serve - Ninguna variable para guardar error en Tensorflow

tensorflow serve

Question

Estoy intentando guardar el modelo y luego reutilizarlo para clasificar mis imágenes, pero desafortunadamente estoy obteniendo errores al restaurar el modelo que he guardado.

El código en el que se ha creado el modelo :

# Deep Learning
# =============
#
# Assignment 4
# ------------
# In[25]:
# These are all the modules we''ll be using later. Make sure you can import them
# before proceeding further.
from __future__ import print_function
import numpy as np
import tensorflow as tf
from six.moves import cPickle as pickle
from six.moves import range
# In[37]:
pickle_file = ''notMNIST.pickle''
with open(pickle_file, ''rb'') as f:
save = pickle.load(f)
train_dataset = save[''train_dataset'']
train_labels = save[''train_labels'']
valid_dataset = save[''valid_dataset'']
valid_labels = save[''valid_labels'']
test_dataset = save[''test_dataset'']
test_labels = save[''test_labels'']
del save # hint to help gc free up memory
print(''Training set'', train_dataset.shape, train_labels.shape)
print(''Validation set'', valid_dataset.shape, valid_labels.shape)
print(''Test set'', test_dataset.shape, test_labels.shape)
print(test_labels)
# Reformat into a TensorFlow-friendly shape:
# - convolutions need the image data formatted as a cube (width by height by #channels)
# - labels as float 1-hot encodings.
# In[38]:
image_size = 28
num_labels = 10
num_channels = 1 # grayscale
import numpy as np
def reformat(dataset, labels):
dataset = dataset.reshape(
(-1, image_size, image_size, num_channels)).astype(np.float32)
#print(np.arange(num_labels))
labels = (np.arange(num_labels) == labels[:,None]).astype(np.float32)
#print(labels[0,:])
print(labels[0])
return dataset, labels
train_dataset, train_labels = reformat(train_dataset, train_labels)
valid_dataset, valid_labels = reformat(valid_dataset, valid_labels)
test_dataset, test_labels = reformat(test_dataset, test_labels)
print(''Training set'', train_dataset.shape, train_labels.shape)
print(''Validation set'', valid_dataset.shape, valid_labels.shape)
print(''Test set'', test_dataset.shape, test_labels.shape)
#print(labels[0])
# In[39]:
def accuracy(predictions, labels):
return (100.0 * np.sum(np.argmax(predictions, 1) == np.argmax(labels, 1))
/ predictions.shape[0])
# Let''s build a small network with two convolutional layers, followed by one fully connected layer. Convolutional networks are more expensive computationally, so we''ll limit its depth and number of fully connected nodes.
# In[47]:
batch_size = 16
patch_size = 5
depth = 16
num_hidden = 64
graph = tf.Graph()
with graph.as_default():
# Input data.
tf_train_dataset = tf.placeholder(
tf.float32, shape=(batch_size, image_size, image_size, num_channels))
tf_train_labels = tf.placeholder(tf.float32, shape=(batch_size, num_labels))
