Develop Reference

tf.train.import_meta_graph(): unable to load some variable values

I'm using tensorflow 1.10.0. I've been following the tutorial for saving and loading a simple trained MLP model. Saving of data works perfectly and creates following files:
train.ckpt.data-00000-of-00001
train.ckpt.index
train.ckpt.meta
When I'm trying to load train_opt or accmetric variable using:
import tensorflow as tf
with tf.Session() as sess:
load_mod = tf.train.import_meta_graph('/home/akshay/train.ckpt.meta')
load_mod.restore(sess, tf.train.latest_checkpoint('/home/akshay/'))
print (tf.get_default_graph().get_tensor_by_name('train_opt:0'))
I get following error:
Traceback (most recent call last):
File "recover_tftrain.py", line 6, in <module>
print (tf.get_default_graph().get_tensor_by_name('accmetric:0'))
File "/home/arpita/anaconda2/lib/python2.7/site-
packages/tensorflow/python/framework/ops.py", line 3515, in get_tensor_by_name
return self.as_graph_element(name, allow_tensor=True, allow_operation=False)
File "/home/arpita/anaconda2/lib/python2.7/site-
packages/tensorflow/python/framework/ops.py", line 3339, in as_graph_element
return self._as_graph_element_locked(obj, allow_tensor, allow_operation)
File "/home/arpita/anaconda2/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 3381, in _as_graph_element_locked
"graph." % (repr(name), repr(op_name)))
KeyError: "The name 'accmetric:0' refers to a Tensor which does not exist.
The operation, 'accmetric', does not exist in the graph."
However, the loss variable loads perfectly:
Tensor("loss:0", shape=(), dtype=float32)
Are there only some specific variables that can be loaded? Or is there any issue of scope?
Complete code:
from create_batches import Batch
import extractData
import tensorflow as tf
# prepare input data and output labels for neural network
datafile = '/home/akshay/Desktop/datafile.csv'
labelfile = '/home/akshay/Desktop/labelfile.csv'
num_input = 2000
num_hidden1 = 200
num_hidden2 = 200
num_hidden3 = 200
num_output = 25
batch_size = 200
epochs = 25
batch = Batch(extractData.create_data(datafile), extractData.create_labels(labelfile), batch_size)
# create tensorflow networks
vowel_inp = tf.placeholder(dtype = tf.float32, shape = [None, 40000], name = "text_inp")
label_oup = tf.placeholder(dtype = tf.int32, shape = [None], name = "label_oup")
vowel_flat = tf.contrib.layers.flatten(vowel_inp)
# fully connected layers
hidden_1 = tf.layers.dense(inputs = vowel_flat, units = num_hidden1, name = "hidden1", activation = tf.nn.sigmoid)
hidden_2 = tf.layers.dense(inputs = hidden_1, units = num_hidden2, name = "hidden2", activation = tf.nn.sigmoid)
hidden_3 = tf.layers.dense(inputs = hidden_2, units = num_hidden3, name = "hidden3", activation = tf.nn.sigmoid)
train_oup = tf.layers.dense(inputs = hidden_3, units = num_output, name = "output")
# define a cost function
xentropy = tf.losses.sparse_softmax_cross_entropy(labels = label_oup, logits = train_oup)
# define a loss function
loss = tf.reduce_mean(xentropy, name = "loss")
# define an optimizer
train_opt = tf.train.AdagradOptimizer(learning_rate = 0.001).minimize(loss, name="train_opt")
# define accuracy metric
acc, acc_metric_update = tf.metrics.accuracy(label_oup, tf.argmax(train_oup, 1), name="accmetric")
loss_val, acc_val = 0, 0
sess = tf.Session()
sess.run(tf.local_variables_initializer())
sess.run(tf.global_variables_initializer())
saver = tf.train.Saver()
for j in range(epochs):
batch.reset()
for i in range(int(2000/batch_size)):
x, y = batch.getBatch()
y = y.reshape(batch_size)
feed_dict = {vowel_inp: x, label_oup: y}
loss_val, _, acc_val = sess.run([loss, train_opt, acc_metric_update], feed_dict=feed_dict)
if j%25==0:
print ('Epoch:', j, 'Accuracy Val:', acc_val)
print ("Final score:",sess.run(acc))
#save the model
print ('Model saved in: ', saver.save(sess, '/home/akshay/train.ckpt'))
sess.close()

