Tensorflow:如何保存/恢复模型?

Tensorflow中训练模型后:

  1. 您如何保存经过训练的模型?
  2. 您以后如何还原此保存的模型?

#1楼

对于TensorFlow版本<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,这意味着在还原检查点时,图形应相同。

这是线性回归的示例,其中存在一个训练循环,该循环保存变量检查点,而评估部分将恢复先前运行中保存的变量并计算预测。 当然,您也可以根据需要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})

这是Variable文档 ,其中包括保存和还原。 这是Saver文档


#2楼

模型分为两部分:模型定义(由Supervisor保存为模型目录中的graph.pbtxt和张量的数值(保存至诸如model.ckpt-1003418类的检查点文件中)。

可以使用tf.import_graph_def还原模型定义,并使用Saver还原权重。

但是, Saver使用了特殊的集合保存列表,该列表包含附加到模型Graph上的变量,并且此集合未使用import_graph_def初始化,因此您目前无法将两者一起使用(正在修复中)。 现在,您必须使用Ryan Sepassi的方法-手动构造具有相同节点名称的图,然后使用Saver将权重加载到其中。

(或者,您可以使用import_graph_def ,手动创建变量,并对每个变量使用tf.add_to_collection(tf.GraphKeys.VARIABLES, variable) ,然后使用Saver来破解它)


#3楼

正如Yaroslav所说,您可以通过导入图形,手动创建变量然后使用Saver来从graph_def和检查点恢复。

我将其实现为个人使用,因此尽管我在这里共享了代码。

链接: https//gist.github.com/nikitakit/6ef3b72be67b86cb7868

(当然,这是黑客,不能保证以此方式保存的模型在TensorFlow的未来版本中仍可读取。)


#4楼

您还可以在TensorFlow / skflow中检出示例 ,该示例提供了saverestore方法,可帮助您轻松管理模型。 它具有一些参数,您还可以控制备份模型的频率。


#5楼

如果是内部保存的模型,则只需为所有变量指定一个还原器即可

restorer = tf.train.Saver(tf.all_variables())

并使用它来还原当前会话中的变量:

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。 您可以使用以下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

可以在Tensorflow源的'./tensorflow/python/tools'文件夹中找到inspect_checkpoint.py脚本。

要指定映射,您可以使用我的Tensorflow-Worklab ,其中包含一组用于训练和重新训练不同模型的类和脚本。 它包含一个重新训练ResNet模型的示例,位于此处


#6楼

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_graphtf.train.import_meta_graph直接保存和恢复模型。

保存模型

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

恢复模型

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_)

#7楼

如问题6255中所述

use '**./**model_name.ckpt'
saver.restore(sess,'./my_model_final.ckpt')

代替

saver.restore('my_model_final.ckpt')

#8楼

您也可以采用这种更简单的方法。

步骤1:初始化所有变量

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, .....

步骤2:将会话保存在Model Saver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")

步骤3:还原模型

with tf.Session(graph=graph_cnn) as session:
    model_saver.restore(session, "saved_models/CNN_New.ckpt")
    print("Model restored.") 
    print('Initialized')

第4步:检查您的变量

W1 = session.run(W1)
print(W1)

在其他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)

#9楼

在大多数情况下,使用tf.train.Saver从磁盘保存和还原是最佳选择:

... # 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,请参见MetaGraph文档 )。 默认情况下, Saver将图形结构保存到.meta文件中。 您可以调用import_meta_graph()进行还原。 它还原图结构并返回一个Saver ,您可以使用该Saver还原模型的状态:

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,在某些情况下,您需要更快的速度。 例如,如果实施提前停止,则希望在训练过程中每次模型改进时都保存检查点(以验证集为准),然后如果一段时间没有进展,则希望回滚到最佳模型。 如果您在每次改进时都将模型保存到磁盘,则会极大地减慢训练速度。 诀窍是将变量状态保存到内存中 ,然后稍后再恢复它们:

... # 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)

快速说明:创建变量X ,TensorFlow自动创建一个赋值操作X/Assign来设置变量的初始值。 与其创建占位符和额外的分配操作(这只会使图形混乱),我们仅使用这些现有的分配操作。 每个赋值op的第一个输入是对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,为了设置所需的任何值(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,因此可以正常工作。


