训练后如何保存/恢复模型?

2024-11-29 08:41:00
admin
原创
188
摘要:问题描述:在 Tensorflow 中训练模型后:如何保存训练好的模型?稍后如何恢复这个保存的模型?解决方案 1:在Tensorflow 0.11 版本中(及之后):保存模型:import tensorflow as tf #Prepare to feed input, i.e. feed_dict and...

问题描述:

在 Tensorflow 中训练模型后:

  1. 如何保存训练好的模型?

  2. 稍后如何恢复这个保存的模型?


解决方案 1:

在Tensorflow 0.11 版本中(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)

恢复模型:

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 

这里已经很好地解释了这个以及一些更高级的用例。

保存和恢复 Tensorflow 模型的快速完整教程

解决方案 2:

在 TensorFlow 0.11.0RC1 版本(及之后)中,您可以根据https://www.tensorflow.org/programmers_guide/meta_graphtf.train.export_meta_graph直接通过调用和保存和恢复您的模型。tf.train.import_meta_graph

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_)

解决方案 3:

Tensorflow 2 文档

保存检查点

改编自文档

# -------------------------
# -----  Toy Context  -----
# -------------------------
import tensorflow as tf


class Net(tf.keras.Model):
    """A simple linear model."""

    def __init__(self):
        super(Net, self).__init__()
        self.l1 = tf.keras.layers.Dense(5)

    def call(self, x):
        return self.l1(x)


def toy_dataset():
    inputs = tf.range(10.0)[:, None]
    labels = inputs * 5.0 + tf.range(5.0)[None, :]
    return (
        tf.data.Dataset.from_tensor_slices(dict(x=inputs, y=labels)).repeat().batch(2)
    )


def train_step(net, example, optimizer):
    """Trains `net` on `example` using `optimizer`."""
    with tf.GradientTape() as tape:
        output = net(example["x"])
        loss = tf.reduce_mean(tf.abs(output - example["y"]))
    variables = net.trainable_variables
    gradients = tape.gradient(loss, variables)
    optimizer.apply_gradients(zip(gradients, variables))
    return loss


# ----------------------------
# -----  Create Objects  -----
# ----------------------------

net = Net()
opt = tf.keras.optimizers.Adam(0.1)
dataset = toy_dataset()
iterator = iter(dataset)
ckpt = tf.train.Checkpoint(
    step=tf.Variable(1), optimizer=opt, net=net, iterator=iterator
)
manager = tf.train.CheckpointManager(ckpt, "./tf_ckpts", max_to_keep=3)

# ----------------------------
# -----  Train and Save  -----
# ----------------------------

ckpt.restore(manager.latest_checkpoint)
if manager.latest_checkpoint:
    print("Restored from {}".format(manager.latest_checkpoint))
else:
    print("Initializing from scratch.")

for _ in range(50):
    example = next(iterator)
    loss = train_step(net, example, opt)
    ckpt.step.assign_add(1)
    if int(ckpt.step) % 10 == 0:
        save_path = manager.save()
        print("Saved checkpoint for step {}: {}".format(int(ckpt.step), save_path))
        print("loss {:1.2f}".format(loss.numpy()))


# ---------------------
# -----  Restore  -----
# ---------------------

# In another script, re-initialize objects
opt = tf.keras.optimizers.Adam(0.1)
net = Net()
dataset = toy_dataset()
iterator = iter(dataset)
ckpt = tf.train.Checkpoint(
    step=tf.Variable(1), optimizer=opt, net=net, iterator=iterator
)
manager = tf.train.CheckpointManager(ckpt, "./tf_ckpts", max_to_keep=3)

# Re-use the manager code above ^

ckpt.restore(manager.latest_checkpoint)
if manager.latest_checkpoint:
    print("Restored from {}".format(manager.latest_checkpoint))
else:
    print("Initializing from scratch.")

for _ in range(50):
    example = next(iterator)
    # Continue training or evaluate etc.

更多链接

检查点会捕获模型使用的所有参数(tf.Variable 对象)的精确值。检查点不包含模型定义的计算的任何描述,因此通常仅在使用已保存参数值的源代码可用时才有用。

另一方面,SavedModel 格式除了参数值(检查点)之外,还包含模型定义的计算的序列化描述。这种格式的模型独立于创建模型的源代码。因此,它们适合通过 TensorFlow Serving、TensorFlow Lite、TensorFlow.js 或其他编程语言(C、C++、Java、Go、Rust、C# 等 TensorFlow API)的程序进行部署。

(重点是我自己加的)


Tensorflow < 2


来自文档:

节省

# 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())

simple_save

很多好的答案,为了完整起见,我将添加我的 2 分:simple_save。 还有一个使用tf.data.DatasetAPI 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

