Intel® Distribution of OpenVINO™ Toolkit
Community support and discussions about the Intel® Distribution of OpenVINO™ toolkit, OpenCV, and all things computer vision-related on Intel® platforms.
5533 Discussions

why i use tensorflow SSD mobilenet v2 training my dataset , get a wrong model can't convert to IR

fa2233
New Contributor I
197 Views

it's auto save model    show  ?x?x?x3   

i set training num_steps 5000 

why it output this kind.

 

0 Kudos
2 Replies
Iffa_Intel
Moderator
181 Views

Greetings,


Based on the errors that you get as per attached photo, it seems like you missed out a couple of instruction required to convert the model such as:

python mo_tf.py -m frozen_inference_graph.pb --tensorflow_use_custom_operations_config ssd_v2_support.json --tensorflow_object_detection_api pipeline.config


This is the complete instruction to convert.


You can refer to this video for the complete and step by step instructions: https://www.youtube.com/watch?v=cbdS3BjjbaQ



Sincerely,

Iffa



Iffa_Intel
Moderator
174 Views

Greetings,


Intel will no longer monitor this thread since we have provided a solution. If you need any additional information from Intel, please submit a new question.


Sincerely,

Iffa


Reply