Tensorflow TypeError: Fetch argument Brak ma nieprawidłowy typ <type 'NoneType'>?

Question

Tworzę RNN luźno oparty na tensorflow's tutorial. Z odpowiednimi częściami mojego modelu następująco ("Komentarz, jeśli chcesz zobaczyć więcej, nie chcę, aby to stanowisko zbyt długo xD):

input_sequence = tf.placeholder(tf.float32, [BATCH_SIZE, TIME_STEPS, PIXEL_COUNT + AUX_INPUTS]) 
output_actual = tf.placeholder(tf.float32, [BATCH_SIZE, OUTPUT_SIZE]) 

lstm_cell = tf.nn.rnn_cell.BasicLSTMCell(CELL_SIZE, state_is_tuple=False) 
stacked_lstm = tf.nn.rnn_cell.MultiRNNCell([lstm_cell] * CELL_LAYERS, state_is_tuple=False) 

initial_state = state = stacked_lstm.zero_state(BATCH_SIZE, tf.float32) 
outputs = [] 

with tf.variable_scope("LSTM"): 
    for step in xrange(TIME_STEPS): 
     if step > 0: 
      tf.get_variable_scope().reuse_variables() 
     cell_output, state = stacked_lstm(input_sequence[:, step, :], state) 
     outputs.append(cell_output) 

final_state = state 

i karmienie:

cross_entropy = tf.reduce_mean(-tf.reduce_sum(output_actual * tf.log(prediction), reduction_indices=[1])) 
train_step = tf.train.AdamOptimizer(learning_rate=LEARNING_RATE).minimize(cross_entropy) 
correct_prediction = tf.equal(tf.argmax(prediction, 1), tf.argmax(output_actual, 1)) 
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32)) 

with tf.Session() as sess: 
    sess.run(tf.initialize_all_variables()) 
    numpy_state = initial_state.eval() 

    for i in xrange(1, ITERATIONS): 
     batch = DI.next_batch() 

     print i, type(batch[0]), np.array(batch[1]).shape, numpy_state.shape 

     if i % LOG_STEP == 0: 
      train_accuracy = accuracy.eval(feed_dict={ 
       initial_state: numpy_state, 
       input_sequence: batch[0], 
       output_actual: batch[1] 
      }) 

      print "Iteration " + str(i) + " Training Accuracy " + str(train_accuracy) 

     numpy_state, train_step = sess.run([final_state, train_step], feed_dict={ 
      initial_state: numpy_state, 
      input_sequence: batch[0], 
      output_actual: batch[1] 
      }) 

a gdy uruchamiam to, pojawia się następujący błąd:

Traceback (most recent call last): 
    File "/home/agupta/Documents/Projects/Image-Recognition-with-LSTM/RNN/feature_tracking/model.py", line 109, in <module> 
    output_actual: batch[1] 
    File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 698, in run 
    run_metadata_ptr) 
    File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 838, in _run 
    fetch_handler = _FetchHandler(self._graph, fetches) 
    File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 355, in __init__ 
    self._fetch_mapper = _FetchMapper.for_fetch(fetches) 
    File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 181, in for_fetch 
    return _ListFetchMapper(fetch) 
    File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 288, in __init__ 
    self._mappers = [_FetchMapper.for_fetch(fetch) for fetch in fetches] 
    File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 178, in for_fetch 
    (fetch, type(fetch))) 
TypeError: Fetch argument None has invalid type <type 'NoneType'> 

Może najdziwniejsze jest to, że ten błąd zostanie rzucony drugą iteracji, a pierwszy w orki zupełnie w porządku. Ruję włosy, próbując to naprawić, więc każda pomoc będzie bardzo cenna.

Answer 1

Ponownie przypisano zmienną train_step do drugiego elementu wyniku sess.run() (która ma być None). Dlatego w drugiej iteracji train_step jest None, co prowadzi do błędu.

Rozwiązaniem jest szczęście proste:

for i in xrange(1, ITERATIONS): 

    # ... 

    # Discard the second element of the result. 
    numpy_state, _ = sess.run([final_state, train_step], feed_dict={ 
     initial_state: numpy_state, 
     input_sequence: batch[0], 
     output_actual: batch[1] 
     })