Metadata-Version: 2.1
Name: thinc
Version: 8.2.3
Summary: A refreshing functional take on deep learning, compatible with your favorite libraries
Home-page: https://github.com/explosion/thinc
Author: Explosion
Author-email: contact@explosion.ai
License: MIT
Classifier: Development Status :: 5 - Production/Stable
Classifier: Environment :: Console
Classifier: Intended Audience :: Developers
Classifier: Intended Audience :: Science/Research
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: POSIX :: Linux
Classifier: Operating System :: MacOS :: MacOS X
Classifier: Operating System :: Microsoft :: Windows
Classifier: Programming Language :: Cython
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.6
Classifier: Programming Language :: Python :: 3.7
Classifier: Programming Language :: Python :: 3.8
Classifier: Programming Language :: Python :: 3.9
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Topic :: Scientific/Engineering
Requires-Python: >=3.6
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: blis <0.8.0,>=0.7.8
Requires-Dist: murmurhash <1.1.0,>=1.0.2
Requires-Dist: cymem <2.1.0,>=2.0.2
Requires-Dist: preshed <3.1.0,>=3.0.2
Requires-Dist: wasabi <1.2.0,>=0.8.1
Requires-Dist: srsly <3.0.0,>=2.4.0
Requires-Dist: catalogue <2.1.0,>=2.0.4
Requires-Dist: confection <1.0.0,>=0.0.1
Requires-Dist: setuptools
Requires-Dist: pydantic !=1.8,!=1.8.1,<3.0.0,>=1.7.4
Requires-Dist: packaging >=20.0
Requires-Dist: dataclasses <1.0,>=0.6 ; python_version < "3.7"
Requires-Dist: contextvars <3,>=2.4 ; python_version < "3.7"
Requires-Dist: typing-extensions <4.5.0,>=3.7.4.1 ; python_version < "3.8"
Requires-Dist: numpy >=1.15.0 ; python_version < "3.9"
Requires-Dist: numpy >=1.19.0 ; python_version >= "3.9"
Provides-Extra: cuda
Requires-Dist: cupy >=5.0.0b4 ; extra == 'cuda'
Provides-Extra: cuda-autodetect
Requires-Dist: cupy-wheel >=11.0.0 ; extra == 'cuda-autodetect'
Provides-Extra: cuda100
Requires-Dist: cupy-cuda100 >=5.0.0b4 ; extra == 'cuda100'
Provides-Extra: cuda101
Requires-Dist: cupy-cuda101 >=5.0.0b4 ; extra == 'cuda101'
Provides-Extra: cuda102
Requires-Dist: cupy-cuda102 >=5.0.0b4 ; extra == 'cuda102'
Provides-Extra: cuda110
Requires-Dist: cupy-cuda110 >=5.0.0b4 ; extra == 'cuda110'
Provides-Extra: cuda111
Requires-Dist: cupy-cuda111 >=5.0.0b4 ; extra == 'cuda111'
Provides-Extra: cuda112
Requires-Dist: cupy-cuda112 >=5.0.0b4 ; extra == 'cuda112'
Provides-Extra: cuda113
Requires-Dist: cupy-cuda113 >=5.0.0b4 ; extra == 'cuda113'
Provides-Extra: cuda114
Requires-Dist: cupy-cuda114 >=5.0.0b4 ; extra == 'cuda114'
Provides-Extra: cuda115
Requires-Dist: cupy-cuda115 >=5.0.0b4 ; extra == 'cuda115'
Provides-Extra: cuda116
Requires-Dist: cupy-cuda116 >=5.0.0b4 ; extra == 'cuda116'
Provides-Extra: cuda117
Requires-Dist: cupy-cuda117 >=5.0.0b4 ; extra == 'cuda117'
Provides-Extra: cuda11x
Requires-Dist: cupy-cuda11x >=11.0.0 ; extra == 'cuda11x'
Provides-Extra: cuda12x
Requires-Dist: cupy-cuda12x >=11.5.0 ; extra == 'cuda12x'
Provides-Extra: cuda80
Requires-Dist: cupy-cuda80 >=5.0.0b4 ; extra == 'cuda80'
Provides-Extra: cuda90
Requires-Dist: cupy-cuda90 >=5.0.0b4 ; extra == 'cuda90'
Provides-Extra: cuda91
Requires-Dist: cupy-cuda91 >=5.0.0b4 ; extra == 'cuda91'
Provides-Extra: cuda92
Requires-Dist: cupy-cuda92 >=5.0.0b4 ; extra == 'cuda92'
Provides-Extra: datasets
Requires-Dist: ml-datasets <0.3.0,>=0.2.0 ; extra == 'datasets'
Provides-Extra: mxnet
Requires-Dist: mxnet <1.6.0,>=1.5.1 ; extra == 'mxnet'
Provides-Extra: tensorflow
Requires-Dist: tensorflow <2.6.0,>=2.0.0 ; extra == 'tensorflow'
Provides-Extra: torch
Requires-Dist: torch >=1.6.0 ; extra == 'torch'
# Thinc: A refreshing functional take on deep learning, compatible with your favorite libraries
### From the makers of [spaCy](https://spacy.io) and [Prodigy](https://prodi.gy)
[Thinc](https://thinc.ai) is a **lightweight deep learning library** that offers
an elegant, type-checked, functional-programming API for **composing models**,
with support for layers defined in other frameworks such as **PyTorch,
TensorFlow and MXNet**. You can use Thinc as an interface layer, a standalone
toolkit or a flexible way to develop new models. Previous versions of Thinc have
been running quietly in production in thousands of companies, via both
[spaCy](https://spacy.io) and [Prodigy](https://prodi.gy). We wrote the new
version to let users **compose, configure and deploy custom models** built with
their favorite framework.
