Silero VAD: pre-trained enterprise-grade Voice Activity Detector

A curated list of awesome inference deployment framework of artificial intelligence (AI) models. OpenVINO, TensorRT, MediaPipe, TensorFlow Lite, TensorFlow Serving, ONNX Runtime, LibTorch, NCNN, TNN, MNN, TVM, MACE, Paddle Lite, MegEngine Lite, OpenPPL, Bolt, ExecuTorch.

Base on tensorrt version 8.2.4, compare inference speed for different tensorrt api.

Easy-to-use danbooru anime image classification model

基于 ResNet 的花卉分类识别系统。A ResNet-based flower classification and recognition system.

Easy to install image and video colorization using onnx converted deoldify model

Comparing PyTorch, JIT and ONNX for inference with Transformers

Babylon.cpp is a C and C++ library for grapheme to phoneme conversion and text to speech synthesis. For phonemization a ONNX runtime port of the DeepPhonemizer model is used. For speech synthesis VITS models are used. Piper models are compatible after a conversion script is run.

Keras/Tensorflow Neural Network Conversion to ONNX and Inference with ONNX Runtime

Run ONNX machine learning models on AWS Lambda

A Flask app that detects table using ONNX model exported from YOLOv7

Enterprise multi-agent framework for secure, borderless data collaboration with zero-trust and federated learning-lightweight edge-ready.

🍡 Toolkit for Distinguishing Anime from Real Images With No Torch.

The Deep Learning approach to classifying Normal Person heartbeat, abnormal heartbeat & Myocardial Infarction.

a discord bot that helps users recycle and reuse

PyTorch super-resolution model (OverNet) with RGB support and ONNX exporter (OverNet: Lightweight Multi-Scale Super-Resolution with Overscaling Network (WACV 2021))

Faster large mini-batch distributed training w/o. squeezing devices

Investigating a neural network response to input parameters using sensitivity analysis techniques.