ValueError: Error when checking input: expected dense_1_input to have 4 dimensions, but got array with shape (20593, 4, 1) - deep-learning

Question

I am trying to follow sentdex's game ai bot tutorial(https://www.youtube.com/watch?v=G-KvpNGudLw), but instead of tflearn, I am trying to use keras for the same implementation.
Model Function
def neural_network_model(input_size):
network = Sequential()
network.add(Dense(units = 128, activation='relu', kernel_initializer = 'uniform', input_shape = [None, input_size, 1]))
network.add(Dropout(0.2))
network.add(Dense(units = 256, activation='relu', kernel_initializer = 'uniform'))
network.add(Dropout(0.2))
network.add(Dense(units = 512, activation='relu', kernel_initializer = 'uniform'))
network.add(Dropout(0.2))
network.add(Dense(units = 256, activation='relu', kernel_initializer = 'uniform'))
network.add(Dropout(0.2))
network.add(Dense(units = 128, activation='relu', kernel_initializer = 'uniform'))
network.add(Dropout(0.2))
network.add(Dense(units = 2, activation = 'softmax', kernel_initializer = 'uniform'))
adam = optimizers.Adam(lr=LR, decay=0.0)
network.compile(optimizer=adam, loss='categorical_crossentropy', metrics = ['accuracy'])
return network
Model Training Function
def train_model(training_data, model=False):
X = np.array([i[0] for i in training_data]).reshape(-1, len(training_data[0][0]), 1)
Y = [i[1] for i in training_data]
if not model:
model = neural_network_model(len(X[0]))
model.fit(X,Y, epochs = 5)
return model
where the training data is :
def initial_population():
training_data = [] # Observations and the move made, append to only when score > 50
scores = []
accepted_scores = []
for x in range(initial_games):
score = 0
game_memory = []
prev_observation = []
for x in range(goal_steps):
action = random.randrange(0,2) # 0's and 1's
observation, reward, done, info = env.step(action)
if len(prev_observation) > 0 :
game_memory.append([prev_observation,action])
prev_observation = observation
score += reward
if done:
break
if score >= score_requirement:
accepted_scores.append(score)
for data in game_memory:
if data[1] == 1:
output = [0,1]
if data[1] == 0:
output = [1,0]
training_data.append([data[0], output])
env.reset()
scores.append(score)
training_data_save = np.array(training_data)
np.save('saved.npy', training_data_save)
print('Average accepted score : ', mean(accepted_scores))
print('Median accepted scores : ', median(accepted_scores))
print(Counter(accepted_scores))
return training_data
training_data = initial_population()
The error I am getting is in the title. I am new to deep learning and I don't have a good grasp yet on the reshaping part.

Answer 1

So after a bit tweaking I finally got the network to work. If anyone is interested, I fixed it by doing the following:
I changed the first Dense layer to :
network.add(Dense(units = 128, activation='relu', kernel_initializer = 'uniform', input_dim = input_size))
and in the model training function, I changed the shape of the input to 2D instead of 3D :
def train_model(training_data, model=False):
X = np.array([i[0] for i in training_data]).reshape(-1, len(training_data[0][0]))
Y = np.array([i[1] for i in training_data])
if not model:
model = neural_network_model(len(X[0]))
model.fit(X,Y, epochs = 5)
return model