Pacote: python3-skorch (1.1.0-1)

[ Fonte: skorch  ]

scikit-learn compatible neural network library that wraps PyTorch

The goal of skorch is to make it possible to use PyTorch with sklearn. This is achieved by providing a wrapper around PyTorch that has an sklearn interface. In that sense, skorch is the spiritual successor to nolearn, but instead of using Lasagne and Theano, it uses PyTorch.

skorch does not re-invent the wheel, instead getting as much out of your way as possible. If you are familiar with sklearn and PyTorch, you don’t have to learn any new concepts, and the syntax should be well known. (If you’re not familiar with those libraries, it is worth getting familiarized.)

Additionally, skorch abstracts away the training loop, making a lot of boilerplate code obsolete. A simple net.fit(X, y) is enough. Out of the box, skorch works with many types of data, be it PyTorch Tensors, NumPy arrays, Python dicts, and so on. However, if you have other data, extending skorch is easy to allow for that.

Overall, skorch aims at being as flexible as PyTorch while having a clean interface as sklearn.

Outros pacotes relacionados a python3-skorch

• dep: python3

  linguagem orientada a objetos de alto nível e interativa (versão python3 padrão)

• dep: python3-numpy

  Python library for numerical computations (Python 3)

• dep: python3-scipy

  ferramentas científicas para Python 3

• dep: python3-sklearn

  Python modules for machine learning and data mining - Python 3

• dep: python3-tabulate

  pretty-print tabular data in Python3

• dep: python3-torch (>= 1.3.1)

  Tensors and Dynamic neural networks in Python (Python Interface)

  ou python3-torch-cuda (>= 1.3.1)

  Tensors and Dynamic neural networks in Python (Python Interface)

• dep: python3-tqdm

  fast, extensible progress bar for Python 3 and CLI tool

Download de python3-skorch

Baixe para todas as arquiteturas disponíveis

Arquitetura	Tamanho do pacote	Tamanho instalado	Arquivos
all	168.0 kB	975.0 kB	[lista de arquivos]