Error "no Variable to save" in tensorflow while storing session

I was trYing to save session in model so that i can use it later on but i am getting an error everytime. My code is like:
with tf.Session() as sess:
sess.run(init)
for j in range(3):
for i in range(xtest.shape[0]):
_, indices = sess.run(pred, feed_dict={x_train: xtrain, x_test: xtest[i,:]})
pred_label = getMajorityPredictions(ytrain, indices)
actual_val = get_char( int( (ytest[i]).argmax() ) )
# print("test: ", i, "prediction: ", get_char(pred_label), " actual: ", actual_val)
# print(pred_label, actual_val, type(pred_label), type(actual_val), sep=" --> ")
if get_char(pred_label) == actual_val:
accuracy += 1/len(xtest)
# print((i / (xtest.shape[0])) * 100)
# os.system("cls")
print("accuracy: ",accuracy)
savedPath = saver.save(sess, "/tmp/model.ckpt")
print("Model saved at: " ,savedPath)
and the error is like:
Traceback (most recent call last):
File "prac3.py", line 74, in <module>
saver = tf.train.Saver()
File "C:\Python36\lib\site-packages\tensorflow\python\training\saver.py", line 1239, in __init__
self.build()
File "C:\Python36\lib\site-packages\tensorflow\python\training\saver.py", line 1248, in build
self._build(self._filename, build_save=True, build_restore=True)
File "C:\Python36\lib\site-packages\tensorflow\python\training\saver.py", line 1272, in _build
raise ValueError("No variables to save")
ValueError: No variables to save

The code you provided does not give much information on the error. You might need to check your previous code to see if you actually have an variables to be saved. You can check tf.global_variables() and see if the list is empty.
In addition, you might want to put an indent before the savedPath = saver.save(sess, "/tmp/model.ckpt") as you used with tf.Session as sess, so the session is actually closed when you are outside that block, then you'll face the problem of 'Attempting to use closed session'.

x_train = tf.placeholder(tf.float32, shape=[None, 4096])
y_train = tf.placeholder(tf.float32, shape=[None, 62])
x_test = tf.placeholder(tf.float32, shape=[4096])
y_test = tf.placeholder(tf.float32, shape=[None, 62])
l1_distance = tf.abs(tf.subtract(x_train, x_test))
dis_l1 = tf.reduce_sum(l1_distance, axis=1)
pred = tf.nn.top_k(tf.negative(dis_l1), k=5)
xtrain, ytrain = TRAIN_SIZE(2852)
xtest, ytest = TEST_SIZE(557)
init = tf.global_variables_initializer()
accuracy = 0
saver = tf.train.Saver()
# --------------------- to create model
with tf.Session() as sess:
sess.run(init)
for j in range(3):
for i in range(xtest.shape[0]):
_, indices = sess.run(pred, feed_dict={x_train: xtrain, x_test: xtest[i,:]})
pred_label = getMajorityPredictions(ytrain, indices)
actual_val = get_char( int( (ytest[i]).argmax() ) )
# print("test: ", i, "prediction: ", get_char(pred_label), " actual: ", actual_val)
# print(pred_label, actual_val, type(pred_label), type(actual_val), sep=" --> ")
if get_char(pred_label) == actual_val:
accuracy += 1/len(xtest)
# print((i / (xtest.shape[0])) * 100)
# os.system("cls")
print("accuracy: ",accuracy)
savedPath = saver.save(sess, "/tmp/model.ckpt")
print("Model saved at: " ,savedPath)

How do I get the tensorflow model to persist load?

