ValueError：检查输入时出错：预期 conv2d_1_input 有 4 个维度

Question

我正在我的数据集上构建一个 2d 卷积网络。我在测试集上运行它，代码如下：#reproducible codefrom keras.models import Sequentialfrom keras.layers import Dense, Dropout, Flattenfrom keras.utils import np_utilsfrom keras import optimizersfrom sklearn.metrics import confusion_matriximport numpy as npimport timefrom keras.layers.convolutional import Conv2Ddata = np.random.rand(1000,22)data.shapetrain_X = data[0:data.shape[0],0:12]train_X.shapetrain_y = data[0:data.shape[0],12:data.shape[1]]train_y.shapetrain_X = train_X.reshape((train_X.shape[0], train_X.shape[1], 1))train_X.shapeneurons = 10model = Sequential()model.add(Conv2D(filters=64,input_shape=train_X.shape, activation='relu',kernel_size = 3))model.add(Flatten())model.add(Dense(neurons,activation='relu')) # first hidden layermodel.add(Dense(neurons, activation='relu')) # second hidden layermodel.add(Dense(neurons, activation='relu')) # third hidden layermodel.add(Dense(10, activation='softmax'))sgd = optimizers.SGD(lr=0.05, decay=1e-6, momentum=0.95, nesterov=True)model.compile(loss='categorical_crossentropy', optimizer=sgd, metrics=['accuracy'])model.summary()model.fit(train_X,train_y, validation_split=0.2, epochs=10, batch_size=100, verbose=0)model.summary()

Answer 1

你没有理由使用 2D 卷积层，因为你的数据是 3D 的。您正在寻找的是 Conv1D。另外，不要n_samples在input_shape.

from tensorflow.keras.models import Sequential

from tensorflow.keras.layers import Dense, Conv1D, Flatten

from tensorflow.keras import optimizers

import numpy as np

data = np.random.rand(1000,22)

train_X = data[0:data.shape[0],0:12]

train_X = train_X.reshape((train_X.shape[0], train_X.shape[1], 1))

train_y = data[0:data.shape[0],12:data.shape[1]]

neurons = 10

model = Sequential()

model.add(Conv1D(filters=64,input_shape=train_X.shape[1:], 

    activation='relu',kernel_size = 3))

model.add(Flatten())

model.add(Dense(neurons,activation='relu')) # first hidden layer

model.add(Dense(10, activation='softmax'))

sgd = optimizers.SGD(lr=0.05, decay=1e-6, momentum=0.95, nesterov=True)

model.compile(loss='categorical_crossentropy', optimizer=sgd, metrics=['accuracy'])

history = model.fit(train_X, train_y, validation_split=0.2, epochs=1, batch_size=100)

Train on 800 samples, validate on 200 samples

100/800 [==>...........................] - ETA: 2s - loss: 11.4786 - acc: 0.0800

800/800 [==============================] - 0s 547us/sample - loss: 55.3883 - acc: 0.1000 

Answer 2

你需要train_X有第四维度。就像错误信息所说的那样。

train_X = train_X.reshape(train_X.shape[0], train_X.shape[1], 1, 1)