Name | Language | Description | Backend | OS |
---|---|---|---|---|
Benchmark | Python | TensorFlow Lite Object detection benchmark with OpenCV. | TensorFLow Lite (EdgeTPU delegate) | Windows, Linux |
Capture using PyCoral | Python | Object detection for camera or video capture using OpenCV and PyCoral API. | PyCoral | Windows, Linux |
PiCamera using PyCoral | Python | Object detection for camera capture using PiCamera and PyCoral API. | PyCoral | Raspberry Pi |
Capture using TensorFlow Lite | Python | Object detection for camera or video capture using OpenCV and TensorFlow Lite API. | TensorFlow Lite (EdgeTPU delegate) | Windows, Linux |
C++ CMake | C++ | C++ CMake Project. Object detection for camera or video capture using OpenCV and TensorFlow Lite API. |
TensorFlow Lite (EdgeTPU delegate) | Windows, Linux |
VC++ | Visual C++ | Visual Studio 2019 (VC++) Sample. TensorFlow Lite and TensorFlow Lite EdgeTPU delegate with Visual Studio. |
TensorFlow Lite (EdgeTPU delegate) | Windows |
This notebook converts the pre-trained model of "TensorFlow 1 Detection Model Zoo" into TF-Lite or Edge TPU Model.
Model Name | Output model type |
---|---|
ssd_mobilenet_v2_coco | INT8, EdgeTPU |
ssd_mobilenet_v3_large_coco | FP32 |
ssd_mobilenet_v3_small_coco | FP32 |
ssd_mobilenet_v2_mnasfpn_coco | FP32 |
ssdlite_mobiledet_cpu_coco | FP32 |
ssdlite_mobiledet_edgetpu_coco | INT8, EdgeTPU |
ssd_mobilenet_edgetpu_coco | INT8, EdgeTPU |