Now I want to write 2 functions:
1 for loading model that I already trained,
2nd is using the the model to classify.
But the two function all need same session, so I make the session as a parameter, so as to seed it to the next function. But I received an error.
Here is my code. The first method is for loading the model, the second one is for using the model to predict something, but I have a few problems while init the session
def callmodel():
with tf.Graph().as_default():
#saver = tf.train.Saver()
model_path = 'E:/MyProject/MachineLearning/callTFModel/model/'
ckpt = tf.train.get_checkpoint_state(model_path)
sess = tf.Session()
saver = tf.train.import_meta_graph(ckpt.model_checkpoint_path + '.meta')
sess.run(tf.global_variables_initializer())
ckpt = tf.train.get_checkpoint_state(model_path)
if ckpt and ckpt.model_checkpoint_path:
saver.restore(sess, ckpt.model_checkpoint_path)
print("load model successful!")
return sess
else:
print("failed to load model!")
def test_one_image(sess,test_dir):
global p, logits
image = Image.open(test_dir)
image = image.resize([32, 32])
image_array = np.array(image)
image = tf.cast(image_array, tf.float32)
image = tf.reshape(image, [1, 32, 32, 3]) # 调整image的形状
p = mmodel(image, 1)
logits = tf.nn.softmax(p)
x = tf.placeholder(tf.float32, shape=[32, 32, 3])
prediction = sess.run(logits, feed_dict={x: image_array})
max_index = np.argmax(prediction)
if max_index == 0:
print('probability of good： %.6f' % prediction[:, 0])
else:
print('probability of Lack of glue： %.6f' % prediction[:, 1])
#######//test
sess=callmodel
path="c:/test/1001.jpg"
test_one_image(sess,path)
it occurs error:
File "E:/MyProject/python/C+pythonModel/test.py", line 175, in <module>
test_one_image(sess,path)
File "E:/MyProject/python/C+pythonModel/test.py", line 164, in test_one_image
prediction = sess.run(logits, feed_dict={x: image_array})
File "D:\study\Anaconda3\lib\site-packages\tensorflow\python\client\session.py", line 895, in run
run_metadata_ptr)
File "D:\study\Anaconda3\lib\site-packages\tensorflow\python\client\session.py", line 1071, in _run
+ e.args[0])
TypeError: Cannot interpret feed_dict key as Tensor: Tensor Tensor("Placeholder:0", shape=(32, 32, 3), dtype=float32) is not an element of this graph.

The problem is not with using the session as parameter, it's with how you recover the input and output nodes of your graph: when you write
p = mmodel(image, 1)
logits = tf.nn.softmax(p)
x = tf.placeholder(tf.float32, shape=[32, 32, 3])
you are not recovering the corresponding nodes in the session graph, but creating new ones. You should instead use:
x= sess.graph().get_tensor_by_name("your_x_placeholder_name")
logits= sess.graph().get_tensor_by_name("your_logits_placeholder_name")
and then prediction = sess.run(logits, feed_dict={x: image_array})
Additionnally, you probably need to check if you have not made any mistake between image and image_array (right now you're reshaping image, not the array, which is useless if you feed with image_array...)

