# ilkarman/DeepLearningFrameworks

Demo of running NNs across different frameworks

Repository: https://github.com/ilkarman/DeepLearningFrameworks
Canonical: https://ross.abutalabs.com/products/deeplearningframeworks
Language: Jupyter Notebook
License: MIT
License Family: permissive
Last push: 2022-10-08T00:19:58+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3290, "days_push": 1426, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1651, forks 353 (observed 2026-08-28T04:05:16.980226+00:00)

## What it is
A collection of Jupyter notebooks implementing the same neural network tasks (CNN on CIFAR-10, RNN, etc.) across many deep learning frameworks to serve as a 'Rosetta Stone' for data scientists. It also provides GPU training-time benchmarks for comparing framework performance.

## Use cases
- compare deep learning framework training speed on GPU
- translate my PyTorch knowledge to TensorFlow or MXNet
- learn how to implement a CNN in multiple frameworks
- verify performance of my deep learning installation
- find equivalent API calls across deep learning frameworks
- benchmark Keras vs PyTorch vs TensorFlow on CIFAR-10

## When to choose
- you want side-by-side, same-task code examples across many DL frameworks
- you need GPU performance benchmarks to pick a framework
- you are migrating expertise from one framework to another

## When to avoid
- you need up-to-date examples for modern framework versions (many frameworks like CNTK, Caffe2, Theano are deprecated)
- you want production-ready training pipelines rather than comparison demos
- you need benchmarks on the latest GPU hardware or CUDA versions

## Facets
- artifact type: learning-resource
- maturity: maintenance
- function: deep-learning, benchmarking, machine-learning
- domain: deep-learning, machine-learning, data-science, tutorials
- platform: python, jvm, cloud
- tags: jupyter-notebooks, framework-comparison, rosetta-stone, cifar-10, vgg, gpu-benchmarks, keras, pytorch, tensorflow, mxnet, cntk, caffe2, chainer, julia, r, gpu

## Member repositories
- ilkarman/DeepLearningFrameworks (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:16.980226+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 2026-08-30T03:45:02.183186+00:00, confidence not recorded.
  - readme: https://github.com/ilkarman/DeepLearningFrameworks (fetched 2026-08-28T04:05:16.980226+00:00, sha c0aa4ed19060)
- Data as of 2026-08-30T08:39:29.467469+00:00.