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.

darknet yolov4 convert IR

local_dd
Beginner
237 Views

hello!

I'm converting Darknet yolov4 model into IR, which has been converted into tensorflow2*

Includes three files: assets, variables, saved_model.pb

But when I execute the command to convert to IR

python3 mo.py --saved_model_dir /home/ubuntu/yolov4 --output_dir models/IRs --input_shape [1,608,608,3] --model_name yolov4

[ ERROR ] Exception occurred during running replacer "REPLACEMENT_ID" (<class 'extensions.load.tf.loader.TFLoader'>): Unexpected exception happened during extracting attributes for node Const.
Original exception message: 'ascii' codec can't decode byte 0x92 in position 1: ordinal not in range(128)

Please tell me how to solve it

0 Kudos
2 Replies
Peh_Intel
Moderator
195 Views

Hi,


Thanks for reaching out to us.


Is the model a pre-trained model or custom model?


Based on the error, we would like to request your model for further investigation. Please share your assets, variables, saved_model.pb files and also the relevant files (.weights file, .cfg file) before converting to TensorFlow model. You can send them privately to me if you do not want to share in public.

 

 

Regards,

Peh


Peh_Intel
Moderator
147 Views

Hi,


Thank you for your question. If you need any additional information from Intel, please submit a new question as this thread is no longer being monitored. 



Regards,

Peh


Reply