在Tensorflow中训练一个模型后:

如何拯救训练过的模型? 您以后如何恢复这个保存的模型?


当前回答

在新版本的tensorflow 2.0中,保存/加载模型的过程要容易得多。因为Keras API的实现,一个TensorFlow的高级API。

保存一个模型: 请查阅相关文档以作参考: 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)

加载一个模型:

https://www.tensorflow.org/versions/r2.0/api_docs/python/tf/keras/models/load_model

model = tf.keras.models.load_model(filepath)

其他回答

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.

下面是我对这两种基本情况的简单解决方案,这两种情况的不同之处在于您是想从文件加载图形还是在运行时构建它。

这个答案适用于Tensorflow 0.12+(包括1.0)。

在代码中重建图形

储蓄

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

graph = ... # build the graph
saver = tf.train.Saver()  # create the saver after the graph
with ... as sess:  # your session object
    saver.restore(sess, tf.train.latest_checkpoint('./'))
    # now you can use the graph, continue training or whatever

还从文件中加载图形

当使用这种技术时,确保所有的层/变量都显式地设置了唯一的名称。否则Tensorflow将使名称本身是唯一的,因此它们将不同于存储在文件中的名称。在前一种技术中,这不是问题,因为名称在加载和保存时都以相同的方式“损坏”。

储蓄

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

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

您可以保存网络中的变量使用

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

要恢复网络以供以后或在另一个脚本中重用,请使用:

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

重要的几点:

第一次运行和以后运行之间的Sess必须相同(一致的结构)。 储蓄者。还原需要保存文件的文件夹路径,而不是单个文件路径。

无论你想把模型保存在哪里,

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

确保你所有的任务。变量有名称,因为您可能希望稍后使用它们的名称来恢复它们。 在你想预测的地方,

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

确保该保护程序在相应的会话中运行。 请记住,如果使用tf.train.latest_checkpoint('./'),那么将只使用最新的检查点。

Tensorflow 2.6:它现在变得更简单了,你可以用两种格式保存模型

Saved_model (tf服务兼容) 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()