CTrLBenchmark - GitLite

KO | EN

gitlite — search

#python #android #machine-learning #rust #linux #docker #nodejs #java #windows #awesome #kubernetes #awesome-list #openai #open-source

CTrLBenchmark

(★ 117)

Benchmark for Lifelong learning research

파일 탐색기

최종 버전 다운로드 (.zip)

- - __init__.py
  - tree.py
  - utils.py
- - __init__.py
  - concept.py
  - concept_tree.py
- - __init__.py
  - DTD.py
  - image_dataset_tree.py
  - md_tree.py
  - taxonomies.py
- - __init__.py
  - attributes_strategy.py
  - data_strategy.py
  - incremental_strategy.py
  - input_domain_strategy.py
  - label_permutation_strategy.py
  - mixed_strategy.py
  - random_mutation_strategy.py
  - split_strategy.py
  - task_creation_strategy.py
- - __init__.py
  - default_datasets.yaml
  - s_in.yaml
  - s_long.yaml
  - s_minus.yaml
  - s_out.yaml
  - s_pl.yaml
  - s_plus.yaml
- - __init__.py
  - task.py
  - task_generator.py
- - __init__.py
  - identity_transformation.py
  - img_rotations.py
  - noisy_nn_transformation.py
  - rainbow_transformation.py
  - randperm_transformation.py
  - transformation.py
  - transformation_pool.py
  - transformation_tree.py
  - utils.py
- __init__.py
- - conf.py
  - index.rst
  - usage.rst
- Makefile
- __init__.py
- test_ctrl.py
.gitignore
CODE_OF_CONDUCT.md
CONTRIBUTING.md
LICENSE
MANIFEST.in
README.md
setup.py

# 설치 가이드

1. 코드 내려받기

git clone https://github.com/facebookresearch/CTrLBenchmark

깃허브에서 프로젝트 코드 전체를 내 컴퓨터로 내려받습니다.

cd CTrLBenchmark

방금 내려받은 프로젝트 폴더 안으로 이동합니다.

2. Python

쉬움 추천

사전 준비물

Git GitHub에서 프로젝트 코드를 내려받으려면 필요합니다.
Python 3 설치 시 'Add Python to PATH' 옵션을 꼭 체크하세요 (Windows).

pip install .

PyPI에 배포된 패키지를 바로 설치합니다. 소스 클론이 필요 없습니다.

python <실행할 파일명>.py # README에서 정확한 실행 파일명을 확인하세요

파이썬 스크립트(또는 모듈)를 실행합니다.

✅ 에러 메시지 없이 실행되고 터미널에 안내 문구가 출력되면 정상입니다.

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# Continual Transfer Learning Benchmark
The CTrL benchmark aims to help research by studying the transfer behaviour of different models in the Lifelong Learning context.

For a quick presentation of the benchmark, please check out [this blog post](https://ai.facebook.com/blog/ctrl-and-mntdp-a-new-open-source-benchmark-and-model-for-continual-learning/).

For more details, the paper is available on [arxiv](https://arxiv.org/abs/2012.12631).

## Creating a Stream:

The `TaskGenerator` class is at the center of the implementation of the CTrL Benchmark. 
It gives access to a high-level API allowing to seamlessly generate a wide variety of streams with a loose coupling between the different components such as the underlying dataset(s), the strategy to generate the tasks (split, incremental, mixture of datasets, ...) and the processing to apply to each task.

The 3 main components of a `Task Generator` are:
- A pool of concepts to select from to generate the tasks. It can be a few classes, a full dataset or even a mixture of datasets.
- A pool of transformation that can be modified or combined to apply specific processing to the data for each task.
- A Strategy, describing how to combine the conecpts and trasnformation over time to generate an actual stream.

Each of these components can be created by hand or using our automatic `TaskGenerator` creation tool using yaml configuration files.

For examples simply executing
```python
import ctrl
task_gen = ctrl.get_stream('s_minus')
```
will return the corresponding task generator that be used either directy to generate tasks on the fly:
```python
t1 = task_gen.add_task()
t2 = task_gen.add_task()
t3 = task_gen.add_task()
...
```

or as an iterator:
```python
for t in task_gen:
    print(t)
```

### Available streams:
In the current version, only the streams of the CTrL benchmark are directly available, they can be obtained by passing the following `name` arguments in `ctrl.get_stream`:
- S<sup>+</sup>: `"s_plus"`
- S<sup>-</sup>: `"s_minus"`
- S<sup>in</sup>: `"s_in"`
- S<sup>out</sup>: `"s_out"`
- S<sup>pl</sup>: `"s_pl"`
- S<sup>long</sup>: `"s_long"`

More documentation and details on the internal components will be progressively added.

See the CONTRIBUTING file for how to help out.

# LICENSE
See the LICENSE file.