如何优化一个简单的、保存的 TensorFlow 1.0.1 图的推理？

Question

我无法在保存的简单 TensorFlow 图（Python 2.7；pip install tensorflow-gpu==1.0.1 安装的软件包）上成功运行 optimize_for_inference 模块。

背景

保存 TensorFlow Graph

这是我的 Python 脚本，用于生成并保存一个简单的图形，以将 5 添加到我的输入 x placeholder 操作。

import tensorflow as tf

# make and save a simple graph
G = tf.Graph()
with G.as_default():
    x = tf.placeholder(dtype=tf.float32, shape=(), name="x")
    a = tf.Variable(5.0, name="a")
    y = tf.add(a, x, name="y")
    saver = tf.train.Saver()

with tf.Session(graph=G) as sess:
    sess.run(tf.global_variables_initializer())
    out = sess.run(fetches=[y], feed_dict={x: 1.0})
    print(out)
    saver.save(sess=sess, save_path="test_model")

恢复 TensorFlow Graph

我有一个简单的恢复脚本，它可以重新创建保存的图形并恢复图形参数。两个保存/恢复脚本产生相同的输出。

import tensorflow as tf

# Restore simple graph and test model output
G = tf.Graph()

with tf.Session(graph=G) as sess:
    # recreate saved graph (structure)
    saver = tf.train.import_meta_graph('./test_model.meta')
    # restore net params
    saver.restore(sess, tf.train.latest_checkpoint('./'))

    x = G.get_operation_by_name("x").outputs[0]
    y = G.get_operation_by_name("y").outputs
    out = sess.run(fetches=[y], feed_dict={x: 1.0})
    print(out[0])

优化尝试

但是，虽然我对优化的期望不高，但当我尝试优化图以进行推理时，我收到以下错误消息。预期的输出节点似乎不在保存的图表中。

$ python -m tensorflow.python.tools.optimize_for_inference --input test_model.data-00000-of-00001 --output opt_model --input_names=x --output_names=y  
Traceback (most recent call last):  
  File "/usr/lib/python2.7/runpy.py", line 174, in _run_module_as_main  
    "__main__", fname, loader, pkg_name)  
  File "/usr/lib/python2.7/runpy.py", line 72, in _run_code  
    exec code in run_globals  
  File "/{path}/lib/python2.7/site-packages/tensorflow/python/tools/optimize_for_inference.py", line 141, in <module>  
    app.run(main=main, argv=[sys.argv[0]] + unparsed)  
  File "/{path}/local/lib/python2.7/site-packages/tensorflow/python/platform/app.py", line 44, in run  
    _sys.exit(main(_sys.argv[:1] + flags_passthrough))
  File "/{path}/lib/python2.7/site-packages/tensorflow/python/tools/optimize_for_inference.py", line 90, in main  
    FLAGS.output_names.split(","), FLAGS.placeholder_type_enum)  
  File "/{path}/local/lib/python2.7/site-packages/tensorflow/python/tools/optimize_for_inference_lib.py", line 91, in optimize_for_inference  
    placeholder_type_enum)  
  File "/{path}/local/lib/python2.7/site-packages/tensorflow/python/tools/strip_unused_lib.py", line 71, in strip_unused  
    output_node_names)  
  File "/{path}/local/lib/python2.7/site-packages/tensorflow/python/framework/graph_util_impl.py", line 141, in extract_sub_graph  
    assert d in name_to_node_map, "%s is not in graph" % d  
AssertionError: y is not in graph  

进一步调查使我检查了已保存图形的检查点，它仅显示 1 个张量（a，没有 x，也没有 y）。

(tf-1.0.1) $ python -m tensorflow.python.tools.inspect_checkpoint --file_name ./test_model --all_tensors
tensor_name:  a
5.0

具体问题

1. 为什么我在检查点看不到x 和y？是因为它们是运算而不是张量吗？
2. 由于我需要为optimize_for_inference 模块提供输入和输出名称，如何构建图形以便引用输入和输出节点？

Answer 1

以下是关于如何优化推理的详细指南：

optimize_for_inference 模块将frozen binary GraphDef 文件作为输入并输出optimized Graph Def 文件，您可以将其用于推理。要获得frozen binary GraphDef file，您需要使用模块freeze_graph，它采用GraphDef proto、SaverDef proto 和一组存储在检查点文件中的变量。实现的步骤如下：

1。保存张量流图

 # make and save a simple graph
 G = tf.Graph()
 with G.as_default():
   x = tf.placeholder(dtype=tf.float32, shape=(), name="x")
   a = tf.Variable(5.0, name="a")
   y = tf.add(a, x, name="y")
   saver = tf.train.Saver()

with tf.Session(graph=G) as sess:
   sess.run(tf.global_variables_initializer())
   out = sess.run(fetches=[y], feed_dict={x: 1.0})

  # Save GraphDef
  tf.train.write_graph(sess.graph_def,'.','graph.pb')
  # Save checkpoint
  saver.save(sess=sess, save_path="test_model")

2。冻结图表

python -m tensorflow.python.tools.freeze_graph --input_graph graph.pb --input_checkpoint test_model --output_graph graph_frozen.pb --output_node_names=y

3。优化推理

python -m tensorflow.python.tools.optimize_for_inference --input graph_frozen.pb --output graph_optimized.pb --input_names=x --output_names=y

4。使用优化图

with tf.gfile.GFile('graph_optimized.pb', 'rb') as f:
   graph_def_optimized = tf.GraphDef()
   graph_def_optimized.ParseFromString(f.read())

G = tf.Graph()

with tf.Session(graph=G) as sess:
    y, = tf.import_graph_def(graph_def_optimized, return_elements=['y:0'])
    print('Operations in Optimized Graph:')
    print([op.name for op in G.get_operations()])
    x = G.get_tensor_by_name('import/x:0')
    out = sess.run(y, feed_dict={x: 1.0})
    print(out)

#Output
#Operations in Optimized Graph:
#['import/x', 'import/a', 'import/y']
#6.0

5。对于多个输出名称

如果有多个输出节点，则指定：output_node_names = 'boxes, scores, classes'并导入graph by，

 boxes,scores,classes, = tf.import_graph_def(graph_def_optimized, return_elements=['boxes:0', 'scores:0', 'classes:0'])

Answer 2

1. 你做错了：input 是 script 的 graphdef 文件，而不是检查点的数据部分。您需要将模型冻结到 .pb 文件/ 或获取图形的 prototxt 并使用优化推理脚本。

This script takes either a frozen binary GraphDef file (where the weight variables have been converted into constants by the freeze_graph script), or a text GraphDef proto file (the weight variables are stored in a separate checkpoint file), and outputs a new GraphDef with the optimizations applied.

1. 使用write_graph获取图形原型文件
2. 获取冻结模型freeze graph