TensorFlowチュートリアル に基づいて大まかにRNNを構築しています。
モデルの関連部分は次のとおりです。
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
そして給餌:
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]
})
これを実行すると、次のエラーが表示されます。
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'>
おそらく最も奇妙な部分は、このエラーがsecond反復をスローし、最初のエラーが完全に正常に動作することです。私はこれを修正しようとして髪を裂いているので、どんな助けでも大歓迎です。
_train_step
_変数をsess.run()
(たまたまNone
である)の結果の2番目の要素に再割り当てしています。したがって、2回目の反復では、_train_step
_はNone
になり、エラーが発生します。
修正は幸い簡単です:
_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]
})
_
このエラーが発生するもう1つの一般的な理由は、要約フェッチ操作を含めても要約を作成していない場合です。
例:
# tf.summary.scalar("loss", loss) # <- uncomment this line and it will work fine
summary_op = tf.summary.merge_all()
sess = tf.Session()
# ...
summary = sess.run([summary_op, ...], feed_dict={...}) # TypeError, summary_op is "None"!
さらに紛らわしいのは、summary_op
はそれ自体Noneではありません。それは、セッションのrunメソッドの内部から発生するエラーです。