Должен указывать значение для тензора-заполнителя
Я пытаюсь настроить график Tensorboard для моей нейронной сети, и у меня возникли некоторые проблемы. Сеть работает нормально без каких-либо опций графика, которые я добавил, но у меня возникают проблемы с пониманием того, как обеспечить передачу правильных параметров в то, что необходимо в Tensorboard. Полное сообщение об ошибке:
File "<ipython-input-15-7ef8ba55b0b8>", line 1, in <module>
runfile(‘INTROPATH/USERNAME/My Documents/Python/trainwithgraph.py', wdir=‘INTROPATH/USERNAME/My Documents/Python')
File "C:\Users\USERNAME\AppData\Local\Continuum\anaconda3\lib\site-packages\spyder\utils\site\sitecustomize.py", line 710, in runfile
execfile(filename, namespace)
File "C:\Users\USERNAME\AppData\Local\Continuum\anaconda3\lib\site-packages\spyder\utils\site\sitecustomize.py", line 101, in execfile
exec(compile(f.read(), filename, 'exec'), namespace)
File “INTROPATH/USERNAME/My Documents/Python/trainwithgraph.py", line 240, in <module>
train(num_iteration=9000)
File “INTROPATH/USERNAME/My Documents/Python/trainwithgraph.py", line 229, in train
summary, acc = session.run([merged,accuracy], feed_dict=feed_dict_val)
File "C:\Users\USERNAME\AppData\Local\Continuum\anaconda3\lib\site-packages\tensorflow\python\client\session.py", line 895, in run
run_metadata_ptr)
File "C:\Users\USERNAME\AppData\Local\Continuum\anaconda3\lib\site-packages\tensorflow\python\client\session.py", line 1128, in _run
feed_dict_tensor, options, run_metadata)
File "C:\Users\USERNAME\AppData\Local\Continuum\anaconda3\lib\site-packages\tensorflow\python\client\session.py", line 1344, in _do_run
options, run_metadata)
File "C:\Users\USERNAME\AppData\Local\Continuum\anaconda3\lib\site-packages\tensorflow\python\client\session.py", line 1363, in _do_call
raise type(e)(node_def, op, message)
InvalidArgumentError: You must feed a value for placeholder tensor 'y_true_8' with dtype float and shape [?,2]
[[Node: y_true_8 = Placeholder[dtype=DT_FLOAT, shape=[?,2], _device="/job:localhost/replica:0/task:0/device:CPU:0"]()]]
Caused by op 'y_true_8', defined at:
File "C:\Users\USERNAME\AppData\Local\Continuum\anaconda3\lib\site-packages\spyder\utils\ipython\start_kernel.py", line 245, in <module>
main()
File "C:\Users\USERNAME\AppData\Local\Continuum\anaconda3\lib\site-packages\spyder\utils\ipython\start_kernel.py", line 241, in main
kernel.start()
File "C:\Users\USERNAME\AppData\Local\Continuum\anaconda3\lib\site-packages\ipykernel\kernelapp.py", line 477, in start
ioloop.IOLoop.instance().start()
File "C:\Users\USERNAME\AppData\Local\Continuum\anaconda3\lib\site-packages\zmq\eventloop\ioloop.py", line 177, in start
super(ZMQIOLoop, self).start()
File "C:\Users\USERNAME\AppData\Local\Continuum\anaconda3\lib\site-packages\tornado\ioloop.py", line 888, in start
handler_func(fd_obj, events)
File "C:\Users\USERNAME\AppData\Local\Continuum\anaconda3\lib\site-packages\tornado\stack_context.py", line 277, in null_wrapper
return fn(*args, **kwargs)
File "C:\Users\USERNAME\AppData\Local\Continuum\anaconda3\lib\site-packages\zmq\eventloop\zmqstream.py", line 440, in _handle_events
self._handle_recv()
File "C:\Users\USERNAME\AppData\Local\Continuum\anaconda3\lib\site-packages\zmq\eventloop\zmqstream.py", line 472, in _handle_recv
self._run_callback(callback, msg)
File "C:\Users\USERNAME\AppData\Local\Continuum\anaconda3\lib\site-packages\zmq\eventloop\zmqstream.py", line 414, in _run_callback
callback(*args, **kwargs)
