在Tensorflow中训练模型后:
- 您如何保存经过训练的模型?
- 您以后如何还原此保存的模型?
在Tensorflow中训练模型后:
Answers:
详尽而有用的教程-> https://www.tensorflow.org/guide/saved_model
Keras保存模型的详细指南-> https://www.tensorflow.org/guide/keras/save_and_serialize
从文档:
# Create some variables.
v1 = tf.get_variable("v1", shape=[3], initializer = tf.zeros_initializer)
v2 = tf.get_variable("v2", shape=[5], initializer = tf.zeros_initializer)
inc_v1 = v1.assign(v1+1)
dec_v2 = v2.assign(v2-1)
# Add an op to initialize the variables.
init_op = tf.global_variables_initializer()
# Add ops to save and restore all the variables.
saver = tf.train.Saver()
# Later, launch the model, initialize the variables, do some work, and save the
# variables to disk.
with tf.Session() as sess:
sess.run(init_op)
# Do some work with the model.
inc_v1.op.run()
dec_v2.op.run()
# Save the variables to disk.
save_path = saver.save(sess, "/tmp/model.ckpt")
print("Model saved in path: %s" % save_path)
tf.reset_default_graph()
# Create some variables.
v1 = tf.get_variable("v1", shape=[3])
v2 = tf.get_variable("v2", shape=[5])
# Add ops to save and restore all the variables.
saver = tf.train.Saver()
# Later, launch the model, use the saver to restore variables from disk, and
# do some work with the model.
with tf.Session() as sess:
# Restore variables from disk.
saver.restore(sess, "/tmp/model.ckpt")
print("Model restored.")
# Check the values of the variables
print("v1 : %s" % v1.eval())
print("v2 : %s" % v2.eval())
这仍然是beta版,因此我建议不要使用。如果您仍然想走那条路,这里就是tf.saved_model
使用指南
simple_save
许多好答案,为完整性起见,我将加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
})
为了演示,以下代码生成随机数据。
Dataset
然后Iterator
。我们得到迭代器的生成张量,称为input_tensor
,它将用作模型的输入。input_tensor
基于:基于GRU的双向RNN,然后是密集分类器。因为为什么不。softmax_cross_entropy_with_logits
,优化为Adam
。在2个时期(每个2批次)之后,我们使用保存了“训练”模型tf.saved_model.simple_save
。如果按原样运行代码,则模型将保存在名为simple/
当前工作目录下中。tf.saved_model.loader.load
。我们使用来抢占占位符并登录,graph.get_tensor_by_name
并使用进行Iterator
初始化操作graph.get_operation_by_name
。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
tf.contrib.layers
?
global_step
,如果您停下来然后尝试再次接受培训,它将认为您是第一步。它会搞砸了起码你tensorboard可视化
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。
在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。
:0
名称?
在TensorFlow版本0.11.0RC1中(及之后),您可以直接调用tf.train.export_meta_graph
并tf.train.import_meta_graph
根据https://www.tensorflow.org/programmers_guide/meta_graph来保存和恢复模型。。
w1 = tf.Variable(tf.truncated_normal(shape=[10]), name='w1')
w2 = tf.Variable(tf.truncated_normal(shape=[20]), name='w2')
tf.add_to_collection('vars', w1)
tf.add_to_collection('vars', w2)
saver = tf.train.Saver()
sess = tf.Session()
sess.run(tf.global_variables_initializer())
saver.save(sess, 'my-model')
# `save` method will call `export_meta_graph` implicitly.
# you will get saved graph files:my-model.meta
sess = tf.Session()
new_saver = tf.train.import_meta_graph('my-model.meta')
new_saver.restore(sess, tf.train.latest_checkpoint('./'))
all_vars = tf.get_collection('vars')
for v in all_vars:
v_ = sess.run(v)
print(v_)
<built-in function TF_Run> returned a result with an error set
tf.get_variable_scope().reuse_variables()
后面的来获取变量 var = tf.get_variable("varname")
。这给了我错误:“ ValueError:变量varname不存在,或者不是使用tf.get_variable()创建的。” 为什么?应该不可能吗?
