Keras模型：用于model.fit的同一数组未在model.predict中处理

Question

I have a model:

model.add(Dense(16, input_dim = X.shape[1], activation = 'tanh'))
model.add(Dropout(0.2))
model.add(Dense(8, activation = 'relu'))
model.add(Dropout(0.2))
model.add(Dense(4, activation = 'tanh'))
model.add(Dropout(0.2))
model.add(Dense(2, activation = 'relu'))
model.add(Dropout(0.2))
model.add(Dense(1))
model.compile(loss='mean_squared_error', optimizer='adam', metrics=['mae'])

And during Model.evaluvate it works just fine with 'X' s input:

history = model.fit(X, Y, validation_split=0.2, epochs=10, callbacks=   [PrintDot()], batch_size=10, verbose=0)

But during prediction as I use X[1] it throws an error:

ValueError: Error when checking input: expected dense_8_input to have shape (500,) but got array with shape (1,)

But X[1].Shape is (500,):

X[1].shape
--> (500,)

How can I mend this error, any help appreciated

Answer 1

Keras model.predict expects to receive input of (amount_of_items, features) .

So even when attempting to predict a single sample, you must reshape it to (1, features) , and in your case, (1, 500) .