[![tests](https://github.com/explosion/thinc/actions/workflows/tests.yml/badge.svg)](https://github.com/explosion/thinc/actions/workflows/tests.yml)
[![Current Release Version](https://img.shields.io/github/v/release/explosion/thinc.svg?include_prereleases&sort=semver&style=flat-square&logo=github)](https://github.com/explosion/thinc/releases)
[![PyPi Version](https://img.shields.io/pypi/v/thinc.svg?include_prereleases&sort=semver&style=flat-square&logo=pypi&logoColor=white)](https://pypi.python.org/pypi/thinc)
[![conda Version](https://img.shields.io/conda/vn/conda-forge/thinc.svg?style=flat-square&logo=conda-forge&logoColor=white)](https://anaconda.org/conda-forge/thinc)
[![Python wheels](https://img.shields.io/badge/wheels-%E2%9C%93-4c1.svg?longCache=true&style=flat-square&logo=python&logoColor=white)](https://github.com/explosion/wheelwright/releases)
[![Code style: black](https://img.shields.io/badge/code%20style-black-000000.svg?style=flat-square)](https://github.com/ambv/black)
[![Open demo in Colab][colab]][intro_to_thinc_colab]
## 🔥 Features
- **Type-check** your model definitions with custom types and
[`mypy`](https://mypy.readthedocs.io/en/latest/) plugin.
- Wrap **PyTorch**, **TensorFlow** and **MXNet** models for use in your network.
- Concise **functional-programming** approach to model definition, using
composition rather than inheritance.
- Optional custom infix notation via **operator overloading**.
- Integrated **config system** to describe trees of objects and hyperparameters.
- Choice of **extensible backends**.
- **[Read more →](https://thinc.ai/docs)**
## 🚀 Quickstart
Thinc is compatible with **Python 3.6+** and runs on **Linux**, **macOS** and
**Windows**. The latest releases with binary wheels are available from
[pip](https://pypi.python.org/pypi/thinc). Before you install Thinc and its
dependencies, make sure that your `pip`, `setuptools` and `wheel` are up to
date. For the most recent releases, pip 19.3 or newer is recommended.
```bash
pip install -U pip setuptools wheel
pip install thinc
```
See the [extended installation docs](https://thinc.ai/docs/install#extended) for
details on optional dependencies for different backends and GPU. You might also
want to
[set up static type checking](https://thinc.ai/docs/install#type-checking) to
take advantage of Thinc's type system.
> ⚠️ If you have installed PyTorch and you are using Python 3.7+, uninstall the
> package `dataclasses` with `pip uninstall dataclasses`, since it may have been
> installed by PyTorch and is incompatible with Python 3.7+.
### 📓 Selected examples and notebooks
Also see the [`/examples`](examples) directory and
[usage documentation](https://thinc.ai/docs) for more examples. Most examples
are Jupyter notebooks – to launch them on
[Google Colab](https://colab.research.google.com) (with GPU support!) click on
the button next to the notebook name.