Tensorflow next word predictor bug

I have the following code
flags = tf.flags
logging = tf.logging
flags.DEFINE_string('model', 'small',
'A type of model. Possible options are: small, medium, large.'
)
flags.DEFINE_string('data_path', None, 'data_path')
flags.DEFINE_string('checkpoint_dir', 'ckpt', 'checkpoint_dir')
flags.DEFINE_bool('use_fp16', False,
'Train using 16-bit floats instead of 32bit floats')
flags.DEFINE_bool('train', False, 'should we train or test')
FLAGS = flags.FLAGS
def data_type():
return tf.float16 if FLAGS.use_fp16 else tf.float32
class PTBModel(object):
"""The PTB model."""
def __init__(self, is_training, config):
self.batch_size = batch_size = config.batch_size
self.num_steps = num_steps = config.num_steps
size = config.hidden_size
vocab_size = config.vocab_size
self._input_data = tf.placeholder(tf.float32, [batch_size,
num_steps])
self._targets = tf.placeholder(tf.int32, [batch_size,
num_steps])
# Slightly better results can be obtained with forget gate biases
# initialized to 1 but the hyperparameters of the model would need to be
# different than reported in the paper.
lstm_cell = tf.nn.rnn_cell.BasicLSTMCell(size, forget_bias=0.0,
state_is_tuple=True)
if is_training and config.keep_prob < 1:
lstm_cell = tf.nn.rnn_cell.DropoutWrapper(lstm_cell,
output_keep_prob=config.keep_prob)
cell = tf.nn.rnn_cell.MultiRNNCell([lstm_cell]
* config.num_layers, state_is_tuple=True)
self._initial_state = cell.zero_state(batch_size, data_type())
with tf.device('/cpu:0'):
embedding = tf.get_variable('embedding', [vocab_size,
size], dtype=data_type())
inputs = tf.nn.embedding_lookup(embedding, self._input_data)
if is_training and config.keep_prob < 1:
inputs = tf.nn.dropout(inputs, config.keep_prob)
# Simplified version of tensorflow.models.rnn.rnn.py's rnn().
# This builds an unrolled LSTM for tutorial purposes only.
# In general, use the rnn() or state_saving_rnn() from rnn.py.
#
# The alternative version of the code below is:
#
# from tensorflow.models.rnn import rnn
inputs = [tf.squeeze(input_, [1]) for input_ in tf.split(inputs, num_steps, axis=1)]
(outputs, state) = tf.nn.rnn(cell, inputs, initial_state=self._initial_state)
# outputs = []
# state = self._initial_state
# with tf.variable_scope("RNN"):
# for time_step in range(num_steps):
# if time_step > 0: tf.get_variable_scope().reuse_variables()
# (cell_output, state) = cell(inputs[:, time_step, :], state)
# outputs.append(cell_output)
output = tf.reshape(tf.concat(outputs, axis=1), [-1, size])
softmax_w = tf.get_variable('softmax_w', [size, vocab_size],
dtype=data_type())
softmax_b = tf.get_variable('softmax_b', [vocab_size],
dtype=data_type())
logits = tf.matmul(output, softmax_w) + softmax_b
loss = tf.nn.seq2seq.sequence_loss_by_example([logits],
[tf.reshape(self._targets, [-1])], [tf.ones([batch_size
* num_steps],
dtype=data_type())])
self._cost = cost = tf.reduce_sum(loss) / batch_size
self._final_state = state
# RANI
self.logits = logits
if not is_training:
return
self._lr = tf.Variable(0.0, trainable=False)
tvars = tf.trainable_variables()
(grads, _) = tf.clip_by_global_norm(tf.gradients(cost, tvars),
config.max_grad_norm)
optimizer = tf.train.GradientDescentOptimizer(self._lr)
self._train_op = optimizer.apply_gradients(zip(grads, tvars))
self._new_lr = tf.placeholder(tf.float32, shape=[],
name='new_learning_rate')
self._lr_update = tf.assign(self._lr, self._new_lr)
def assign_lr(self, session, lr_value):
session.run(self._lr_update, feed_dict={self._new_lr: lr_value})
...
However, When I run it, I get the following errors
File "ptb_word_lm.py", line 349, in <module>
tf.app.run()
File "C:\Users\Josh Goldman\AppData\Local\Programs\Python\Python35\lib\site-packages\tensorflow\python\platform\app.py", line 48, in run
_sys.exit(main(_sys.argv[:1] + flags_passthrough))
File "ptb_word_lm.py", line 299, in main
m = PTBModel(is_training=True, config=config)
File "ptb_word_lm.py", line 60, in __init__
inputs = tf.nn.embedding_lookup(embedding, self._input_data)
File "C:\Users\Josh Goldman\AppData\Local\Programs\Python\Python35\lib\site-packages\tensorflow\python\ops\embedding_ops.py", line 122, in embedding_lookup
return maybe_normalize(_do_gather(params[0], ids, name=name))
File "C:\Users\Josh Goldman\AppData\Local\Programs\Python\Python35\lib\site-packages\tensorflow\python\ops\embedding_ops.py", line 42, in _do_gather
return array_ops.gather(params, ids, name=name)
File "C:\Users\Josh Goldman\AppData\Local\Programs\Python\Python35\lib\site-packages\tensorflow\python\ops\gen_array_ops.py", line 1179, in gather
validate_indices=validate_indices, name=name)
File "C:\Users\Josh Goldman\AppData\Local\Programs\Python\Python35\lib\site-packages\tensorflow\python\framework\op_def_library.py", line 589, in apply_op
param_name=input_name)
File "C:\Users\Josh Goldman\AppData\Local\Programs\Python\Python35\lib\site-packages\tensorflow\python\framework\op_def_library.py", line 60, in _SatisfiesTypeConstraint
", ".join(dtypes.as_dtype(x).name for x in allowed_list)))
TypeError: Value passed to parameter 'indices' has DataType float32 not in list of allowed values: int32, int64
Someone, please help me. I have all my packages upgraded to the newest version. I'm using the correct interpreter. I'm sorry if the error is very simple. I'm only 13 and am very new to programming. By the way, this code is not mine; I got it from Github.

