时间:2020-11-24 16:32:07 | 栏目:Python代码 | 点击:次
获取所有variable(每个op中可训练的张量)的name:
for variable_name in tf.global_variables(): print(variable_name)
获取所有tensor(每个op的输出张量)的name:
for tensor_name in tf.contrib.graph_editor.get_tensors(tf.get_default_graph()): print(tensor_name)
获取所有op及其输入输出的name:
with tf.Session() as sess: for node in sess.graph_def.node: print(node)