easyolo python library
Project description
EasYoloD
Easy Yolo Detect
用户快速部署yolo的识别程序,支持onnxruntime, opencv(dnn), openvino
仅需简短几行代码即可实现yolo目标检测
Provider 介绍
- onnxruntime:
- cpu: 适配性最高的版本,不需要GPU即可执行
- gpu: onnxruntime-gpu 需要英伟达GPU,并且安装对应版本cuda,cudnn之后才能使用,速度快
- onnxdml: onnxruntime-directml 不需要使用特定GPU,核显也可以允许,而且不需要安装任何额外程序,速度一般,而且仅适用与windos系统
- openvino:
- cpu: 同onnx的cpu一样
- gpu: 仅适用于intel的GPU,其他GPU不可用
- opencv:
- cpu: 同上
- gpu: 需要单独编译带有cuda的opencv包,并正确配置路径,并且安装好cuda和cudnn,速度快
安装和使用
pip install easyolod
Requirements
- Python 3.8-3.12
- opencv-python <= 4.10.0.84
- numpy <= 1.26
使用:
import easyolod
easyolod.init(provider='onnxruntime',gpu=False) # onnxruntime-directml 则使用onnxdml,openvino使用 openvino
model = easyolod.Model()
# conf 置信度
# ious
# namse 可以是文件,也可以是一个list
model.load('modelpath', conf, ious, names)
# or 你使用的是opencv dnn yolov4的weight模型
# model.load('config path', 'weight path', inputsize, names, conf, nms)
result = model.detect(img=image)
# or 你希望自己处理输出
# result = model.detect_only(img=image)
Project details
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
easyolod-0.1.6.tar.gz
(7.7 kB
view details)
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file easyolod-0.1.6.tar.gz.
File metadata
- Download URL: easyolod-0.1.6.tar.gz
- Upload date:
- Size: 7.7 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.1.0 CPython/3.11.11
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
1342b197af0374ebd2e4680f71cfcff98d590d338e8a790ed9206a5fa3630ea6
|
|
| MD5 |
36c5a2942f9773e8aefb51d609d1c276
|
|
| BLAKE2b-256 |
d841eb5fdddf195ae11149c0fb9f04d0533cde25187cdc3ec63f42ff905fe618
|
File details
Details for the file EasYoloD-0.1.6-py3-none-any.whl.
File metadata
- Download URL: EasYoloD-0.1.6-py3-none-any.whl
- Upload date:
- Size: 7.9 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.1.0 CPython/3.11.11
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
cfae0f117f01f38c4de6611395a3d8abb9c4d199f091208e80e0b0e38bb1b622
|
|
| MD5 |
2fd54447a3148ac8638e29cf3fd83023
|
|
| BLAKE2b-256 |
3fdadb8517d20987e3f803ffc009cba15e24ada1122c07ced19ceae88bed5444
|