我正在尝试保存模型，然后重复使用它来对我的图像进行分类，但遗憾的是我在恢复已保存的模型时遇到错误。
已创建模型的代码：
## One way to do this:
## - get the first row for each group, then shift it back one to give us the class for the previous row
## - then join it all back together
dt_previous <- DF[order(Date), .I[1], by=.(GroupID)]
dt_previous[, V1 := V1 - 1]
## Get the previous Class according to the new V1/row index
dt_previous[ , previous_class := c(NA, DF[dt_previous$V1, as.character(Class)]) ]
## Join the 'previous_class' onto DF
DF <- dt_previous[, .(GroupID, previous_class)][ DF, on=c("GroupID")]
## define the number of rows for each group
DF[, nRows := .N, by=.(GroupID)]
## Update 'Green' to 'Red' where nRows < 46
DF[ nRows < 46 & Class == "Green" & previous_class == "Red", Class := "Red"]
## Redefine the groups
DF[, GroupID := rleid(Class)]
ggplot(DF, aes(Date, Data, colour=Class, group=1)) + geom_line()
一切正常，模型存储在相应的文件夹中。
我已经创建了一个python文件，我尝试恢复模型但是在那里收到错误
# 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)
无需保存的变量
任何帮助将不胜感激
答案 0 :(得分：36)
这里的错误非常微妙。在graph中，您创建一个名为graph的{{3}}，并将其设置为tf.Graph块的默认值。这意味着所有变量都是在graph.all_variables()中创建的，如果您打印with，您应该会看到变量列表。
但，在创建（i）with graph.as_default():和（ii）tf.Session之前退出tf.Graph块。这意味着会话和保护程序是在不同的图形（当您没有显式创建并将其设置为默认值时使用的全局默认with graph.as_default():创建的） t包含任何变量 - 或任何节点。
至少有两种解决方案：
作为tf.train.Saver，您可以在不使用tf.train.Saver块的情况下编写程序，从而避免与多个图形混淆。但是，这可能会导致IPython笔记本中不同单元格之间的名称冲突，这在使用name时很难，因为它使用tf.Variable的{{1}}属性作为密钥。检查点文件。
您可以在<{1}}块内创建 ，并使用显式图创建with graph.as_default():，如下所示：
tf.Session或者，您可以在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....
块中创建<{1}} ，在这种情况下，它将使用tf.Session进行所有操作。
答案 1 :(得分：1)
您正在In[17]中创建一个用于清除变量的新会话。此外，如果您只有一个默认图表和一个默认会话，则不需要使用with块，您可以改为执行此类操作
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")