在Tensorflow中训练模型后：
答案 0 :(得分：243)
我正在改进我的答案，添加更多有关保存和恢复模型的详细信息。
在（及之后） Tensorflow版本0.11 ：
保存模型：
<div class="grid-container">
<div>
<h1>A</h1>
</div>
<div>
<h1>B</h1>
</div>
<div class="a">
<h1>C</h1>
</div>
</div>恢复模型：
import tensorflow as tf
#Prepare to feed input, i.e. feed_dict and placeholders
w1 = tf.placeholder("float", name="w1")
w2 = tf.placeholder("float", name="w2")
b1= tf.Variable(2.0,name="bias")
feed_dict ={w1:4,w2:8}
#Define a test operation that we will restore
w3 = tf.add(w1,w2)
w4 = tf.multiply(w3,b1,name="op_to_restore")
sess = tf.Session()
sess.run(tf.global_variables_initializer())
#Create a saver object which will save all the variables
saver = tf.train.Saver()
#Run the operation by feeding input
print sess.run(w4,feed_dict)
#Prints 24 which is sum of (w1+w2)*b1
#Now, save the graph
saver.save(sess, 'my_test_model',global_step=1000)
这里已经很好地解释了这个和一些更高级的用例。
A quick complete tutorial to save and restore Tensorflow models
答案 1 :(得分：177)
在TensorFlow版本0.11.0RC1中（及之后），您可以根据https://www.tensorflow.org/programmers_guide/meta_graph调用tf.train.export_meta_graph和tf.train.import_meta_graph来直接保存和恢复您的模型。
w1 = tf.Variable(tf.truncated_normal(shape=[10]), name='w1')
w2 = tf.Variable(tf.truncated_normal(shape=[20]), name='w2')
tf.add_to_collection('vars', w1)
tf.add_to_collection('vars', w2)
saver = tf.train.Saver()
sess = tf.Session()
sess.run(tf.global_variables_initializer())
saver.save(sess, 'my-model')
# `save` method will call `export_meta_graph` implicitly.
# you will get saved graph files:my-model.meta
sess = tf.Session()
new_saver = tf.train.import_meta_graph('my-model.meta')
new_saver.restore(sess, tf.train.latest_checkpoint('./'))
all_vars = tf.get_collection('vars')
for v in all_vars:
v_ = sess.run(v)
print(v_)
答案 2 :(得分：125)
对于TensorFlow版本＆lt; 0.11.0RC1：
保存的检查点包含模型中Variable的值，而不是模型/图形本身，这意味着恢复检查点时图形应该相同。
这是一个线性回归的例子，其中有一个训练循环可以保存变量检查点，还有一个评估部分可以恢复先前运行中保存的变量并计算预测。当然，如果您愿意，也可以恢复变量并继续训练。
x = tf.placeholder(tf.float32)
y = tf.placeholder(tf.float32)
w = tf.Variable(tf.zeros([1, 1], dtype=tf.float32))
b = tf.Variable(tf.ones([1, 1], dtype=tf.float32))
y_hat = tf.add(b, tf.matmul(x, w))
...more setup for optimization and what not...
saver = tf.train.Saver() # defaults to saving all variables - in this case w and b
with tf.Session() as sess:
sess.run(tf.initialize_all_variables())
if FLAGS.train:
for i in xrange(FLAGS.training_steps):
...training loop...
if (i + 1) % FLAGS.checkpoint_steps == 0:
saver.save(sess, FLAGS.checkpoint_dir + 'model.ckpt',
global_step=i+1)
else:
# Here's where you're restoring the variables w and b.
# Note that the graph is exactly as it was when the variables were
# saved in a prior training run.
ckpt = tf.train.get_checkpoint_state(FLAGS.checkpoint_dir)
if ckpt and ckpt.model_checkpoint_path:
saver.restore(sess, ckpt.model_checkpoint_path)
else:
...no checkpoint found...
# Now you can run the model to get predictions
batch_x = ...load some data...
predictions = sess.run(y_hat, feed_dict={x: batch_x})
以下是Variable的{{3}}，其中包括保存和恢复。以下是Saver的{{3}}。
答案 3 :(得分：69)
他们构建了一个详尽而有用的教程 - ＆gt; https://www.tensorflow.org/guide/saved_model
来自文档：
# Create some variables.
v1 = tf.get_variable("v1", shape=[3], initializer = tf.zeros_initializer)
v2 = tf.get_variable("v2", shape=[5], initializer = tf.zeros_initializer)
inc_v1 = v1.assign(v1+1)
dec_v2 = v2.assign(v2-1)
# Add an op to initialize the variables.
init_op = tf.global_variables_initializer()
# Add ops to save and restore all the variables.
saver = tf.train.Saver()
# Later, launch the model, initialize the variables, do some work, and save the
# variables to disk.
with tf.Session() as sess:
sess.run(init_op)
# Do some work with the model.
inc_v1.op.run()
dec_v2.op.run()
# Save the variables to disk.
save_path = saver.save(sess, "/tmp/model.ckpt")
print("Model saved in path: %s" % save_path)
tf.reset_default_graph()
# Create some variables.
v1 = tf.get_variable("v1", shape=[3])
v2 = tf.get_variable("v2", shape=[5])
# Add ops to save and restore all the variables.
saver = tf.train.Saver()
# Later, launch the model, use the saver to restore variables from disk, and
# do some work with the model.
with tf.Session() as sess:
# Restore variables from disk.
saver.restore(sess, "/tmp/model.ckpt")
print("Model restored.")
