python - 从文件打开 tensorflow 图

Question

我正在尝试使用 tensorflow 进行研究，但我不明白如何打开和使用早期保存在文件中的 tf.Graph 类型的图表。像这样:

import tensorflow as tf

my_graph = tf.Graph()

with g.as_default():
    x = tf.Variable(0)
    b = tf.constant(-5)
    k = tf.constant(2)

    y = k*x + b

tf.train.write_graph(my_graph, '.', 'graph.pbtxt')

f = open('graph.pbtxt', "r")

# Do something with "f" to get my saved graph and use it below in
# tf.Session(graph=...) instead of dots

with tf.Session(graph=...) as sess:
    tf.initialize_all_variables().run()

    y1 = sess.run(y, feed_dict={x: 5})
    y2 = sess.run(y, feed_dict={x: 10})
    print(y1, y2)

Answer 1

您必须加载文件内容，将其解析为 GraphDef，然后导入。 它将被导入到当前图表中。你可能想用 graph.as_default(): 上下文管理器来包装它。

import tensorflow as tf
from tensorflow.core.framework import graph_pb2 as gpb
from google.protobuf import text_format as pbtf

gdef = gpb.GraphDef()

with open('my-graph.pbtxt', 'r') as fh:
    graph_str = fh.read()

pbtf.Parse(graph_str, gdef)

tf.import_graph_def(gdef)