我最近一直在学习张量流，我无法将相应大小和类型的数值数据发送到tensorflow中的占位符。此代码已改编自https://github.com/SullyChen/Nvidia-Autopilot-TensorFlow。
我的模特档案：
import tensorflow as tf
import scipy
from tensorflow.python.ops import rnn, rnn_cell
def weight_variable(shape):
initial = tf.truncated_normal(shape, stddev=0.1)
return tf.Variable(initial)
def bias_variable(shape):
initial = tf.constant(0.1, shape=shape)
return tf.Variable(initial)
def conv2d(x, W, stride):
return tf.nn.conv2d(x, W, strides=[1, stride, stride, 1], padding='VALID')
class AutopilotRCNModel(object):
"""
Use Recurrent Neural Networks in combination with Convolutional Neural
Networks to predict steering wheel angle.
"""
def __init__(self, n_hidden=50):
# Create a state variable to be passed in through feed_dict
self.c_state = tf.placeholder(tf.float32, shape=[1, n_hidden])
self.h_state = tf.placeholder(tf.float32, shape=[1, n_hidden])
# Do the same with the input x and the target variable y_
self.x = tf.placeholder(tf.float32, shape=[None, 66, 200, 3])
self.y_ = tf.placeholder(tf.float32, shape=[None, 1])
x_image = self.x
# First convolutional layer.
W_conv1 = weight_variable([5, 5, 3, 24])
b_conv1 = bias_variable([24])
# Stride is 2.
h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1, 2) + b_conv1)
# Second convolutional layer.
W_conv2 = weight_variable([5, 5, 24, 36])
b_conv2 = bias_variable([36])
# Stride still set to 2.
h_conv2 = tf.nn.relu(conv2d(h_conv1, W_conv2, 2) + b_conv2)
# Third convolutional layer.
W_conv3 = weight_variable([5, 5, 36, 48])
b_conv3 = bias_variable([48])
# Stride still 2.
h_conv3 = tf.nn.relu(conv2d(h_conv2, W_conv3, 2) + b_conv3)
# Fourth convolutional layer.
W_conv4 = weight_variable([3, 3, 48, 64])
b_conv4 = bias_variable([64])
# Stride now set to 1.
h_conv4 = tf.nn.relu(conv2d(h_conv3, W_conv4, 1) + b_conv4)
# Fifth convolutional layer.
W_conv5 = weight_variable([3, 3, 64, 64])
b_conv5 = bias_variable([64])
# Stride of 1.
h_conv5 = tf.nn.relu(conv2d(h_conv4, W_conv5, 1) + b_conv5)
# Fully connected layer 1.
W_fc1 = weight_variable([1152, 1164])
b_fc1 = bias_variable([1164])
# Requires flattening out the activations.
h_conv5_flat = tf.reshape(h_conv5, [-1, 1152])
h_fc1 = tf.nn.relu(tf.matmul(h_conv5_flat, W_fc1) + b_fc1)
self.keep_prob = tf.placeholder(tf.float32)
h_fc1_drop = tf.nn.dropout(h_fc1, self.keep_prob)
# Fully connected layer 2.
W_fc2 = weight_variable([1164, 100])
b_fc2 = bias_variable([100])
h_fc2 = tf.nn.relu(tf.matmul(h_fc1_drop, W_fc2) + b_fc2)
h_fc2_drop = tf.nn.dropout(h_fc2, self.keep_prob)
print(h_fc2_drop.get_shape())
# LSTM layer 1
# Create weight matrix and bias to map from output of LSTM
# to steering wheel angle in radians.
# Input gate input weights, recurrent weights, and bias.
W_i = weight_variable([100, n_hidden])
U_i = weight_variable([n_hidden, n_hidden])
b_i = bias_variable([n_hidden])
# Forget gate input weights, recurrent weights, and bias.
W_f = weight_variable([100,n_hidden])
U_f = weight_variable([n_hidden, n_hidden])
b_f = bias_variable([n_hidden])
# Candidate gate input weights, recurrent weights, and bias.
W_c = weight_variable([100, n_hidden])
U_c = weight_variable([n_hidden,n_hidden])
b_c = bias_variable([n_hidden])
