tensorflow转换ckpt为saved_model模型

ckpt模型

转换ckpt为saved_model模型

import tensorflow as tf
import sys

trained_checkpoint_prefix = sys.argv[1]
export_dir = sys.argv[2]

graph = tf.Graph()
config = tf.ConfigProto(allow_soft_placement=True, log_device_placement=True)
with tf.compat.v1.Session(graph=graph, config=config) as sess:
    # Restore from checkpoint
    loader = tf.compat.v1.train.import_meta_graph(trained_checkpoint_prefix + '.meta')
    loader.restore(sess, trained_checkpoint_prefix)
    # Export checkpoint to SavedModel
    builder = tf.compat.v1.saved_model.builder.SavedModelBuilder(export_dir)
    # builder.add_meta_graph_and_variables(sess, [],strip_default_attrs=True)
    # builder.add_meta_graph_and_variables(sess, [tf.saved_model.TRAINING], strip_default_attrs=True)
    builder.add_meta_graph_and_variables(sess, [tf.saved_model.TRAINING, tf.saved_model.SERVING],
                                         strip_default_attrs=True)
    builder.save()

会在save目录下生成
save
├── saved_model.pb
└── variables
\quad ├── variables.data-00000-of-00001
\quad └── variables.index

[tf.saved_model.TRAINING, tf.saved_model.SERVING] 可根据需要修改此列表，比如如果模型中只有SERVING那么要改成
[tf.saved_model.SERVING] ,否则会提示 TRAINING不存在的错误。

以上内容有误，具体见 https://www.pythonf.cn/read/65049