Showing results for 
Search instead for 
Did you mean: 

mo.utils.error.Error: 'TensorProto' object has no attribute 'uint8_val'

I am trying to convert the tensorflow ICNet model using the following command,

python --input_meta_graph model.ckpt-0.meta --data_type FP16 --log=DEBUG

It generates the following error

[ ERROR ]  'TensorProto' object has no attribute 'uint8_val'
Unexpected exception happened during extracting attributes for node Reshape_1.
Original exception message: 'TensorProto' object has no attribute 'uint8_val'
[ 2019-11-03 19:05:46,514 ] [ DEBUG ] [ main:304 ]  Traceback (most recent call last):
  File "C:\Program Files (x86)\IntelSWTools\openvino\deployment_tools\model_optimizer\mo\front\", line 608, in extract_node_attrs
    supported, new_attrs = extractor(Node(graph, node))
  File "C:\Program Files (x86)\IntelSWTools\openvino\deployment_tools\model_optimizer\mo\pipeline\", line 132, in <lambda>
    extract_node_attrs(graph, lambda node: tf_op_extractor(node, check_for_duplicates(tf_op_extractors)))
  File "C:\Program Files (x86)\IntelSWTools\openvino\deployment_tools\model_optimizer\mo\front\tf\", line 109, in tf_op_extractor
    attrs = tf_op_extractors[op](node)
  File "C:\Program Files (x86)\IntelSWTools\openvino\deployment_tools\model_optimizer\mo\front\tf\", line 65, in <lambda>
    return lambda node: pb_extractor(node.pb)
  File "C:\Program Files (x86)\IntelSWTools\openvino\deployment_tools\model_optimizer\mo\front\tf\extractors\", line 31, in tf_const_ext
    result['value'] = tf_tensor_content(pb_tensor.dtype, result['shape'], pb_tensor)
  File "C:\Program Files (x86)\IntelSWTools\openvino\deployment_tools\model_optimizer\mo\front\tf\extractors\", line 71, in tf_tensor_content
    value = type_helper[1](pb_tensor)
  File "C:\Program Files (x86)\IntelSWTools\openvino\deployment_tools\model_optimizer\mo\front\tf\", line 26, in <lambda>
    ('DT_UINT8', np.uint8, lambda pb: pb.uint8_val, lambda x: np.uint8(x)),
AttributeError: 'TensorProto' object has no attribute 'uint8_val'

Please advise .Thanks.

0 Kudos
0 Replies