convert-to-uff the tensorflow model of inceptionV3 make error

I use TensorFlow 1.6.0.
The inceptionV3 is trained by https://github.com/tensorflow/models/tree/master/research/slim/train_image_classifier.py.
The dataset is flowers.

  1. model training
    DATASET_DIR=/tmp/flowers
    TRAIN_DIR=./resnet_v1_50/train_model
    /home/bigdata/anaconda3/bin/python3.6 train_image_classifier.py
    –train_dir={TRAIN_DIR} \ --dataset_name=flowers \ --dataset_split_name=train \ --dataset_dir={DATASET_DIR}
    –model_name=inception_v3

2.freeze graph
meta_path = ‘model.ckpt-126385.meta’ # Your .meta file
output_node_names = [‘InceptionV3/Predictions/Softmax’] # Output nodes

with tf.Session() as sess:
# Restore the graph
saver = tf.train.import_meta_graph(meta_path)
# Load weights
saver.restore(sess,tf.train.latest_checkpoint(’.’))
graphdef = tf.get_default_graph().as_graph_def()
print([node.name for node in graphdef.node])
# Freeze the graph
frozen_graph_def = tf.graph_util.convert_variables_to_constants(
sess,
graphdef,
output_node_names)
tf_model = tf.graph_util.remove_training_nodes(frozen_graph_def)
with tf.gfile.FastGFile(‘output_graph.pb’, mode=‘wb’) as f:
f.write(tf_model.SerializeToString())
3. convert-to-uff
convert-to-uff tensorflow --input-file output_graph.pb -O “InceptionV3/Predictions/Softmax”

But it makes a error.
Traceback (most recent call last):
File “/home/bigdata/.local/bin/convert-to-uff”, line 11, in
sys.exit(main())
File “/home/bigdata/.local/lib/python3.5/site-packages/uff/bin/convert_to_uff.py”, line 104, in main
output_filename=args.output
File “/home/bigdata/.local/lib/python3.5/site-packages/uff/converters/tensorflow/conversion_helpers.py”, line 103, in from_tensorflow_frozen_model
return from_tensorflow(graphdef, output_nodes, **kwargs)
File “/home/bigdata/.local/lib/python3.5/site-packages/uff/converters/tensorflow/conversion_helpers.py”, line 75, in from_tensorflow
name=“main”)
File “/home/bigdata/.local/lib/python3.5/site-packages/uff/converters/tensorflow/converter.py”, line 64, in convert_tf2uff_graph
uff_graph, input_replacements)
File “/home/bigdata/.local/lib/python3.5/site-packages/uff/converters/tensorflow/converter.py”, line 51, in convert_tf2uff_node
op, name, tf_node, inputs, uff_graph, tf_nodes=tf_nodes)
File “/home/bigdata/.local/lib/python3.5/site-packages/uff/converters/tensorflow/converter.py”, line 28, in convert_layer
fields = cls.parse_tf_attrs(tf_node.attr)
File “/home/bigdata/.local/lib/python3.5/site-packages/uff/converters/tensorflow/converter.py”, line 177, in parse_tf_attrs
for key, val in attrs.items()}
File “/home/bigdata/.local/lib/python3.5/site-packages/uff/converters/tensorflow/converter.py”, line 177, in
for key, val in attrs.items()}
File “/home/bigdata/.local/lib/python3.5/site-packages/uff/converters/tensorflow/converter.py”, line 172, in parse_tf_attr_value
return cls.convert_tf2uff_field(code, val)
File “/home/bigdata/.local/lib/python3.5/site-packages/uff/converters/tensorflow/converter.py”, line 157, in convert_tf2uff_field
‘type’: ‘dtype’, ‘list’: ‘list’}[code]
KeyError: ‘shape’

who know the reason and help me. Thanks!