The error is due to tensorflow version, syntax of tf.split is changed in the newer version. there is another same problem with tf.concat
# replace this line with the following one
inputs = [tf.squeeze(input_, [1]) for input_ in tf.split(1, num_steps, inputs)]
# this support `tensorflow >= 1.0.0`
inputs = [tf.squeeze(input_, [1]) for input_ in tf.split(inputs, num_steps, axis=1)]
# Also use dtype float32 for inputs
self._input_data = tf.placeholder(tf.float32, [batch_size,
num_steps])
# replace this line
output = tf.reshape(tf.concat(1, outputs), [-1, size])
# with this one
output = tf.reshape(tf.concat(outputs, axis=1), [-1, size])

tensorflow static_rnn error: input must be a sequence

I'm trying to feed my own 3D data to a LSTM. The data have: height = 365, width = 310, time = unknown / inconsistent, consist of 0 and 1, each block of data that produce an output are separated to a single file.
import tensorflow as tf
import os
from tensorflow.contrib import rnn
filename = "C:/Kuliah/EmotionRecognition/Train1/D2N2Sur.txt"
hm_epochs = 10
n_classes = 12
n_chunk = 443
n_hidden = 500
data = tf.placeholder(tf.bool, name='data')
cat = tf.placeholder("float", [None, n_classes])
weights = {
'out': tf.Variable(tf.random_normal([n_hidden, n_classes]))
}
biases = {
'out': tf.Variable(tf.random_normal([n_classes]))
}
def RNN(x, weights, biases):
lstm_cell = rnn.BasicLSTMCell(n_hidden, forget_bias=1.0)
outputs, states = rnn.static_rnn(lstm_cell, x, dtype=tf.float32)
return tf.matmul(outputs[-1], weights['out']) + biases['out']
pred = RNN(data, weights, biases)
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=pred, labels=cat))
optimizer = tf.train.AdamOptimizer(learning_rate=0.001).minimize(cost)
correct_pred = tf.equal(tf.argmax(pred, 1), tf.argmax(cat, 1))
accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32))
saver = tf.train.Saver()
temp = [[]]
d3 = [[]]
counter = 0
with tf.Session() as sess:
#load
#saver.restore(sess, "C:/Kuliah/EmotionRecognition/model.ckpt")
sess.run(tf.global_variables_initializer())
with open(filename) as inf:
for line in inf:
bla = list(line)
bla.pop(len(bla) - 1)
for index, item in enumerate(bla):
if (item == '0'):
bla[index] = False
else:
bla[index] = True
temp.append(bla)
counter += 1
if counter%365==0: #height 365
temp.pop(0)
d3.append(temp)
temp = [[]]
temp.pop(0)
d3.append(temp)
batch_data = d3.reshape()
sess.run(optimizer, feed_dict={data: d3, cat: 11})
acc = sess.run(accuracy, feed_dict={data: d3, cat: 11})
loss = sess.run(loss, feed_dict={data: d3, cat: 11})
print(acc)
print(loss)
#save
saver.save(sess, "C:/Kuliah/EmotionRecognition/model.ckpt")
this code throw me an error:
Traceback (most recent call last):
File "C:/Kuliah/EmotionRecognition/Main", line 31, in <module>
pred = RNN(data, weights, biases)
File "C:/Kuliah/EmotionRecognition/Main", line 28, in RNN
outputs, states = rnn.static_rnn(lstm_cell, x, dtype=tf.float32)
File "C:\Users\Anonymous\AppData\Roaming\Python\Python35\site-packages\tensorflow\python\ops\rnn.py", line 1119, in static_rnn
raise TypeError("inputs must be a sequence")
TypeError: inputs must be a sequence

When you call pred = RNN(data, weights, biases), the data argument should be a sequence of length the length of your RNN. But in your case, it's a data = tf.placeholder(tf.bool, name='data').
You could try pred = RNN([data], weights, biases).
See the string doc of the method:
inputs: A length T list of inputs, each a Tensor of shape
[batch_size, input_size], or a nested tuple of such elements.
If the length of your RNN is unknow, you should consider use tf.nn.dynamic_rnn.