# amaiya/ktrain

ktrain is a Python library that makes deep learning and AI more accessible and easier to apply

Repository: https://github.com/amaiya/ktrain
Canonical: https://ross.abutalabs.com/products/ktrain
Language: Jupyter Notebook
License: Apache-2.0
License Family: permissive
Topics: deep-learning, machine-learning, tensorflow, keras, python, nlp, computer-vision, graph-neural-networks, tabular-data
Last push: 2025-02-06T20:19:28+00:00

## Health v2 (maintenance only)
Score: 25/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 5, release rhythm 8, longevity 100
- inputs: {"age_days": 2765, "days_push": 573, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1268, forks 260 (observed 2026-08-28T04:04:11.501589+00:00)

## What it is
ktrain is a lightweight Python wrapper around TensorFlow Keras that provides pre-canned, low-code models for text, vision, graph, and tabular data. It aims to make deep learning accessible with only a few lines of code for tasks like text classification, NER, and image classification.

## Use cases
- classify text with BERT in a few lines of code
- train a named entity recognition model
- fine-tune transformer models for text regression
- build image classifiers without writing Keras boilerplate
- apply graph neural networks to node classification
- train models on tabular data easily
- learn deep learning as a beginner with simple API

## When to choose
- you want fast, low-code deep learning on TensorFlow Keras
- you need pre-canned models for text, vision, graph, or tabular data
- you are a newcomer who wants accessible ML workflows
- you want fastai-like ergonomics in the TensorFlow ecosystem

## When to avoid
- you need PyTorch instead of TensorFlow
- you require full low-level control over model architecture and training loops
- you need generative question-answering, which moved to the OnPrem.LLM package
- you need production-scale distributed training features

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, deep-learning, nlp, computer-vision, llm-training
- domain: machine-learning, deep-learning, computer-vision, data-science
- platform: python
- tags: keras, tensorflow, text-classification, ner, graph-neural-networks, tabular-data, low-code-ml, fastai-inspired, natural-language-processing

## Member repositories
- amaiya/ktrain (main) score 25

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:11.501589+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 2026-08-30T05:03:36.640686+00:00, confidence not recorded.
  - readme: https://github.com/amaiya/ktrain (fetched 2026-08-28T04:04:11.501589+00:00, sha f41a298dce19)
  - registry_pypi: https://pypi.org/pypi/ktrain/json (fetched 2026-08-29T12:15:29.030209+00:00, sha e6f717ca26a3)
- Data as of 2026-08-30T08:39:29.467469+00:00.