skorch 1.0.0

资源

• 文档

• 源代码

• 安装

示例

要查看更详细的示例，请点击这里。

import numpy as np
from sklearn.datasets import make_classification
from torch import nn
from skorch import NeuralNetClassifier

X, y = make_classification(1000, 20, n_informative=10, random_state=0)
X = X.astype(np.float32)
y = y.astype(np.int64)

class MyModule(nn.Module):
    def __init__(self, num_units=10, nonlin=nn.ReLU()):
        super().__init__()

        self.dense0 = nn.Linear(20, num_units)
        self.nonlin = nonlin
        self.dropout = nn.Dropout(0.5)
        self.dense1 = nn.Linear(num_units, num_units)
        self.output = nn.Linear(num_units, 2)
        self.softmax = nn.Softmax(dim=-1)

    def forward(self, X, **kwargs):
        X = self.nonlin(self.dense0(X))
        X = self.dropout(X)
        X = self.nonlin(self.dense1(X))
        X = self.softmax(self.output(X))
        return X

net = NeuralNetClassifier(
    MyModule,
    max_epochs=10,
    lr=0.1,
    # Shuffle training data on each epoch
    iterator_train__shuffle=True,
)

net.fit(X, y)
y_proba = net.predict_proba(X)

在sklearn Pipeline中

from sklearn.pipeline import Pipeline
from sklearn.preprocessing import StandardScaler

pipe = Pipeline([
    ('scale', StandardScaler()),
    ('net', net),
])

pipe.fit(X, y)
y_proba = pipe.predict_proba(X)

使用网格搜索

from sklearn.model_selection import GridSearchCV

# deactivate skorch-internal train-valid split and verbose logging
net.set_params(train_split=False, verbose=0)
params = {
    'lr': [0.01, 0.02],
    'max_epochs': [10, 20],
    'module__num_units': [10, 20],
}
gs = GridSearchCV(net, params, refit=False, cv=3, scoring='accuracy', verbose=2)

gs.fit(X, y)
print("best score: {:.3f}, best params: {}".format(gs.best_score_, gs.best_params_))

skorch还提供了许多便利的功能，其中包括

• 学习率调度器（Warm restarts，周期性LR等）

• 使用sklearn（和自定义）评分函数进行评分

• 提前停止

• 检查点

• 参数冻结/解冻

• 进度条（适用于CLI和jupyter）

• 自动推断CLI参数

• 与GPyTorch进行高斯过程集成

• 与Hugging Face 🤗集成

安装

skorch需要Python 3.8或更高版本。

conda install -c conda-forge skorch

python -m pip install -U skorch

git clone https://github.com/skorch-dev/skorch.git
cd skorch
conda create -n skorch-env python=3.10
conda activate skorch-env
conda install -c pytorch pytorch
python -m pip install -r requirements.txt
python -m pip install .

git clone https://github.com/skorch-dev/skorch.git
cd skorch
conda create -n skorch-env python=3.10
conda activate skorch-env
conda install -c pytorch pytorch
python -m pip install -r requirements.txt
python -m pip install -r requirements-dev.txt
python -m pip install -e .

py.test  # unit tests
pylint skorch  # static code checks

git clone https://github.com/skorch-dev/skorch.git
cd skorch
# create and activate a virtual environment
python -m pip install -r requirements.txt
# install pytorch version for your system (see below)
python -m pip install .

git clone https://github.com/skorch-dev/skorch.git
cd skorch
# create and activate a virtual environment
python -m pip install -r requirements.txt
# install pytorch version for your system (see below)
python -m pip install -r requirements-dev.txt
python -m pip install -e .

py.test  # unit tests
pylint skorch  # static code checks

# using conda:
conda install pytorch pytorch-cuda -c pytorch
# using pip
python -m pip install torch

外部资源

• @jakubczakon: 博文 “8 Creators and Core Contributors Talk About Their Model Training Libraries From PyTorch Ecosystem” 2020

• @BenjaminBossan: 演讲 1 “skorch: A scikit-learn compatible neural network library” at PyCon/PyData 2019

• @githubnemo: 海报 for the PyTorch developer conference 2019

• @thomasjpfan: 演讲 2 “Skorch: A Union of Scikit learn and PyTorch” at SciPy 2019

• @thomasjpfan: 演讲 3 “Skorch - A Union of Scikit-learn and PyTorch” at PyData 2018

• @BenjaminBossan: 演讲 4 “Extend your scikit-learn workflow with Hugging Face and skorch” at PyData Amsterdam 2023 (幻灯片 4)

沟通

• GitHub讨论：用户问题、想法、安装问题、一般讨论。

• GitHub问题：错误报告、功能请求、RFC等。

• Slack：我们在PyTorch Slack服务器上运行#skorch频道，您可以在这里申请访问。