# Check the values of the variables
print("v1 : %s" % v1.eval())
print("v2 : %s" % v2.eval())
simple_save 许多好的答案，为了完整性，我将加上我的2美分： simple_save 。也是使用tf.data.Dataset API的独立代码示例。
Python 3; Tensorflow 1.7
import tensorflow as tf
from tensorflow.python.saved_model import tag_constants
with tf.Graph().as_default():
with tf.Session as sess:
...
# Saving
inputs = {
"batch_size_placeholder": batch_size_placeholder,
"features_placeholder": features_placeholder,
"labels_placeholder": labels_placeholder,
}
outputs = {"prediction": model_output}
tf.saved_model.simple_save(
sess, 'path/to/your/location/', inputs, outputs
)
恢复：
graph = tf.Graph()
with restored_graph.as_default():
with tf.Session as sess:
tf.saved_model.loader.load(
sess,
[tag_constants.SERVING],
'path/to/your/location/',
)
batch_size_placeholder = graph.get_tensor_by_name('batch_size_placeholder:0')
features_placeholder = graph.get_tensor_by_name('features_placeholder:0')
labels_placeholder = graph.get_tensor_by_name('labels_placeholder:0')
prediction = restored_graph.get_tensor_by_name('dense/BiasAdd:0')
sess.run(prediction, feed_dict={
batch_size_placeholder: some_value,
features_placeholder: some_other_value,
labels_placeholder: another_value
})
以下代码为了演示而生成随机数据。
Dataset，然后创建Iterator。我们得到了迭代器生成的张量，称为input_tensor，它将作为我们模型的输入。input_tensor构建的：基于GRU的双向RNN，后跟密集分类器。因为为什么不呢。softmax_cross_entropy_with_logits，已使用Adam优化。在2个时期（每个2批）之后，我们使用tf.saved_model.simple_save保存“训练”模型。如果按原样运行代码，则模型将保存在当前工作目录中名为simple/的文件夹中。tf.saved_model.loader.load恢复已保存的模型。我们使用graph.get_tensor_by_name抓取占位符和logits，使用Iterator抓取graph.get_operation_by_name初始化操作。代码：
import os
import shutil
import numpy as np
import tensorflow as tf
from tensorflow.python.saved_model import tag_constants
def model(graph, input_tensor):
"""Create the model which consists of
a bidirectional rnn (GRU(10)) followed by a dense classifier
Args:
graph (tf.Graph): Tensors' graph
input_tensor (tf.Tensor): Tensor fed as input to the model
Returns:
tf.Tensor: the model's output layer Tensor
"""
cell = tf.nn.rnn_cell.GRUCell(10)
with graph.as_default():
((fw_outputs, bw_outputs), (fw_state, bw_state)) = tf.nn.bidirectional_dynamic_rnn(
cell_fw=cell,
cell_bw=cell,
inputs=input_tensor,
sequence_length=[10] * 32,
dtype=tf.float32,
swap_memory=True,
scope=None)
outputs = tf.concat((fw_outputs, bw_outputs), 2)
mean = tf.reduce_mean(outputs, axis=1)
dense = tf.layers.dense(mean, 5, activation=None)
return dense
def get_opt_op(graph, logits, labels_tensor):
"""Create optimization operation from model's logits and labels
Args:
graph (tf.Graph): Tensors' graph
logits (tf.Tensor): The model's output without activation
labels_tensor (tf.Tensor): Target labels
Returns:
tf.Operation: the operation performing a stem of Adam optimizer
"""
with graph.as_default():
with tf.variable_scope('loss'):
loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(
logits=logits, labels=labels_tensor, name='xent'),
name="mean-xent"
)
with tf.variable_scope('optimizer'):
opt_op = tf.train.AdamOptimizer(1e-2).minimize(loss)
return opt_op
if __name__ == '__main__':
# Set random seed for reproducibility
# and create synthetic data
np.random.seed(0)
features = np.random.randn(64, 10, 30)
labels = np.eye(5)[np.random.randint(0, 5, (64,))]
graph1 = tf.Graph()
with graph1.as_default():
# Random seed for reproducibility
tf.set_random_seed(0)
# Placeholders
batch_size_ph = tf.placeholder(tf.int64, name='batch_size_ph')
features_data_ph = tf.placeholder(tf.float32, [None, None, 30], 'features_data_ph')
labels_data_ph = tf.placeholder(tf.int32, [None, 5], 'labels_data_ph')
# Dataset
dataset = tf.data.Dataset.from_tensor_slices((features_data_ph, labels_data_ph))
dataset = dataset.batch(batch_size_ph)
iterator = tf.data.Iterator.from_structure(dataset.output_types, dataset.output_shapes)
dataset_init_op = iterator.make_initializer(dataset, name='dataset_init')
input_tensor, labels_tensor = iterator.get_next()
# Model
logits = model(graph1, input_tensor)
# Optimization
opt_op = get_opt_op(graph1, logits, labels_tensor)
with tf.Session(graph=graph1) as sess:
# Initialize variables
tf.global_variables_initializer().run(session=sess)
for epoch in range(3):
batch = 0
# Initialize dataset (could feed epochs in Dataset.repeat(epochs))
sess.run(
dataset_init_op,
feed_dict={
features_data_ph: features,
labels_data_ph: labels,
batch_size_ph: 32
})
values = []
while True:
try:
if epoch < 2:
# Training
_, value = sess.run([opt_op, logits])
print('Epoch {}, batch {} | Sample value: {}'.format(epoch, batch, value[0]))
batch += 1
else:
# Final inference
values.append(sess.run(logits))
print('Epoch {}, batch {} | Final inference | Sample value: {}'.format(epoch, batch, values[-1][0]))
batch += 1
except tf.errors.OutOfRangeError:
break
# Save model state
print('\nSaving...')
