使用 PyTorch，我在下面有一个 ANN 模型（用于分类任务）：
import torch
import torch.nn as nn
# Setting up artifical neural net model which separates out categorical
# from continuous features, so that embedding could be applied to
# categorical features
class TabularModel(nn.Module):
# Initialize parameters embeds, emb_drop, bn_cont and layers
def __init__(self, emb_szs, n_cont, out_sz, layers, p=0.5):
super().__init__()
self.embeds = nn.ModuleList([nn.Embedding(ni, nf) for ni, nf in emb_szs])
self.emb_drop = nn.Dropout(p)
self.bn_cont = nn.BatchNorm1d(n_cont)
# Create empty list for each layer in the neural net
layerlist = []
# Number of all embedded columns for categorical features
n_emb = sum((nf for ni, nf in emb_szs))
# Number of inputs for each layer
n_in = n_emb + n_cont
for i in layers:
# Set the linear function for the weights and biases, wX + b
layerlist.append(nn.Linear(n_in, i))
# Using ReLu activation function
layerlist.append(nn.ReLU(inplace=True))
# Normalised all the activation function output values
layerlist.append(nn.BatchNorm1d(i))
# Set some of the normalised activation function output values to zero
layerlist.append(nn.Dropout(p))
# Reassign number of inputs for the next layer
n_in = i
# Append last layer
layerlist.append(nn.Linear(layers[-1], out_sz))
# Create sequential layers
self.layers = nn.Sequential(*layerlist)
# Function for feedforward
def forward(self, x_cat_cont):
x_cat = x_cat_cont[:,0:cat_train.shape[1]].type(torch.int64)
x_cont = x_cat_cont[:,cat_train.shape[1]:].type(torch.float32)
# Create empty list for embedded categorical features
embeddings = []
# Embed categorical features
for i, e in enumerate(self.embeds):
embeddings.append(e(x_cat[:,i]))
# Concatenate embedded categorical features
x = torch.cat(embeddings, 1)
# Apply dropout rates to categorical features
x = self.emb_drop(x)
# Batch normalize continuous features
x_cont = self.bn_cont(x_cont)
# Concatenate categorical and continuous features
x = torch.cat([x, x_cont], 1)
# Feed categorical and continuous features into neural net layers
x = self.layers(x)
return x
我正在尝试将此模型与 skorch 的 GridSearchCV 一起使用，如下所示：
from skorch import NeuralNetBinaryClassifier
# Random seed chosen to ensure results are reproducible by using the same
# initial random weights and biases, and applying dropout rates to the same
# random embedded categorical features and neurons in the hidden layers
torch.manual_seed(0)
net = NeuralNetBinaryClassifier(module=TabularModel,
module__emb_szs=emb_szs,
module__n_cont=con_train.shape[1],
module__out_sz=2,
module__layers=[30],
module__p=0.0,
criterion=nn.CrossEntropyLoss,
criterion__weight=cls_wgt,
optimizer=torch.optim.Adam,
optimizer__lr=0.001,
max_epochs=150,
device='cuda'
)
from sklearn.model_selection import GridSearchCV
param_grid = {'module__layers': [[30], [50,20]],
'module__p': [0.0, 0.2, 0.4],
'max_epochs': [150, 175, 200, 225]
}
models = GridSearchCV(net, param_grid, scoring='roc_auc').fit(cat_con_train.cpu(), y_train.cpu())
models.best_params_
但是当我运行代码时，我在下面收到此错误消息：
/usr/local/lib/python3.6/dist-packages/sklearn/model_selection/_validation.py:536: FitFailedWarning: Estimator fit failed. The score on this train-test partition for these parameters will be set to nan. Details:
ValueError: Expected module output to have shape (n,) or (n, 1), got (128, 2) instead
FitFailedWarning)
/usr/local/lib/python3.6/dist-packages/sklearn/model_selection/_validation.py:536: FitFailedWarning: Estimator fit failed. The score on this train-test partition for these parameters will be set to nan. Details:
ValueError: Expected module output to have shape (n,) or (n, 1), got (128, 2) instead
FitFailedWarning)
/usr/local/lib/python3.6/dist-packages/sklearn/model_selection/_validation.py:536: FitFailedWarning: Estimator fit failed. The score on this train-test partition for these parameters will be set to nan. Details:
ValueError: Expected module output to have shape (n,) or (n, 1), got (128, 2) instead
FitFailedWarning)
/usr/local/lib/python3.6/dist-packages/sklearn/model_selection/_validation.py:536: FitFailedWarning: Estimator fit failed. The score on this train-test partition for these parameters will be set to nan. Details:
ValueError: Expected module output to have shape (n,) or (n, 1), got (128, 2) instead
FitFailedWarning)
/usr/local/lib/python3.6/dist-packages/sklearn/model_selection/_validation.py:536: FitFailedWarning: Estimator fit failed. The score on this train-test partition for these parameters will be set to nan. Details:
ValueError: Expected module output to have shape (n,) or (n, 1), got (128, 2) instead
FitFailedWarning)
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
<ipython-input-86-c408d65e2435> in <module>()
98
---> 99 models = GridSearchCV(net, param_grid, scoring='roc_auc').fit(cat_con_train.cpu(), y_train.cpu())
100
101 models.best_params_
11 frames
/usr/local/lib/python3.6/dist-packages/skorch/classifier.py in infer(self, x, **fit_params)
303 raise ValueError(
304 "Expected module output to have shape (n,) or "
--> 305 "(n, 1), got {} instead".format(tuple(y_infer.shape)))
306
307 y_infer = y_infer.reshape(-1)
ValueError: Expected module output to have shape (n,) or (n, 1), got (128, 2) instead
我不确定出了什么问题或如何解决此问题。对此的任何帮助将不胜感激。
提前谢谢了！