File "C:\Users\USERNAME\AppData\Local\Continuum\anaconda3\lib\site-packages\tornado\stack_context.py", line 277, in null_wrapper
return fn(*args, **kwargs)
File "C:\Users\USERNAME\AppData\Local\Continuum\anaconda3\lib\site-packages\ipykernel\kernelbase.py", line 283, in dispatcher
return self.dispatch_shell(stream, msg)
File "C:\Users\USERNAME\AppData\Local\Continuum\anaconda3\lib\site-packages\ipykernel\kernelbase.py", line 235, in dispatch_shell
handler(stream, idents, msg)
File "C:\Users\USERNAME\AppData\Local\Continuum\anaconda3\lib\site-packages\ipykernel\kernelbase.py", line 399, in execute_request
user_expressions, allow_stdin)
File "C:\Users\USERNAME\AppData\Local\Continuum\anaconda3\lib\site-packages\ipykernel\ipkernel.py", line 196, in do_execute
res = shell.run_cell(code, store_history=store_history, silent=silent)
File "C:\Users\USERNAME\AppData\Local\Continuum\anaconda3\lib\site-packages\ipykernel\zmqshell.py", line 533, in run_cell
return super(ZMQInteractiveShell, self).run_cell(*args, **kwargs)
File "C:\Users\USERNAME\AppData\Local\Continuum\anaconda3\lib\site-packages\IPython\core\interactiveshell.py", line 2698, in run_cell
interactivity=interactivity, compiler=compiler, result=result)
File "C:\Users\USERNAME\AppData\Local\Continuum\anaconda3\lib\site-packages\IPython\core\interactiveshell.py", line 2808, in run_ast_nodes
if self.run_code(code, result):
File "C:\Users\USERNAME\AppData\Local\Continuum\anaconda3\lib\site-packages\IPython\core\interactiveshell.py", line 2862, in run_code
exec(code_obj, self.user_global_ns, self.user_ns)
File "<ipython-input-12-7ef8ba55b0b8>", line 1, in <module>
runfile(‘INTROPATH/USERNAME/My Documents/Python/trainwithgraph.py', wdir=‘INTROPATH/USERNAME/My Documents/Python')
File "C:\Users\USERNAME\AppData\Local\Continuum\anaconda3\lib\site-packages\spyder\utils\site\sitecustomize.py", line 710, in runfile
execfile(filename, namespace)
File "C:\Users\USERNAME\AppData\Local\Continuum\anaconda3\lib\site-packages\spyder\utils\site\sitecustomize.py", line 101, in execfile
exec(compile(f.read(), filename, 'exec'), namespace)
File “INTROPATH/USERNAME/My Documents/Python/trainwithgraph.py", line 43, in <module>
y_true = tf.placeholder(tf.float32, shape=[None, num_classes], name='y_true')
File "C:\Users\USERNAME\AppData\Local\Continuum\anaconda3\lib\site-packages\tensorflow\python\ops\array_ops.py", line 1680, in placeholder
return gen_array_ops._placeholder(dtype=dtype, shape=shape, name=name)
File "C:\Users\USERNAME\AppData\Local\Continuum\anaconda3\lib\site-packages\tensorflow\python\ops\gen_array_ops.py", line 4105, in _placeholder
"Placeholder", dtype=dtype, shape=shape, name=name)
File "C:\Users\USERNAME\AppData\Local\Continuum\anaconda3\lib\site-packages\tensorflow\python\framework\op_def_library.py", line 787, in _apply_op_helper
op_def=op_def)
File "C:\Users\USERNAME\AppData\Local\Continuum\anaconda3\lib\site-packages\tensorflow\python\framework\ops.py", line 3160, in create_op
op_def=op_def)
File "C:\Users\USERNAME\AppData\Local\Continuum\anaconda3\lib\site-packages\tensorflow\python\framework\ops.py", line 1625, in __init__
self._traceback = self._graph._extract_stack() # pylint: disable=protected-access
InvalidArgumentError (see above for traceback): You must feed a value for placeholder tensor 'y_true_8' with dtype float and shape [?,2]
[[Node: y_true_8 = Placeholder[dtype=DT_FLOAT, shape=[?,2], _device="/job:localhost/replica:0/task:0/device:CPU:0"]()]]
Набор данных компилируется отдельным скриптом Python, и ему удается без проблем выполнить этот шаг. Я считаю, что основной проблемой является неправильная подача словарных переменных в элементы графика. Мой код:
