Tensorflow 2 Docs

储蓄检查点

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.

更多的链接

详尽而有用的教程saved_model -> https://www.tensorflow.org/guide/saved_model Keras详细指南保存模型-> https://www.tensorflow.org/guide/keras/save_and_serialize

Checkpoints capture the exact value of all parameters (tf.Variable objects) used by a model. Checkpoints do not contain any description of the computation defined by the model and thus are typically only useful when source code that will use the saved parameter values is available. The SavedModel format on the other hand includes a serialized description of the computation defined by the model in addition to the parameter values (checkpoint). Models in this format are independent of the source code that created the model. They are thus suitable for deployment via TensorFlow Serving, TensorFlow Lite, TensorFlow.js, or programs in other programming languages (the C, C++, Java, Go, Rust, C# etc. TensorFlow APIs).

(重点是我自己的)

---

Tensorflow < 2

---

从文档中可以看出:

Save

# 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

很多不错的答案，为了完整起见，我将添加我的2分:simple_save。这也是一个使用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
        })

独立的例子

原创博客文章

为了便于演示，下面的代码生成随机数据。

We start by creating the placeholders. They will hold the data at runtime. From them, we create the Dataset and then its Iterator. We get the iterator's generated tensor, called input_tensor which will serve as input to our model. The model itself is built from input_tensor: a GRU-based bidirectional RNN followed by a dense classifier. Because why not. The loss is a softmax_cross_entropy_with_logits, optimized with Adam. After 2 epochs (of 2 batches each), we save the "trained" model with tf.saved_model.simple_save. If you run the code as is, then the model will be saved in a folder called simple/ in your current working directory. In a new graph, we then restore the saved model with tf.saved_model.loader.load. We grab the placeholders and logits with graph.get_tensor_by_name and the Iterator initializing operation with graph.get_operation_by_name. Lastly we run an inference for both batches in the dataset, and check that the saved and restored model both yield the same values. They do!

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

这里所有的答案都很棒，但我想补充两点。

首先，详细说明@user7505159的答案，“。添加到要恢复的文件名的开头可能很重要。

例如，您可以保存没有“的图形。/"在文件名中如下所示:

# 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)

但是为了恢复图形，您可能需要在前面加上一个"。/"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)

你并不总是需要“。/”，但是它会根据你的环境和TensorFlow版本而导致问题。

它还想提到sess.run(tf.global_variables_initializer())在恢复会话之前可能很重要。

如果在尝试恢复保存的会话时收到关于未初始化变量的错误，请确保在保存程序之前包含sess.run(tf.global_variables_initializer())。恢复(sess, save_file)行。这样你就不用头疼了。

最简单的方法是使用keras api，在线保存模型和一行加载模型

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

你也可以在TensorFlow/skflow中查看例子，它提供了保存和恢复方法，可以帮助你轻松地管理模型。它具有一些参数，您还可以控制备份模型的频率。

在大多数情况下，使用tf.train.Saver从磁盘保存和恢复是最好的选择:

... # 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/恢复图结构本身(详细信息请参阅MetaGraph文档)。默认情况下，保存程序将图形结构保存到.meta文件中。您可以调用import_meta_graph()来恢复它。它恢复图形结构并返回一个你可以用来恢复模型状态的保护程序:

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

然而，在某些情况下，您需要更快的方法。例如，如果您实现了早期停止，那么您希望在训练期间每次模型改进时都保存检查点(在验证集上测量)，然后如果一段时间内没有进展，则希望回滚到最佳模型。如果每次模型改进时都将其保存到磁盘，则会极大地降低训练速度。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)

A quick explanation: when you create a variable X, TensorFlow automatically creates an assignment operation X/Assign to set the variable's initial value. Instead of creating placeholders and extra assignment ops (which would just make the graph messy), we just use these existing assignment ops. The first input of each assignment op is a reference to the variable it is supposed to initialize, and the second input (assign_op.inputs[1]) is the initial value. So in order to set any value we want (instead of the initial value), we need to use a feed_dict and replace the initial value. Yes, TensorFlow lets you feed a value for any op, not just for placeholders, so this works fine.

我的环境:Python 3.6, Tensorflow 1.3.0

虽然有很多解决方案，但大多数都是基于tf.train.Saver。当我们加载由Saver保存的.ckpt文件时，我们必须要么重新定义张量流网络，要么使用一些奇怪且难以记住的名称，例如:“placehold_0:0”,“密集/亚当/重量:0”。这里我推荐使用tf。saved_model，下面给出的一个最简单的例子，你可以从为TensorFlow模型服务中学到更多:

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})