keras 顺序 model 用于图像数据

Question

i'm trying to train a dense network for images.

the train set shape returns:

train_X.shape
(26032, 32, 32)

and the network architecture is:

def get_model(input_shape):
    model = Sequential([
    Dense(16, activation='relu', input_shape=(input_shape[1],input_shape[2],1)),
    Dense(8, activation='relu'),
    Dense(64, activation='relu'),
    Flatten(),
    Dense(10, activation='softmax')]) 
    return model

but i get an error when i try to train it:

Error when checking input: expected dense_17_input to have 4 dimensions, but got array with shape (73257, 32, 32)

can u assist please?

Answer 1

For this specific architecture, you don't need a 4th dimension. In input_shape , you won't need to add a 1 .

 input_shape=(input_shape[1], input_shape[2])

You will only need to do so for a CNN.