Metadata-Version: 2.1
Name: diagnnose
Version: 0.1a0
Summary: A library that facilitates a broad set of tools for analysing hidden activations of neural models.
Home-page: https://github.com/i-machine-think/diagnnose
License: Apache License 2.0
Keywords: introspection,analysis,deep learning,nlp
Platform: UNKNOWN
Classifier: Intended Audience :: Science/Research
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Classifier: Programming Language :: Python :: 3.7
Requires-Python: >=3.7.0
Description-Content-Type: text/markdown
Requires-Dist: numpy (>=1.16.2)
Requires-Dist: torch (>=1.1.0)
Requires-Dist: scipy
Requires-Dist: dataclasses
Requires-Dist: overrides
Requires-Dist: tqdm
Requires-Dist: torchtext
Requires-Dist: unidecode
Provides-Extra: dev
Requires-Dist: check-manifest ; extra == 'dev'
Provides-Extra: test
Requires-Dist: coverage ; extra == 'test'

# diagnnose &middot; [![Build Status](https://travis-ci.com/i-machine-think/diagnnose.svg?branch=master)](https://travis-ci.com/i-machine-think/diagnnose)

This library contains a set of modules that can be used to analyse recurrent neural networks.
In particular, it contains functionality to:
- Extracting activations from different types of (language) models
- Running diagnostic classifiers [1] on extracted activations
- Doing intervention studies [2] with language models
- Analysing word embeddings
- Doing dimensionality reduction and plotting state space trajectories of trained models

# Quickstart

Our library is not (yet) officially registered with pip. You can use the library by cloning it and do an editable install with pip:

```
git clone git@github.com:i-machine-think/diagnnose.git $custom_path
pip3 install -e $custom_path
```

We will shortly update this README with explanations for the different scripts provided in the library.


## Requirements

This library runs with Pytorch 1.0. We refer to the [PyTorch website](http://pytorch.org/) to install the right version for your environment.
The preferred version of python is >=3.7.

To install additional requirements, run:

`pip install -r requirements.txt`


