Keras中Conv1D的数据形状存在问题

Question

I'm learning Keras , and I'm trying to classify signals according to their frequencies.

So for beginning my code is like that:

import numpy as np
from keras.models import Sequential
from keras.layers import Conv1D
from keras.layers import AveragePooling1D
from keras.layers import Dense
from keras.layers import Dropout

#DATA
time=np.arange(0,20,0.05)
signal=np.sin(time)
out=np.array([1,0,0])

#MODEL
model = Sequential()

model.add(Conv1D(4, 60, padding='same', activation='relu',input_shape=(400,1)))
model.add(AveragePooling1D(pool_size=5, strides=None, padding='valid'))
model.add(Dropout(0.25))
model.add(Flatten())
model.add(Dense(3, activation='softmax'))

model.compile(loss='binary_crossentropy', optimizer='Adam', metrics=['accuracy'])

history = model.fit(signal, out)

and I have this error.

builtins.ValueError: Error when checking input: expected conv1d_1_input to have 3 dimensions, but got array with shape (400, 1)

but I don't understand where the problem is.

Answer 1

try reshaping your data like this:

history = model.fit(signal.reshape(1,400,1), out.reshape(1,3))

edit

model.fit() expects arrays of input and outputs and not a single input and output.