以下代码为了演示而生成随机数据。

  1. 我们首先创建占位符。它们将在运行时保存数据。从它们开始,我们创建Dataset,然后创建Iterator。我们得到迭代器生成的张量,称为input_tensor,它将作为我们模型的输入。

  2. 该模型本身由以下部分构成input_tensor:基于 GRU 的双向 RNN,后跟密集分类器。因为为什么不呢。

  3. 损失为softmax_cross_entropy_with_logits,使用 进行优化Adam。经过 2 个时期(每个时期 2 个批次)后,我们使用 保存“训练好的”模型tf.saved_model.simple_save。如果您按原样运行代码,则模型将保存在simple/当前工作目录中名为 的文件夹中。

  4. 然后,在新的图中,我们使用 恢复已保存的模型tf.saved_model.loader.load。我们使用 抓取占位符和对数函数graph.get_tensor_by_name,并Iterator使用 执行初始化操作graph.get_operation_by_name

  5. 最后,我们对数据集中的两个批次进行推理,并检查保存和恢复的模型是否都产生相同的值。确实如此!

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('
Saving...')
            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('
Restoring...')
            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('
Inferences 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

解决方案 4:

对于 TensorFlow 版本 <0.11.0RC1:

保存的检查点包含Variable模型中 s 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。

以下是线性回归的示例,其中有一个训练循环,用于保存变量检查点,还有一个评估部分,用于恢复上次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s的文档Variable,其中介绍了保存和恢复。以下是的文档Saver

解决方案 5:

我的环境:Python 3.6,Tensorflow 1.3.0

虽然已经有很多解决方案,但大多数都是基于tf.train.Saver。当我们加载.ckpt由 保存的模型时Saver,我们必须重新定义 TensorFlow 网络,或者使用一些奇怪且难记的名字,例如'placehold_0:0''dense/Adam/Weight:0'这里我建议使用tf.saved_model,下面给出一个最简单的例子,你可以从Serving a TensorFlow Model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})

解决方案 6:

该模型分为两部分:模型定义(保存在Supervisor模型graph.pbtxt目录中)和张量的数值(保存在检查点文件中,如)model.ckpt-1003418

可以使用 恢复模型定义tf.import_graph_def,并使用 恢复权重Saver

但是,Saver使用特殊集合来保存附加到模型图的变量列表,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(这是我们的路线图要修复的问题)。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,并使用Saver将权重加载到其中。

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

解决方案 7:

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, .....

第 2 步:将会话保存在模型内部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:恢复模型

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

步骤 4:检查变量

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

在不同的 Python 实例中运行时,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)

解决方案 8:

在大多数情况下,使用以下方法从磁盘保存和恢复tf.train.Saver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

您还可以保存/恢复图形结构本身(有关详细信息,请参阅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()来恢复它。它会恢复图形结构并返回一个Saver,您可以使用它来恢复模型的状态:

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,有些情况下你需要更快的速度。例如,如果你实施提前停止,你希望在训练期间模型每次改进时都保存检查点(以验证集为衡量标准),然后如果一段时间内没有进展,你希望回滚到最佳模型。如果每次改进时都将模型保存到磁盘,这将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)

简单解释一下:当您创建一个变量时X,TensorFlow 会自动创建一个赋值操作X/Assign来设置变量的初始值。我们只需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(这只会使图形变得混乱)。每个赋值操作的第一个输入是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一个值,而不仅仅是占位符,所以这可以正常工作。

解决方案 9:

正如雅罗斯拉夫所说,您可以通过导入图形、手动创建变量,然后使用 Saver 来从 graph_def 和检查点进行恢复。

我实现这个是为了个人使用,所以我想在这里分享代码。

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

(当然,这只是一种黑客行为,并且不能保证以这种方式保存的模型在未来版本的 TensorFlow 中仍然可读。)

解决方案 10:

如果它是一个内部保存的模型,您只需为所有变量指定一个恢复器即可

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您的变量名的映射。您可以使用命令查看模型变量名

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

解决方案 11:

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加载图表还是在运行时构建图表。

该答案适用于 Tensorflow 0.12+(包括 1.0)。

在代码中重建图表

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')

加载中

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

从文件加载图表

使用此技术时,请确保所有层/变量都明确设置了唯一名称。否则 Tensorflow 会自行设置唯一名称,因此它们将与文件中存储的名称不同。这在前一种技术中不是问题,因为名称在加载和保存时都以相同的方式“混乱”。

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')

