2

我尝试使用从 nolearn 包导入的 DBN 函数,这是我的代码:

from nolearn.dbn import DBN
import numpy as np
from sklearn import cross_validation

fileName = 'data.csv'
fileName_1 = 'label.csv'

data = np.genfromtxt(fileName, dtype=float, delimiter = ',')
label = np.genfromtxt(fileName_1, dtype=int, delimiter = ',')

clf = DBN(
    [data, 300, 10],
    learn_rates=0.3,
    learn_rate_decays=0.9,
    epochs=10,
    verbose=1,
    )

clf.fit(data,label)
score = cross_validation.cross_val_score(clf, data, label,scoring='f1', cv=10)
print score

由于我的数据具有形状 (1231, 229) 和带有形状 (1231,13) 的标签,因此标签集看起来像 ([0 0 1 0 1 0 1 0 0 0 1 1 0] ...,[.. ..]),当我运行我的代码时,我收到了这个错误消息:输入形状错误(1231,13)。我想知道这里可能会发生两个问题:

  1. DBN 不支持多标签分类
  2. 我的标签不适合在 DBN 拟合函数中使用。
4

2 回答 2

5

正如弗朗西斯科巴尔加斯所提到的,nolearn.dbn已弃用,您应该nolearn.lasagne改用(如果可以的话)。

如果你想在千层面进行多标签分类,那么你应该将你的regression参数设置为True,定义一个验证分数和一个自定义损失。

这是一个例子:

import numpy as np
import theano.tensor as T
from lasagne import layers
from lasagne.updates import nesterov_momentum
from nolearn.lasagne import NeuralNet
from nolearn.lasagne import BatchIterator
from lasagne import nonlinearities

# custom loss: multi label cross entropy
def multilabel_objective(predictions, targets):
    epsilon = np.float32(1.0e-6)
    one = np.float32(1.0)
    pred = T.clip(predictions, epsilon, one - epsilon)
    return -T.sum(targets * T.log(pred) + (one - targets) * T.log(one - pred), axis=1)


net = NeuralNet(
    # customize "layers" to represent the architecture you want
    # here I took a dummy architecture
    layers=[(layers.InputLayer, {"name": 'input', 'shape': (None, 1, 229, 1)}),

            (layers.DenseLayer, {"name": 'hidden1', 'num_units': 20}),
            (layers.DenseLayer, {"name": 'output', 'nonlinearity': nonlinearities.sigmoid, 'num_units': 13})], #because you have 13 outputs

    # optimization method:
    update=nesterov_momentum,
    update_learning_rate=5*10**(-3),
    update_momentum=0.9,

    max_epochs=500,  # we want to train this many epochs
    verbose=1,

    #Here are the important parameters for multi labels
    regression=True,  

    objective_loss_function=multilabel_objective,
    custom_score=("validation score", lambda x, y: np.mean(np.abs(x - y)))

    )

net.fit(X_train, labels_train)
于 2015-08-25T07:52:39.893 回答
0

Fit 调用 BuildDBN 可以在此处找到,需要注意的重要一点是 dbn 已被弃用,您只能找到它old_commits。无论如何,如果您正在寻找额外的信息,那么从我在您的代码段中看到的内容中检查这两个可能很好,即的第一个参数DBN应该[data, 300, 10]基于[data.shape[1], 300, 10]文档和源代码。希望这可以帮助。

于 2015-08-24T17:26:57.057 回答