Aprendizaje automático · GitHub

Strongly typed configurable building blocks for A/B testing ML research.

PyTorch implementation of the InfoNCE loss for self-supervised learning.

Enhanced stain normalization for histopathology images with batch processing support. Optimized for CPU, GPU (CUDA), and MPS (Apple Silicon) devices.

• Multiple algorithms: Histogram Matching, Reinhard, and Macenko normalization
• Torch backends: torch (CPU / CUDA / MPS) and optional torch_cuda compiled kernels

A handbook for ML built on answers.

Self-hosted drop-in replacement for Face++ Compare API — powered by DeepFace/Facenet512

Pre-trained models, data, code & materials from the paper "ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness" (ICLR 2019 Oral)

Open datasets for training and benchmarking AI and robotic systems in agriculture and off-road environments

List of resources for mineral exploration and machine learning, generally with useful code and examples.

• These you can reproduce the output geospatially from the data given.

Pytorch implementation of ResUnet and ResUnet ++

DeepLabv3+ built in TensorFlow

AMD's graph optimization engine.

FlyDSL is the Python front‑end of the project: a Flexible Layout Python DSL for expressing tiling, partitioning, data movement, and kernel structure at a high level.

A fully functional and simple Machine Learning library made entirely from scratch with Python.

⚡ In-Memory Vector Search Engine & HNSW ANN Graph in Java 21 Loom. Sub-millisecond KNN retrieval, 8-bit scalar quantization (SQ8), 16,000+ QPS.

Babel Street Analytics Client Library for Python