加载中

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

解决方案 12:

tf.keras 模型保存TF2.0

我看到了关于使用 TF1.x 保存模型的很好的答案。我想提供一些关于保存tensorflow.keras模型的更多提示,这有点复杂,因为保存模型的方法有很多。

这里我提供了一个将tensorflow.keras模型保存到model_path当前目录下文件夹的示例。这与最新的 tensorflow (TF2.0) 配合得很好。如果近期有任何变化,我会更新此描述。

保存并加载整个模型

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

如果你只想保存模型权重,然后加载权重来恢复模型,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 检查点回调保存和恢复

# 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

当我们有自定义操作(如下例所示tf.tile)时,我们需要创建一个函数并用 Lambda 层包装。否则,模型无法保存。

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保存 tf.keras 模型的多种方法中的几种。但是,还有许多其他方法。如果您发现上面没有涵盖您的用例,请在下面评论。

解决方案 13:

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,它将使用会话钩子来处理这些操作。

解决方案 14:

这里的所有答案都很棒,但我想补充两点。

首先,详细说明@user7505159 的回答,“./”对于添加到要恢复的文件名开头非常重要。

例如,您可以保存文件名中不包含“./”的图表,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)

但为了恢复图表,您可能需要在 file_name 前面添加“./”:

# 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“。/”,但它可能会根据您的环境和 TensorFlow 版本导致问题。

还想提一下,sess.run(tf.global_variables_initializer())在恢复会话之前这可能很重要。

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sess.run(tf.global_variables_initializer())在该saver.restore(sess, save_file)行之前包含。它可以为您省去很多麻烦。

解决方案 15:

根据新版 Tensorflow,tf.train.Checkpoint保存和恢复模型的首选方式是:

Checkpoint.saveCheckpoint.restore写入和读取基于对象的检查点,而 tf.train.Saver 则写入和读取基于 variable.name 的检查点。基于对象的检查点保存具有命名边的 Python 对象(层、优化器、变量等)之间的依赖关系图,此图用于在恢复检查点时匹配变量。它可以对 Python 程序中的更改更加稳健,并有助于在急切执行时支持变量的恢复创建。对于新代码,**最好tf.train.Checkpoint使用
tf.train.Saver**。

以下是一个例子:

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)

这里有更多信息和示例。

解决方案 16:

如下期6255所述:

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

而不是

saver.restore('my_model_final.ckpt')

解决方案 17:

对于TensorFlow 2.0来说,非常简单

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

恢复方法:

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

解决方案 18:

对于 tensorflow-2.0

这非常简单。

import tensorflow as tf

节省

model.save("model_name")

恢复

model = tf.keras.models.load_model('model_name')

解决方案 19:

Tensorflow 2.6:现在变得更加简单,你可以以两种格式保存模型

  1. Saved_model(兼容 tf-serving)

  2. H5 或 HDF5

以两种格式保存模型:

 from tensorflow.keras import Model
 inputs = tf.keras.Input(shape=(224,224,3))
 y = tf.keras.layers.Conv2D(24, 3, activation='relu', input_shape=input_shape[1:])(inputs)
 outputs = tf.keras.layers.Dense(5, activation=tf.nn.softmax)(y)
 model = tf.keras.Model(inputs=inputs, outputs=outputs)
 model.save("saved_model/my_model") #To Save in Saved_model format
 model.save("my_model.h5") #To save model in H5 or HDF5 format

以两种格式加载模型

import tensorflow as tf
h5_model = tf.keras.models.load_model("my_model.h5") # loading model in h5 format
h5_model.summary()
saved_m = tf.keras.models.load_model("saved_model/my_model") #loading model in saved_model format
saved_m.summary()

解决方案 20:

下面是一个使用Tensorflow 2.0 SavedModel格式(根据文档,这是推荐的格式)的简单示例,用于简单的 MNIST 数据集分类器,使用 Keras 功能 API,没有太多花哨的操作:

# 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

这是您选择的标签的签名定义的名称(在本例中,serve选择了默认标签)。此外,这里解释了如何使用 查找模型的标签和签名saved_model_cli

免责声明

如果您只是想启动并运行它,这只是一个基本示例,但绝不是一个完整的答案 - 也许我可以在未来更新它。我只是想给出一个使用SavedModelTF 2.0 的简单示例,因为我还没有在任何地方见过,即使是这么简单。

@Tom的回答是一个 SavedModel 示例,但它不适用于 Tensorflow 2.0,因为不幸的是有一些重大变化。

@ Vishnuvardhan Janapati的回答说是 TF 2.0,但它不适用于 SavedModel 格式。

解决方案 21:

您可以使用以下方式保存网络中的变量

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

恢复网络以供稍后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(....) 