cwd = os.getcwd()
path = os.path.join(cwd, 'simple')
shutil.rmtree(path, ignore_errors=True)
inputs_dict = {
"batch_size_ph": batch_size_ph,
"features_data_ph": features_data_ph,
"labels_data_ph": labels_data_ph
}
outputs_dict = {
"logits": logits
}
tf.saved_model.simple_save(
sess, path, inputs_dict, outputs_dict
)
print('Ok')
# Restoring
graph2 = tf.Graph()
with graph2.as_default():
with tf.Session(graph=graph2) as sess:
# Restore saved values
print('\nRestoring...')
tf.saved_model.loader.load(
sess,
[tag_constants.SERVING],
path
)
print('Ok')
# Get restored placeholders
labels_data_ph = graph2.get_tensor_by_name('labels_data_ph:0')
features_data_ph = graph2.get_tensor_by_name('features_data_ph:0')
batch_size_ph = graph2.get_tensor_by_name('batch_size_ph:0')
# Get restored model output
restored_logits = graph2.get_tensor_by_name('dense/BiasAdd:0')
# Get dataset initializing operation
dataset_init_op = graph2.get_operation_by_name('dataset_init')
# Initialize restored dataset
sess.run(
dataset_init_op,
feed_dict={
features_data_ph: features,
labels_data_ph: labels,
batch_size_ph: 32
}
)
# Compute inference for both batches in dataset
restored_values = []
for i in range(2):
restored_values.append(sess.run(restored_logits))
print('Restored values: ', restored_values[i][0])
# Check if original inference and restored inference are equal
valid = all((v == rv).all() for v, rv in zip(values, restored_values))
print('\nInferences match: ', valid)
这将打印：
$ python3 save_and_restore.py
Epoch 0, batch 0 | Sample value: [-0.13851789 -0.3087595 0.12804556 0.20013677 -0.08229901]
Epoch 0, batch 1 | Sample value: [-0.00555491 -0.04339041 -0.05111827 -0.2480045 -0.00107776]
Epoch 1, batch 0 | Sample value: [-0.19321944 -0.2104792 -0.00602257 0.07465433 0.11674127]
Epoch 1, batch 1 | Sample value: [-0.05275984 0.05981954 -0.15913513 -0.3244143 0.10673307]
Epoch 2, batch 0 | Final inference | Sample value: [-0.26331693 -0.13013336 -0.12553 -0.04276478 0.2933622 ]
Epoch 2, batch 1 | Final inference | Sample value: [-0.07730117 0.11119192 -0.20817074 -0.35660955 0.16990358]
Saving...
INFO:tensorflow:Assets added to graph.
INFO:tensorflow:No assets to write.
INFO:tensorflow:SavedModel written to: b'/some/path/simple/saved_model.pb'
Ok
Restoring...
