Real-time face parsing and facial semantic segmentation with BiSeNet - PyTorch training, ONNX export, pretrained weights.
-
Updated
Apr 14, 2026 - Python
8000
Real-time face parsing and facial semantic segmentation with BiSeNet - PyTorch training, ONNX export, pretrained weights.
Serving AI/ML models in the open standard formats PMML and ONNX with both HTTP (REST API) and gRPC endpoints
Pre-trained image models using ONNX for fast, out-of-the-box inference.
A type-safe, lightweight, modern, and performant binding Java binding of Microsoft's ONNX Runtime
YOLOv8 trained on CrowdHuman dataset and supports ONNX Runtime Inference for Image, Video and Webcam
Python scripts performing object detection using the YOLOv11 model in ONNX.
Create&Synthesis&Modify your AI-powered Virtual Singer. Powered by SoulX-Singer
XMem ONNX Inference
Machine learning model for predicting the drone deployment for the smart agriculture use case. Developed in collaboration between University College Dublin (UCD) and Augmenta (acquired by CNH Industrial) for the EU MLSysOps project.
Simple, safe, and fast common subexpression elimination in ONNX models
ONNX implementation of Pyannote Speaker Diarization Community-1 pipeline.
Run arbitrary ONNX image-processing models directly inside ComfyUI. ComfyUI-ONNX provides a flexible ONNX Runtime inference node with automatic model discovery, graph inspection, dynamic input/output handling, CUDA acceleration with CPU fallback, FP16 support, image batching, tiled inference, session caching, model favorites, metadata inspection
🐱 Kitten TTS Studio using local onnx models TTS Offline
A Deep Reinforcement Learning (PPO) model exported for optimizing VM placement and lifecycle management. Developed by UCD for the EU MLSysOps project.
Classify 160 different tags from scifi and fantasy questions.
Classify movie genre from its summary.
An AI framework for Neural Networks written purely in go with no dependencies
Machine learning model for noise prediction in smart city lampposts, developed in collaboration between by University College Dublin (UCD) and Ubiwhere for the EU MLSysOps project.
A content recommendation engine using two-tower neural networks, reactive Java, and event-driven architecture.
Add a description, image, and links to the onnx-inference topic page so that developers can more easily learn about it.
To associate your repository with the onnx-inference topic, visit your repo's landing page and select "manage topics."