我想在keras做一个基本的MLP示例。我的输入数据的形状为train_data.shape = (2000,75,75)
,我的测试数据的形状为test_data.shape = (500,75,75)
。 2000
和500
是训练和测试数据的样本数量(换句话说,数据的形状是(75,75)
,但有2000和500件训练和测试数据)。输出应该有两个类。Keras正确的输入形状为多层感知器
我不确定在网络的第一层上使用input_shape
参数有什么价值。在keras库使用来自MNIST例子的代码,我有(更新):
from six.moves import cPickle
from keras.models import Sequential
from keras.layers import Dense, Dropout, Activation
from keras.utils import np_utils
from keras.optimizers import RMSprop
# Globals
NUM_CLASSES = 2
NUM_EPOCHS = 10
BATCH_SIZE = 250
def loadData():
fData = open('data.pkl','rb')
fLabels = open('labels.pkl','rb')
data = cPickle.load(fData)
labels = cPickle.load(fLabels)
train_data = data[0:2000]
train_labels = labels[0:2000]
test_data = data[2000:]
test_labels = labels[2000:]
return (train_data, train_labels, test_data, test_labels)
# Load data and corresponding labels for model
train_data, train_labels, test_data, test_labels = loadData()
train_labels = np_utils.to_categorical(train_labels, NUM_CLASSES)
test_labels = np_utils.to_categorical(test_labels, NUM_CLASSES)
print(train_data.shape)
print(test_data.shape)
model = Sequential()
model.add(Dense(512, input_shape=(5625,)))
model.add(Activation('relu'))
model.add(Dropout(0.2))
model.add(Dense(512))
model.add(Activation('relu'))
model.add(Dropout(0.2))
model.add(Dense(2))
model.add(Activation('softmax'))
model.summary()
model.compile(loss='categorical_crossentropy',
optimizer=RMSprop(),
metrics=['accuracy'])
history = model.fit(train_data, train_labels, validation_data=(test_data, test_labels),
batch_size=BATCH_SIZE, nb_epoch=NUM_EPOCHS,
verbose=1)
score = model.evaluate(test_data, test_labels, verbose=0)
print('Test score:', score[0])
print('Test accuracy:', score[1])
其中5625
是75 * 75(模仿MNIST例子)。我得到的错误是:
Error when checking model input: expected dense_input_1 to have 2 dimensions, but got array with shape (2000, 75, 75)
任何想法?
你能展示更多的代码吗?具体包括那条给你那个错误的线?你提到了两个变量'train_data'和'test_data',但是我没有看到它们在代码中使用,所以我不确定它们将如何影响你发现的情况。是否有完整的,最小的代码示例产生这个错误? – onlynone
你可能只需要改变'test_data'和'train_data'来匹配'5625',用'X.reshape(-1,75 * 75)' – toine