要点:

  1. sess第一次运行和后续运行之间必须相同(连贯结构)。

  2. saver.restore需要保存文件的文件夹路径,而不是单个文件的路径。

解决方案 22:

按照@Vishnuvardhan Janapati 的回答,这是在TensorFlow 2.0.0下使用自定义层/度量/损失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,一旦你执行了这样的代码,并使用tf.keras.models.save_modelmodel.saveModelCheckpoint回调保存了你的模型,你可以重新加载你的模型,而不需要精确的自定义对象,就像

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

解决方案 23:

用于保存模型。请记住,如果要减小模型大小,则tf.train.Saver需要指定。可以是:var_list`val_list`

  • tf.trainable_variables或者

  • tf.global_variables

解决方案 24:

无论你想将模型保存在哪里,

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

确保所有数据都有tf.Variable名称,因为您可能希望稍后使用它们的名称来恢复它们。并且您想要预测的位置,

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 saver 在相应的会话内运行。请记住,如果您使用tf.train.latest_checkpoint('./'),则只会使用最新的检查点。

解决方案 25:

我使用的版本:

tensorflow (1.13.1)
tensorflow-gpu (1.13.1)

简单的方法是

节省:

model.save("model.h5")

恢复:

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

解决方案 26:

在新版本 TensorFlow 2.0 中,保存/加载模型的过程变得容易得多。这要归功于 TensorFlow 的高级 API Keras API 的实现。

要保存模型:查看参考文档:
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)

解决方案 27:

最简单的方法是使用 keras api,一行用于保存模型,一行用于加载模型

from keras.models import load_model

my_model.save('my_model.h5')  # creates a HDF5 file 'my_model.h5'

del my_model  # deletes the existing model


my_model = load_model('my_model.h5') # returns a compiled model identical to the previous one

解决方案 28:

您可以使用 Tensorflow 中的 saver 对象来保存训练好的模型。此对象提供了保存和恢复模型的方法。

要在 TensorFlow 中保存训练好的模型:

tf.train.Saver.save(sess, save_path, global_step=None, latest_filename=None,
                    meta_graph_suffix='meta', write_meta_graph=True,
                    write_state=True, strip_default_attrs=False,
                    save_debug_info=False)

要在 TensorFlow 中恢复已保存的模型:

tf.train.Saver.restore(sess, save_path, latest_filename=None,
                       meta_graph_suffix='meta', clear_devices=False,
                       import_scope=None)
相关推荐
  政府信创国产化的10大政策解读一、信创国产化的背景与意义信创国产化,即信息技术应用创新国产化,是当前中国信息技术领域的一个重要发展方向。其核心在于通过自主研发和创新,实现信息技术应用的自主可控,减少对外部技术的依赖,并规避潜在的技术制裁和风险。随着全球信息技术竞争的加剧,以及某些国家对中国在科技领域的打压,信创国产化显...
工程项目管理   3998  
  为什么项目管理通常仍然耗时且低效?您是否还在反复更新电子表格、淹没在便利贴中并参加每周更新会议?这确实是耗费时间和精力。借助软件工具的帮助,您可以一目了然地全面了解您的项目。如今,国内外有足够多优秀的项目管理软件可以帮助您掌控每个项目。什么是项目管理软件?项目管理软件是广泛行业用于项目规划、资源分配和调度的软件。它使项...
项目管理软件   2749  
  本文介绍了以下10款项目管理软件工具:禅道项目管理软件、Freshdesk、ClickUp、nTask、Hubstaff、Plutio、Productive、Targa、Bonsai、Wrike。在当今快速变化的商业环境中,项目管理已成为企业成功的关键因素之一。然而,许多企业在项目管理过程中面临着诸多痛点,如任务分配不...
项目管理系统   85  
  本文介绍了以下10款项目管理软件工具:禅道项目管理软件、Monday、TeamGantt、Filestage、Chanty、Visor、Smartsheet、Productive、Quire、Planview。在当今快速变化的商业环境中,项目管理已成为企业成功的关键因素之一。然而,许多项目经理和团队在管理复杂项目时,常...
开源项目管理工具   96  
  本文介绍了以下10款项目管理软件工具:禅道项目管理软件、Smartsheet、GanttPRO、Backlog、Visor、ResourceGuru、Productive、Xebrio、Hive、Quire。在当今快节奏的商业环境中,项目管理已成为企业成功的关键因素之一。然而,许多企业在选择项目管理工具时常常面临困惑:...
项目管理系统   83  
热门文章
项目管理软件有哪些?
曾咪二维码

扫码咨询,免费领取项目管理大礼包!

云禅道AD
禅道项目管理软件

云端的项目管理软件

尊享禅道项目软件收费版功能

无需维护,随时随地协同办公

内置subversion和git源码管理

每天备份,随时转为私有部署

免费试用