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@Vishnuvardhan Janapati的回答之后,这里是另一种在TensorFlow 2.0.0下保存和重载自定义层/度量/损失模型的方法

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,一旦您执行了这些代码,并使用tf.keras.models保存了您的模型。Save_model或model。save或ModelCheckpoint回调,您可以重新加载您的模型,而不需要精确的自定义对象,就像这样简单

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

其他回答

如果您使用tf.train.MonitoredTrainingSession作为默认会话,则不需要添加额外的代码来执行保存/恢复操作。只需将检查点目录名称传递给MonitoredTrainingSession的构造函数,它将使用会话挂钩来处理这些。

使用tf.train.Saver保存模型。记住,如果想要减小模型大小,就需要指定var_list。val_list可以是:

特遣部队。trainable_variables或 tf.global_variables。

如第6255期所述:

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

而不是

saver.restore('my_model_final.ckpt')

对于张量流2.0,它非常简单

#保存模型 model.save(“path_to_my_model.h5”)

恢复:

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

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。