# Streamlit-YOLOv5-Modle2X

**Repository Path**: CV_Lab/streamlit_yolov5_modle2x

## Basic Information

- **Project Name**: Streamlit-YOLOv5-Modle2X
- **Description**: 🚀 基于Streamlit的YOLOv5模型转换可视化工具
- **Primary Language**: Python
- **License**: GPL-3.0
- **Default Branch**: master
- **Homepage**: https://gitee.com/PyCVer
- **GVP Project**: No

## Statistics

- **Stars**: 26
- **Forks**: 15
- **Created**: 2022-07-12
- **Last Updated**: 2025-03-30

## Categories & Tags

**Categories**: ai

**Tags**: YOLOv5, 模型转换, 计算机视觉, streamlit, streamlit, onnx

## README

<p align="center">
<a href="https://gitee.com/CV_Lab/streamlit_yolov5_modle2x">
<img src="https://pycver.gitee.io/ows-pics/imgs/streamlit_yolov5_model2x_logo.png" alt="Simple Icons" >
</a>
<p align="center">
    基于Streamlit的YOLOv5模型转换可视化工具
</p>
</p>
<p align="center">
<a href="./CodeCheck.md"><img src="https://img.shields.io/badge/CodeCheck-passing-success" alt="code check" /></a>
<a href="https://gitee.com/CV_Lab/streamlit_yolov5_modle2x/releases/v0.3"><img src="https://img.shields.io/badge/Releases-v0.3-green" alt="Releases Version" /></a>
<a href="https://github.com/streamlit/streamlit"><img src="https://img.shields.io/badge/Streamlit-1.10.0-orange?logo=streamlit" alt="Streamlit Version" /></a>
<a href="https://huggingface.co/"><img src="https://img.shields.io/badge/%F0%9F%A4%97-Hugging%20Face-blue" alt="Hugging Face Spaces" /></a>
<a href="https://huggingface.co/spaces"><img src="https://img.shields.io/badge/🤗%20Hugging%20Face-Spaces-blue" alt="Hugging Face Spaces" /></a>
<a href="https://gitee.com/CV_Lab/gradio_yolov5_det/blob/master/LICENSE"><img src="https://img.shields.io/badge/License-GPL--3.0-blue" alt="License" /></a>
</p>
<p align="center">
<a href="https://github.com/ultralytics/yolov5"><img src="https://img.shields.io/badge/YOLOv5-v6.2-blue" alt="YOLOv5 Version" /></a>
<a href="#"><img src="https://img.shields.io/badge/Python-3.8%2B-blue?logo=python" alt="Python Version" /></a>
<a href="https://pypi.org/project/torch/"><img src="https://img.shields.io/badge/torch-1.11.0%2B-important?logo=pytorch" alt="Torch Version" /></a>
<a href="https://pypi.org/project/torchvision/"><img src="https://img.shields.io/badge/torchvision-0.12.0%2B-green?logo=pytorch" alt="TorchVision Version" /></a>
<a href="https://github.com/pre-commit/pre-commit"><img src="https://img.shields.io/badge/checks-pre--commit-brightgreen" alt="pre-commit"></a>
</p>



## 🚀 作者简介

曾逸夫，从事人工智能研究与开发；主研领域：计算机视觉；[YOLOv8官方开源项目代码贡献人](https://github.com/ultralytics/ultralytics/graphs/contributors)；[YOLOv5官方开源项目代码贡献人](https://github.com/ultralytics/yolov5/graphs/contributors)；[YOLOv5 v6.1代码贡献人](https://github.com/ultralytics/yolov5/releases/tag/v6.1)；[YOLOv5 v6.2代码贡献人](https://github.com/ultralytics/yolov5/releases/tag/v6.2)；[YOLOv5 v7.0代码贡献人](https://github.com/ultralytics/yolov5/releases/tag/v7.0)；[Gradio官方开源项目代码贡献人](https://github.com/gradio-app/gradio/graphs/contributors)

❤️  Github：https://github.com/Zengyf-CVer

🔥 YOLOv8 官方开源项目PR ID：

- Fix YOLOv8 Chinese introduction：https://github.com/ultralytics/ultralytics/pull/219
- Add codespell and upgrade some components：https://github.com/ultralytics/ultralytics/pull/599
- Add pycln：https://github.com/ultralytics/ultralytics/pull/7141
- Fix heatmap width and height parameter bug：https://github.com/ultralytics/ultralytics/pull/7368
- ultralytics 8.0.237 cv2.CAP_PROP fix and in_counts and out_counts displays：https://github.com/ultralytics/ultralytics/pull/7380

