5 रिपॉजिटरी
Awesome GitHub RepositoriesGraph Neural Network Implementations
Implementations of neural network architectures designed for non-Euclidean data and geometric deep learning.
Distinct from Neural Network Implementations: Candidates focus on general neural network implementations; this specifically targets graph-structured data.
Explore 5 awesome GitHub repositories matching artificial intelligence & ml · Graph Neural Network Implementations. Refine with filters or upvote what's useful.
Awesome Graph Neural Network Implementations GitHub Repositories
AI के साथ बेहतरीन रिपॉजिटरी खोजें।हम AI का उपयोग करके सबसे सटीक रिपॉजिटरी खोजेंगे।
- nvidia/deeplearningexamples
NVIDIA/DeepLearningExamples
14,819GitHub पर देखेंThis project is a collection of optimized scripts, deployment patterns, and reference implementations designed for scaling and accelerating state-of-the-art AI models. It serves as a multi-domain model zoo and a distributed training framework, providing PyTorch reference implementations for training and deploying models on GPU-accelerated infrastructure. The repository distinguishes itself through an optimization suite focused on NVIDIA GPU hardware, utilizing automatic mixed precision and specialized math modes to increase training speed and throughput. It provides enterprise deployment patt
Provides reference implementations for processing non-Euclidean data and geometric deep learning tasks.
Jupyter Notebookcomputer-visiondeep-learningdrug-discovery - magicleap/supergluepretrainednetwork
magicleap/SuperGluePretrainedNetwork
4,035GitHub पर देखेंयह प्रोजेक्ट इमेज फीचर मैचिंग, स्थानिक संरेखण (spatial alignment) और विज़ुअल लोकलाइज़ेशन के लिए डिज़ाइन किए गए न्यूरल नेटवर्क मॉडल्स और ज्यामितीय टूल्स का एक संग्रह है। यह स्थानीय प्रशिक्षण की आवश्यकता के बिना विरल इमेज फीचर्स के बीच उच्च-सटीक पत्राचार (correspondences) की पहचान करने के लिए एक प्री-ट्रेंड न्यूरल नेटवर्क मॉडल प्रदान करता है। यह सिस्टम एक ग्राफ न्यूरल नेटवर्क मैचर का उपयोग करता है जो इमेज फीचर पॉइंट्स के बीच स्थानिक संबंधों को सीखने के लिए अटेंशन मैकेनिज्म और मैसेज पासिंग का उपयोग करता है। यह फीचर मैचेस को फिल्टर करने और दो कैमरा दृष्टिकोणों के बीच सापेक्ष स्थानिक परिवर्तन की गणना करने के लिए एक RANSAC कैमरा पोज़ एस्टिमेटर को इंटीग्रेट करता है। यह लाइब्रेरी 3D रिकंस्ट्रक्शन वर्कफ़्लो, विज़ुअल लोकलाइज़ेशन और सटीकता व पोज़ एरर मेट्रिक्स के माध्यम से मैचिंग सटीकता के मूल्यांकन सहित कंप्यूटर विज़न क्षमताओं की एक विस्तृत श्रृंखला को कवर करती है। इसमें कीपॉइंट पत्राचार को विज़ुअलाइज़ करने और डाउनस्ट्रीम प्रोसेसिंग के लिए मैचिंग रिजल्ट्स को एक्सपोर्ट करने की यूटिलिटीज भी शामिल हैं।
Uses a graph neural network with message passing to learn spatial relationships and correspondences between image feature points.
Pythondeep-learningfeature-matchinggraph-neural-networks - girafe-ai/ml-course
girafe-ai/ml-course
3,484GitHub पर देखेंThis repository provides a comprehensive educational framework for mastering machine learning and deep learning through a structured curriculum. It integrates theoretical mathematical foundations—including calculus, probability, and linear algebra—with hands-on laboratory implementations that require learners to build algorithms and neural network architectures from scratch. The project distinguishes itself by emphasizing first-principles development, ensuring that students understand the underlying mechanics of backpropagation, layer-wise computation, and model optimization. It covers a broa
Provides foundational resources for applying deep learning techniques to complex graph-structured data.
Jupyter Notebookcomputer-visioncoursedeep-learning - dsgiitr/graph_nets
dsgiitr/graph_nets
1,237GitHub पर देखेंGraph Nets is a graph neural network library and educational toolkit implemented in PyTorch, providing implementations of popular graph representation learning algorithms and research papers. The project covers core graph machine learning tasks including semi-supervised node classification, inductive and unsupervised node embedding generation, and neighborhood feature aggregation. The library supports diverse algorithmic approaches for processing network structures, ranging from shared-parameter graph convolutions and attention-weighted neighborhood aggregation to spectral Chebyshev filtering
Implements popular graph neural network algorithms and research papers using PyTorch for representation learning.
Jupyter Notebookchebyshev-polynomialsdeepwalkgraph-attention-networks - packtpublishing/hands-on-graph-neural-networks-using-python
PacktPublishing/Hands-On-Graph-Neural-Networks-Using-Python
1,044GitHub पर देखेंThis repository serves as an educational resource for implementing graph neural networks using Python. It provides a collection of structured code examples and tutorials designed to guide developers through the process of building and training machine learning models that operate on complex, interconnected datasets. The project covers the core mechanics of graph-based deep learning, including message-passing architectures, feature aggregation, and the stacking of convolutional layers. It demonstrates how to represent non-Euclidean data as static graphs and how to manage memory during training
Constructs and trains machine learning models that process complex data structures through structured code examples and tutorials.
Jupyter Notebook