INFO:tensorflow:Restoring parameters from b'/some/path/simple/variables/variables'
Ok
Restored values: [-0.26331693 -0.13013336 -0.12553 -0.04276478 0.2933622 ]
Restored values: [-0.07730117 0.11119192 -0.20817074 -0.35660955 0.16990358]
Inferences match: True
答案 4 :(得分：65)
我的环境：Python 3.6，Tensorflow 1.3.0
虽然有很多解决方案，但大多数都基于tf.train.Saver。当我们加载由.ckpt保存的Saver时，我们必须重新定义张量流网络或使用一些奇怪且难以记住的名称，例如'placehold_0:0'，'dense/Adam/Weight:0'。在这里，我建议使用tf.saved_model，下面给出一个最简单的示例，您可以从Serving a TensorFlow Model了解更多信息：
保存模型：
import tensorflow as tf
# define the tensorflow network and do some trains
x = tf.placeholder("float", name="x")
w = tf.Variable(2.0, name="w")
b = tf.Variable(0.0, name="bias")
h = tf.multiply(x, w)
y = tf.add(h, b, name="y")
sess = tf.Session()
sess.run(tf.global_variables_initializer())
# save the model
export_path = './savedmodel'
builder = tf.saved_model.builder.SavedModelBuilder(export_path)
tensor_info_x = tf.saved_model.utils.build_tensor_info(x)
tensor_info_y = tf.saved_model.utils.build_tensor_info(y)
prediction_signature = (
tf.saved_model.signature_def_utils.build_signature_def(
inputs={'x_input': tensor_info_x},
outputs={'y_output': tensor_info_y},
method_name=tf.saved_model.signature_constants.PREDICT_METHOD_NAME))
builder.add_meta_graph_and_variables(
sess, [tf.saved_model.tag_constants.SERVING],
signature_def_map={
tf.saved_model.signature_constants.DEFAULT_SERVING_SIGNATURE_DEF_KEY:
prediction_signature
},
)
builder.save()
加载模型：
import tensorflow as tf
sess=tf.Session()
signature_key = tf.saved_model.signature_constants.DEFAULT_SERVING_SIGNATURE_DEF_KEY
input_key = 'x_input'
output_key = 'y_output'
export_path = './savedmodel'
meta_graph_def = tf.saved_model.loader.load(
sess,
[tf.saved_model.tag_constants.SERVING],
export_path)
signature = meta_graph_def.signature_def
x_tensor_name = signature[signature_key].inputs[input_key].name
y_tensor_name = signature[signature_key].outputs[output_key].name
x = sess.graph.get_tensor_by_name(x_tensor_name)
y = sess.graph.get_tensor_by_name(y_tensor_name)
y_out = sess.run(y, {x: 3.0})
答案 5 :(得分：55)
模型有两个部分，模型定义，由模型目录中的Supervisor保存为graph.pbtxt，张量的数值保存在model.ckpt-1003418等检查点文件中。
可以使用tf.import_graph_def恢复模型定义，并使用Saver恢复权重。
但是，Saver使用附加到模型Graph的变量的特殊集合保持列表，并且此集合未使用import_graph_def初始化，因此您暂时不能将这两个一起使用（它在我们的路线图中）修理）。目前，您必须使用Ryan Sepassi的方法 - 手动构建具有相同节点名称的图形，并使用Saver将权重加载到其中。
（或者您可以通过使用import_graph_def进行操作，手动创建变量，并为每个变量使用tf.add_to_collection(tf.GraphKeys.VARIABLES, variable)，然后使用Saver）
答案 6 :(得分：39)
您也可以采用这种方式。
W1 = tf.Variable(tf.truncated_normal([6, 6, 1, K], stddev=0.1), name="W1")
B1 = tf.Variable(tf.constant(0.1, tf.float32, [K]), name="B1")
Similarly, W2, B2, W3, .....
Saver中并保存model_saver = tf.train.Saver()
# Train the model and save it in the end
model_saver.save(session, "saved_models/CNN_New.ckpt")
with tf.Session(graph=graph_cnn) as session:
model_saver.restore(session, "saved_models/CNN_New.ckpt")
print("Model restored.")
print('Initialized')
W1 = session.run(W1)
print(W1)
在不同的python实例中运行时，请使用
with tf.Session() as sess:
# Restore latest checkpoint
saver.restore(sess, tf.train.latest_checkpoint('saved_model/.'))
