import tensorflow as tf

saved_model_dir = "./saved_model"

with tf.Session(graph=tf.Graph()) as sess:
    tf.saved_model.loader.load(sess, ["serve"], saved_model_dir)
    graph = tf.get_default_graph()
    [print(n.name) for n in tf.get_default_graph().as_graph_def().node]

# 得到name之后,就可以获取相应的tensor了,例如:
# input_tensor = sess.graph.get_tensor_by_name('input:0')
# output_tensor = sess.graph.get_tensor_by_name('output:0')

相关文章:

  • 2022-12-23
  • 2022-12-23
  • 2021-08-14
  • 2021-09-15
  • 2022-12-23
  • 2022-12-23
  • 2021-12-07
猜你喜欢
  • 2022-12-23
  • 2021-10-06
  • 2022-12-23
  • 2022-01-15
  • 2021-12-18
  • 2022-12-23
  • 2021-07-25
相关资源
相似解决方案