tf_valid_dataset = tf.constant(valid_dataset)
tf_test_dataset = tf.constant(test_dataset)
# Variables.
layer1_weights = tf.Variable(tf.truncated_normal(
[patch_size, patch_size, num_channels, depth], stddev=0.1),name="layer1_weights")
layer1_biases = tf.Variable(tf.zeros([depth]),name = "layer1_biases")
layer2_weights = tf.Variable(tf.truncated_normal(
[patch_size, patch_size, depth, depth], stddev=0.1),name = "layer2_weights")
layer2_biases = tf.Variable(tf.constant(1.0, shape=[depth]),name ="layer2_biases")
layer3_weights = tf.Variable(tf.truncated_normal(
[image_size // 4 * image_size // 4 * depth, num_hidden], stddev=0.1),name="layer3_biases")
layer3_biases = tf.Variable(tf.constant(1.0, shape=[num_hidden]),name = "layer3_biases")
layer4_weights = tf.Variable(tf.truncated_normal(
[num_hidden, num_labels], stddev=0.1),name = "layer4_weights")
layer4_biases = tf.Variable(tf.constant(1.0, shape=[num_labels]),name = "layer4_biases")
# Model.
def model(data):
conv = tf.nn.conv2d(data, layer1_weights, [1, 2, 2, 1], padding=''SAME'')
hidden = tf.nn.relu(conv + layer1_biases)
conv = tf.nn.conv2d(hidden, layer2_weights, [1, 2, 2, 1], padding=''SAME'')
hidden = tf.nn.relu(conv + layer2_biases)
shape = hidden.get_shape().as_list()
reshape = tf.reshape(hidden, [shape[0], shape[1] * shape[2] * shape[3]])
hidden = tf.nn.relu(tf.matmul(reshape, layer3_weights) + layer3_biases)
return tf.matmul(hidden, layer4_weights) + layer4_biases
# Training computation.
logits = model(tf_train_dataset)
loss = tf.reduce_mean(
tf.nn.softmax_cross_entropy_with_logits(logits, tf_train_labels))
# Optimizer.
optimizer = tf.train.GradientDescentOptimizer(0.05).minimize(loss)
# Predictions for the training, validation, and test data.
train_prediction = tf.nn.softmax(logits)
valid_prediction = tf.nn.softmax(model(tf_valid_dataset))
test_prediction = tf.nn.softmax(model(tf_test_dataset))
# In[48]:
num_steps = 1001
#saver = tf.train.Saver()
with tf.Session(graph=graph) as session:
tf.initialize_all_variables().run()
print(''Initialized'')
for step in range(num_steps):
offset = (step * batch_size) % (train_labels.shape[0] - batch_size)
batch_data = train_dataset[offset:(offset + batch_size), :, :, :]
batch_labels = train_labels[offset:(offset + batch_size), :]
feed_dict = {tf_train_dataset : batch_data, tf_train_labels : batch_labels}
_, l, predictions = session.run(
[optimizer, loss, train_prediction], feed_dict=feed_dict)
if (step % 50 == 0):
print(''Minibatch loss at step %d: %f'' % (step, l))
print(''Minibatch accuracy: %.1f%%'' % accuracy(predictions, batch_labels))
print(''Validation accuracy: %.1f%%'' % accuracy(
valid_prediction.eval(), valid_labels))
print(''Test accuracy: %.1f%%'' % accuracy(test_prediction.eval(), test_labels))
save_path = tf.train.Saver().save(session, "/tmp/model.ckpt")
print("Model saved in file: %s" % save_path)