# Initalize the variables
sess.run(tf.global_variables_initializer())
# Get default graph (supply your custom graph if you have one)
graph = tf.get_default_graph()
# It will give tensor object
W1 = graph.get_tensor_by_name('W1:0')
# To get the value (numpy array)
W1_value = session.run(W1)
答案 7 :(得分：20)
在大多数情况下，使用tf.train.Saver从磁盘保存和恢复是最佳选择：
... # build your model
saver = tf.train.Saver()
with tf.Session() as sess:
... # train the model
saver.save(sess, "/tmp/my_great_model")
with tf.Session() as sess:
saver.restore(sess, "/tmp/my_great_model")
... # use the model
您也可以保存/恢复图形结构本身（有关详细信息，请参阅MetaGraph documentation）。默认情况下，Saver会将图表结构保存到.meta文件中。您可以致电import_meta_graph()进行恢复。它恢复图形结构并返回可用于恢复模型状态的Saver：
saver = tf.train.import_meta_graph("/tmp/my_great_model.meta")
with tf.Session() as sess:
saver.restore(sess, "/tmp/my_great_model")
... # use the model
但是，有些情况下你需要更快的东西。例如，如果您实施提前停止，则希望每次模型在训练期间改进时保存检查点（在验证集上测量），然后如果一段时间没有进展，则需要回滚到最佳模型。如果每次改进时将模型保存到磁盘，都会极大地减慢培训速度。诀窍是将变量状态保存到内存，然后稍后恢复它们：
... # build your model
# get a handle on the graph nodes we need to save/restore the model
graph = tf.get_default_graph()
gvars = graph.get_collection(tf.GraphKeys.GLOBAL_VARIABLES)
assign_ops = [graph.get_operation_by_name(v.op.name + "/Assign") for v in gvars]
init_values = [assign_op.inputs[1] for assign_op in assign_ops]
with tf.Session() as sess:
... # train the model
# when needed, save the model state to memory
gvars_state = sess.run(gvars)
# when needed, restore the model state
feed_dict = {init_value: val
for init_value, val in zip(init_values, gvars_state)}
sess.run(assign_ops, feed_dict=feed_dict)
快速解释：当您创建变量X时，TensorFlow会自动创建赋值操作X/Assign以设置变量的初始值。我们只使用这些现有的赋值操作，而不是创建占位符和额外的赋值操作（这会使图形变得混乱）。每个赋值op的第一个输入是对它应该初始化的变量的引用，第二个输入（assign_op.inputs[1]）是初始值。因此，为了设置我们想要的任何值（而不是初始值），我们需要使用feed_dict并替换初始值。是的，TensorFlow允许您为任何操作提供值，而不仅仅是占位符，所以这样可以正常工作。
答案 8 :(得分：17)
正如Yaroslav所说，您可以通过导入图表，手动创建变量，然后使用Saver来破解从graph_def和检查点恢复。
我是为个人使用而实现的，所以我虽然在这里分享代码。
链接：https://gist.github.com/nikitakit/6ef3b72be67b86cb7868
（当然，这是一个黑客，并且无法保证在未来的TensorFlow版本中以这种方式保存的模型仍然可读。）
答案 9 :(得分：14)
如果它是内部保存的模型，您只需将所有变量的恢复器指定为
restorer = tf.train.Saver(tf.all_variables())
并使用它来恢复当前会话中的变量：
restorer.restore(self._sess, model_file)
对于外部模型，您需要指定从其变量名到变量名的映射。您可以使用命令
查看模型变量名称python /path/to/tensorflow/tensorflow/python/tools/inspect_checkpoint.py --file_name=/path/to/pretrained_model/model.ckpt
inspect_checkpoint.py脚本可以在＆＃39; ./ tensorflow / python / tools＆＃39;中找到。 Tensorflow源文件夹。
要指定映射，您可以使用我的Tensorflow-Worklab，其中包含一组类和脚本来训练和重新训练不同的模型。它包括一个重新训练ResNet模型的例子，位于here
答案 10 :(得分：11)
这是我的两个基本案例的简单解决方案，不同之处在于您是要从文件加载图形还是在运行时构建它。
这个答案适用于Tensorflow 0.12+（包括1.0）。
graph = ... # build the graph
saver = tf.train.Saver() # create the saver after the graph
with ... as sess: # your session object
saver.save(sess, 'my-model')
graph = ... # build the graph
saver = tf.train.Saver() # create the saver after the graph
with ... as sess: # your session object
saver.restore(sess, tf.train.latest_checkpoint('./'))
# now you can use the graph, continue training or whatever
使用此技术时，请确保所有图层/变量都已明确设置唯一名称。否则Tensorflow会使名称本身唯一，因此它们将与文件中存储的名称不同。这在以前的技术中不是问题，因为名称在加载和保存时都以相同的方式被“损坏”。
graph = ... # build the graph
for op in [ ... ]: # operators you want to use after restoring the model
tf.add_to_collection('ops_to_restore', op)
saver = tf.train.Saver() # create the saver after the graph
with ... as sess: # your session object
saver.save(sess, 'my-model')
with ... as sess: # your session object
saver = tf.train.import_meta_graph('my-model.meta')
saver.restore(sess, tf.train.latest_checkpoint('./'))
ops = tf.get_collection('ops_to_restore') # here are your operators in the same order in which you saved them to the collection
答案 11 :(得分：10)
您还可以在examples中查看TensorFlow/skflow，picture提供可帮助您轻松管理模型的save和restore方法。它具有参数，您还可以控制备份模型的频率。
答案 12 :(得分：9)
