0. Sign up
1. Install
2. Prepare COCO dataset
3. Training
4. Conver YOLOX to _torchfx
5. Model compression with NetsPresso Python Package
6. Fine-tuning the compressed model
7. Convert a compressed YOLOX model by -n
To get started with the NetsPresso Python package, you will need to sign up at NetsPresso.
Clone repo and install requirements.txt in a Python>=3.7.0 environment, including PyTorch >= 1.11, < 2.0.
git clone https://github.com/Nota-NetsPresso/ModelZoo-YOLOX.git # clone
cd ModelZoo-YOLOX
pip3 install -v -e . # or python3 setup.py developcd <YOLOX_HOME>
ln -s /path/to/your/COCO ./datasets/COCOpython tools/train.py -n yolox-s -d 8 -b 64 --fp16 -o [--cache]- -d: number of gpu devices
- -b: total batch size, the recommended number for -b is num-gpu * 8
- --fp16: mixed precision training
- --cache: caching imgs into RAM to accelarate training, which need large system RAM.
python tools/export_netspresso.py -n yolox-s -c your/checkpoint/pathExecuting this code will create 'model_to_compress.pt' and 'model_head.pt'.
Upload & compress your 'model_to_compress.pt' by using NetsPresso Python Package
pip install netspressoFirst, import the packages and set a NetsPresso username and password.
from netspresso.compressor import ModelCompressor, Task, Framework, CompressionMethod, RecommendationMethod
EMAIL = "YOUR_EMAIL"
PASSWORD = "YOUR_PASSWORD"
compressor = ModelCompressor(email=EMAIL, password=PASSWORD)Second, upload 'model_to_compress.pt', which is the model converted to torchfx in step 4, with the following code.
# Upload Model
UPLOAD_MODEL_NAME = "yolox_model"
TASK = Task.OBJECT_DETECTION
FRAMEWORK = Framework.PYTORCH
UPLOAD_MODEL_PATH = "./model_to_compress.pt"
INPUT_SHAPES = [{"batch": 1, "channel": 3, "dimension": [640, 640]}]
model = compressor.upload_model(
model_name=UPLOAD_MODEL_NAME,
task=TASK,
framework=FRAMEWORK,
file_path=UPLOAD_MODEL_PATH,
input_shapes=INPUT_SHAPES,
)Finally, you can compress the uploaded model with the desired options through the following code.
# Recommendation Compression
COMPRESSED_MODEL_NAME = "test_l2norm"
COMPRESSION_METHOD = CompressionMethod.PR_L2
RECOMMENDATION_METHOD = RecommendationMethod.SLAMP
RECOMMENDATION_RATIO = 0.6
OUTPUT_PATH = "./model_compressed.pt"
compressed_model = compressor.recommendation_compression(
model_id=model.model_id,
model_name=COMPRESSED_MODEL_NAME,
compression_method=COMPRESSION_METHOD,
recommendation_method=RECOMMENDATION_METHOD,
recommendation_ratio=RECOMMENDATION_RATIO,
output_path=OUTPUT_PATH,
)Click to check 'Full upload & compress code'
pip install netspressofrom netspresso.compressor import ModelCompressor, Task, Framework, CompressionMethod, RecommendationMethod
EMAIL = "YOUR_EMAIL"
PASSWORD = "YOUR_PASSWORD"
compressor = ModelCompressor(email=EMAIL, password=PASSWORD)
# Upload Model
UPLOAD_MODEL_NAME = "yolox_model"
TASK = Task.OBJECT_DETECTION
FRAMEWORK = Framework.PYTORCH
UPLOAD_MODEL_PATH = "./model_to_compress.pt"
INPUT_SHAPES = [{"batch": 1, "channel": 3, "dimension": [640, 640]}]
model = compressor.upload_model(
model_name=UPLOAD_MODEL_NAME,
task=TASK,
framework=FRAMEWORK,
file_path=UPLOAD_MODEL_PATH,
input_shapes=INPUT_SHAPES,
)
# Recommendation Compression
COMPRESSED_MODEL_NAME = "test_l2norm"
COMPRESSION_METHOD = CompressionMethod.PR_L2
RECOMMENDATION_METHOD = RecommendationMethod.SLAMP
RECOMMENDATION_RATIO = 0.6
OUTPUT_PATH = "./model_compressed.pt"
compressed_model = compressor.recommendation_compression(
model_id=model.model_id,
model_name=COMPRESSED_MODEL_NAME,
compression_method=COMPRESSION_METHOD,
recommendation_method=RECOMMENDATION_METHOD,
recommendation_ratio=RECOMMENDATION_RATIO,
output_path=OUTPUT_PATH,
)More commands can be found in the official NetsPresso Python Package docs: https://nota-netspresso.github.io/PyNetsPresso-docs
Alternatively, you can do the same as above through the GUI on our website: https://console.netspresso.ai/models
Check yolox-s-netspresso.py file, and change the addresses of self.compressed_model and self.head models accordingly. You can compress and retrain other models by referring to 'yolox-s-netspresso.py'.
python tools/train.py -n yolox-s-netspresso -d 8 -b 64 --fp16 -o [--cache]Now you can use the compressed model however you like!
