0
を実行し、次の例で考えてみましょう:私はその中間を維持するために、各反復でゆっくりと変化するテンソルstate
を持つように期待していた保存テンソル値
import tensorflow as tf
import math
import numpy as np
INPUTS = 10
HIDDEN_1 = 20
BATCH_SIZE = 3
def create_graph(inputs):
with tf.name_scope('h1'):
weights = tf.Variable(
tf.truncated_normal([INPUTS, HIDDEN_1],
stddev=1.0/math.sqrt(float(INPUTS))),
name='weights')
biases = tf.Variable(tf.zeros([HIDDEN_1]),
name='biases')
state = tf.Variable(tf.zeros([HIDDEN_1]), name='inner_state')
state = tf.Print(state, [state], message=" this is state before: ")
state = 0.9*state + 0.1*(tf.matmul(inputs, weights) + biases)
state = tf.Print(state, [state], message=" this is state after: ")
output = tf.nn.relu(state)
return output
def data_iter():
while True:
idxs = np.random.rand(BATCH_SIZE, INPUTS)
yield idxs
with tf.Graph().as_default():
inputs = tf.placeholder(tf.float32, shape=(BATCH_SIZE, INPUTS))
output = create_graph(inputs)
sess = tf.Session()
# Run the Op to initialize the variables.
init = tf.initialize_all_variables()
sess.run(init)
iter_ = data_iter()
for i in xrange(0, 2):
print ("iteration: ",i)
input_data = iter_.next()
out = sess.run(output, feed_dict={ inputs: input_data})
を。しかし、私が見ていて、各sess.run
呼び出しで、状態はゼロ値に開始できることである:
('iteration: ', 0)
I tensorflow/core/kernels/logging_ops.cc:79] this is state before: [0 0 0...]
I tensorflow/core/kernels/logging_ops.cc:79] this is state after: [0.007762237 0.044753391 0.049343754...]
('iteration: ', 1)
I tensorflow/core/kernels/logging_ops.cc:79] this is state before: [0 0 0...]
I tensorflow/core/kernels/logging_ops.cc:79] this is state after: [0.040079735 0.074709542 0.078258425...]
私はこの振る舞い
編集
に対処する方法を任意の明確化をお願い申し上げますの行をtf.Print
行に書き換えて間違った割り当てを置き換えた後
state = state.assign(0.9*state + 0.1*(tf.matmul(inputs, weights) + biases))
私はこれらのエラーを取得する:あなたがstate = 0.9 * state + 0.1 * (tf.matmul(inputs, weights) + biases)
を書くとき、あなたは変数state
の値を
Traceback (most recent call last):
File "cycles_in_graphs.py", line 33, in <module>
output = create_graph(inputs)
File "cycles_in_graphs.py", line 21, in create_graph
state = state.assign(0.9*state + 0.1*(tf.matmul(inputs, weights) + biases))
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/variables.py", line 453, in assign
return state_ops.assign(self._variable, value, use_locking=use_locking)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/gen_state_ops.py", line 40, in assign
use_locking=use_locking, name=name)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/op_def_library.py", line 655, in apply_op
op_def=op_def)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py", line 2156, in create_op
set_shapes_for_outputs(ret)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py", line 1612, in set_shapes_for_outputs
shapes = shape_func(op)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/state_ops.py", line 197, in _AssignShape
return [op.inputs[0].get_shape().merge_with(op.inputs[1].get_shape())]
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/tensor_shape.py", line 554, in merge_with
(self, other))
ValueError: Shapes (20,) and (3, 20) are not compatible
ありがとうございました。 AttributeError: 'Tensor'オブジェクトに 'assign'属性がありません。 " – diffeomorphism
はい、このエラーが発生しました。「状態= state.assign(0.9 *状態+ 0.1 *(tf.matmul(入力、重み)+バイアス)直前に 'state = tf.Print(state)'を実行します。 'tf.Variable'だけが属性' assign() 'を持っています –
ありがとう!私は代入式を更新しましたが、いくつかの互換性のない形状エラーが発生しました。私は誤差を伴うOPを更新しました – diffeomorphism