Keras假形状，

Question

有人知道keras吗？我无法理解问题是什么？我遇到了这个问题：

ValueError: You are passing a target array of shape (1000, 1) while 

using as loss `categorical_crossentropy`. `categorical_crossentropy` 

expects targets to be binary matrices (1s and 0s) of shape (samples, 

classes). If your targets are integer classes, you can convert them to 

the expected format via...

from keras.utils import to_categorical

y_binary = to_categorical(y_int)

Alternatively, you can use the loss function ` 

sparse_categorical_crossentropy` instead, which does expect integer targets.

Hieer是完整代码：https ://ideone.com/v9yojt

Answer 1

改变categorical_crossentropy与binary_crossentropy在第 83 行中设置：model.compile(loss='binary_crossentropy', optimizer="sgd", metrics=['accuracy'])