我在tensorflow中有以下代码，我试图在其中使用GRU计算反向传播的梯度。
SQLSTATE[42S02]: Base table or view not found: 1146 Table
'mycrm.access_permissions' doesn't exist (SQL: select `permissions`.*,
`access_permissions`.`id_role` as `pivot_id_role`,
`access_permissions`.`id_permission` as `pivot_id_permission` from
`permissions` inner join `access_permissions` on `permissions`.`id` =
`access_permissions`.`id_permission` where `access_permissions`.`id_role` =
1) (View:
F:\MYCRM\mycrm\packages\tc\calculator\src\views\permission_pack.blade.php)
因此，只需在代码开头将dtype从import tensorflow as tf
import numpy as np
cell_size = 32
seq_length = 1000
time_steps1 = 500
time_steps2 = seq_length - time_steps1
x_t = np.arange(1, seq_length + 1)
x_t_plus_1 = np.arange(2, seq_length + 2)
tf.set_random_seed(123)
m_dtype = tf.float32
input_1 = tf.placeholder(dtype=m_dtype, shape=[None, time_steps1, 1], name="input_1")
input_2 = tf.placeholder(dtype=m_dtype, shape=[None, time_steps2, 1], name="input_2")
labels1 = tf.placeholder(dtype=m_dtype, shape=[None, time_steps1, 1], name="labels_1")
labels2 = tf.placeholder(dtype=m_dtype, shape=[None, time_steps2, 1], name="labels_2")
labels = tf.concat([labels1, labels2], axis=1, name="labels")
def model(input_feat1, input_feat2):
with tf.variable_scope("GRU"):
cell1 = tf.nn.rnn_cell.GRUCell(cell_size)
cell2 = tf.nn.rnn_cell.GRUCell(cell_size)
initial_state = tf.placeholder(shape=[None, cell_size], dtype=m_dtype, name="initial_state")
with tf.variable_scope("First50"):
# output1: shape=[1, time_steps1, 32]
output1, new_state1 = tf.nn.dynamic_rnn(cell1, input_feat1, dtype=m_dtype, initial_state=initial_state)
with tf.variable_scope("Second50"):
# output2: shape=[1, time_steps2, 32]
output2, new_state2 = tf.nn.dynamic_rnn(cell2, input_feat2, dtype=m_dtype, initial_state=new_state1)
with tf.variable_scope("output"):
# output shape: [1, time_steps1 + time_steps2, 32] => [1, 100, 32]
output = tf.concat([output1, output2], axis=1)
output = tf.reshape(output, shape=[-1, cell_size])
output = tf.layers.dense(output, units=1)
output = tf.reshape(output, shape=[1, time_steps1 + time_steps2, 1])
with tf.variable_scope("outputs_1_2_reshaped"):
output1 = tf.slice(input_=output, begin=[0, 0, 0], size=[-1, time_steps1, -1])
output2 = tf.slice(input_=output, begin=[0, time_steps1, 0], size=[-1, time_steps2, 1])
print(output.get_shape().as_list(), "1")
print(output1.get_shape().as_list(), "2")
print(output2.get_shape().as_list(), "3")
return output, output1, output2, initial_state, new_state1, new_state2
def loss(output, output1, output2, labels, labels1, labels2):
loss = tf.reduce_sum(tf.sqrt(tf.square(output - labels)))
loss1 = tf.reduce_sum(tf.sqrt(tf.square(output1 - labels1)))
loss2 = tf.reduce_sum(tf.sqrt(tf.square(output2 - labels2)))
return loss, loss1, loss2
def optimize(loss, loss1, loss2, initial_state, new_state1, new_state2):
with tf.name_scope('Optimizer'):
update_ops = tf.get_collection(tf.GraphKeys.UPDATE_OPS)
with tf.control_dependencies(update_ops):
optimizer = tf.train.AdamOptimizer(learning_rate=0.001)
grads1 = tf.gradients(loss2, new_state1)
grads2 = tf.gradients(loss1, initial_state)
grads3 = tf.gradients(new_state1, initial_state, grad_ys=grads1)
grads_wrt_initial_state_1 = tf.add(grads2, grads3)
grads_wrt_initial_state_2 = tf.gradients(loss, initial_state, grad_ys=None)
return grads_wrt_initial_state_1, grads_wrt_initial_state_2
output, output1, output2, initial_state, new_state1, new_state2 = model(input_1, input_2)
loss, loss1, loss2 = loss(output, output1, output2, labels, labels1, labels2)
grads_wrt_initial_state_1, grads_wrt_initial_state_2 = optimize(loss, loss1, loss2, initial_state, new_state1, new_state2)
init = tf.global_variables_initializer()
with tf.Session() as sess:
sess.run(init)
in1 = np.reshape(x_t[:time_steps1], newshape=(1, time_steps1, 1))
in2 = np.reshape(x_t[time_steps1:], newshape=(1, time_steps2, 1))
l1 = np.reshape(x_t_plus_1[:time_steps1], newshape=(1, time_steps1, 1))
l2 = np.reshape(x_t_plus_1[time_steps1:], newshape=(1, time_steps2, 1))
i_s = np.zeros([1, cell_size])
t1, t2 = sess.run([grads_wrt_initial_state_1, grads_wrt_initial_state_2], feed_dict={input_1: in1,
input_2: in2,
labels1: l1,
labels2: l2,
initial_state: i_s})
print(np.mean(t1), np.mean(t2))
print(np.sum(t1), np.sum(t2))
更改为tf.float32，即可使用张量流更改反向传播梯度的整个值。
所以我想知道为什么以及应该使用tf.float64还是tf.float32