Yolox

Latest version: v0.3.0

Safety actively analyzes 685525 Python packages for vulnerabilities to keep your Python projects secure.

Scan your dependencies

Page 1 of 2

0.3.0

Updates notes

【2022/04/22】

Features
* support loading YOLOX model through `torch.hub` 1189
* support just-in-time compile op 1241
* support wandb logger 1144
* support `freeze` function for torch module 1156
* support showing YOLOX demo in a live window 1138
* support custom dataset for evaluator 1131
* add option for decode output in export_onnx 1113
* add HuggingFace web demo, click link [here](https://huggingface.co/spaces/Sultannn/YOLOX-Demo) #1184
* add pre-commit 1263
* add `get_trainer` method in Exp class 1263

For pip users
pip install yolox could help you to install yolox for most platform.
For windows users, yolox will compile self-defined operator in YOLOX package just-in-time. Otherwise, yolox will compile operator during installation automatically.

Thanks
Contributors (sort by timestamp of commit)
woowonjin robin-maillot wico-silva
AaronNZH nemonameless ArMaxik
joakimeriksson shenyi0220 manangoel99
wep21 futabato AK391
DoubleChuang Ar-Ray-code PieroMacaluso
Joe0120 Yulv-git

0.2.1

Japanese

作成後、多くのスターおよびフォークを頂けてうれしい限りです。ありがとうございます。

[GitHub Sponsors](https://github.com/sponsors/Ar-Ray-code)で支援して頂ければ開発とメンテナンスの励みになります!

全てのバージョンにおいて、挙動は[yolox_ros.py](https://github.com/Ar-Ray-code/YOLOX-ROS/blob/main/yolox_ros_py/yolox_ros_py/yolox_ros.py)を標準としています。すべてのソースコード(スクリプト)のメンテナンスは行っていないため、気になるところがあればissueなどで教えてください。

---更新---

- yolox_ros_py/yolox_ros.pyのパラメータの変更

- 削除:yolo_type(default: `yolox-s`)

- 追加:yolox_exp_py (default: `''`)

- 実行のためには [exps/default/yolox_s.py](https://github.com/Megvii-BaseDetection/YOLOX/blob/main/exps/default/yolox_s.py) のようなファイルパスを引数で指定する必要があります。インストール手順が正しければ、share/以下にインストールされます。これは、カスタムトレーニングモデルの使用を想定しています。

bash
yolox_ros_share_dir = get_package_share_directory('yolox_ros_py')

yolox_ros = launch_ros.actions.Node(
package="yolox_ros_py", executable="yolox_ros",
parameters=[
{"image_size/width": 640},
{"image_size/height": 480},
{"yolox_exp_py" : yolox_ros_share_dir+'/yolox_s.py'},
{"device" : 'cpu'},
{"fp16" : True},
{"fuse" : False},
{"legacy" : False},
{"trt" : False},
{"ckpt" : yolox_ros_share_dir+"/yolox_s.pth"},
{"conf" : 0.3},
{"threshold" : 0.65},
{"resize" : 640},
],
)


- Python + OpenVINO がv0.2.0上でも動作するように修正を行いました。
- YOLOXの自動インストールスクリプトの追加をしました。
- `bash YOLOX-ROS/yolox_ros_py/install_yolox_py.bash`を実行することでダウンロードできます。

- launch.pyやparamの追加・削除を行いました。
- yolox_ros_cpp の Jetson Nano対応を行いました。(貢献:[fateshelled](https://github.com/fateshelled))

English

I'm glad to get so many stars and forks after creating it. Thank you for your support.

If you can help me with [GitHub Sponsors](https://github.com/sponsors/Ar-Ray-code), it will encourage me to develop and maintain it!

In all versions, the standard behavior is [yolox_ros.py](https://github.com/Ar-Ray-code/YOLOX-ROS/blob/main/yolox_ros_py/yolox_ros_py/yolox_ros.py) The behavior is standard in all versions. I do not maintain all the source code (scripts), so if you have any concerns, please let me know via issues.