import dataset
import tensorflow as tf
import time
from datetime import timedelta
import math
import random
import numpy as np
#Adding Seed so that random initialization is consistent
from numpy.random import seed
seed(1)
from tensorflow import set_random_seed
set_random_seed(2)
FLAGS = None
batch_size = 32
#Prepare input data
classes = ['icmp','deleted']
num_classes = len(classes)
# 20% of the data will automatically be used for validation
validation_size = 0.2
img_size = 128
num_channels = 3
train_path='training_data'
# We shall load all the training and validation images and labels into memory using openCV and use that during training
data = dataset.read_train_sets(train_path, img_size, classes, validation_size=validation_size)
print("Complete reading input data. Will Now print a snippet of it")
print("Number of files in Training-set:\t\t{}".format(len(data.train.labels)))
print("Number of files in Validation-set:\t{}".format(len(data.valid.labels)))
session = tf.Session()
x = tf.placeholder(tf.float32, shape=[None, img_size,img_size,num_channels], name='x')
keep_prob = tf.placeholder(tf.float32)
## labels
y_true = tf.placeholder(tf.float32, shape=[None, num_classes], name='y_true')
y_true_cls = tf.argmax(y_true, axis=1)
##Network graph params
filter_size_conv1 = 3
num_filters_conv1 = 64
filter_size_conv2 = 3
num_filters_conv2 = 32
filter_size_conv3 = 3
num_filters_conv3 = 32
fc_layer_size = 128
def create_weights(shape):
return tf.Variable(tf.truncated_normal(shape, stddev=0.05))
def create_biases(size):
return tf.Variable(tf.constant(0.05, shape=[size]))
def variable_summaries(var):
with tf.name_scope('summaries'):
mean = tf.reduce_mean(var)
tf.summary.scalar('mean', mean)
with tf.name_scope('stddev'):
stddev = tf.sqrt(tf.reduce_mean(tf.square(var-mean)))
tf.summary.scalar('stddev', stddev)
tf.summary.scalar('max', tf.reduce_max(var))
tf.summary.scalar('min', tf.reduce_min(var))
tf.summary.histogram('histogram', var)
def create_convolutional_layer(input,
num_input_channels,
conv_filter_size,
num_filters,
layer_name):
## We shall define the weights that will be trained using create_weights function.
weights = create_weights(shape=[conv_filter_size, conv_filter_size, num_input_channels, num_filters])
## We create biases using the create_biases function. These are also trained.
biases = create_biases(num_filters)
## Creating the convolutional layer
layer = tf.nn.conv2d(input=input,
filter=weights,
strides=[1, 1, 1, 1],
padding='SAME')
layer += biases
## We shall be using max-pooling.
layer = tf.nn.max_pool(value=layer,
ksize=[1, 2, 2, 1],
strides=[1, 2, 2, 1],
padding='SAME')
## Output of pooling is fed to Relu which is the activation function for us.
layer = tf.nn.relu(layer)
with tf.name_scope(layer_name):
tf.summary.histogram('activations', layer)
return layer
def create_flatten_layer(layer):
#We know that the shape of the layer will be [batch_size img_size img_size num_channels]
# But let's get it from the previous layer.
layer_shape = layer.get_shape()
## Number of features will be img_height * img_width* num_channels. But we shall calculate it in place of hard-coding it.
num_features = layer_shape[1:4].num_elements()
## Now, we Flatten the layer so we shall have to reshape to num_features
layer = tf.reshape(layer, [-1, num_features])
return layer
def create_fc_layer(input,
num_inputs,
num_outputs,
layer_name,
use_relu=True):
#Let's define trainable weights and biases.
