4

我想用 skorch 做多输出回归。我创建了一个小玩具示例,如下所示。在示例中,NN 应预测 5 个输出。我还想使用使用 sklearn 管道合并的预处理步骤(在此示例中使用 PCA,但它可以是任何其他预处理器)。执行此示例时,我在 Torch 的 Variable._execution_engine.run_backward 步骤中收到以下错误:

RuntimeError: Found dtype Double but expected Float

我是不是忘记了什么?我怀疑,必须在某个地方投射一些东西,但由于 skorch 处理了很多 pytorch 的东西,我看不出是什么和在哪里。

例子:

import torch
import skorch
from sklearn.datasets import make_classification, make_regression
from sklearn.pipeline import Pipeline, make_pipeline
from sklearn.decomposition import PCA

X, y = make_regression(n_samples=1000, n_features=40, n_targets=5)
X = X.astype('float32')

class RegressionModule(torch.nn.Module):
    def __init__(self, input_dim=80):
        super().__init__()
        self.l0 = torch.nn.Linear(input_dim, 10)
        self.l1 = torch.nn.Linear(10, 5)

    def forward(self, X):
        y = self.l0(X)
        y = self.l1(y)
        return y


class InputShapeSetter(skorch.callbacks.Callback):
    def on_train_begin(self, net, X, y):
        net.set_params(module__input_dim=X.shape[-1])


net = skorch.NeuralNetRegressor(
    RegressionModule,
    callbacks=[InputShapeSetter()],
)

pipe = make_pipeline(PCA(n_components=10), net)

pipe.fit(X, y)
print(pipe.predict(X))

编辑1:

从这个例子可以看出,在开始时将 X 转换为 float32 并不适用于每个预处理器:

import torch
import skorch
from sklearn.datasets import make_classification, make_regression
from sklearn.pipeline import Pipeline
from sklearn.decomposition import PCA
from category_encoders import OneHotEncoder

X, y = make_regression(n_samples=1000, n_features=40, n_targets=5)
X = pd.DataFrame(X,columns=[f'feature_{i}' for i in range(X.shape[1])])
X['feature_1'] = pd.qcut(X['feature_1'], 3, labels=["good", "medium", "bad"])


y = y.astype('float32')

class RegressionModule(torch.nn.Module):
    def __init__(self, input_dim=80):
        super().__init__()
        self.l0 = torch.nn.Linear(input_dim, 10)
        self.l1 = torch.nn.Linear(10, 5)

    def forward(self, X):
        y = self.l0(X)
        y = self.l1(y)
        return y


class InputShapeSetter(skorch.callbacks.Callback):
    def on_train_begin(self, net, X, y):
        net.set_params(module__input_dim=X.shape[-1])


net = skorch.NeuralNetRegressor(
    RegressionModule,
    callbacks=[InputShapeSetter()],
)

pipe = make_pipeline(OneHotEncoder(cols=['feature_1'], return_df=False), net)

pipe.fit(X, y)
print(pipe.predict(X))
4

1 回答 1

3

默认情况下OneHotEncoder返回 numpy 数组dtype=float64。因此,在输入模型X时可以简单地转换输入数据forward()

class RegressionModule(torch.nn.Module):
    def __init__(self, input_dim=80):
        super().__init__()
        self.l0 = torch.nn.Linear(input_dim, 10)
        self.l1 = torch.nn.Linear(10, 5)

    def forward(self, X):
        X = X.to(torch.float32)
        y = self.l0(X)
        y = self.l1(y)
        return y
于 2021-04-12T16:05:20.620 回答