TensorFlow Lite samples (Python/C++, Raspberry Pi/VisionFive 2/Windows/Linux).
- CPU(XNNPACK) inference
- Coral Edge TPU Delegate
- GPU Delegate
| Name | Language | Description | API | OS |
|---|---|---|---|---|
| Camouflage | Python | Object detection and camouflage objects by PiCamera. | PyCoral | Linux Windows |
| Classify | Python | Image classifilcation by PiCamera or Video Capture. | TF-Lite PyCoral |
Linux Windows |
| CenterNet | Python C++ |
CenterNet on-device with TensorFlow Lite. | TF-Lite | Liux Windows |
| DeepLab | Python C++ |
Semantic Segmentation using DeepLab v3. | TF-Lite EdgeTPU API |
Linux Windows |
| Object detection | Python C++ VC++ |
Object detection by PiCamera or Video Capture. | TF-Lite PyCoral |
Linux Windows |
| U-Net MobileNet v2 | Python | Image segmentation model U-Net MobileNet v2. | TF-Lite | Linux Windows |
| Super resolution | Python | Super resolution using ESRGAN. | TF-Lite | Linux Windows |
| YOLOX | Python | YOLOX with TensorFlow Lite. | TF-Lite | Linux Windows |
| DeepLab V3+ EdgeTPUV2 and AutoSeg EdgeTPU | Python | DeepLab V3+ EdgeTPUV2 and AutoSeg EdgeTPU with TensorFlow Lite. | TF-Lite EdgeTPU |
Linux Windows |
| FFNet | C++ | VisionFive 2 TensorFlow Lite GPU Delegate FFNet | TF-Lite GPU delegate |
Linux |
| Object detection | Camouflage | DeepLab |
|---|---|---|
 |
 |
 |
| Segmentation | CenterNet | YOLOX |
|---|---|---|
 |
 |
 |
| DeepLab V3+ EdgeTPUV2 and AutoSeg EdgeTPU | VisionFive 2 TensorFlow Lite GPU Delegate FFNet46NS CCC Mobile Pre-Down Fused-Argmax |
VisionFive 2 TensorFlow Lite GPU Delegate EfficientDet-Lite0 |
|---|---|---|
YouTube Link |
YouTube Link |
YouTube Link |
- Coral Edge TPU USB Accelerator
- Raspberry Pi (3 B+ / 4) + PiCamera or UVC Camera
- Dev Board
- VisionFive 2
- x64 PC(Windows or Linux) + Video file or UVC Camera
- Python3
- OpenCV with OpenCV's extra modules(3.4.5 or higher)
- TensorFlow Lite Runtime (Python quickstart).
- Edge TPU Python library (Get started with the USB Accelerator).