weights = create_weights(shape=[num_inputs, num_outputs])
biases = create_biases(num_outputs)
# Fully connected layer takes input x and produces wx+b.Since, these are matrices, we use matmul function in Tensorflow
layer = tf.matmul(input, weights) + biases
if use_relu:
layer = tf.nn.relu(layer)
return layer
layer_conv1 = create_convolutional_layer(input=x,
num_input_channels=num_channels,
conv_filter_size=filter_size_conv1,
num_filters=num_filters_conv1,
layer_name='layer_conv1')
layer_conv2 = create_convolutional_layer(input=layer_conv1,
num_input_channels=num_filters_conv1,
conv_filter_size=filter_size_conv2,
num_filters=num_filters_conv2,
layer_name='layer_conv2')
dropoutcl = tf.nn.dropout(layer_conv2, keep_prob = 0.9)
layer_conv3= create_convolutional_layer(input=dropoutcl,
num_input_channels=num_filters_conv2,
conv_filter_size=filter_size_conv3,
num_filters=num_filters_conv3,
layer_name='layer_conv3')
layer_flat = create_flatten_layer(layer_conv3)
layer_fc1 = create_fc_layer(input=layer_flat,
num_inputs=layer_flat.get_shape()[1:4].num_elements(),
num_outputs=fc_layer_size,
layer_name = 'layer_fc1',
use_relu=True)
dropoutfc = tf.nn.dropout(layer_fc1, keep_prob = 0.6)
layer_fc2 = create_fc_layer(input=dropoutfc,
num_inputs=fc_layer_size,
num_outputs=num_classes,
layer_name = 'layer_fc2',
use_relu=False)
y_pred = tf.nn.softmax(layer_fc2,name='y_pred')
y_pred_cls = tf.argmax(y_pred, axis=1)
with session:
writer = tf.summary.FileWriter('training-data', session.graph)
session.run(tf.global_variables_initializer())
with tf.name_scope('cross_entropy'):
with tf.name_scope('total'):
cross_entropy = tf.nn.softmax_cross_entropy_with_logits_v2(logits=layer_fc2,
labels=y_true)
tf.summary.scalar('cross_entropy', cross_entropy)
cost = tf.reduce_mean(cross_entropy)
with tf.name_scope('train'):
optimizer = tf.train.AdamOptimizer(learning_rate=1e-4).minimize(cost)
with tf.name_scope('accuracy'):
with tf.name_scope('correct_prediction'):
correct_prediction = tf.equal(y_pred_cls, y_true_cls)
with tf.name_scope('accuracy'):
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
tf.summary.scalar('accuracy', accuracy)
merged = tf.summary.merge_all()
train_writer = tf.summary.FileWriter('training-data', session.graph)
test_writer = tf.summary.FileWriter('testing-data')
session.run(tf.global_variables_initializer())
def show_progress(epoch, feed_dict_train, feed_dict_validate, val_loss):
acc = session.run(accuracy, feed_dict=feed_dict_train)
val_acc = session.run(accuracy, feed_dict=feed_dict_validate)
msg = "Training Epoch {0} --- Training Accuracy: {1:>6.1%}, Validation Accuracy: {2:>6.1%}, Validation Loss: {3:.3f}"
print(msg.format(epoch + 1, acc, val_acc, val_loss))
total_iterations = 0
saver = tf.train.Saver()
def train(num_iteration):
global total_iterations
for i in range(total_iterations,
total_iterations + num_iteration):
x_batch, y_true_batch, _, cls_batch = data.train.next_batch(batch_size)
x_valid_batch, y_valid_batch, _, valid_cls_batch = data.valid.next_batch(batch_size)
feed_dict_tr = {x: x_batch,
y_true: y_true_batch}
feed_dict_val = {x: x_valid_batch,
y_true: y_valid_batch}
session.run(optimizer, feed_dict=feed_dict_tr)
summary, acc = session.run([merged,accuracy], feed_dict=feed_dict_val)
test_writer.add_summary(summary, i)
if i % int(data.train.num_examples/batch_size) == 0:
val_loss = session.run(cost, feed_dict=feed_dict_val)
epoch = int(i / int(data.train.num_examples/batch_size))
show_progress(epoch, feed_dict_tr, feed_dict_val, val_loss)
summary, _ = session.run([merged, epoch], feed_dict=feed_dict_tr)
train_writer.add_summary(summary, i)
saver.save(session, './dogs-cats-model')
total_iterations += num_iteration
train(num_iteration=9000)