# LAMDA-CL/PyCIL

PyCIL: A Python Toolbox for Class-Incremental Learning

Repository: https://github.com/LAMDA-CL/PyCIL
Canonical: https://ross.abutalabs.com/products/pycil
Language: Python
License: NOASSERTION
License Family: other
Topics: incremental-learning, lifelong-learning, continual-learning, machine-learning, reproducible-research, deep-learning, pytorch, open-environment-recognition, open-world, representation-learning
Last push: 2026-01-29T04:40:21+00:00

## Health v2 (maintenance only)
Score: 52/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 64, release rhythm 8, longevity 100
- inputs: {"age_days": 1714, "days_push": 216, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1098, forks 162 (observed 2026-08-28T04:03:34.804492+00:00)

## What it is
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
- artifact type: library
- maturity: active
- function: machine-learning, deep-learning, benchmarking
- domain: machine-learning, deep-learning
- platform: python
- tags: class-incremental-learning, continual-learning, lifelong-learning, pytorch, reproducible-research, open-world-recognition, algorithms, gpu

## Member repositories
- LAMDA-CL/PyCIL (main) score 52

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:34.804492+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 2026-08-30T06:46:12.949608+00:00, confidence not recorded.
  - readme: https://github.com/LAMDA-CL/PyCIL (fetched 2026-08-28T04:03:34.804492+00:00, sha 897d6ebfd200)
- Data as of 2026-08-30T08:39:29.467469+00:00.