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

你可以使用Tensorflow中的saver对象来保存你训练过的模型。该对象提供保存和恢复模型的方法。

在TensorFlow中保存一个训练好的模型:

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)

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)

根据新的Tensorflow版本，tf.train.Checkpoint是保存和恢复模型的最佳方式:

Checkpoint.save and Checkpoint.restore write and read object-based checkpoints, in contrast to tf.train.Saver which writes and reads variable.name based checkpoints. Object-based checkpointing saves a graph of dependencies between Python objects (Layers, Optimizers, Variables, etc.) with named edges, and this graph is used to match variables when restoring a checkpoint. It can be more robust to changes in the Python program, and helps to support restore-on-create for variables when executing eagerly. Prefer tf.train.Checkpoint over tf.train.Saver for new code.

这里有一个例子:

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。

你也可以用更简单的方法。

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:在模型Saver中保存会话并保存它

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)

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MNIST数据集分类器的简单示例，使用Keras函数式API，没有太多的花哨操作:

# 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

serving_default是什么?

它是所选标记的签名定义的名称(在本例中，选择了默认的服务标记)。此外，本文还解释了如何使用saved_model_cli查找模型的标记和签名。

免责声明

这只是一个基本的例子，如果你只是想让它运行起来，但这绝不是一个完整的答案-也许我可以在未来更新它。我只是想给出一个在TF 2.0中使用SavedModel的简单示例，因为我在任何地方都没有见过这样简单的SavedModel。

@Tom的回答是一个SavedModel的例子，但它在Tensorflow 2.0上不起作用，因为不幸的是有一些突破性的变化。

@Vishnuvardhan Janapati的回答是TF 2.0，但它不适合SavedModel格式。

我在版本:

tensorflow (1.13.1)
tensorflow-gpu (1.13.1)

简单的方法是

拯救策略:

model.save("model.h5")

恢复:

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