# stared/livelossplot

Live training loss plot in Jupyter Notebook for Keras, PyTorch and others

Repository: https://github.com/stared/livelossplot
Canonical: https://ross.abutalabs.com/products/livelossplot
Language: Python
License: MIT
License Family: permissive
Topics: jupyter-notebook, keras, keras-visualization, deep-learning, pytorch
Last push: 2026-07-26T07:29:59+00:00

## Health v2 (maintenance only)
Score: 91/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 94, release rhythm 82, longevity 100
- inputs: {"age_days": 3098, "days_push": 38, "days_rel": 120, "gap_med": 0, "n_releases_24m": 2}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1319, forks 141 (observed 2026-08-28T04:04:21.300330+00:00)

## What it is
A Python library that draws live training loss and metric plots inside Jupyter Notebooks for Keras, PyTorch, and other deep learning frameworks. It integrates via framework callbacks so you can watch each epoch's progress without leaving the notebook.

## Use cases
- plot training loss live in jupyter notebook
- visualize keras training progress per epoch
- monitor pytorch training curves in a notebook
- watch loss and accuracy while training a deep learning model
- lightweight alternative to tensorboard for notebooks
- teach deep learning with live training plots

## When to choose
- you train models in Jupyter and want instant visual feedback per epoch
- you find TensorBoard too heavy or awkward for notebook-based exploration and teaching
- you use Keras, PyTorch, or fastai and want a one-line callback for live plots

## When to avoid
- you need production-grade experiment tracking with dashboards, runs, and team collaboration (use TensorBoard, MLflow, or W&B)
- you train outside notebooks or in headless/CI environments
- you need GPU utilization or system-level monitoring rather than metric curves

## Facets
- artifact type: library
- maturity: stable
- function: data-visualization, machine-learning, deep-learning
- domain: deep-learning, data-visualization, machine-learning
- platform: python
- tags: jupyter-notebook, keras, pytorch, training-monitoring, loss-plotting, callbacks, jupyter

## Member repositories
- stared/livelossplot (main) score 91

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:21.300330+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 2026-08-30T04:47:55.701159+00:00, confidence not recorded.
  - readme: https://github.com/stared/livelossplot (fetched 2026-08-28T04:04:21.300330+00:00, sha a8d1ffe7b390)
  - registry_pypi: https://pypi.org/pypi/livelossplot/json (fetched 2026-08-29T12:06:36.436025+00:00, sha 12f6b8c47b53)
- Data as of 2026-08-30T08:39:29.467469+00:00.