# Output gate input weights, recurrent weights and bias.
W_o = weight_variable([100, n_hidden])
U_o = weight_variable([n_hidden, n_hidden])
b_o = bias_variable([1])
V_o = weight_variable([n_hidden, n_hidden])
ingate = tf.nn.sigmoid(tf.matmul(h_fc2_drop, W_i) + tf.matmul(self.h_state, U_i) + b_i)
cgate = tf.nn.tanh(tf.matmul(h_fc2_drop, W_c) + tf.matmul(self.h_state, U_c) + b_c)
fgate = tf.nn.sigmoid(tf.matmul(h_fc2_drop, W_f) + tf.matmul(self.h_state, U_f) + b_f)
self.c_state = tf.mul(ingate, cgate) + tf.mul(fgate, self.c_state)
h_rnn1 = tf.nn.sigmoid(tf.matmul(h_fc2_drop, W_o) + \
tf.matmul(self.h_state, U_o) + tf.matmul(self.c_state, V_o) + b_o)
self.h_state = tf.mul(h_rnn1, tf.nn.tanh(self.c_state))
W_out = weight_variable([n_hidden,1])
b_out = bias_variable([1])
self.y = tf.mul(tf.atan(tf.matmul(h_rnn1, W_out) + b_out), 2)
self.loss = tf.square(tf.sub(self.y, self.y_))
第一个测试人员代码在这里：
import model
import driving_data
import tensorflow as tf
import numpy as np
n_hidden = 65
rcn = model.AutopilotRCNModel(n_hidden=n_hidden)
xs, ys = driving_data.LoadTrainBatch(1)
c_state = np.zeros((1,n_hidden),dtype=np.float32)
h_state = np.zeros((1,n_hidden),dtype=np.float32)
sess = tf.InteractiveSession()
train_step = tf.train.AdamOptimizer().minimize(rcn.loss)
sess.run(tf.initialize_all_variables())
train_step.run(
feed_dict = {
rcn.x: xs,
rcn.y_: ys,
rcn.keep_prob: 0.8,
rcn.c_state: c_state,
rcn.h_state: h_state
}
)
我收到了这个错误：
Traceback (most recent call last):
File "test.py", line 28, in <module>
rcn.h_state: h_state
File "/home/thomas/.local/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 1621, in run
_run_using_default_session(self, feed_dict, self.graph, session)
File "/home/thomas/.local/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 3804, in _run_using_default_session
session.run(operation, feed_dict)
File "/home/thomas/.local/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 717, in run
run_metadata_ptr)
File "/home/thomas/.local/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 915, in _run
feed_dict_string, options, run_metadata)
File "/home/thomas/.local/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 965, in _do_run
target_list, options, run_metadata)
File "/home/thomas/.local/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 985, in _do_call
raise type(e)(node_def, op, message)
tensorflow.python.framework.errors.InvalidArgumentError: You must feed a value for placeholder tensor 'Placeholder' with dtype float and shape [1,65]
[[Node: Placeholder = Placeholder[dtype=DT_FLOAT, shape=[1,65], _device="/job:localhost/replica:0/task:0/gpu:0"]()]]
[[Node: _recv_add_13_0 = _Recv[client_terminated=true, recv_device="/job:localhost/replica:0/task:0/cpu:0", send_device="/job:localhost/replica:0/task:0/cpu:0", send_device_incarnation=7747556615882019196, tensor_name="add_13:0", tensor_type=DT_FLOAT, _device="/job:localhost/replica:0/task:0/cpu:0"]()]]
Caused by op u'Placeholder', defined at:
File "test.py", line 9, in <module>
rcn = model.AutopilotRCNModel(n_hidden=n_hidden)
File "/home/thomas/projects/lstm_autopilot/model.py", line 27, in __init__
self.c_state = tf.placeholder(tf.float32, shape=[1, n_hidden])
File "/home/thomas/.local/lib/python2.7/site-packages/tensorflow/python/ops/array_ops.py", line 1330, in placeholder
name=name)
File "/home/thomas/.local/lib/python2.7/site-packages/tensorflow/python/ops/gen_array_ops.py", line 1762, in _placeholder
name=name)
File "/home/thomas/.local/lib/python2.7/site-packages/tensorflow/python/framework/op_def_library.py", line 748, in apply_op
op_def=op_def)
File "/home/thomas/.local/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 2388, in create_op
original_op=self._default_original_op, op_def=op_def)
File "/home/thomas/.local/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 1300, in __init__
self._traceback = _extract_stack()
InvalidArgumentError (see above for traceback): You must feed a value for placeholder tensor 'Placeholder' with dtype float and shape [1,65]
[[Node: Placeholder = Placeholder[dtype=DT_FLOAT, shape=[1,65], _device="/job:localhost/replica:0/task:0/gpu:0"]()]]
[[Node: _recv_add_13_0 = _Recv[client_terminated=true, recv_device="/job:localhost/replica:0/task:0/cpu:0", send_device="/job:localhost/replica:0/task:0/cpu:0", send_device_incarnation=7747556615882019196, tensor_name="add_13:0", tensor_type=DT_FLOAT, _device="/job:localhost/replica:0/task:0/cpu:0"]()]]
我的实际数字feed_dict数据与占位符所需的形状和类型相同。不确定这里有什么问题。我认为np.zeros((1,n_hidden), dtype=np.float32)应该很好地提供tf.placeholder(tf.float32,size=[1,n_hidden])。
答案 0 :(得分：1)
我的问题是我正在更新课堂内的占位符，这是一个明确的禁忌。我刚刚改变了
self.c_state = tf.mul(ingate, cgate) + tf.mul(fgate, self.c_state)
到
self.new_c_state = tf.mul(ingate, cgate) + tf.mul(fgate, self.c_state)
和
self.h_state = tf.mul(h_rnn1, tf.nn.tanh(self.c_state))
到
self.new_h_state = tf.mul(h_rnn1, tf.nn.tanh(self.new_c_state))
!!!这一切都有道理。占位符是数据的占位符。不要对它们进行更新操作或事情变得棘手。