cancel
Showing results for 
Search instead for 
Did you mean: 
Highlighted
Contributor
Contributor
385 Views
Registered: ‎07-12-2019

Edge ai platform tutorials MNIST_TF

#####################################
EVALUATE QUANTIZED GRAPH
#####################################
/root/anaconda3/envs/decent/lib/python3.6/site-packages/tensorflow/python/framework/dtypes.py:523: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
_np_qint8 = np.dtype([("qint8", np.int8, 1)])
/root/anaconda3/envs/decent/lib/python3.6/site-packages/tensorflow/python/framework/dtypes.py:524: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
_np_quint8 = np.dtype([("quint8", np.uint8, 1)])
/root/anaconda3/envs/decent/lib/python3.6/site-packages/tensorflow/python/framework/dtypes.py:525: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
_np_qint16 = np.dtype([("qint16", np.int16, 1)])
/root/anaconda3/envs/decent/lib/python3.6/site-packages/tensorflow/python/framework/dtypes.py:526: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
_np_quint16 = np.dtype([("quint16", np.uint16, 1)])
/root/anaconda3/envs/decent/lib/python3.6/site-packages/tensorflow/python/framework/dtypes.py:527: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
_np_qint32 = np.dtype([("qint32", np.int32, 1)])
/root/anaconda3/envs/decent/lib/python3.6/site-packages/tensorflow/python/framework/dtypes.py:532: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
np_resource = np.dtype([("resource", np.ubyte, 1)])
WARNING:tensorflow:From eval_graph.py:60: FastGFile.__init__ (from tensorflow.python.platform.gfile) is deprecated and will be removed in a future version.
Instructions for updating:
Use tf.gfile.GFile.
Traceback (most recent call last):
File "eval_graph.py", line 82, in <module>
tf.app.run(main=main, argv=[sys.argv[0]] + unparsed)
File "/root/anaconda3/envs/decent/lib/python3.6/site-packages/tensorflow/python/platform/app.py", line 125, in run
_sys.exit(main(argv))
File "eval_graph.py", line 61, in main
graph_eval(input_graph_def, FLAGS.input_node, FLAGS.output_node)
File "eval_graph.py", line 26, in graph_eval
tf.import_graph_def(input_graph_def,name = '')
File "/root/anaconda3/envs/decent/lib/python3.6/site-packages/tensorflow/python/util/deprecation.py", line 488, in new_func
return func(*args, **kwargs)
File "/root/anaconda3/envs/decent/lib/python3.6/site-packages/tensorflow/python/framework/importer.py", line 418, in import_graph_def
graph._c_graph, serialized, options) # pylint: disable=protected-access
tensorflow.python.framework.errors_impl.NotFoundError: Op type not registered 'FixNeuron' in binary running on xilinx-GL63-8RC. Make sure the Op and Kernel are registered in the binary running in this process. Note that if you are loading a saved graph which used ops from tf.contrib, accessing (e.g.) `tf.contrib.resampler` should be done before importing the graph, as contrib ops are lazily registered when the module is first accessed.
#####################################
EVALUATE QUANTIZED GRAPH COMPLETED
#####################################

 

what should i do ?

0 Kudos
3 Replies
Highlighted
Visitor
Visitor
245 Views
Registered: ‎09-23-2019

Re: Edge ai platform tutorials MNIST_TF

Hi,

I have encountered the same issue: 

Op type not registered 'FixNeuron' in binary running on...

 Have you found a solution to this yet. Any help would be appreciated! Thanks!

0 Kudos
Highlighted
Xilinx Employee
Xilinx Employee
218 Views
Registered: ‎03-27-2013

Re: Edge ai platform tutorials MNIST_TF

Hi @katherineyun ,

 

I have met similiar issue as @edz_xilinx posted.

When I met that issue I tried to load my quantized pb file to evaluate. So I just follow the recommendation to run "tf.contrib.resampler" first the issue would not occur.

Here is my test code:

https://github.com/gewuek/flower_classification_dnndk_v1/blob/master/x86/evaluate_quantized_graph.py

Not issue if you met the same issue here.

Best Regards,
Jason
-----------------------------------------------------------------------------------------------
Please mark the Answer as "Accept as solution" if the information provided is helpful.

Give Kudos to a post which you think is helpful and reply oriented.
-----------------------------------------------------------------------------------------------
0 Kudos
Highlighted
Visitor
Visitor
138 Views
Registered: ‎11-04-2019

Re: Edge ai platform tutorials MNIST_TF


@katherineyun wrote:

Hi,

I have encountered the same issue: 

Op type not registered 'FixNeuron' in binary running on...

 Have you found a solution to this yet. Any help would be appreciated! Thanks!


Hi @katherineyun,

I was wondering if you found a solution to this. I've been stuck trying to figure this out. Thanks!

0 Kudos