YOLOv5 🚀 in PyTorch > ONNX > CoreML > TFLite
-
Updated
May 28, 2024 - Python
YOLOv5 🚀 in PyTorch > ONNX > CoreML > TFLite
Self-Created Tools to convert ONNX files (NCHW) to TensorFlow/TFLite/Keras format (NHWC). The purpose of this tool is to solve the massive Transpose extrapolation problem in onnx-tensorflow (onnx-tf). I don't need a Star, but give me a pull request.
🚀 Accelerate training and inference of 🤗 Transformers and 🤗 Diffusers with easy to use hardware optimization tools
Recyclr is a revolutionary waste management app. It uses advanced Object Detection to identify and classify 91 waste items in real-time, then notifies nearby agencies for automatic pickup with precise geolocation. ♻️🗑️📍
A 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), EdgeTPU, CoreML.
Bharat Leaf Lens is your pocket guide to identifying medicinal plants in India. No user images are stored in our database, ensuring privacy.
⚡ TensorFlowASR: Almost State-of-the-art Automatic Speech Recognition in Tensorflow 2. Supported languages that can use characters or subwords
Highly optimized inference engine for Binarized Neural Networks
Seeed SenseCraft Model Assistant is an open-source project focused on embedded AI. 🔥🔥🔥
Convert TensorFlow, Keras, Tensorflow.js and Tflite models to ONNX
Want a faster ML processor? Do it yourself! -- A framework for playing with custom opcodes to accelerate TensorFlow Lite for Microcontrollers (TFLM). . . . . . Online tutorial: https://google.github.io/CFU-Playground/ For reference docs, see the link below.
Quantization of Models : Post-Training Quantization(PTQ) and Quantize Aware Training(QAT)
Deep Learning Inference benchmark. Supports OpenVINO™ toolkit, Caffe, TensorFlow, TensorFlow Lite, ONNX Runtime, OpenCV DNN, MXNet, PyTorch, Apache TVM, ncnn, etc.
🔥 High-performance TensorFlow Lite library for React Native with GPU acceleration
🍅🍅🍅YOLOv5-Lite: Evolved from yolov5 and the size of model is only 900+kb (int8) and 1.7M (fp16). Reach 15 FPS on the Raspberry Pi 4B~
Welcome to our cutting-edge Real-Time Object Detection app, built using Flutter and TensorFlow Lite (TFLite). This application is designed to provide an intuitive and efficient way to detect objects in real-time using your device's camera. Whether you are a developer, a tech enthusiast, or simply curious about AI-powered applications, our app offer
Pytorch to Keras/Tensorflow conversion made intuitive
虚拟爱抖露(アイドル)共享计划, 是基于单目RGB摄像头的人眼与人脸特征点检测算法, 在实时3D面部捕捉以及模型驱动领域的应用.
Add a description, image, and links to the tflite topic page so that developers can more easily learn about it.
To associate your repository with the tflite topic, visit your repo's landing page and select "manage topics."