stared/livelossplot

Health v2 · maintenance only

Adoption not part of the score

1319 stars · 141 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

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

library · maturity stable

data-visualization machine-learning deep-learning deep-learning data-visualization machine-learning python jupyter-notebook keras pytorch training-monitoring loss-plotting callbacks jupyter

Member repositories

For agents

markdown · JSON · MCP: product_card(name="stared/livelossplot")