|
9#
楼主 |
发表于 2019-8-30 11:53:01
|
只看该作者
我是两个层conv后带有一个maxpool,打印conv1 conv addbias 及relu层的输出和tf推理pb的结果不在一个量级上,想打印placeholder(未进行推理的tensor)这个tensor 报错
--> Loading model
D import clients finished
I Current TF Model producer version 0 min consumer version 0 bad consumer version []
I Have 0 tensors convert to const tensor
[]
I build output layer attach_Placeholderut0
I build input layer Placeholderut0
--- Logging error ---
Traceback (most recent call last):
File "/usr/lib/python3.6/logging/__init__.py", line 996, in emit
stream.write(msg)
ValueError: I/O operation on closed file.
Call stack:
File "test.py", line 21, in <module>
ret = rknn.load_tensorflow(tf_pb='vgg-new.pb',inputs=['Placeholder'],outputs=['Placeholder'],input_size_list=[[112, 112, 1]])
File "/usr/local/lib/python3.6/dist-packages/rknn/api/rknn.py", line 62, in load_tensorflow
std_values=std_values)
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/util/deprecation.py", line 323, in new_func
instructions)
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/platform/tf_logging.py", line 166, in warning
get_logger().warning(msg, *args, **kwargs)
Message: 'From %s: %s (from %s) is deprecated and will be removed %s.\nInstructions for updating:\n%s'
Arguments: ('/usr/local/lib/python3.6/dist-packages/rknn/api/rknn.py:62', 'extract_sub_graph', 'tensorflow.python.framework.graph_util_impl', 'in a future version', 'Use tf.compat.v1.graph_util.extract_sub_graph')
W Not get any connection of Placeholderut0
E Catch exception when loading tensorflow model: vgg-new.pb!
T Traceback (most recent call last):
T File "rknn/api/rknn_base.py", line 186, in rknn.api.rknn_base.RKNNBase.load_tensorflow
T File "rknn/base/RKNNlib/converter/convert_tf.py", line 655, in rknn.base.RKNNlib.converter.convert_tf.convert_tf.graph_connection_build
T AttributeError: 'NoneType' object has no attribute 'lid'
|
|