💡 Ultralytics v8.1.0 代码贡献链接：

- https://github.com/ultralytics/ultralytics/releases/tag/v8.1.0

🔥 YOLOv5 官方开源项目PR ID：

- Save \*.npy features on detect.py `--visualize`：https://github.com/ultralytics/yolov5/pull/5701
- Fix `detect.py --view-img` for non-ASCII paths：https://github.com/ultralytics/yolov5/pull/7093
- Fix Flask REST API：https://github.com/ultralytics/yolov5/pull/7210
- Add yesqa to precommit checks：https://github.com/ultralytics/yolov5/pull/7511
- Add mdformat to precommit checks and update other version：https://github.com/ultralytics/yolov5/pull/7529
- Add TensorRT dependencies：https://github.com/ultralytics/yolov5/pull/8553
- Add paddle tips：https://github.com/ultralytics/yolov5/pull/9502

💡 YOLOv5 v6.1 & v6.2 & v7.0 代码贡献链接：

- https://github.com/ultralytics/yolov5/releases/tag/v6.1
- https://github.com/ultralytics/yolov5/releases/tag/v6.2
- https://github.com/ultralytics/yolov5/releases/tag/v7.0


🔥 Gradio 官方开源项目PR ID：

- Create a color generator demo：https://github.com/gradio-app/gradio/pull/1872

<h2 align="center">🚀更新走势</h2>

- `2022-08-14` **⚡ [Streamlit YOLOv5 Model2X v0.3](https://gitee.com/CV_Lab/streamlit_yolov5_modle2x/releases/v0.3)正式上线**
- `2022-07-17` **⚡ [Streamlit YOLOv5 Model2X v0.2](https://gitee.com/CV_Lab/streamlit_yolov5_modle2x/releases/v0.2)正式上线**
- `2022-07-15` **⚡ [Streamlit YOLOv5 Model2X v0.1](https://gitee.com/CV_Lab/streamlit_yolov5_modle2x/releases/v0.1)正式上线**

<h2 align="center">🤗在线Demo</h2>

### ❤️ 快速体验

本项目提供了**在线demo**，点击下面的logo，进入**Hugging Face Spaces**中快速体验：

<div align="center" >
<a href="https://huggingface.co/spaces/Zengyf-CVer/Streamlit_YOLOv5_Model2x">
<img src="https://pycver.gitee.io/ows-pics/imgs/huggingface_logo.png">
</a>
</div>

<h2 align="center">💎项目流程与用途</h2>

### 📌 项目整体流程

<div align="center" >
<img src="https://pycver.gitee.io/ows-pics/imgs/streamlit_yolov5_model2x_workflow.png">
</div>

### 📌 项目示例

#### ❤️ 单选，单个模型转换界面与下载效果

<div align="center" >
<img src="https://pycver.gitee.io/ows-pics/imgs/stym_upload.png">
</div>

<div align="center" >
上传界面
</div>
<div align="center" >
<img src="https://pycver.gitee.io/ows-pics/imgs/stym_app01_01.png">
</div>

<div align="center" >
单选 模型界面（v0.1）
</div>

<div align="center" >
<img src="https://pycver.gitee.io/ows-pics/imgs/stym_app01_02.png">
</div>
<div align="center" >
单选 模型转换与下载界面（v0.1）
</div>

#### ❤️ 多选，多项模型转换界面与下载效果

<div align="center" >
<img src="https://pycver.gitee.io/ows-pics/imgs/stym_03_01.png">
</div>

<div align="center" >
多选 模型界面（v0.2）
</div>

<div align="center" >
<img src="https://pycver.gitee.io/ows-pics/imgs/stym_03_02.png">
</div>
<div align="center" >
多选 模型操作与转换界面（v0.2）
</div>

<div align="center" >
<img src="https://pycver.gitee.io/ows-pics/imgs/stym_03_03.png">
</div>
<div align="center" >
多选 模型转换界面（v0.2）
</div>

<div align="center" >
<img src="https://pycver.gitee.io/ows-pics/imgs/stym_03_04.png">
</div>
<div align="center" >
多选 模型转换与下载界面（v0.2）
</div>

<div align="center" >
<img src="https://pycver.gitee.io/ows-pics/imgs/stym_03_05.png">
</div>
<div align="center" >
模型下载解压界面（v0.2）
</div>