You can convert the compressed && retrained model to onnx by running the following code.
python3 tools/export_onnx.py --output-name yolox_s_compressed.onnx -n yolox-s-netspresso -c /best_ckpt.pthDo you need a converter to upload to a device or a benchmarker to measure model performance?
If you use LaunchX, you can easily convert and benchmark!
LaunchX address: https://launchx.netspresso.ai
Join our Discussion Forum for providing feedback or sharing your use cases, and if you want to talk more with Nota, please contact us here.
Or you can also do it via email([email protected]) or phone(+82 2-555-8659)!
YOLOX 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. For more details, please refer to our report on Arxiv.
This repo is an implementation of PyTorch version YOLOX, there is also a MegEngine implementation.
- 【2023/02/28】 We support assignment visualization tool, see doc here.
- 【2022/04/14】 We support jit compile op.
- 【2021/08/19】 We optimize the training process with 2x faster training and ~1% higher performance! See notes for more details.
- 【2021/08/05】 We release MegEngine version YOLOX.
- 【2021/07/28】 We fix the fatal error of memory leak
- 【2021/07/26】 We now support MegEngine deployment.
- 【2021/07/20】 We have released our technical report on Arxiv.
- YOLOX-P6 and larger model.
- Objects365 pretrain.
- Transformer modules.
- More features in need.
| Model | size | mAPval 0.5:0.95 |
mAPtest 0.5:0.95 |
Speed V100 (ms) |
Params (M) |
FLOPs (G) |
weights |
|---|---|---|---|---|---|---|---|
| YOLOX-s | 640 | 40.5 | 40.5 | 9.8 | 9.0 | 26.8 | github |
| YOLOX-m | 640 | 46.9 | 47.2 | 12.3 | 25.3 | 73.8 | github |
| YOLOX-l | 640 | 49.7 | 50.1 | 14.5 | 54.2 | 155.6 | github |
| YOLOX-x | 640 | 51.1 | 51.5 | 17.3 | 99.1 | 281.9 | github |
| YOLOX-Darknet53 | 640 | 47.7 | 48.0 | 11.1 | 63.7 | 185.3 | github |
Legacy models
| Model | size | mAPtest 0.5:0.95 |
Speed V100 (ms) |
Params (M) |
FLOPs (G) |
weights |
|---|---|---|---|---|---|---|
| YOLOX-s | 640 | 39.6 | 9.8 | 9.0 | 26.8 | onedrive/github |
| YOLOX-m | 640 | 46.4 | 12.3 | 25.3 | 73.8 | onedrive/github |
| YOLOX-l | 640 | 50.0 | 14.5 | 54.2 | 155.6 | onedrive/github |
| YOLOX-x | 640 | 51.2 | 17.3 | 99.1 | 281.9 | onedrive/github |
| YOLOX-Darknet53 | 640 | 47.4 | 11.1 | 63.7 | 185.3 | onedrive/github |
| Model | size | mAPval 0.5:0.95 |
Params (M) |
FLOPs (G) |
weights |
|---|---|---|---|---|---|
| YOLOX-Nano | 416 | 25.8 | 0.91 | 1.08 | github |
| YOLOX-Tiny | 416 | 32.8 | 5.06 | 6.45 | github |
Legacy models
| Model | size | mAPval 0.5:0.95 |
Params (M) |
FLOPs (G) |
weights |
|---|---|---|---|---|---|
| YOLOX-Nano | 416 | 25.3 | 0.91 | 1.08 | github |
| YOLOX-Tiny | 416 | 32.8 | 5.06 | 6.45 | github |
Installation
Step1. Install YOLOX from source.
git clone [email protected]:Megvii-BaseDetection/YOLOX.git
cd YOLOX
pip3 install -v -e . # or python3 setup.py developDemo
Step1. Download a pretrained model from the benchmark table.
