Community
cancel
Showing results for 
Search instead for 
Did you mean: 
CChiH13
Novice
298 Views

Can NCSDK2 compile the SSD_model normally?i have some trouble when i compile the frozen_graph.pb to .graph

Jump to solution

i use ssd_inception_v2 pretrained model to train my own model.

i try to compile it with NCSDK2 and get an error above

Traceback (most recent call last): File "/usr/local/bin/mvNCCompile", line 208, in <module> args.old_parser, args.cpp, args) File "/usr/local/bin/mvNCCompile", line 186, in create_graph load_ret = load_network(args, parser, myriad_config) File "/usr/local/bin/ncsdk/Controllers/Scheduler.py", line 72, in load_network parsedLayers = p.parse(arguments) File "/usr/local/bin/ncsdk/Controllers/Parsers/TensorFlow.py", line 659, in parse dummy_feed_dict = self._gen_dummy_feed_dict(arguments) File "/usr/local/bin/ncsdk/Controllers/Parsers/TensorFlow.py", line 576, in _gen_dummy_feed_dict feed_dict = {self.tf_input_op.outputs[0] : np.ones(self.get_input_shape(arguments))} File "/usr/local/bin/ncsdk/Controllers/Parsers/TensorFlow.py", line 457, in get_input_shape if inferred_input_shape[axis] != None: IndexError: list index out of range

and than it is my config file i edit it refer this website https://movidius.github.io/ncsdk/tools/tf_ssd_config.html

input_height: 300 input_width: 300   postprocessing_params { num_classes: 3 background_label_id: 0 max_detections: 10   nms_params { score_threshold: 0.300000011921 iou_threshold: 0.600000023842 max_detections_per_class: 10 }   box_params { var: 0.1 var: 0.1 var: 0.2 var: 0.2 } }   score_converter: SIGMOID

 

0 Kudos

Accepted Solutions
CChiH13
Novice
80 Views

i have finished my project already, thank for reply

i change mobile net pretrained models and finally compile it and run it correctly,😊

View solution in original post

7 Replies
80 Views

Hi CChiH13, 

 

Thanks for reaching out. To help you, could you please answer some question that we have for you: 

 

Which version of the Intel® Movidius™ NCSDK are you using? 

What Operative System do you have? 

Can you share with us your model? 

Which is the command that you used to compile your model? 

 

On the other hand, the Intel® Movidius™ NCSDK is no longer being maintained, so, we recommend you migrate to the OpenVINO™ toolkit. 

 

Regards,  

  

Javier A.  

Intel Customer Support Technician  

A Contingent Worker at Intel 

 

CChiH13
Novice
80 Views

NCSDK verison:2.10.01.01

i have Ubuntu16.04,Ubuntu18.04,Windows10,Raspbian Stretch

i use command as below

mvNCCompile frozen_inference_graph.pb --tf-ssd-config ssd_inception.config

models is uploading, i will post it as soon as possible

CChiH13
Novice
80 Views

model:https://drive.google.com/file/d/1796s3I9FmqSDrhpBVueaTh2jXRA5F50A/view?usp=sharing

demo file contain an python code and two image , it can run in ubuntu normally

demo:https://drive.google.com/file/d/19qJGad1G2ONkazHDmS9gWg5PBx9DToIr/view?usp=sharing

 

thank for your help

CChiH13
Novice
80 Views
item { id: 1 name: 'LeiKaChon' }   item { id: 2 name: 'ChanChiHang' }   item { id: 3 name: 'Unknown' }

Here is the content about "object_detection.pbtxt" i forgot pack it into the zip file

80 Views

Hi CChiH13, 

 

Thank you for your response. We are trying to replicate your issue from our end, but we are getting a different error. We  think it is because we are using a different version of TensorFlow, could you please answer some questions that we have for you: 

 

Which TensorFlow version did you use to train your network? 

Which TensorFlow version are you using with the NCSDK? 

 

By the way, is there any reason to continue using the Intel® Movidius™ NCSDK and not migrate to OpenVINO™ toolkit? 

 

Regards,  

  

Javier A.  

Intel Customer Support Technician  

A Contingent Worker at Intel 

 

CChiH13
Novice
81 Views

i have finished my project already, thank for reply

i change mobile net pretrained models and finally compile it and run it correctly,😊

View solution in original post

JesusE_Intel
Moderator
80 Views

Hi CChiH13,

 

I'm glad you were able to get it to work! Feel free to reach out again if you have additional questions.

 

Regards,

Jesus