我有以下示例代码来测试BasicRNNCell
。我想获取其内部矩阵,以便我可以使用自己的代码计算output_res
,newstate_res
的值,以确保我可以重现output_res
的值, newstate_res
。
在tensorflow源代码中,它表示output = new_state = act(W * input + U * state + B)
。有人知道如何获得W
和U
吗? (我尝试访问cell._kernel
,但它不可用。)
$ cat ./main.py
#!/usr/bin/env python
# vim: set noexpandtab tabstop=2 shiftwidth=2 softtabstop=-1 fileencoding=utf-8:
import tensorflow as tf
import numpy as np
batch_size = 4
vector_size = 3
inputs = tf.placeholder(
tf.float32
, [batch_size, vector_size]
)
num_units = 2
state = tf.zeros([batch_size, num_units], tf.float32)
cell = tf.contrib.rnn.BasicRNNCell(num_units=num_units)
output, newstate = cell(inputs = inputs, state = state)
X = np.zeros([batch_size, vector_size])
#X = np.ones([batch_size, vector_size])
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
output_res, newstate_res = sess.run([output, newstate], feed_dict = {inputs: X})
print(output_res)
print(newstate_res)
sess.close()
$ ./main.py
[[ 0. 0.]
[ 0. 0.]
[ 0. 0.]
[ 0. 0.]]
[[ 0. 0.]
[ 0. 0.]
[ 0. 0.]
[ 0. 0.]]
答案 0 :(得分:4)
简短回答:你在cell._kernel
之后认出你了。这里有一些使用variables
属性来获取内核(和偏差)的代码,该属性位于大多数TensorFlow RNN中:
import tensorflow as tf
import numpy as np
batch_size = 4
vector_size = 3
inputs = tf.placeholder(tf.float32, [batch_size, vector_size])
num_units = 2
state = tf.zeros([batch_size, num_units], tf.float32)
cell = tf.contrib.rnn.BasicRNNCell(num_units=num_units)
output, newstate = cell(inputs=inputs, state=state)
print("Output of cell.variables is a list of Tensors:")
print(cell.variables)
kernel, bias = cell.variables
X = np.zeros([batch_size, vector_size])
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
output_, newstate_, k_, b_ = sess.run(
[output, newstate, kernel, bias], feed_dict = {inputs: X})
print("Output:")
print(output_)
print("New State == Output:")
print(newstate_)
print("\nKernel:")
print(k_)
print("\nBias:")
print(b_)
输出
Output of cell.variables is a list of Tensors:
[<tf.Variable 'basic_rnn_cell/kernel:0' shape=(5, 2) dtype=float32_ref>,
<tf.Variable 'basic_rnn_cell/bias:0' shape=(2,) dtype=float32_ref>]
Output:
[[ 0. 0.]
[ 0. 0.]
[ 0. 0.]
[ 0. 0.]]
New State == Output:
[[ 0. 0.]
[ 0. 0.]
[ 0. 0.]
[ 0. 0.]]
Kernel:
[[ 0.41417515 -0.64997244]
[-0.40868729 -0.90995187]
[ 0.62134564 -0.88962835]
[-0.35878009 -0.25680023]
[ 0.35606658 -0.83596271]]
Bias:
[ 0. 0.]
答案很长:你也问过如何获得W和U.让我复制call
的实现并讨论W和U的位置。
def call(self, inputs, state):
"""Most basic RNN: output = new_state = act(W * input + U * state + B)."""
gate_inputs = math_ops.matmul(
array_ops.concat([inputs, state], 1), self._kernel)
gate_inputs = nn_ops.bias_add(gate_inputs, self._bias)
output = self._activation(gate_inputs)
return output, output
不看起来像那里有W和U,但他们在那里。本质上,内核的第一行vector_size
是W,内核的下一行num_units
行是U.也许在LaTeX中查看元素数学是有帮助的:
我使用 m 作为通用批处理索引, v 作为vector_size
, n 作为{{ 1}}和 b 为num_units
。 [; ] 表示连接。由于TensorFlow是批量主要的,因此实现通常使用右乘乘矩阵。
由于这是一个非常基本的RNN,batch_size
。 &#34;历史&#34;对于下一次迭代,只是当前迭代的输出。