Step2. Use either -n or -f to specify your detector's config. For example:
python tools/demo.py image -n yolox-s -c /path/to/your/yolox_s.pth --path assets/dog.jpg --conf 0.25 --nms 0.45 --tsize 640 --save_result --device [cpu/gpu]or
python tools/demo.py image -f exps/default/yolox_s.py -c /path/to/your/yolox_s.pth --path assets/dog.jpg --conf 0.25 --nms 0.45 --tsize 640 --save_result --device [cpu/gpu]Demo for video:
python tools/demo.py video -n yolox-s -c /path/to/your/yolox_s.pth --path /path/to/your/video --conf 0.25 --nms 0.45 --tsize 640 --save_result --device [cpu/gpu]Reproduce our results on COCO
Step1. Prepare COCO dataset
cd <YOLOX_HOME>
ln -s /path/to/your/COCO ./datasets/COCOStep2. Reproduce our results on COCO by specifying -n:
python -m yolox.tools.train -n yolox-s -d 8 -b 64 --fp16 -o [--cache]
yolox-m
yolox-l
yolox-x- -d: number of gpu devices
- -b: total batch size, the recommended number for -b is num-gpu * 8
- --fp16: mixed precision training
- --cache: caching imgs into RAM to accelarate training, which need large system RAM.
When using -f, the above commands are equivalent to:
python -m yolox.tools.train -f exps/default/yolox_s.py -d 8 -b 64 --fp16 -o [--cache]
exps/default/yolox_m.py
exps/default/yolox_l.py
exps/default/yolox_x.pyMulti Machine Training
We also support multi-nodes training. Just add the following args:
- --num_machines: num of your total training nodes
- --machine_rank: specify the rank of each node
Suppose you want to train YOLOX on 2 machines, and your master machines's IP is 123.123.123.123, use port 12312 and TCP.
On master machine, run
python tools/train.py -n yolox-s -b 128 --dist-url tcp://123.123.123.123:12312 --num_machines 2 --machine_rank 0On the second machine, run
python tools/train.py -n yolox-s -b 128 --dist-url tcp://123.123.123.123:12312 --num_machines 2 --machine_rank 1Logging to Weights & Biases
To log metrics, predictions and model checkpoints to W&B use the command line argument --logger wandb and use the prefix "wandb-" to specify arguments for initializing the wandb run.
python tools/train.py -n yolox-s -d 8 -b 64 --fp16 -o [--cache] --logger wandb wandb-project <project name>
yolox-m
yolox-l
yolox-xAn example wandb dashboard is available here
Others
See more information with the following command:
python -m yolox.tools.train --helpEvaluation
We support batch testing for fast evaluation:
python -m yolox.tools.eval -n yolox-s -c yolox_s.pth -b 64 -d 8 --conf 0.001 [--fp16] [--fuse]
yolox-m
yolox-l
yolox-x- --fuse: fuse conv and bn
- -d: number of GPUs used for evaluation. DEFAULT: All GPUs available will be used.
- -b: total batch size across on all GPUs
To reproduce speed test, we use the following command:
python -m yolox.tools.eval -n yolox-s -c yolox_s.pth -b 1 -d 1 --conf 0.001 --fp16 --fuse
yolox-m
yolox-l
yolox-xTutorials
- MegEngine in C++ and Python
- ONNX export and an ONNXRuntime
- TensorRT in C++ and Python
- ncnn in C++ and Java
- OpenVINO in C++ and Python
- Accelerate YOLOX inference with nebullvm in Python
- YOLOX for streaming perception: StreamYOLO (CVPR 2022 Oral)
- The YOLOX-s and YOLOX-nano are Integrated into ModelScope. Try out the Online Demo at YOLOX-s and YOLOX-Nano respectively 🚀.
- Integrated into Huggingface Spaces 🤗 using Gradio. Try out the Web Demo:
- The ncnn android app with video support: ncnn-android-yolox from FeiGeChuanShu
- YOLOX with Tengine support: Tengine from BUG1989
- YOLOX + ROS2 Foxy: YOLOX-ROS from Ar-Ray
- YOLOX Deploy DeepStream: YOLOX-deepstream from nanmi
- YOLOX MNN/TNN/ONNXRuntime: YOLOX-MNN、YOLOX-TNN and YOLOX-ONNXRuntime C++ from DefTruth
- Converting darknet or yolov5 datasets to COCO format for YOLOX: YOLO2COCO from Daniel
If you use YOLOX in your research, please cite our work by using the following BibTeX entry:
@article{yolox2021,
title={YOLOX: Exceeding YOLO Series in 2021},
author={Ge, Zheng and Liu, Songtao and Wang, Feng and Li, Zeming and Sun, Jian},
journal={arXiv preprint arXiv:2107.08430},
year={2021}
}Without the guidance of Dr. Jian Sun, YOLOX would not have been released and open sourced to the community. The passing away of Dr. Jian is a huge loss to the Computer Vision field. We add this section here to express our remembrance and condolences to our captain Dr. Jian. It is hoped that every AI practitioner in the world will stick to the concept of "continuous innovation to expand cognitive boundaries, and extraordinary technology to achieve product value" and move forward all the way.
