# NVIDIA/DeepLearningExamples

State-of-the-Art Deep Learning scripts organized by models - easy to train and deploy with reproducible accuracy and performance on enterprise-grade infrastructure.

Repository: https://github.com/NVIDIA/DeepLearningExamples
Canonical: https://ross.abutalabs.com/products/deeplearningexamples
Language: Jupyter Notebook
License Family: other
Topics: computer-vision, deep-learning, drug-discovery, forecasting, large-language-models, mxnet, paddlepaddle, pytorch, recommender-systems, speech-recognition, speech-synthesis, tensorflow, tensorflow2, translation, nlp
Last push: 2024-08-12T14:01:29+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3045, "days_push": 751, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 14840, forks 3411 (observed 2026-08-28T04:11:07.791415+00:00)

## What it is
A collection of state-of-the-art deep learning model training and deployment scripts from NVIDIA, organized by model and optimized for Tensor Cores on NVIDIA GPUs. It covers computer vision, NLP, speech, recommendation, and forecasting models across PyTorch, TensorFlow, and other frameworks.

## Use cases
- train a model with best performance on NVIDIA GPUs
- deploy deep learning models with TensorRT and Triton
- find reference implementations of state-of-the-art models
- reproduce benchmark accuracy for models like BERT or EfficientNet
- learn how to optimize training with mixed precision and multi-GPU

## When to choose
- you need NVIDIA-optimized reference implementations for training or deploying models
- you want reproducible high-performance examples on Volta, Turing, or Ampere GPUs
- you need multi-GPU or multi-node training recipes

## When to avoid
- you need a production-ready library or API rather than example scripts
- you train on non-NVIDIA hardware
- you need a permissively licensed dependency - the repo has no explicit license

## Facets
- artifact type: learning-resource
- maturity: active
- function: deep-learning, machine-learning, llm-training, benchmarking
- domain: deep-learning, machine-learning, computer-vision, large-language-models, gpu-computing
- platform: python
- tags: nvidia, tensor-cores, pytorch, tensorflow, model-training, inference, triton, tensorrt, example-scripts, gpu, docker, linux

## Member repositories
- NVIDIA/DeepLearningExamples (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:07.791415+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:07:07.999263+00:00, confidence not recorded.
  - readme: https://github.com/NVIDIA/DeepLearningExamples (fetched 2026-08-28T04:11:07.791415+00:00, sha 52324fed3418)
- Data as of 2026-08-30T08:39:29.467469+00:00.