我使用is_training的占位符训练模型：
is_training_ph = tf.placeholder(tf.bool)
然而，一旦完成训练和验证，我想永久地为此值注入常量false，然后“重新优化”图形（即使用optimize_for_inference）。是否有freeze_graph的内容可以做到这一点？
答案 0 :(得分：6)
一种可能性是使用tf.import_graph_def()函数及其with tf.Graph().as_default() as training_graph:
# Build model.
is_training_ph = tf.placeholder(tf.bool, name="is_training")
# ...
training_graph_def = training_graph.as_graph_def()
with tf.Graph().as_default() as temp_graph:
tf.import_graph_def(training_graph_def,
input_map={is_training_ph.name: tf.constant(False)})
temp_graph_def = temp_graph.as_graph_def()
参数来重写图中该张量的值。例如，您可以按如下方式构建程序：
temp_graph_def构建freeze_graph后，您可以将其用作freeze_graph的输入。
可能与optimize_for_inference和graph_util.convert_variables_to_constants()脚本（对变量名和检查点键进行假设）更兼容的替代方法是修改TensorFlow的def convert_placeholders_to_constants(input_graph_def,
placeholder_to_value_map):
"""Replaces placeholders in the given tf.GraphDef with constant values.
Args:
input_graph_def: GraphDef object holding the network.
placeholder_to_value_map: A map from the names of placeholder tensors in
`input_graph_def` to constant values.
Returns:
GraphDef containing a simplified version of the original.
"""
output_graph_def = tf.GraphDef()
for node in input_graph_def.node:
output_node = tf.NodeDef()
if node.op == "Placeholder" and node.name in placeholder_to_value_map:
output_node.op = "Const"
output_node.name = node.name
dtype = node.attr["dtype"].type
data = np.asarray(placeholder_to_value_map[node.name],
dtype=tf.as_dtype(dtype).as_numpy_dtype)
output_node.attr["dtype"].type = dtype
output_node.attr["value"].CopyFrom(tf.AttrValue(
tensor=tf.contrib.util.make_tensor_proto(data,
dtype=dtype,
shape=data.shape)))
else:
output_node.CopyFrom(node)
output_graph_def.node.extend([output_node])
return output_graph_def
函数，以便它转换占位符代替：
training_graph_def ...然后你可以像上面那样构建temp_graph_def = convert_placeholders_to_constants(training_graph_def,
{is_training_ph.op.name: False})
，然后写：
{{1}}