YOLOX 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. For more details, please refer to our report on Arxiv.
This repo is an implementation of PyTorch version YOLOX, there is also a MegEngine implementation.
- 【2023/02/28】 We support assignment visualization tool, see doc here.
- 【2022/04/14】 We support jit compile op.
- 【2021/08/19】 We optimize the training process with 2x faster training and ~1% higher performance! See notes for more details.
- 【2021/08/05】 We release MegEngine version YOLOX.
- 【2021/07/28】 We fix the fatal error of memory leak
- 【2021/07/26】 We now support MegEngine deployment.
- 【2021/07/20】 We have released our technical report on Arxiv.
- YOLOX-P6 and larger model.
- Objects365 pretrain.
- Transformer modules.
- More features in need.
| Model | size | mAPval 0.5:0.95 |
mAPtest 0.5:0.95 |
Speed V100 (ms) |
Params (M) |
FLOPs (G) |
weights |
|---|---|---|---|---|---|---|---|
| YOLOX-s | 640 | 40.5 | 40.5 | 9.8 | 9.0 | 26.8 | github |
| YOLOX-m | 640 | 46.9 | 47.2 | 12.3 | 25.3 | 73.8 | github |
| YOLOX-l | 640 | 49.7 | 50.1 | 14.5 | 54.2 | 155.6 | github |
| YOLOX-x | 640 | 51.1 | 51.5 | 17.3 | 99.1 | 281.9 | github |
| YOLOX-Darknet53 | 640 | 47.7 | 48.0 | 11.1 | 63.7 | 185.3 | github |
Legacy models
| Model | size | mAPtest 0.5:0.95 |
Speed V100 (ms) |
Params (M) |
FLOPs (G) |
weights |
|---|---|---|---|---|---|---|
| YOLOX-s | 640 | 39.6 | 9.8 | 9.0 | 26.8 | onedrive/github |
| YOLOX-m | 640 | 46.4 | 12.3 | 25.3 | 73.8 | onedrive/github |
| YOLOX-l | 640 | 50.0 | 14.5 | 54.2 | 155.6 | onedrive/github |
| YOLOX-x | 640 | 51.2 | 17.3 | 99.1 | 281.9 | onedrive/github |
| YOLOX-Darknet53 | 640 | 47.4 | 11.1 | 63.7 | 185.3 | onedrive/github |
| Model | size | mAPval 0.5:0.95 |
Params (M) |
FLOPs (G) |
weights |
|---|---|---|---|---|---|
| YOLOX-Nano | 416 | 25.8 | 0.91 | 1.08 | github |
| YOLOX-Tiny | 416 | 32.8 | 5.06 | 6.45 | github |
Legacy models
| Model | size | mAPval 0.5:0.95 |
Params (M) |
FLOPs (G) |
weights |
|---|---|---|---|---|---|
| YOLOX-Nano | 416 | 25.3 | 0.91 | 1.08 | github |
| YOLOX-Tiny | 416 | 32.8 | 5.06 | 6.45 | github |
Installation
Step1. Install YOLOX from source.
git clone [email protected]:Megvii-BaseDetection/YOLOX.git
cd YOLOX
pip3 install -v -e . # or python3 setup.py developDemo
Step1. Download a pretrained model from the benchmark table.
Step2. Use either -n or -f to specify your detector's config. For example:
python tools/demo.py image -n yolox-s -c /path/to/your/yolox_s.pth --path assets/dog.jpg --conf 0.25 --nms 0.45 --tsize 640 --save_result --device [cpu/gpu]or
python tools/demo.py image -f exps/default/yolox_s.py -c /path/to/your/yolox_s.pth --path assets/dog.jpg --conf 0.25 --nms 0.45 --tsize 640 --save_result --device [cpu/gpu]Demo for video:
python tools/demo.py video -n yolox-s -c /path/to/your/yolox_s.pth --path /path/to/your/video --conf 0.25 --nms 0.45 --tsize 640 --save_result --device [cpu/gpu]Reproduce our results on COCO
Step1. Prepare COCO dataset
cd <YOLOX_HOME>
ln -s /path/to/your/COCO ./datasets/COCOStep2. Reproduce our results on COCO by specifying -n:
python -m yolox.tools.train -n yolox-s -d 8 -b 64 --fp16 -o [--cache]
yolox-m
yolox-l
yolox-x- -d: number of gpu devices
- -b: total batch size, the recommended number for -b is num-gpu * 8
- --fp16: mixed precision training
- --cache: caching imgs into RAM to accelarate training, which need large system RAM.