---Update---

- Change parameters in yolox_ros_py/yolox_ros.py

- Remove: yolo_type (default: `yolox-s`)

- Add: yolox_exp_py (default: `''`)

- For execution, specify a file path like [exps/default/yolox_s.py](https://github.com/Megvii-BaseDetection/YOLOX/blob/main/exps/default/yolox_s.py) as an argument The following is a list of the most common problems with the system. If the installation procedure is correct, it will be installed under share/. This assumes using a custom training model.

bash
yolox_ros_share_dir = get_package_share_directory('yolox_ros_py')

yolox_ros = launch_ros.actions.Node(
package="yolox_ros_py", executable="yolox_ros",
parameters=[
{"image_size/width": 640},
{"image_size/height": 480},
{"yolox_exp_py" : yolox_ros_share_dir+'/yolox_s.py'},
{"device" : 'cpu'},
{"fp16" : True},
{"fuse" : False},
{"legacy" : False},
{"trt" : False},
{"ckpt" : yolox_ros_share_dir+"/yolox_s.pth"},
{"conf" : 0.3},
{"threshold" : 0.65},
{"resize" : 640},
],
)


- Python + OpenVINO has been modified to work on v0.2.0.
- Added an automatic installation script for YOLOX.
- You can download it by running `bash YOLOX-ROS/yolox_ros_py/install_yolox_py.bash`.

- Added/removed `launch.py` and `param`.
- Added Jetson Nano support for yolox_ros_cpp. (Contributed by [fateshelled](https://github.com/fateshelled))

Supported YOLOX version

0.2.0

- [yolox-ros.py](https://github.com/Ar-Ray-code/YOLOX-ROS/blob/main/yolox_ros_py/yolox_ros_py/yolox_ros.py)のパラメータを大きく更新しました。
- [yolox-ros.py](https://github.com/Ar-Ray-code/YOLOX-ROS/blob/main/yolox_ros_py/yolox_ros_py/yolox_ros.py)の細かな不具合を修正しました。

English

I'm glad to get so many stars and forks after creating it. Thank you for your support.

If you can help me with [GitHub Sponsors](https://github.com/sponsors/Ar-Ray-code), it will encourage me to develop and maintain it!

In all versions, the standard behavior is [yolox_ros.py](https://github.com/Ar-Ray-code/YOLOX-ROS/blob/main/yolox_ros_py/yolox_ros_py/yolox_ros.py) The behavior is standard in all versions. I do not maintain all the source code (scripts), so if you have any concerns, please let me know via issues.

---Update---

- The documentation has been updated to match the update to [YOLOX-v0.2.0](https://github.com/Megvii-BaseDetection/YOLOX/releases/tag/0.2.0).
- The parameters of [yolox-ros.py](https://github.com/Ar-Ray-code/YOLOX-ROS/blob/main/yolox_ros_py/yolox_ros_py/yolox_ros.py) have been updated significantly.
- Fixed a minor bug in [yolox-ros.py](https://github.com/Ar-Ray-code/YOLOX-ROS/blob/main/yolox_ros_py/yolox_ros_py/yolox_ros.py).

Translated with www.DeepL.com/Translator (free version)

Contributors
- [Ar-Ray](https://github.com/Ar-Ray-code)
- [fateshelled](https://github.com/fateshelled)

0.1.1pre

Updates notes

【2021/08/19】

Features
* Support image caching for faster training, which requires large system RAM.
* Remove the dependence of apex and support torch amp training.
* Optimize the preprocessing for faster training
* Replace the older distort augmentation with new HSV aug for faster training and better performance.

2X Faster training

We optimize the data preprocess and support image caching with `--cache` flag:

shell
python tools/train.py -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.

Higher performance

New models achive **~1%** higher performance! See [Model_Zoo](model_zoo.md) for more details.

Support torch amp

We now support torch.cuda.amp training and Apex is not used anymore.

Breaking changes

We remove the normalization operation like -mean/std. This will make the old weights **incompatible**.

If you still want to use old weights, you can add `--legacy' in demo and eval:

shell
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] [--legacy]


and

shell
python tools/eval.py -n yolox-s -c yolox_s.pth -b 64 -d 8 --conf 0.001 [--fp16] [--fuse] [--legacy]
yolox-m
yolox-l
yolox-x


But for deployment demo, we don't suppor the old weights anymore.

0.1.1rc0

0.1.0

⚠️ There is a LICENSE problme in this release, but this LICENSE will not be changed. (This LICENSE is in accordance with YOLOX.)
Check 4 .

Page 1 of 2

© 2024 Safety CLI Cybersecurity Inc. All Rights Reserved.