Community
cancel
Showing results for 
Search instead for 
Did you mean: 
idata
Community Manager
279 Views

when I complie the graph_freeze.pb on the ncs ,it a problem as :

from ._conv import register_converters as _register_converters

 

Traceback (most recent call last):

 

File "/usr/local/bin/mvNCCompile", line 118, in

 

create_graph(args.network, args.inputnode, args.outputnode, args.outfile, args.nshaves, args.inputsize, args.weights)

 

File "/usr/local/bin/mvNCCompile", line 104, in create_graph

 

net = parse_tensor(args, myriad_config)

 

File "/usr/local/bin/ncsdk/Controllers/TensorFlowParser.py", line 259, in parse_tensor

 

input_data = np.random.uniform(0, 1, shape)

 

File "mtrand.pyx", line 1307, in mtrand.RandomState.uniform

 

File "mtrand.pyx", line 242, in mtrand.cont2_array_sc

 

TypeError: 'NoneType' object cannot be interpreted as an integer

 

The project graph_freeze.pb is on the web below:

 

https://github.com/ildoonet/tf-pose-estimation/tree/master/models/graph/mobilenet_thin

 

Can anyone can help me ?
0 Kudos
5 Replies
idata
Community Manager
41 Views

It is the Mobilenet on the tensorflow.however ,I can't compile :'(

idata
Community Manager
41 Views

@wangrongxin

 

请问你找到这个问题的解决方法了吗?请指导,感激不尽!
idata
Community Manager
41 Views

Hi @neilwu

 

The error you are seeing has been discussed in another thread.

 

The error is due to the model using variable input sizes which is currently not supported on the NCSDK.

 

Hope this helps!

 

Regards,

 

Jesus
idata
Community Manager
41 Views

Hi @Jesus_at_Intel

 

Thanks for the information.

 

After I change the model's variable input to a fixed size (432,368), the original error is gone.

 

But I met the problem like https://ncsforum.movidius.com/discussion/comment/2310/#Comment_2310.

 

The errors like this:

 

Fusing depthconv and conv in Openpose/MConv_Stage1_L1_1_depthwise/depthwise and Openpose/MConv_Stage1_L1_1_pointwise/Conv2D

 

Traceback (most recent call last):

 

File "/usr/local/bin/mvNCCompile", line 118, in

 

create_graph(args.network, args.inputnode, args.outputnode, args.outfile, args.nshaves, args.inputsize, args.weights)

 

File "/usr/local/bin/mvNCCompile", line 104, in create_graph

 

net = parse_tensor(args, myriad_config)

 

File "/usr/local/bin/ncsdk/Controllers/TensorFlowParser.py", line 630, in parse_tensor

 

prev_node.addBias( bias.astype(np.float16) )

 

AttributeError: 'int' object has no attribute 'addBias'

 

If there is any pose estimation demo that can run on Movidius? Please tell me about that.I am going to collapse.

 

Sincerely,

 

Neil
idata
Community Manager
41 Views

Hi @neilwu

 

I shared some info regarding the Pose Estimation example using the OpenVINO Toolkit.

 

https://ncsforum.movidius.com/discussion/1565/pose-estimation-performance#latest

 

Regards,

 

Jesus