Edge Impulse Experts / NVIDIA_TAO_traffic_analysis
An object detection project that will be used in the Vehicle Traffic Analysis use case which can track object location, speed and direction. To make the process easier, we will use Nvidia TAO pre-trained blocks and will be deployed on Nvidia Jetson Orin Nano.
About this project
NVIDIA TAO test - vehicles detection (counting, tracking speed and direction)
Download block output
| Title | Type | Size | |
|---|---|---|---|
| Image training data | NPY file | 123 windows | |
| Image training labels | JSON file | 123 windows | |
| Image testing data | NPY file | 27 windows | |
| Image testing labels | JSON file | 27 windows | |
| Object detection model | TensorFlow Lite (float32) | 57 MB | |
| Object detection model | TensorFlow Lite (int8 quantized) | 15 MB | |
| Object detection model | ONNX model | 57 MB | |
| Object detection model | NVIDIA TAO NMS attributes | 263 Bytes | |
| Object detection model | NVIDIA TAO original TensorRT model | 57 MB | |
| Object detection model | TensorFlow SavedModel | 53 MB | |
| Object detection model | Model evaluation metrics (JSON file) | - |
Clone project
You are viewing a public Edge Impulse project. Clone this project to add data or make changes.
Summary
Data collected
150 itemsProject info
| Project ID | 310628 |
| License | Apache 2.0 |