如果您使用tf.train.MonitoredTrainingSession作为默认会话，则无需添加额外代码来执行保存/恢复操作。只需将检查点目录名称传递给MonitoredTrainingSession的构造函数，它将使用会话挂钩来处理这些。
答案 13 :(得分：8)
这里的所有答案都很棒，但我想添加两件事。
首先，详细说明@ user7505159的答案，＆＃34; ./"添加到要还原的文件名的开头可能很重要。
例如，您可以保存没有＆＃34; ./"的图表;在文件名中如下：
# Some graph defined up here with specific names
saver = tf.train.Saver()
save_file = 'model.ckpt'
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
saver.save(sess, save_file)
但是为了恢复图形，您可能需要预先添加＆＃34; ./"到file_name：
# Same graph defined up here
saver = tf.train.Saver()
save_file = './' + 'model.ckpt' # String addition used for emphasis
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
saver.restore(sess, save_file)
您并不总是需要＆＃34; ./"，但它可能会导致问题，具体取决于您的环境和TensorFlow版本。
还要提到在恢复会话之前sess.run(tf.global_variables_initializer())可能很重要。
如果您在尝试恢复已保存的会话时收到有关未初始化变量的错误，请确保在sess.run(tf.global_variables_initializer())行之前添加saver.restore(sess, save_file)。它可以让你头疼。
答案 14 :(得分：7)
如问题6255中所述：
use '**./**model_name.ckpt'
saver.restore(sess,'./my_model_final.ckpt')
而不是
saver.restore('my_model_final.ckpt')
答案 15 :(得分：5)
根据新的Tensorflow版本，tf.train.Checkpoint是保存和恢复模型的首选方法：
Checkpoint.save和Checkpoint.restore写入和读取基于对象 检查点，与写入和读取的tf.train.Saver相反 基于variable.name的检查点。基于对象的检查点保存 Python对象（层，优化器， 具有命名边的变量等），此图用于匹配 恢复检查点时的变量。它可以更强大 Python程序中的更改，并有助于支持创建时还原 急于执行时的变量。 优先选择tf.train.Checkpointtf.train.Saver获取新代码。
这里是一个例子：
import tensorflow as tf
import os
tf.enable_eager_execution()
checkpoint_directory = "/tmp/training_checkpoints"
checkpoint_prefix = os.path.join(checkpoint_directory, "ckpt")
checkpoint = tf.train.Checkpoint(optimizer=optimizer, model=model)
status = checkpoint.restore(tf.train.latest_checkpoint(checkpoint_directory))
for _ in range(num_training_steps):
optimizer.minimize( ... ) # Variables will be restored on creation.
status.assert_consumed() # Optional sanity checks.
checkpoint.save(file_prefix=checkpoint_prefix)
答案 16 :(得分：3)
使用tf.train.Saver保存模型，重命名，如果要减小模型大小，则需要指定var_list。 val_list可以是tf.trainable_variables或tf.global_variables。
答案 17 :(得分：3)
您可以使用
将变量保存在网络中saver = tf.train.Saver()
saver.save(sess, 'path of save/fileName.ckpt')
要还原网络以供以后使用或在另一个脚本中重复使用，请使用：
saver = tf.train.Saver()
saver.restore(sess, tf.train.latest_checkpoint('path of save/')
sess.run(....)
重要点：
sess在首次运行和后续运行之间必须相同（一致的结构）。 saver.restore需要已保存文件的文件夹路径，而不是单个文件路径。 答案 18 :(得分：2)
要保存模型的任何地方，
perl6 -e 'use Pod::Load; .perl.say for load("pod-load-clean.pod6")'
请确保您所有的self.saver = tf.train.Saver()
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
...
self.saver.save(sess, filename)
都有名称，因为您以后可能想使用它们的名称来还原它们。
还有您要预测的地方
tf.Variable确保saver在相应的会话中运行。
请记住，如果您使用saver = tf.train.import_meta_graph(filename)
name = 'name given when you saved the file'
with tf.Session() as sess:
saver.restore(sess, name)
print(sess.run('W1:0')) #example to retrieve by variable name
，则将仅使用最新的检查点。
答案 19 :(得分：2)
TF2.0保存模型对于使用TF1.x保存模型，我看到了很好的答案。我想在保存tensorflow.keras模型时提供更多的指针，这有点复杂，因为有很多方法可以保存模型。
在这里，我提供了一个将tensorflow.keras模型保存到当前目录下的model_path文件夹中的示例。这与最新的tensorflow（TF2.0）一起很好地工作。如果将来有任何变化，我将更新此说明。
import tensorflow as tf
from tensorflow import keras
mnist = tf.keras.datasets.mnist
#import data
(x_train, y_train),(x_test, y_test) = mnist.load_data()
x_train, x_test = x_train / 255.0, x_test / 255.0
# create a model
def create_model():
model = tf.keras.models.Sequential([
tf.keras.layers.Flatten(input_shape=(28, 28)),
tf.keras.layers.Dense(512, activation=tf.nn.relu),
tf.keras.layers.Dropout(0.2),
tf.keras.layers.Dense(10, activation=tf.nn.softmax)
])
# compile the model
model.compile(optimizer='adam',
loss='sparse_categorical_crossentropy',
metrics=['accuracy'])
return model
# Create a basic model instance
model=create_model()
model.fit(x_train, y_train, epochs=1)
loss, acc = model.evaluate(x_test, y_test,verbose=1)
print("Original model, accuracy: {:5.2f}%".format(100*acc))
# Save entire model to a HDF5 file
model.save('./model_path/my_model.h5')
