# yolov5-tensorrt

**Repository Path**: wangjc5736/yolov5-tensorrt

## Basic Information

- **Project Name**: yolov5-tensorrt
- **Description**: 用TensorRT和Numpy编写的Yolov5推理。在【Nvidia Jetson】设备上运行，无需依赖任何pytorch / torchvision。
- **Primary Language**: Unknown
- **License**: Not specified
- **Default Branch**: master
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 1
- **Forks**: 3
- **Created**: 2020-08-22
- **Last Updated**: 2022-03-14

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

# yolov5-tensorrt 

> port pytorch/onnx yolov5 model to run on a Jetson Nano

`ipynb` is for testing pytorch code and exporting onnx models using Google Colab

`python` code runs numpy/tensorrt implementation on Jetson Nano 

```
├── python
│   ├── lib
|       ├── demo.py
|       ├── Processor.py
|       ├── Visualizer.py
|       ├── classes.py
|       └── models
|           ├── yolov5s-simple-32.trt
|           ├── yolov5s-simple-16.trt
|           └── yolov5s-simple.onnx
│   └── export_tensorrt.py
```

- [x] convert yolov5 onnx model to tensorrt
- [x] pre-process image 
- [x] run inference against input using tensorrt engine
- [x] post process output (forward pass)
- [x] apply nms thresholding on candidate boxes
- [x] visualize results

___

| model  |  fp precision  | input size |  time (ms)   |
| ------------- | ------------- | ---------- | ---- |
| small-simple  |  32  |  640x640x3  | 15.46 |
| small-simple  |  16  |  640x640x3  | 9.47  |


____

### Object Probability

![](docs/object_grids.png)