Theano的断言错误

Question

我收到了一个AssertionError：

  

形状沿轴0不匹配：（107,13）; （0,535）

运行以下代码进行分类。

  

n_samples = 535，n_features = 13，n_classes = 7

非常感谢任何帮助。

import theanets

from sklearn.metrics import confusion_matrix

import scipy.io

import numpy

X = scipy.io.loadmat('berlinFeaturesCAFE.mat')

X_F = X['featureContainer'];

X_F_A = numpy.require(X_F, dtype=numpy.float32, requirements=None)

y = scipy.io.loadmat('convertLabel.mat')

y_F = y['xdNew']

cut = int(len(X_F_A) * 0.8) # training / validation split

train = X_F_A[:cut], y_F[:cut]

valid = X_F_A[cut:], y_F[cut:]

net = theanets.Classifier([13, 7])



# Train the model using SGD with momentum.

net.train(train, valid, algo='sgd', learning_rate=1e-4, momentum=0.9)



# Show confusion matrices on the training/validation splits.

for label, (X, y) in (('training:', train), ('validation:', valid)):

print(label)

print(confusion_matrix(y, net.predict(X)))