Todo funciona bien y el modelo se almacena en la carpeta correspondiente.

He creado un archivo de python más en el que he intentado restaurar el modelo pero obteniendo un error allí

# In[1]:
from __future__ import print_function
import numpy as np
import tensorflow as tf
from six.moves import cPickle as pickle
from six.moves import range
# In[3]:
image_size = 28
num_labels = 10
num_channels = 1 # grayscale
import numpy as np
# In[4]:
def accuracy(predictions, labels):
return (100.0 * np.sum(np.argmax(predictions, 1) == np.argmax(labels, 1))
/ predictions.shape[0])
# In[8]:
batch_size = 16
patch_size = 5
depth = 16
num_hidden = 64
graph = tf.Graph()
with graph.as_default():
''''''# Input data.
tf_train_dataset = tf.placeholder(
tf.float32, shape=(batch_size, image_size, image_size, num_channels))
tf_train_labels = tf.placeholder(tf.float32, shape=(batch_size, num_labels))
tf_valid_dataset = tf.constant(valid_dataset)
tf_test_dataset = tf.constant(test_dataset)''''''
# Variables.
layer1_weights = tf.Variable(tf.truncated_normal(
[patch_size, patch_size, num_channels, depth], stddev=0.1),name="layer1_weights")
layer1_biases = tf.Variable(tf.zeros([depth]),name = "layer1_biases")
layer2_weights = tf.Variable(tf.truncated_normal(
[patch_size, patch_size, depth, depth], stddev=0.1),name = "layer2_weights")
layer2_biases = tf.Variable(tf.constant(1.0, shape=[depth]),name ="layer2_biases")
layer3_weights = tf.Variable(tf.truncated_normal(
[image_size // 4 * image_size // 4 * depth, num_hidden], stddev=0.1),name="layer3_biases")
layer3_biases = tf.Variable(tf.constant(1.0, shape=[num_hidden]),name = "layer3_biases")
layer4_weights = tf.Variable(tf.truncated_normal(
[num_hidden, num_labels], stddev=0.1),name = "layer4_weights")
layer4_biases = tf.Variable(tf.constant(1.0, shape=[num_labels]),name = "layer4_biases")
# Model.
def model(data):
conv = tf.nn.conv2d(data, layer1_weights, [1, 2, 2, 1], padding=''SAME'')
hidden = tf.nn.relu(conv + layer1_biases)
conv = tf.nn.conv2d(hidden, layer2_weights, [1, 2, 2, 1], padding=''SAME'')
hidden = tf.nn.relu(conv + layer2_biases)
shape = hidden.get_shape().as_list()
reshape = tf.reshape(hidden, [shape[0], shape[1] * shape[2] * shape[3]])
hidden = tf.nn.relu(tf.matmul(reshape, layer3_weights) + layer3_biases)
return tf.matmul(hidden, layer4_weights) + layer4_biases
''''''# Training computation.
logits = model(tf_train_dataset)
loss = tf.reduce_mean(
tf.nn.softmax_cross_entropy_with_logits(logits, tf_train_labels))
# Optimizer.
optimizer = tf.train.GradientDescentOptimizer(0.05).minimize(loss)''''''
# Predictions for the training, validation, and test data.
#train_prediction = tf.nn.softmax(logits)
#valid_prediction = tf.nn.softmax(model(tf_valid_dataset))
#test_prediction = tf.nn.softmax(model(tf_test_dataset))
# In[17]:
#saver = tf.train.Saver()
with tf.Session() as sess:
# Restore variables from disk.
tf.train.Saver().restore(sess, "/tmp/model.ckpt")
print("Model restored.")
# Do some work with the model

error que estoy recibiendo es:

No hay variables para guardar

Cualquier ayuda sería apreciada

Answer 1

El error aquí es bastante sutil. En In[8] crea un tf.Graph llamado tf.Graph y lo configura como predeterminado para el with graph.as_default(): . Esto significa que todas las variables se crean en el graph , y si imprime graph.all_variables() debería ver una lista de sus variables.

Sin embargo , tf.Session bloque with antes de crear (i) la tf.Session la tf.Session (ii) la tf.train.Saver . Esto significa que la sesión y el protector se crean en un gráfico diferente (el gráfico global predeterminado tf.Graph que se usa cuando no crea explícitamente uno y lo establece como predeterminado), que no contiene ninguna variable, ni ningún nodo en todos.

Hay al menos dos soluciones:

1. Como sugiere Yaroslav , puede escribir su programa sin usar el with graph.as_default(): que evita la confusión con múltiples gráficos. Sin embargo, esto puede llevar a colisiones de nombres entre diferentes celdas en su cuaderno de IPython, lo cual es incómodo cuando se usa el tf.train.Saver , ya que usa la propiedad del name de tf.Variable como la clave en el archivo de punto de control.

2. Puede crear el protector dentro del with graph.as_default(): y crear la tf.Session con un gráfico explícito, de la siguiente manera:

   with graph.as_default():
   # [Variable and model creation goes here.]
   saver = tf.train.Saver() # Gets all variables in `graph`.
   with tf.Session(graph=graph) as sess:
   saver.restore(sess)
   # Do some work with the model....

   Alternativamente, puede crear la tf.Session dentro del with graph.as_default(): en cuyo caso utilizará el graph para todas sus operaciones.

Answer 2

Está creando una nueva sesión en In[17] que borra sus variables. Además, no necesita usar bloques si solo tiene un gráfico predeterminado y una sesión predeterminada, puede hacer algo como esto

sess = tf.InteractiveSession()
layer1_weights = tf.Variable(tf.truncated_normal(
[patch_size, patch_size, num_channels, depth], stddev=0.1),name="layer1_weights")
tf.train.Saver().restore(sess, "/tmp/model.ckpt")