When using -f, the above commands are equivalent to:
python -m yolox.tools.train -f exps/default/yolox_s.py -d 8 -b 64 --fp16 -o [--cache]
exps/default/yolox_m.py
exps/default/yolox_l.py
exps/default/yolox_x.pyMulti Machine Training
We also support multi-nodes training. Just add the following args:
- --num_machines: num of your total training nodes
- --machine_rank: specify the rank of each node
Suppose you want to train YOLOX on 2 machines, and your master machines's IP is 123.123.123.123, use port 12312 and TCP.
On master machine, run
python tools/train.py -n yolox-s -b 128 --dist-url tcp://123.123.123.123:12312 --num_machines 2 --machine_rank 0On the second machine, run
python tools/train.py -n yolox-s -b 128 --dist-url tcp://123.123.123.123:12312 --num_machines 2 --machine_rank 1Logging to Weights & Biases
To log metrics, predictions and model checkpoints to W&B use the command line argument --logger wandb and use the prefix "wandb-" to specify arguments for initializing the wandb run.
python tools/train.py -n yolox-s -d 8 -b 64 --fp16 -o [--cache] --logger wandb wandb-project <project name>
yolox-m
yolox-l
yolox-xAn example wandb dashboard is available here
Others
See more information with the following command:
python -m yolox.tools.train --helpEvaluation
We support batch testing for fast evaluation:
python -m yolox.tools.eval -n yolox-s -c yolox_s.pth -b 64 -d 8 --conf 0.001 [--fp16] [--fuse]
yolox-m
yolox-l
yolox-x- --fuse: fuse conv and bn
- -d: number of GPUs used for evaluation. DEFAULT: All GPUs available will be used.
- -b: total batch size across on all GPUs
To reproduce speed test, we use the following command:
python -m yolox.tools.eval -n yolox-s -c yolox_s.pth -b 1 -d 1 --conf 0.001 --fp16 --fuse
yolox-m
yolox-l
yolox-xTutorials
- MegEngine in C++ and Python
- ONNX export and an ONNXRuntime
- TensorRT in C++ and Python
- ncnn in C++ and Java
- OpenVINO in C++ and Python
- Accelerate YOLOX inference with nebullvm in Python
- YOLOX for streaming perception: StreamYOLO (CVPR 2022 Oral)
- The YOLOX-s and YOLOX-nano are Integrated into ModelScope. Try out the Online Demo at YOLOX-s and YOLOX-Nano respectively 🚀.
- Integrated into Huggingface Spaces 🤗 using Gradio. Try out the Web Demo:
- The ncnn android app with video support: ncnn-android-yolox from FeiGeChuanShu
- YOLOX with Tengine support: Tengine from BUG1989
- YOLOX + ROS2 Foxy: YOLOX-ROS from Ar-Ray
- YOLOX Deploy DeepStream: YOLOX-deepstream from nanmi
- YOLOX MNN/TNN/ONNXRuntime: YOLOX-MNN、YOLOX-TNN and YOLOX-ONNXRuntime C++ from DefTruth
- Converting darknet or yolov5 datasets to COCO format for YOLOX: YOLO2COCO from Daniel
If you use YOLOX in your research, please cite our work by using the following BibTeX entry:
@article{yolox2021,
title={YOLOX: Exceeding YOLO Series in 2021},
author={Ge, Zheng and Liu, Songtao and Wang, Feng and Li, Zeming and Sun, Jian},
journal={arXiv preprint arXiv:2107.08430},
year={2021}
}Without the guidance of Dr. Jian Sun, YOLOX would not have been released and open sourced to the community. The passing away of Dr. Jian is a huge loss to the Computer Vision field. We add this section here to express our remembrance and condolences to our captain Dr. Jian. It is hoped that every AI practitioner in the world will stick to the concept of "continuous innovation to expand cognitive boundaries, and extraordinary technology to achieve product value" and move forward all the way.