❗ 注：`tflite`和`tfjs`需要分开导出；除`CoreML`外，其他`half`导出需要选中`cuda:0`

<h2 align="center">💡项目结构</h2>

```
.
├── streamlit_yolov5_modle2x				# 项目名称
│   ├── models								# YOLOv5官方模型文件
│   ├── model_config						# YOLOv5官方工具包
│   ├── val.py								# YOLOv5官方验证文件
│   ├── export.py							# YOLOv5官方导出文件
│   ├── __init__.py							# 初始化文件
│   ├── app_01.py							# 单选，单个模型转换和下载
│   ├── app_02.py							# 多选，多项模型转换和打包下载
│   ├── app_03.py							# 多选，多项模型转换和打包下载
│   ├── LICENSE								# 项目许可
│   ├── CodeCheck.md						# 代码检查
│   ├── .gitignore							# git忽略文件
│   ├── setup.cfg							# pre-commit CI检查源配置文件
│   ├── .pre-commit-config.yaml				# pre-commit配置文件
│   ├── yolov5_pytorch_gpu.md				# YOLOv5 PyTorch GPU安装教程
│   ├── README.md							# 项目说明
│   └── requirements.txt					# 脚本依赖包
```

<h2 align="center">🔥安装教程</h2>

### ✅ 第一步：创建conda环境

```shell
conda create -n yolo python==3.8
conda activate yolo # 进入环境
```

### ✅ 第二步：克隆

```shell
git clone https://gitee.com/CV_Lab/streamlit_yolov5_modle2x.git
```

### ✅ 第三步：安装Streamlit YOLOv5 Model2X依赖

```shell
cd streamlit_yolov5_modle2x
pip install -r ./requirements.txt
# 注：requirements.txt中onnxruntime-gpu、tensorflow、nvidia-pyindex和nvidia-tensorrt均需要在GPU模式下安装
```

❗ 注意：yolov5默认采用pip安装PyTorch GPU版，如果采用官网安装**PyTorch GPU**版，参见[YOLOv5 PyTorch GPU安装教程](./yolov5_pytorch_gpu.md)

<h2 align="center">⚡使用教程</h2>

### 💡 多选，多个模型转换和下载

```shell
streamlit run app_04.py # v0.3 推荐（适用于cuda:0）
streamlit run app_03.py # v0.2 推荐（适用于cpu）
streamlit run app_02.py # v0.1
```

### 💡 单选，单个模型转换和下载

```shell
streamlit run app_01.py # v0.1
```

| 编号 |                             格式                             |     参数      |           模型            |     用途     |
| :--: | :----------------------------------------------------------: | :-----------: | :-----------------------: | :----------: |
|  01  |               [PyTorch](https://pytorch.org/)                |       -       |       `yolov5s.pt`        |      -       |
|  02  |   [TorchScript](https://pytorch.org/docs/stable/jit.html)    | `torchscript` |   `yolov5s.torchscript`   |    移动端    |
|  03  |                   [ONNX](https://onnx.ai/)                   |    `onnx`     |      `yolov5s.onnx`       |     通用     |
|  04  |    [OpenVINO](https://docs.openvino.ai/latest/index.html)    |  `openvino`   | `yolov5s_openvino_model/` |   边缘 云    |
|  05  |      [TensorRT](https://developer.nvidia.com/tensorrt)       |   `engine`    |     `yolov5s.engine`      |   边缘计算   |
|  06  |        [CoreML](https://github.com/apple/coremltools)        |   `coreml`    |     `yolov5s.mlmodel`     |    Apple     |
|  07  | [TensorFlow SavedModel](https://www.tensorflow.org/guide/saved_model) | `saved_model` |  `yolov5s_saved_model/`   | 完整的TF模型 |
|  08  | [TensorFlow GraphDef](https://www.tensorflow.org/api_docs/python/tf/Graph) |     `pb`      |       `yolov5s.pb`        |   数据流图   |
|  09  |      [TensorFlow Lite](https://www.tensorflow.org/lite)      |   `tflite`    |     `yolov5s.tflite`      |    移动端    |
|  10  | [TensorFlow Edge TPU](https://coral.ai/docs/edgetpu/models-intro/) |   `edgetpu`   | `yolov5s_edgetpu.tflite`  |   边缘计算   |
|  11  |        [TensorFlow.js](https://www.tensorflow.org/js)        |    `tfjs`     |   `yolov5s_web_model/`    |     web      |
|  12  |       [PaddlePaddle](https://www.paddlepaddle.org.cn/)       |   `paddle`    |  `yolov5s_paddle_model`   |              |

❗ 注：参考官方文档：https://github.com/ultralytics/yolov5/releases/tag/v6.1

### [❓相关问题解决办法](./QA.md)

❗ 注：在运行程序时可能会遇到的问题与解决办法

### 💬 技术交流

- 如果你发现任何Streamlit YOLOv5 Model2X存在的问题或者是建议, 欢迎通过[Gitee Issues](https://gitee.com/CV_Lab/streamlit_yolov5_modle2x/issues)给我提issues。
- 欢迎加入CV Lab技术交流群

<div align="center" >
<img src="https://pycver.gitee.io/ows-pics/imgs/qq_group.jpg" width="20%">
</div>