#10楼

这是我针对两种基本情况的简单解决方案,不同之处在于您是要从文件中加载图形还是在运行时构建图形。

该答案适用于Tensorflow 0.12+(包括1.0)。

在代码中重建图形

保存

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')

载入中

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

还从文件加载图形

使用此技术时,请确保所有图层/变量均已明确设置唯一名称。 否则,Tensorflow将使名称本身具有唯一性,因此它们将与文件中存储的名称不同。 在以前的技术中这不是问题,因为在加载和保存时都以相同的方式“混合”了名称。

保存

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')

载入中

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

#11楼

我正在改善我的答案,以添加更多有关保存和还原模型的详细信息。

Tensorflow版本0.11中 (及之后):

保存模型:

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)

还原模型:

import tensorflow as tf

sess=tf.Session()    
#First let's load meta graph and restore weights
saver = tf.train.import_meta_graph('my_test_model-1000.meta')
saver.restore(sess,tf.train.latest_checkpoint('./'))


# Access saved Variables directly
print(sess.run('bias:0'))
# This will print 2, which is the value of bias that we saved


# Now, let's access and create placeholders variables and
# create feed-dict to feed new data

graph = tf.get_default_graph()
w1 = graph.get_tensor_by_name("w1:0")
w2 = graph.get_tensor_by_name("w2:0")
feed_dict ={w1:13.0,w2:17.0}

#Now, access the op that you want to run. 
op_to_restore = graph.get_tensor_by_name("op_to_restore:0")

print sess.run(op_to_restore,feed_dict)
#This will print 60 which is calculated 

这里和一些更高级的用例已经很好地解释了。

快速完整的教程,用于保存和恢复Tensorflow模型


#12楼

如果您将tf.train.MonitoredTrainingSession用作默认会话,则无需添加额外的代码即可保存/还原内容。 只需将检查点目录名传递给MonitoredTrainingSession的构造函数,它将使用会话挂钩来处理这些。


#13楼

这里的所有答案都很好,但我想补充两点。

首先,要详细说明@ user7505159的答案,将“ ./”添加到要还原的文件名的开头很重要。

例如,您可以保存一个图形,文件名中不包含“ ./”,如下所示:

# 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)

但是为了还原图形,您可能需要在file_name前面加上“ ./”:

# 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)

您不一定总是需要“ ./”,但是根据您的环境和TensorFlow的版本,它可能会引起问题。

还需要提及的是,在恢复会话之前, sess.run(tf.global_variables_initializer())很重要。

如果在尝试还原保存的会话时收到关于未初始化变量的错误,请确保在saver.restore(sess, save_file)行之前包括sess.run(tf.global_variables_initializer()) 。 它可以节省您的头痛。


#14楼

我的环境:Python 3.6,Tensorflow 1.3.0

尽管有很多解决方案,但是大多数解决方案都是基于tf.train.Saver 。 当我们加载由Saver保存的.ckpt ,我们必须重新定义tensorflow网络或使用一些怪异而难以记住的名称,例如'placehold_0:0''dense/Adam/Weight:0' 。 在这里,我建议使用tf.saved_model ,这是下面给出的一个最简单的示例,您可以从服务TensorFlow模型中了解更多信息:

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})

#15楼

文件

他们构建了详尽且有用的教程-> https://www.tensorflow.org/guide/saved_model

从文档:

保存

# 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)

恢复

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())

Tensorflow 2

这仍然是beta版,因此我建议不要使用。 如果您仍然想走这条路,这里是tf.saved_model使用指南

Tensorflow <2

simple_save

为了完整起见 ,我给出了很多好答案,我将添加2美分: simple_save 。 也是使用tf.data.Dataset API的独立代码示例。

Python 3; Tensorflow 1.14

import tensorflow as tf
from tensorflow.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
        })

独立示例

原始博客文章

为了演示,以下代码生成随机数据。

  1. 我们首先创建占位符。 它们将在运行时保存数据。 根据它们,我们创建Dataset ,然后创建其Iterator 。 我们得到迭代器生成的张量,称为input_tensor ,它将用作模型的输入。
  2. 该模型本身是由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。
  3. 损失是softmax_cross_entropy_with_logits ,使用Adam优化。 经过2个时期(每个批次2个批次)后,我们将tf.saved_model.simple_save保存为“训练过的”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。
  4. 在新图中,然后使用tf.saved_model.loader.load恢复保存的模型。 我们抢占位符和logits与graph.get_tensor_by_nameIterator与初始化操作graph.get_operation_by_name
  5. 最后,我们对数据集中的两个批次进行推断,并检查保存和恢复的模型是否产生相同的值。 他们是这样!

