ONNX export and an ONNXRuntime demo.] ( ./demo/ONNXRuntime )
143+ 2 . [ TensorRT in both C++ and Python] ( ./demo/TensorRT )
144+ 3 . [ NCNN in C++] ( ./demo/ncnn/android )
145+ 4 . [ OpenVINO in both C++ and Python] ( ./demo/OpenVINO )
127146
128- TODO
147+ ## Citing YOLOX
148+ If you use YOLOX in your research, please cite our work by using the following BibTeX entry:
0 commit comments