LAMDA-CL/PyCIL

Health v2 · maintenance only

Flags: no_license

Adoption not part of the score

1098 stars · 162 forks observed · 2026-08-28

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

PyCIL is a PyTorch-based Python toolbox for class-incremental learning, implementing the largest collection of CIL methods for reproducible research. It provides standardized benchmarks, reproduced results, and a common framework for developing and comparing continual learning algorithms.

Use cases

• reproduce class-incremental learning baselines
• benchmark continual learning methods in pytorch
• implement a new class-incremental learning algorithm
• study catastrophic forgetting in deep networks
• run lifelong learning experiments on standard datasets
• compare state-of-the-art incremental learning methods

When to choose

• you need a comprehensive, reproducible collection of class-incremental learning methods
• you want a standardized PyTorch framework for continual learning research
• you need benchmark results to compare against published CIL baselines

When to avoid

• you need general-purpose continual learning beyond class-incremental settings
• you want a production inference system rather than a research toolbox
• you work outside PyTorch or need non-Python tooling

Facets

library · maturity active

machine-learning deep-learning benchmarking machine-learning deep-learning python class-incremental-learning continual-learning lifelong-learning pytorch reproducible-research open-world-recognition algorithms gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="LAMDA-CL/PyCIL")