yolov5-export-to-raspberry-pi-mnn

KO | EN

gitlite — search

#javascript #python #hacktoberfest #react #ai #typescript #llm #go #golang #android #machine-learning #rust #deep-learning #linux

yolov5-export-to-raspberry-pi-mnn

★ 9 Open GitHub ↗

No description available.

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# Export YOLOv5 to run on Raspberry Pi
Export processing consists of two steps: 
1️⃣ Convert Pytorch model weights to MNN model weights. 
2️⃣ Run the inference on Raspberry Pi. 
**You can compare inference time of YOLOv5 model on two frameworks MNN and Pytorch in my [Google Colab](https://colab.research.google.com/drive/1V4wzynFtBEPsQk4bmmgbbSUZt-_6s69G?usp=sharing)** [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1V4wzynFtBEPsQk4bmmgbbSUZt-_6s69G?usp=sharing) (👍👍👍***Open and run on Google Chrome recommended***).

## Documentation
ℹ️ MNN is a lightweight deep neural network inference engine. 
🔎 You can find more information about MNN in [here](https://www.yuque.com/mnn/en/about). 
🔎 MNN github repository in [here](https://github.com/alibaba/MNN).

## Requirements
👍 python>=3.6 is required.

## Installation
### Step 1: Convert Pytorch model weights to MNN model weights

**If you don't want to install anything on your system then use this [Google Colab](https://colab.research.google.com/drive/1CpV_RTNJamhMpFLT4tW2gBHB41bWaACp?usp=sharing) (*Recommended*).**  [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1CpV_RTNJamhMpFLT4tW2gBHB41bWaACp?usp=sharing) (👍👍👍***Open and run on Google Chrome recommended***).

**And if you want to perform the conversion on your system then follow bellow instructions:**

📣 I recommend to create a new conda environment (python version 3.6 recommended):

```bash
$ conda create -n yolov5_conversion python=3.6
$ conda activate yolov5_conversion
```

➡️ Then run below commands and replace **yolov5s.pt** with your own model weights in path **weights/pt/** and also change **yolov5s.yaml** in path **models/** accordingly.

```bash
$ git clone https://github.com/AnhPC03/yolov5.git
$ cd yolov5
$ pip install -r requirements.txt
$ bash export_mnn.sh yolov5s 640
```
✅ With ***yolov5s*** is model name and ***640*** is input size of your Pytorch model. 
✅ After you run above commands, you will see **successfully message**. And you can find MNN converted model in path **weights/mnn/**. 
✅ Attention about model quantization: The size of MNN model weight is much smaller than origin Pytorch model weight because of using `--weightQuantBits 8` in **export_mnn.sh** file. This reduced model size while also improving CPU and hardware accelerator latency, with little degradation in model accuracy. If you want to keep fully model accuracy, feel free to delete `--weightQuantBits 8` in **export_mnn.sh** file. 
✅ Because of running on Raspberry Pi, so I decided to quantize my model.

### Step 2: Run the inference on Raspberry Pi
⚙️ **Setup**

📣 If you **don't want** to install virtual environment into your Raspberry Pi, feel free to **skip** these below commands. 
Otherwise I recommend you creat a virtual environment (python version>=3 is required):

```bash
$ sudo pip install virtualenv
$ virtualenv mnn_raspberry_pi
$ source mnn_raspberry_pi/bin/activate
```

➡️ Follow below steps to install minimum required environment for converting Pytorch to MNN model weight file:

```bash
$ git clone https://github.com/AnhPC03/yolov5-export-to-cpu-mnn.git
$ cd yolov5-export-to-cpu-mnn
$ pip3 install -r requirements.txt
```
✅ Replace content of **classes.txt** file with your classes when you trained your Pytorch model.

🎉 **Run inference** 
🍻 *Result will be saved to **results/** folder*
```bash
$ python3 inference/run_mnn_detector.py \
 --weights path/to/your/mnn/weight \
 --source 0 # webcam
 file.jpg # image 
 file.mp4 # video
 path/ # directory
 'https://youtu.be/NUsoVlDFqZg' # YouTube video
 'rtsp://example.com/media.mp4' # RTSP, RTMP, HTTP stream
```
✅ With *path/to/your/mnn/weight* is path to MNN model weight which you just converted in the above step. 
✅ You can use --nodisplay to do not display image or webcam while inference. Or --nosave to do not save inference results. 
✅ **For example**: my MNN model weight in ***yolov5-export-to-cpu-mnn/weights/yolov5s.mnn***. Then I run inference on images in ***inference/images/*** folder as below:
```bash
$ python3 inference/run_mnn_detector.py --weights weights/yolov5s.mnn --source inference/images
```

yolov5-export-to-raspberry-pi-mnn

Explore Similar Repositories

Was this content helpful?

Recent Feedback

Download README