Ecosyste.ms sponsors
An open API service aggregating public data about GitHub Sponsors.
An open API service aggregating public data about GitHub Sponsors.
Hobby programmer. Intel Software Innovator Program member.
Funding Links: https://github.com/sponsors/PINTO0309
In order to use Tensorflow and Tensorflow Lite with low-spec edge devices, I have created a Wheel installer that is not provided by the official website. The Python API of Tensorflow Lite provided by me runs twice as fast as the official one by implementing additional multithreading. Depending on how busy me is, the build work is carried out sequentially within a week each time the latest version is released from the official website. I am an engineer who mainly develops in Python.
[High Performance / MAX 30 FPS] RaspberryPi3(RaspberryPi/Raspbian Stretch) or Ubuntu + Multi Neural Compute Stick(NCS/NCS2) + RealSense D435(or USB Camera or PiCamera) + MobileNet-SSD(MobileNetSSD)…
Language: Python - Stars: 366YoloV3/tiny-YoloV3+RaspberryPi3/Ubuntu LaptopPC+NCS/NCS2+USB Camera+Python+OpenVINO
Language: Python - Stars: 537[5 FPS - 150 FPS] Learning Deep Features for One-Class Classification (AnomalyDetection). Corresponds RaspberryPi3. Convert to Tensorflow, ONNX, Caffe, PyTorch. Implementation by Python + OpenVINO/…
Language: Jupyter Notebook - Stars: 128Prebuilt binary with Tensorflow Lite enabled. For RaspberryPi / Jetson Nano. Support for custom operations in MediaPipe. XNNPACK, XNNPACK Multi-Threads, FlexDelegate.
Language: Shell - Stars: 501Prebuilt binary for TensorFlowLite's standalone installer. For RaspberryPi. A very lightweight installer. I provide a FlexDelegate, MediaPipe Custom OP and XNNPACK enabled binary.
Language: Shell - Stars: 209A repository for storing models that have been inter-converted between various frameworks. Supported frameworks are TensorFlow, PyTorch, ONNX, OpenVINO, TFJS, TFTRT, TensorFlowLite (Float32/16/INT8…
Language: Python - Stars: 3618