# Recreate the exact same model, including weights and optimizer.
new_model = keras.models.load_model('./model_path/my_model.h5')
loss, acc = new_model.evaluate(x_test, y_test)
print("Restored model, accuracy: {:5.2f}%".format(100*acc))
如果您只想保存模型权重，然后再加载权重以恢复模型，那么
model.fit(x_train, y_train, epochs=5)
loss, acc = model.evaluate(x_test, y_test,verbose=1)
print("Original model, accuracy: {:5.2f}%".format(100*acc))
# Save the weights
model.save_weights('./checkpoints/my_checkpoint')
# Restore the weights
model = create_model()
model.load_weights('./checkpoints/my_checkpoint')
loss,acc = model.evaluate(x_test, y_test)
print("Restored model, accuracy: {:5.2f}%".format(100*acc))
# include the epoch in the file name. (uses `str.format`)
checkpoint_path = "training_2/cp-{epoch:04d}.ckpt"
checkpoint_dir = os.path.dirname(checkpoint_path)
cp_callback = tf.keras.callbacks.ModelCheckpoint(
checkpoint_path, verbose=1, save_weights_only=True,
# Save weights, every 5-epochs.
period=5)
model = create_model()
model.save_weights(checkpoint_path.format(epoch=0))
model.fit(train_images, train_labels,
epochs = 50, callbacks = [cp_callback],
validation_data = (test_images,test_labels),
verbose=0)
latest = tf.train.latest_checkpoint(checkpoint_dir)
new_model = create_model()
new_model.load_weights(latest)
loss, acc = new_model.evaluate(test_images, test_labels)
print("Restored model, accuracy: {:5.2f}%".format(100*acc))
import tensorflow as tf
from tensorflow import keras
mnist = tf.keras.datasets.mnist
(x_train, y_train),(x_test, y_test) = mnist.load_data()
x_train, x_test = x_train / 255.0, x_test / 255.0
# Custom Loss1 (for example)
@tf.function()
def customLoss1(yTrue,yPred):
return tf.reduce_mean(yTrue-yPred)
# Custom Loss2 (for example)
@tf.function()
def customLoss2(yTrue, yPred):
return tf.reduce_mean(tf.square(tf.subtract(yTrue,yPred)))
def create_model():
model = tf.keras.models.Sequential([
tf.keras.layers.Flatten(input_shape=(28, 28)),
tf.keras.layers.Dense(512, activation=tf.nn.relu),
tf.keras.layers.Dropout(0.2),
tf.keras.layers.Dense(10, activation=tf.nn.softmax)
])
model.compile(optimizer='adam',
loss='sparse_categorical_crossentropy',
metrics=['accuracy', customLoss1, customLoss2])
return model
# Create a basic model instance
model=create_model()
# Fit and evaluate model
model.fit(x_train, y_train, epochs=1)
loss, acc,loss1, loss2 = model.evaluate(x_test, y_test,verbose=1)
print("Original model, accuracy: {:5.2f}%".format(100*acc))
model.save("./model.h5")
new_model=tf.keras.models.load_model("./model.h5",custom_objects={'customLoss1':customLoss1,'customLoss2':customLoss2})
当在以下情况下（tf.tile）具有自定义操作时，我们需要创建一个函数并包装一个Lambda层。否则，无法保存模型。
import numpy as np
import tensorflow as tf
from tensorflow.keras.layers import Input, Lambda
from tensorflow.keras import Model
def my_fun(a):
out = tf.tile(a, (1, tf.shape(a)[0]))
return out
a = Input(shape=(10,))
#out = tf.tile(a, (1, tf.shape(a)[0]))
out = Lambda(lambda x : my_fun(x))(a)
model = Model(a, out)
x = np.zeros((50,10), dtype=np.float32)
print(model(x).numpy())
model.save('my_model.h5')
#load the model
new_model=tf.keras.models.load_model("my_model.h5")
我认为我已经介绍了许多保存tf.keras模型的方法。但是，还有许多其他方法。如果您发现上面没有涉及用例，请在下面发表评论。谢谢！
答案 20 :(得分：1)
对于 tensorflow 2.0 ，它是as simple as
<nav class="awemenu-nav awemenu-has-logo <?php print $is_transparent_mode ? 'awe-header--transparent' : ''; ?>" data-sticky="<?php echo esc_attr( (bool) mojado_option( 'mojado_header_nav_sticky' ) ); ?>"> <div class="container"> <div class="awemenu-container"> <div class="awemenu-language-search awe-fr"> <?php get_template_part( 'template-parts/header-search' ); ?> <?php get_template_part( 'template-parts/header-language' ); ?> </div> <?php if ( $is_transparent_mode ) : ?> <?php print mojado_site_logo( 'home_logo', true, '<div class="home-logo">', '</div>' ); // WPCS: XSS OK. ?> <?php endif; ?> <?php /** * Navigation Main Menu. */ wp_nav_menu( array( 'container' => '', 'menu_id' => 'primary-menu', 'menu_class' => 'main-navigation awemenu', 'theme_location' => 'primary', 'walker' => new Mojado_Walker_Menu, 'fallback_cb' => array( 'Mojado_Menu_Support', 'fallback' ), ) ); ?> </div><!-- .awemenu-container --> </div><!-- .container --> </nav><!-- .awemenu-nav -->
