我尝试使用从nolearn导入的DBN函数,下面是我的代码:
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)和带有形状的标签(1231,13),标签集看起来类似于(0 0 1 0 1 0 1 0 0 1 0.,.),当我运行代码时,我得到了以下错误消息:错误的输入形状(1231,13)。我想知道这里可能发生了两个问题:
发布于 2015-08-25 07:52:39
正如Francisco所提到的,nolearn.dbn是不推荐的,您应该使用nolearn.lasagne (如果可以的话)。
如果您想在千层面中进行多标签分类,那么您应该将regression参数设置为True,定义验证分数和自定义损失。
下面是一个例子:
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)发布于 2015-08-24 17:26:57
Fit调用BuildDBN --这里可以找到这里 --需要注意的是,dbn已被废弃,您只能找到提交。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片段中可以看到的是,DBN的第一个参数,即[data, 300, 10],应该是基于文档和源代码的[data.shape[1], 300, 10]。希望这能有所帮助。
https://stackoverflow.com/questions/32187175
复制相似问题