对于TensorFlow版本<0.11.0RC1:
保存的检查点包含以下值: Variable
模型中 s,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})
batch_x
需要采用哪种格式?二进制?块数组?
undefined
。您能告诉我该代码的FLAGS定义是什么。@RyanSepassi
我的环境:Python 3.6,Tensorflow 1.3.0
尽管有许多解决方案,但是大多数解决方案都基于tf.train.Saver
。当我们加载.ckpt
保存的Saver
,我们必须要么重新定义tensorflow网络,或者使用一些奇怪的和难以记住的名称,例如'placehold_0:0'
,'dense/Adam/Weight:0'
。我建议在这里使用tf.saved_model
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})
有两个部分的模型,该模型定义,通过保存Supervisor
为graph.pbtxt
模型中的目录和张量的数值,保存到像检查点文件model.ckpt-1003418
。
可以使用还原模型定义tf.import_graph_def
,并使用还原权重Saver
。
但是,Saver
使用包含在模型Graph上的变量的特殊集合保存列表,并且此集合未使用import_graph_def进行初始化,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Saver
将权重加载到其中。
(或者,您可以通过使用import_graph_def
,手动创建变量,并tf.add_to_collection(tf.GraphKeys.VARIABLES, variable)
针对每个变量使用,然后使用来对其进行破解Saver
)
您也可以采用这种更简单的方法。
W1 = tf.Variable(tf.truncated_normal([6, 6, 1, K], stddev=0.1), name="W1")
B1 = tf.Variable(tf.constant(0.1, tf.float32, [K]), name="B1")
Similarly, W2, B2, W3, .....
Saver
将会话保存在模型中并保存model_saver = tf.train.Saver()
# Train the model and save it in the end
model_saver.save(session, "saved_models/CNN_New.ckpt")
with tf.Session(graph=graph_cnn) as session:
model_saver.restore(session, "saved_models/CNN_New.ckpt")
print("Model restored.")
print('Initialized')
W1 = session.run(W1)
print(W1)
在其他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)
在大多数情况下,使用a从磁盘保存和还原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
您也可以保存/恢复图结构本身(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。您可以致电import_meta_graph()
进行恢复。它还原图形结构并返回一个Saver
可用于还原模型状态的:
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:创建变量时X
,TensorFlow自动创建一个赋值操作X/Assign
以设置变量的初始值。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a 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。
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。)
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
all_variables()
现在已弃用
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)。
graph = ... # build the graph
saver = tf.train.Saver() # create the saver after the graph
with ... as sess: # your session object
saver.save(sess, 'my-model')
graph = ... # build the graph
saver = tf.train.Saver() # create the saver after the graph
with ... as sess: # your session object
saver.restore(sess, tf.train.latest_checkpoint('./'))
# now you can use the graph, continue training or whatever
使用此技术时,请确保所有图层/变量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。
graph = ... # build the graph
for op in [ ... ]: # operators you want to use after restoring the model
tf.add_to_collection('ops_to_restore', op)
saver = tf.train.Saver() # create the saver after the graph
with ... as sess: # your session object
saver.save(sess, 'my-model')
with ... as sess: # your session object
saver = tf.train.import_meta_graph('my-model.meta')
saver.restore(sess, tf.train.latest_checkpoint('./'))
ops = tf.get_collection('ops_to_restore') # here are your operators in the same order in which you saved them to the collection
global_step
批量归一化的变量和移动平均值是不可训练的变量,但是绝对值得保存。另外,您应该更清楚地将图形的构造与运行会话区分开,例如,Saver(...).save()
每次运行时都会创建新的节点。可能不是您想要的。还有更多...:/
您还可以在TensorFlow / skflow中查看示例,这些示例和方法可以帮助您轻松管理模型。它具有的参数还可以控制您备份模型的频率。save
restore
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。
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。
它还要提到,sess.run(tf.global_variables_initializer())
在恢复会话之前,这可能很重要。
如果在尝试还原已保存的会话时收到关于未初始化变量的错误,请确保在行sess.run(tf.global_variables_initializer())
之前包括saver.restore(sess, save_file)
。它可以节省您的头痛。
根据新的Tensorflow版本,tf.train.Checkpoint
保存和还原模型的首选方法是:
Checkpoint.save
并Checkpoint.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。身高tf.train.Checkpoint
超过tf.train.Saver
对新代码。
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)
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')
TF2.0
对于使用TF1.x保存模型,我看到了很好的答案。我想在保存中提供更多的指示tensorflow.keras
模型时这有点复杂,因为有很多方法可以保存模型。
在这里,我提供了一个将tensorflow.keras
模型保存到model_path
当前目录下的文件夹的示例。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。
import tensorflow as tf
from tensorflow import keras
mnist = tf.keras.datasets.mnist
#import data
(x_train, y_train),(x_test, y_test) = mnist.load_data()
x_train, x_test = x_train / 255.0, x_test / 255.0
# create a model
def create_model():
model = tf.keras.models.Sequential([
tf.keras.layers.Flatten(input_shape=(28, 28)),
tf.keras.layers.Dense(512, activation=tf.nn.relu),
tf.keras.layers.Dropout(0.2),
tf.keras.layers.Dense(10, activation=tf.nn.softmax)
])
# compile the model
model.compile(optimizer='adam',
loss='sparse_categorical_crossentropy',
metrics=['accuracy'])
return model
# Create a basic model instance
model=create_model()
model.fit(x_train, y_train, epochs=1)
loss, acc = model.evaluate(x_test, y_test,verbose=1)
print("Original model, accuracy: {:5.2f}%".format(100*acc))
# Save entire model to a HDF5 file
model.save('./model_path/my_model.h5')