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

#16楼

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。


#17楼

根据新的Tensorflow版本, tf.train.Checkpoint是保存和还原模型的首选方法:

Checkpoint.saveCheckpoint.restore写入和读取基于对象的检查点,而tf.train.Saver则可以写入和读取基于variable.name的检查点。 基于对象的检查点保存带有命名边的Python对象(层,优化程序,变量等)之间的依存关系图,该图用于在恢复检查点时匹配变量。 它对Python程序中的更改可能更健壮,并有助于在急切执行时支持变量的创建时恢复。 对于新代码, tf.train.Saver使用tf.train.Checkpoint不是tf.train.Saver

这是一个例子:

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)

更多信息和示例在这里。


#18楼

无论您要将模型保存到哪里,

self.saver = tf.train.Saver()
with tf.Session() as sess:
            sess.run(tf.global_variables_initializer())
            ...
            self.saver.save(sess, filename)

确保您的所有tf.Variable都有名称,因为您以后可能要使用其名称来还原它们。 在您想要预测的地方

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

确保保护程序在相应的会话中运行。 请记住,如果您使用tf.train.latest_checkpoint('./') ,那么将仅使用最新的检查点。


#19楼

您可以使用以下方法将变量保存到网络

saver = tf.train.Saver() 
saver.save(sess, 'path of save/fileName.ckpt')

还原网络以供以后重复使用或在另一个脚本中使用,请使用:

saver = tf.train.Saver()
saver.restore(sess, tf.train.latest_checkpoint('path of save/')
sess.run(....) 

要点:

  1. 在初次运行和后续运行之间(连续结构), sess必须相同。
  2. saver.restore需要已保存文件的文件夹路径,而不是单个文件路径。

#20楼

对于tensorflow 2.0 ,它很简单

 # Save the model model.save('path_to_my_model.h5') 

恢复:

new_model = tensorflow.keras.models.load_model('path_to_my_model.h5')

#21楼

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")

恢复:

model = tf.keras.models.load_model("model.h5")

#22楼

在新版本的tensorflow 2.0中,保存/加载模型的过程要容易得多。 由于实施了Keras API,因此是TensorFlow的高级API。

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)

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)

#23楼

tf.keras使用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,我提供一个将tensorflow.keras模型保存到当前目录下的model_path文件夹的示例。 这与最新的tensorflow(TF2.0)一起很好地工作。 如果近期有任何更改,我将更新此描述。

保存和加载整个模型

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))

仅保存和加载模型权重

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))

使用keras检查点回调进行保存和还原

# 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))

使用自定义指标保存模型

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})

使用自定义操作保存Keras模型

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")

我想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!


#24楼

遵循@Vishnuvardhan Janapati的回答,这是在TensorFlow 2.0.0下使用自定义图层/度量/损耗来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})  

这样,一旦执行了此类代码,并使用tf.keras.models.save_modelmodel.saveModelCheckpoint回调保存了模型,就可以重新加载模型,而无需精确的自定义对象,就像

new_model = tf.keras.models.load_model("./model.h5"})

#25楼

对于tensorflow-2.0

这很简单。

import tensorflow as tf

保存

model.save("model_name")

恢复

model = tf.keras.models.load_model('model_name')
Tensorflow:如何保存/恢复模型?Tensorflow:如何保存/恢复模型? asdfgh0077 发布了0 篇原创文章 · 获赞 1 · 访问量 3192 私信 关注
上一篇:人工智能实践:Tensorflow笔记学习记录(一)


下一篇:吴裕雄 python 神经网络——TensorFlow 多线程队列操作