Edge Impulse Experts / Hi-res_hi-speed_counting_FOMO_720x720
Object Detection - FOMO in 720x720 pixels with 60fps camera - Deploy in TensorRT library that optimize GPU in Jetson Nano
About this project
After PIzza QC with Jetson Nano project, I want to try further with much more objects with higher camera resolutions (720x720 pixels with 60fps) and high speed conveyor belt. Basicaly explore capability of FOMO models that have been optimized with the TensorRT library for the GPU to the max. In this project, the production line / conveyor belt will run very fast with lots of small objects with random position and the number of objects will be counted live.
Download block output
Title | Type | Size | |
---|---|---|---|
Image training data | NPY file | 22 windows | |
Image training labels | JSON file | 22 windows | |
Image testing data | NPY file | 5 windows | |
Image testing labels | JSON file | 5 windows | |
Object detection model | TensorFlow Lite (float32) | 81 KB | |
Object detection model | TensorFlow Lite (int8 quantized) | 55 KB | |
Object detection model | Model evaluation metrics (JSON file) | 3 KB | |
Object detection model | TensorFlow SavedModel | 186 KB | |
Object detection model | Keras h5 model | 88 KB |
Clone project
You are viewing a public Edge Impulse project. Clone this project to add data or make changes.
Summary
Data collected
27 itemsProject info
Project ID | 207728 |
License | Apache 2.0 |