input_shape of an 8x8 board game to a Neural Network with Keras

Question

I am very green behind the ears when it comes to creating a NN. Right now I am receiving the following error:

ValueError: Error when checking : expected dense_1_input to have 3 dimensions, but got array with shape (8, 8)

Background: I am using an 8x8 board this is how I am initializing it:

self.state = np.zeros((LENGTH, LENGTH))

Here is the code where I build my Model:

def build_model(self):
    #builds the NN for Deep-Q Model
    model = Sequential() 
    model.add(Dense(24,input_shape = (LENGTH, LENGTH), activation='relu'))
    model.add(Flatten())
    model.add(Dense(24, activation='relu'))
    model.add(Dense(self.action_size, activation = 'linear'))
    model.compile(loss='mse', optimizer='Adam')

    return model

I figured since the shape of the board is (8,8) that the input_size should be the same. Not sure what I am doing wrong?

Just in case this is helpful:

The game I have made is super simple that involves 5 pieces on the board:

• player1 has 1 piece and can move forward and backward diagonally only 1 step
• player2 has 4 pieces and can only move forward from their position diagonally 1 step

The objective for player1 is to get to the other side of the board The objective for player2 is to trap player 1 so he cannot move

Any help would be greatly appreciated!

Answer 1

I managed to get it to run... but this is how: I changed input_shape to this input_shape = (LENGTH, ) the problem is I have no idea why it accepts this? and if I am even doing it right?

No, the first input shape you have used (i.e. (LENGTH,LENGTH)) was the correct one. Note that the input_shape argument specifies the shape of one and only one single training sample, and not all the training data you have. For example, if you have 1000 boards of 8x8 then the training data has a shape of (1000, 8, 8) but the input_shape argument must be assigned (8,8), i.e. the shape of one training sample.

Further, as you may or may not know the Dense layer is applied on the last axis and since you have defined the input shape of Dense layer as (LENGTH,LENGTH), the Dense layer would be applied not on all of the input (i.e. board) but on the second axis (i.e. rows of the board). I guess this is not what you are looking for, so you have two options here: 1) you can move the Flatten layer to the top and put it as the first layer of the model:

model = Sequential()
model.add(Flatten(input_shape=(LENGTH, LENGTH)))
model.add(Dense(24, activation='relu'))
# the rest of the model

or 2) you can reshape the training data to make it have a shape of (num_boards, LENGTH*LENGTH) and adjust the input_shape argument accordingly (in this case there is no need for the Flatten layer you have in your model, you can remove it):

training_data = np.reshape(training_data, (num_boards, LENGTH*LENGTH))

model = Sequential() 
model.add(Dense(24,input_shape=(LENGTH*LENGTH,), activation='relu'))

---

As a side note, if you have only one training/test sample (which is odd!) or whatever number of training/test samples, the first axis of the training/test data array must corresponds to samples, i.e. the shape of all the training/test data array must be (num_sample, ...). Otherwise, you would get errors complaining about shape, as you have gotten, when calling fit/predict/evaluate methods. The same thing applies to the array that contains the training/test labels.