Deploy RT-EDTR with onnx from paddlepaddle framwork and graph cut
-
Updated
May 5, 2023 - Python
Deploy RT-EDTR with onnx from paddlepaddle framwork and graph cut
DGORL: Distributed Graph Optimization based Relative Localization of Multi-Robot Systems
Torch-MIGraphX integrates AMD's graph inference engine with the PyTorch ecosystem.
Tightly-coupled IMU + GNSS RTK on GTSAM factor graphs
High Information Mapper (HiMap), successor of the Lead Optimization Mapper (LOMAP)
Implementation of Least Squares Graph Optimization algorithm for graph-based SLAM.
Symbolic shape inference for ONNX
GPU implementation of Floyd-Warshall and R-Kleene algorithms to solve the All-Pairs-Shortest-Paths(APSP) problem on Graphs. Code includes random graph generators and benchmarking/plotting scripts.
ConsciousDB – Your Vector Database Is the Model
Topology-aware modular quantum layout and abstract routing optimizer for Qiskit. Reduces communication cost and inter-chip hops on multi-chip hardware graphs.
A gravity-inspired physics optimization kernel with a constraint-driven runtime (Ising/QUBO as the description layer).
Waste transport route optimization and visualization for applied mathematical-modeling competition analysis.
Hitting Set Solver
From-scratch graph optimizer for torch.compile: constant folding, CSE and DCE on PyTorch FX graphs.
AI-first open-source graph partitioning and optimization for Python, NetworkX, METIS, KaHIP, and AI agents.
University Course Assignment Optimization
Neural graph optimizer with an immutable Python reference runtime and a native C++/MLIR dialect
A small ML graph compiler: ONNX IR, fusion and folding passes (141 nodes to 32 on resnet18, outputs identical to 1.2e-06), liveness memory planning (13.8MB to 4MB), NumPy runtime verified against onnxruntime
🗄️ Streamline data analysis with ConsciousDB, a vector database that integrates directly with your models for enhanced performance and ease of use.
To associate your repository with the graph-optimization topic, visit your repo's landing page and select "manage topics."