Skip to content
Categorías de proyectos

Aprendizaje automático · GitHub

Explora herramientas para entrenar, evaluar y ejecutar modelos, y compara el interés de la comunidad.

Proyectos útiles de GitHub

12,809 proyectos
999estrellas
open-metric-learning preview

Metric learning and retrieval pipelines, models and zoo.

  • Logginglogger = TensorBoardPipelineLogger() logger = NeptunePipelineLogger() logger = WandBPipelineLogger() logger = MLFlowPipelineLogger() logger = ClearMLPipelineLogger() - PMLfrom pytorch_metric_learning import losses criterion = losses.TripletMarginLoss(0.2, "all") pred = ViTExtractor()(data) criterion(pred, gts)

familiar

oncoray

31estrellas

Repository for the familiar R-package. Familiar implements an end-to-end pipeline for interpretable machine learning of tabular data.

OneScience

onescience-ai

50estrellas
OneScience preview

A Python toolkit of deep learning models for AI4Science: earth systems, life sciences, CFD, structural mechanics, and materials chemistry. GPU + DCU ready.

ir-py

onnx

54estrellas
ir-py preview

Efficient in-memory representation for ONNX, in Python

  • Full ONNX spec support: all valid models representable by ONNX protobuf, and a subset of invalid models (so you can load and fix them).
  • Low memory footprint: mmap'ed external tensors; unified interface for ONNX TensorProto, Numpy arrays and PyTorch Tensors etc. No tensor size limitation. Zero copies.

onnxsim

onnxsim

4,420estrellas
onnxsim preview

Simplifica tu modelo ONNX

  • Shape inference. Propagates tensor shapes through the graph — including partial shape evaluation via ONNX data propagation — to unlock more folding.
  • Correctness checking. Optionally validates the simplified model against the original on N random inputs (the positional check_n argument, with configurable --check-rtol/--check-atol). Choose how the generated inputs are filled with --input-fill (Python: input_fill=): random (uniform [0, 1), the default), ones, zeros or arange.

trackforge

onuralpszr

37estrellas

Unified, high-performance computer vision tracking library

  • 🚀 Native Rust Core Blazingly fast tracking (< 1ms/frame for ByteTrack) with full memory safety
  • 🐍 Python Bindings First-class pip install trackforge support via PyO3