要还原：
# Save the model
model.save('path_to_my_model.h5')
答案 21 :(得分：1)
这是使用 Tensorflow 2.0 SavedModel 格式（建议的格式according to the docs）的简单示例，用于简单的MNIST数据集分类器，并使用Keras函数没有太多幻想的API：
# Imports
import tensorflow as tf
from tensorflow.keras.layers import Input, Dense, Flatten
from tensorflow.keras.models import Model
import matplotlib.pyplot as plt
# Load data
mnist = tf.keras.datasets.mnist # 28 x 28
(x_train,y_train), (x_test, y_test) = mnist.load_data()
# Normalize pixels [0,255] -> [0,1]
x_train = tf.keras.utils.normalize(x_train,axis=1)
x_test = tf.keras.utils.normalize(x_test,axis=1)
# Create model
input = Input(shape=(28,28), dtype='float64', name='graph_input')
x = Flatten()(input)
x = Dense(128, activation='relu')(x)
x = Dense(128, activation='relu')(x)
output = Dense(10, activation='softmax', name='graph_output', dtype='float64')(x)
model = Model(inputs=input, outputs=output)
model.compile(optimizer='adam',
loss='sparse_categorical_crossentropy',
metrics=['accuracy'])
# Train
model.fit(x_train, y_train, epochs=3)
# Save model in SavedModel format (Tensorflow 2.0)
export_path = 'model'
tf.saved_model.save(model, export_path)
# ... possibly another python program
# Reload model
loaded_model = tf.keras.models.load_model(export_path)
# Get image sample for testing
index = 0
img = x_test[index] # I normalized the image on a previous step
# Predict using the signature definition (Tensorflow 2.0)
predict = loaded_model.signatures["serving_default"]
prediction = predict(tf.constant(img))
# Show results
print(np.argmax(prediction['graph_output'])) # prints the class number
plt.imshow(x_test[index], cmap=plt.cm.binary) # prints the image
什么是serving_default？
这是您选择的signature def of the tag的名称（在这种情况下，已选择默认的serve标签）。另外，here解释了如何使用saved_model_cli查找模型的标签和签名。
免责声明
这只是一个基本示例，如果您只想启动并运行它，但绝不是一个完整的答案-也许以后我可以对其进行更新。我只是想举一个在TF 2.0中使用SavedModel的简单示例，因为我在任何地方都没有看到一个，甚至这个简单的示例。
@ Tom的答案是一个SavedModel示例，但不幸的是，由于某些重大更改，它在Tensorflow 2.0上不起作用。
@ Vishnuvardhan Janapati的回答是TF 2.0，但不是SavedModel格式的。
答案 22 :(得分：0)
我正在使用版本：
tensorflow (1.13.1)
tensorflow-gpu (1.13.1)
简单的方法是
保存：
model.save("model.h5")
还原：
model = tf.keras.models.load_model("model.h5")
答案 23 :(得分：0)
在新版本的tensorflow 2.0中，保存/加载模型的过程要容易得多。由于Keras API的实现，TensorFlow的高级API。
要保存模型： 检查文档以供参考： https://www.tensorflow.org/versions/r2.0/api_docs/python/tf/keras/models/save_model
tf.keras.models.save_model(model_name, filepath, save_format)
要加载模型：
https://www.tensorflow.org/versions/r2.0/api_docs/python/tf/keras/models/load_model
model = tf.keras.models.load_model(filepath)
答案 24 :(得分：0)
按照@Vishnuvardhan Janapati的回答，这是使用 TensorFlow 2.0.0 下的自定义层/度量/损耗保存和重新加载模型的另一种方法
import tensorflow as tf
from tensorflow.keras.layers import Layer
from tensorflow.keras.utils.generic_utils import get_custom_objects
# custom loss (for example)
def custom_loss(y_true,y_pred):
return tf.reduce_mean(y_true - y_pred)
get_custom_objects().update({'custom_loss': custom_loss})
# custom loss (for example)
class CustomLayer(Layer):
def __init__(self, ...):
...
# define custom layer and all necessary custom operations inside custom layer
get_custom_objects().update({'CustomLayer': CustomLayer})
通过这种方式，一旦您执行了此类代码，并使用tf.keras.models.save_model或model.save或ModelCheckpoint回调保存了模型，就可以重新加载模型而无需精确自定义对象，就像
new_model = tf.keras.models.load_model("./model.h5"})
答案 25 :(得分：0)
对于tensorflow-2.0
这很简单。
import tensorflow as tf
model.save("model_name")
model = tf.keras.models.load_model('model_name')