machine-learning - ValueError : Error when checking model target: expected dense_4 to have shape (None, 4) 但得到形状为 (13252, 1) 的数组

Question

嗨，有人知道为什么会发生此错误吗？这是错误

ValueError: Error when checking model target: expected dense_4 to have   shape (None, 4) but got array with shape (13252, 1)

这是代码:

from keras.models import Sequential
from keras.layers import *

model = Sequential()
model.add(Cropping2D(cropping=((0,0), (50,20)), input_shape=(160 ,320, 3))) #(None, 90, 320, 3)
model.add(Lambda(lambda x: x/127.5 - 1.)) 
model.add(Convolution2D(32, 3, 3,)) #(None, 88, 318, 32)
model.add(Activation('relu'))
model.add(Convolution2D(32, 3, 3)) #(None, 86, 316, 32)
model.add(Activation('relu'))
model.add(Flatten()) #(None, 869632)
model.add(Dense(128)) #(None, 128)
model.add(Activation('relu'))
model.add(Dense(4)) #(None, 4)
print(model.summary())

model.compile(loss='mse', optimizer='adam')
model.fit(X, y, validation_split=0.2, batch_size=32, nb_epoch=3, verbose=1)

输入形状为(X):

(13252, 160, 320, 3)

和(y):

(13252,)

Answer 1

由于您的网络有四个输出，因此您的y必须是 N x 4 矩阵，而不是长度为 N 的向量。要么更改 y，要么将最后一层更改为密集(1)