Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.

Awesome Lists | Featured Topics | Projects

https://github.com/nobuotsukamoto/tflite-cv-example

TensorFlow Lite, Coral Edge TPU samples (Python/C++, Raspberry Pi/Windows/Linux).
https://github.com/nobuotsukamoto/tflite-cv-example

coral deeplab detection edge-tpu edgetpu segmentation tensorflow-lite

Last synced: about 5 hours ago
JSON representation

TensorFlow Lite, Coral Edge TPU samples (Python/C++, Raspberry Pi/Windows/Linux).

Host: GitHub
URL: https://github.com/nobuotsukamoto/tflite-cv-example
Owner: NobuoTsukamoto
License: mit
Created: 2019-03-13T12:48:44.000Z (almost 6 years ago)
Default Branch: master
Last Pushed: 2024-08-24T23:22:58.000Z (4 months ago)
Last Synced: 2024-12-15T07:05:36.707Z (7 days ago)
Topics: coral, deeplab, detection, edge-tpu, edgetpu, segmentation, tensorflow-lite
Language: Python
Homepage:
Size: 56.2 MB
Stars: 120
Watchers: 5
Forks: 15
Open Issues: 1
Metadata Files:
- Readme: README.md
- License: LICENSE

Awesome Lists containing this project

README

        # TensorFlow Lite samples.

## About

TensorFlow Lite samples (Python/C++, Raspberry Pi/VisionFive 2/Windows/Linux).

 - CPU(XNNPACK) inference

 - Coral Edge TPU Delegate

 - GPU Delegate 

## List of samples.

| Name | Language | Description | API | OS |

|:---|:---|:---|:---|:---|

|[Camouflage](camouflage)| Python | Object detection and camouflage objects by PiCamera. | PyCoral | Linux
Windows |

|[Classify](classify) | Python | Image classifilcation by PiCamera or Video Capture.| TF-Lite
PyCoral | Linux
Windows |

|[CenterNet](centernet)|Python
C++|CenterNet on-device with TensorFlow Lite.|TF-Lite|Liux
Windows|

| [DeepLab](deeplab) | Python
C++ | Semantic Segmentation using DeepLab v3. | TF-Lite
EdgeTPU API | Linux
Windows |

| [Object detection](detection) | Python
C++
VC++ | Object detection by PiCamera or Video Capture. | TF-Lite
PyCoral | Linux
Windows |

| [U-Net MobileNet v2](segmentation) | Python | Image segmentation model U-Net MobileNet v2. | TF-Lite | Linux
Windows 

| [Super resolution](super_resolution) | Python | Super resolution using ESRGAN. | TF-Lite | Linux
Windows |

| [YOLOX](yolox/python) | Python | YOLOX with TensorFlow Lite. | TF-Lite | Linux
Windows |

| [DeepLab V3+ EdgeTPUV2 and AutoSeg EdgeTPU](deeplab_edgetpu2) | Python | DeepLab V3+ EdgeTPUV2 and AutoSeg EdgeTPU with TensorFlow Lite. | TF-Lite
EdgeTPU | Linux
Windows |

| [FFNet ](ffnet) | C++ | VisionFive 2 TensorFlow Lite GPU Delegate FFNet | TF-Lite
GPU delegate | Linux |

## Images

|Object detection|Camouflage|DeepLab|

|:--:|:--:|:--:|

|![detection](detection/g3doc/img/output.gif)|![camouflage](camouflage/g3doc/img/output.gif)|![deeplab](deeplab/g3doc/img/output.gif)|

|Segmentation|CenterNet|YOLOX|

|:--:|:--:|:--:|

|![segmentation](segmentation/g3doc/segmentation.gif)|![centernet](centernet/g3doc/img/centernet.gif)|![yolox](yolox/g3doc/yolox.gif)|

|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
[![](https://img.youtube.com/vi/-F9R51vFOS8/mqdefault.jpg)](https://www.youtube.com/watch?v=-F9R51vFOS8)|YouTube Link
[![](https://img.youtube.com/vi/QDNdEaW8Z8U/mqdefault.jpg)](https://www.youtube.com/watch?v=QDNdEaW8Z8U)|YouTube Link
[![](https://img.youtube.com/vi/1SAccRvKuFM/mqdefault.jpg)](https://www.youtube.com/watch?v=1SAccRvKuFM)|

## Environment

- 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

## Installation

- OpenCV with OpenCV's extra modules(3.4.5 or higher)

- TensorFlow Lite Runtime [(Python quickstart)](https://www.tensorflow.org/lite/guide/python).

- Edge TPU Python library [(Get started with the USB Accelerator)](https://coral.withgoogle.com/tutorials/accelerator/).

## Reference

- [Get started with the USB Accelerator](https://coral.withgoogle.com/tutorials/accelerator/)

- [TensorFlow models on the Edge TPU](https://coral.withgoogle.com/tutorials/edgetpu-models-intro/#model-requirements)

- [Models Built for the Edge TPU](https://coral.withgoogle.com/models/)

- [Megvii-BaseDetection/YOLOX](https://github.com/Megvii-BaseDetection/YOLOX)

- [PINTO0309/PINTO_model_zoo](https://github.com/PINTO0309/PINTO_model_zoo)