fit error help
Opened this issue · 0 comments
redcatH commented
model = Sequential()
model.add(Conv2D(32, kernel_size=(5, 9),
activation='relu', input_shape=input_shape))
model.add(MaxPooling2D(pool_size=(2, 4)))
model.add(Conv2D(16, kernel_size=(5, 7), activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 3)))
model.add(Flatten())
#num_classes*4 =104
model.add(Dense(num_classes*4, activation='sigmoid'))
model.compile(loss=keras.losses.binary_crossentropy,
optimizer=keras.optimizers.Adadelta(),
metrics=['accuracy'])
model.fit(x_train, y_train,
batch_size=batch_size,
epochs=epochs,
verbose=1,
validation_data=(x_test, y_test))
ValueError: Error when checking target: expected dense_1 to have shape (104,) but got array with shape (26,)
why? help me~~~~thks~