向量的一维卷积

我正在学习如何使用具有一维卷积的卷积神经网络：

这是一个家庭作业示例：

import numpy as np
import keras
from keras.models import Sequential
from keras.layers import Dense, Dropout, Flatten
from keras.layers import Conv2D, MaxPooling2D
from keras import backend as K
from keras.utils import np_utils
from keras.layers.convolutional import Conv1D
from keras.layers.convolutional import MaxPooling1D


epochs=20
batch_size=50
num_classes=20


x_train = np.random.rand(60000,400)
x_val = np.random.rand(10000,400)

y_tain = np.eye(20)[np.random.choice(5, 60000)]
y_val = np.eye(20)[np.random.choice(5, 10000)]

model = Sequential()
model.add(Conv1D(filters=64, kernel_size=3, activation='relu', input_shape=(400,)))
model.add(Conv1D(filters=64, kernel_size=3, activation='relu'))
model.add(Dropout(0.5))
model.add(MaxPooling1D(pool_size=2))
model.add(Flatten())
model.add(Dense(100, activation='relu'))
model.add(Dense(20, activation='softmax'))
model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])


model.fit(x_train, y_tain,
          batch_size=batch_size,
          epochs=epochs,
          verbose=1,
          validation_data=(x_val, y_val))
score = model.evaluate(x_val, y_val, verbose=0)
print('Test loss:', score[0])
print('Test accuracy:', score[1])

当我尝试运行它时，出现了一些错误：

ValueError: Input 0 is incompatible with layer conv1d_1: expected ndim=3, found ndim=2

你如何让它编译 ？

仔细查看错误消息：您的输入是二维的，而您的卷积层需要三个维度......