| Notebook | Description |
| --------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| [`intro_to_thinc`][intro_to_thinc]
[![Open in Colab][colab]][intro_to_thinc_colab] | Everything you need to know to get started. Composing and training a model on the MNIST data, using config files, registering custom functions and wrapping PyTorch, TensorFlow and MXNet models. |
| [`transformers_tagger_bert`][transformers_tagger_bert]
[![Open in Colab][colab]][transformers_tagger_bert_colab] | How to use Thinc, `transformers` and PyTorch to train a part-of-speech tagger. From model definition and config to the training loop. |
| [`pos_tagger_basic_cnn`][pos_tagger_basic_cnn]
[![Open in Colab][colab]][pos_tagger_basic_cnn_colab] | Implementing and training a basic CNN for part-of-speech tagging model without external dependencies and using different levels of Thinc's config system. |
| [`parallel_training_ray`][parallel_training_ray]
[![Open in Colab][colab]][parallel_training_ray_colab] | How to set up synchronous and asynchronous parameter server training with Thinc and [Ray](https://ray.readthedocs.io/en/latest/). |
**[View more →](examples)**
[colab]:
https://gistcdn.githack.com/ines/dcf354aa71a7665ae19871d7fd14a4e0/raw/461fc1f61a7bc5860f943cd4b6bcfabb8c8906e7/colab-badge.svg
[intro_to_thinc]: examples/00_intro_to_thinc.ipynb
[intro_to_thinc_colab]:
https://colab.research.google.com/github/explosion/thinc/blob/master/examples/00_intro_to_thinc.ipynb
[transformers_tagger_bert]: examples/02_transformers_tagger_bert.ipynb
[transformers_tagger_bert_colab]:
https://colab.research.google.com/github/explosion/thinc/blob/master/examples/02_transformers_tagger_bert.ipynb
[pos_tagger_basic_cnn]: examples/03_pos_tagger_basic_cnn.ipynb
[pos_tagger_basic_cnn_colab]:
https://colab.research.google.com/github/explosion/thinc/blob/master/examples/03_pos_tagger_basic_cnn.ipynb
[parallel_training_ray]: examples/04_parallel_training_ray.ipynb
[parallel_training_ray_colab]:
https://colab.research.google.com/github/explosion/thinc/blob/master/examples/04_parallel_training_ray.ipynb
### 📖 Documentation & usage guides
| Documentation | Description |
| --------------------------------------------------------------------------------- | ----------------------------------------------------- |
| [Introduction](https://thinc.ai/docs) | Everything you need to know. |
| [Concept & Design](https://thinc.ai/docs/concept) | Thinc's conceptual model and how it works. |
| [Defining and using models](https://thinc.ai/docs/usage-models) | How to compose models and update state. |
| [Configuration system](https://thinc.ai/docs/usage-config) | Thinc's config system and function registry. |
| [Integrating PyTorch, TensorFlow & MXNet](https://thinc.ai/docs/usage-frameworks) | Interoperability with machine learning frameworks |
| [Layers API](https://thinc.ai/docs/api-layers) | Weights layers, transforms, combinators and wrappers. |
| [Type Checking](https://thinc.ai/docs/usage-type-checking) | Type-check your model definitions and more. |
## 🗺 What's where
| Module | Description |
| ----------------------------------------- | --------------------------------------------------------------------------------- |
| [`thinc.api`](thinc/api.py) | **User-facing API.** All classes and functions should be imported from here. |
| [`thinc.types`](thinc/types.py) | Custom [types and dataclasses](https://thinc.ai/docs/api-types). |
| [`thinc.model`](thinc/model.py) | The `Model` class. All Thinc models are an instance (not a subclass) of `Model`. |
| [`thinc.layers`](thinc/layers) | The layers. Each layer is implemented in its own module. |
| [`thinc.shims`](thinc/shims) | Interface for external models implemented in PyTorch, TensorFlow etc. |
| [`thinc.loss`](thinc/loss.py) | Functions to calculate losses. |
| [`thinc.optimizers`](thinc/optimizers.py) | Functions to create optimizers. Currently supports "vanilla" SGD, Adam and RAdam. |
| [`thinc.schedules`](thinc/schedules.py) | Generators for different rates, schedules, decays or series. |
| [`thinc.backends`](thinc/backends) | Backends for `numpy` and `cupy`. |
| [`thinc.config`](thinc/config.py) | Config parsing and validation and function registry system. |
| [`thinc.util`](thinc/util.py) | Utilities and helper functions. |
## 🐍 Development notes
Thinc uses [`black`](https://github.com/psf/black) for auto-formatting,
[`flake8`](http://flake8.pycqa.org/en/latest/) for linting and
[`mypy`](https://mypy.readthedocs.io/en/latest/) for type checking. All code is
written compatible with **Python 3.6+**, with type hints wherever possible. See
the [type reference](https://thinc.ai/docs/api-types) for more details on
Thinc's custom types.
### 👷♀️ Building Thinc from source
Building Thinc from source requires the full dependencies listed in
[`requirements.txt`](requirements.txt) to be installed. You'll also need a
compiler to build the C extensions.
```bash
git clone https://github.com/explosion/thinc
cd thinc
python -m venv .env
source .env/bin/activate
pip install -U pip setuptools wheel
pip install -r requirements.txt
pip install --no-build-isolation .
```
Alternatively, install in editable mode:
```bash
pip install -r requirements.txt
pip install --no-build-isolation --editable .
```
Or by setting `PYTHONPATH`:
```bash
export PYTHONPATH=`pwd`
pip install -r requirements.txt
python setup.py build_ext --inplace
```
### 🚦 Running tests
Thinc comes with an [extensive test suite](thinc/tests). The following should
all pass and not report any warnings or errors:
```bash
python -m pytest thinc # test suite
python -m mypy thinc # type checks
python -m flake8 thinc # linting
```
To view test coverage, you can run `python -m pytest thinc --cov=thinc`. We aim
for a 100% test coverage. This doesn't mean that we meticulously write tests for
every single line – we ignore blocks that are not relevant or difficult to test
and make sure that the tests execute all code paths.