CODEWITHSUNDEEP
numpykerastheano
ZerkTheMighty
ZerkTheMighty

Reputation: 25

ValueError: Error when checking : expected input_2 to have shape (162,) but got array with shape (1,)

I have defined the following model in Keras:

init_weights = he_normal()
main_input = Input(shape=(FEATURE_VECTOR_SIZE,)) #size 54
aux_input = Input(shape=(AUX_FEATURE_VECTOR_SIZE,)) #size 162
merged_input = concatenate([main_input, aux_input])

shared1 = Dense(164, activation='relu', kernel_initializer=init_weights)(merged_input)
shared2 = Dense(150, activation='relu', kernel_initializer=init_weights)(shared1)

main_output = Dense(NUM_ACTIONS, activation='linear', kernel_initializer=init_weights, name='main_output')(shared2)
aux_output = Dense(1, activation='linear', kernel_initializer=init_weights, name='aux_output')(shared2)

rms = RMSprop(lr=ALPHA)
model = Model(inputs=[main_input, aux_input], outputs=[main_output, aux_output])
model.compile(optimizer=rms, loss='mse')

Later on I attempt to use it to make a prediction, as below:

aux_dummy = np.zeros(shape=(AUX_FEATURE_VECTOR_SIZE,))
print(aux_dummy.shape)
print(aux_dummy)
q_vals, _ = model.predict([encode_1_hot(next_state), aux_dummy], batch_size=1)

However, I get an error complaining that the auxiliary input is not of the proper shape (Keras claims it should be shape (162,) and that it is actually shape (1,))

But when I print out the shape I get exactly what it seems to be asking for (see below).

(162,)
[0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0.
 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0.
 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0.
 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0.
 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0.
 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0.
 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]
Traceback (most recent call last):
  File "grid_exp.py", line 94, in 
    RL_episode(max_steps)
  File "/Users/ZerkTheMighty/Code/RL2/project/Gridworld/rl_glue.py", line 220, in RL_episode
    rl_step_result = RL_step()
  File "/Users/ZerkTheMighty/Code/RL2/project/Gridworld/rl_glue.py", line 151, in RL_step
    last_action = agent.agent_step(result['reward'],result['state'])
  File "/Users/ZerkTheMighty/Code/RL2/project/Gridworld/grid_agent.py", line 170, in agent_step
    q_vals, _ = model.predict([encode_1_hot(next_state), aux_dummy], batch_size=1)
  File "/Users/ZerkTheMighty/Code/RL2/lib/python2.7/site-packages/keras/engine/training.py", line 1817, in predict
    check_batch_axis=False)
  File "/Users/ZerkTheMighty/Code/RL2/lib/python2.7/site-packages/keras/engine/training.py", line 123, in _standardize_input_data
    str(data_shape))
ValueError: Error when checking : expected input_2 to have shape (162,) but got array with shape (1,)

I'm at a loss as to what I should be changing in order to get this to work, but I have a suspicion that I'm overlooking something obvious. Suggestions?

I'm using Keras 2.1.5, Theano 1.0.1, numpy 1.14.2, and python 2.7.12

Upvotes: 0

Views: 193

Answers (2)

WindStreet
WindStreet

Reputation: 21

Try this:

 q_vals, _ = model.predict([[encode_1_hot(next_state), aux_dummy]], batch_size=1)

[[]] is like the form that you give

Upvotes: 0

Daniel GL
Daniel GL

Reputation: 1249

Try with

aux_dummy = np.zeros(shape=(1,AUX_FEATURE_VECTOR_SIZE,))

The first dimension is needed to specify the number of examples given to the model.

Upvotes: 1

Related Questions