# Recreate the exact same model, including weights and optimizer.
new_model = keras.models.load_model('./model_path/my_model.h5')
loss, acc = new_model.evaluate(x_test, y_test)
print("Restored model, accuracy: {:5.2f}%".format(100*acc))
如果只对保存模型权重感兴趣,然后对加载权重以恢复模型感兴趣,那么
model.fit(x_train, y_train, epochs=5)
loss, acc = model.evaluate(x_test, y_test,verbose=1)
print("Original model, accuracy: {:5.2f}%".format(100*acc))
# Save the weights
model.save_weights('./checkpoints/my_checkpoint')
# Restore the weights
model = create_model()
model.load_weights('./checkpoints/my_checkpoint')
loss,acc = model.evaluate(x_test, y_test)
print("Restored model, accuracy: {:5.2f}%".format(100*acc))
# include the epoch in the file name. (uses `str.format`)
checkpoint_path = "training_2/cp-{epoch:04d}.ckpt"
checkpoint_dir = os.path.dirname(checkpoint_path)
cp_callback = tf.keras.callbacks.ModelCheckpoint(
checkpoint_path, verbose=1, save_weights_only=True,
# Save weights, every 5-epochs.
period=5)
model = create_model()
model.save_weights(checkpoint_path.format(epoch=0))
model.fit(train_images, train_labels,
epochs = 50, callbacks = [cp_callback],
validation_data = (test_images,test_labels),
verbose=0)
latest = tf.train.latest_checkpoint(checkpoint_dir)
new_model = create_model()
new_model.load_weights(latest)
loss, acc = new_model.evaluate(test_images, test_labels)
print("Restored model, accuracy: {:5.2f}%".format(100*acc))
import tensorflow as tf
from tensorflow import keras
mnist = tf.keras.datasets.mnist
(x_train, y_train),(x_test, y_test) = mnist.load_data()
x_train, x_test = x_train / 255.0, x_test / 255.0
# Custom Loss1 (for example)
@tf.function()
def customLoss1(yTrue,yPred):
return tf.reduce_mean(yTrue-yPred)
# Custom Loss2 (for example)
@tf.function()
def customLoss2(yTrue, yPred):
return tf.reduce_mean(tf.square(tf.subtract(yTrue,yPred)))
def create_model():
model = tf.keras.models.Sequential([
tf.keras.layers.Flatten(input_shape=(28, 28)),
tf.keras.layers.Dense(512, activation=tf.nn.relu),
tf.keras.layers.Dropout(0.2),
tf.keras.layers.Dense(10, activation=tf.nn.softmax)
])
model.compile(optimizer='adam',
loss='sparse_categorical_crossentropy',
metrics=['accuracy', customLoss1, customLoss2])
return model
# Create a basic model instance
model=create_model()
# Fit and evaluate model
model.fit(x_train, y_train, epochs=1)
loss, acc,loss1, loss2 = model.evaluate(x_test, y_test,verbose=1)
print("Original model, accuracy: {:5.2f}%".format(100*acc))
model.save("./model.h5")
new_model=tf.keras.models.load_model("./model.h5",custom_objects={'customLoss1':customLoss1,'customLoss2':customLoss2})
如以下情况(tf.tile
)所示,当我们具有自定义操作时,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!
您可以使用以下方法将变量保存到网络中
saver = tf.train.Saver()
saver.save(sess, 'path of save/fileName.ckpt')
要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(....)
重要事项:
sess
首次运行和后续运行之间必须相同(一致的结构)。 saver.restore
需要已保存文件的文件夹路径,而不是单个文件路径。 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)
确保您所有的人tf.Variable
都有名字,因为您以后可能要使用他们的名字来还原它们。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,如果使用tf.train.latest_checkpoint('./')
,则将仅使用最新的检查点。
对于tensorflow-2.0
这很简单。
import tensorflow as tf
model.save("model_name")
model = tf.keras.models.load_model('model_name')
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_model
或model.save
或ModelCheckpoint
回调保存了模型,就可以重新加载模型,而无需精确的自定义对象,就像
new_model = tf.keras.models.load_model("./model.h5"})
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)