Intel® Distribution of OpenVINO™ Toolkit
Community assistance about the Intel® Distribution of OpenVINO™ toolkit, OpenCV, and all aspects of computer vision-related on Intel® platforms.
6404 Discussions

Error loading text-recognition-0012 model (Openvino 2019.3.376)

FVian
Beginner
782 Views

Hi,

Environment:

OS: linux

Openvino version: 2019.3.376

Engine: CPU

I'm trying to run the text-recognition-0012 model but the following error appears:

[ ERROR ] /teamcity/work/scoring_engine_build/releases_2019_R3/thirdparty/clDNN/src/reshape.cpp at line: 92
Error has occured for: lstmsequence:shadow/LSTMLayers/encoder/stack_bidirectional_rnn/cell_0/bidirectional_rnn/bw/bw/while/lstm_cell/concat/LSTMCell_sequence
/opt/intel/openvino_2019.3.376/deployment_tools/inference_engine/include/details/ie_exception_conversion.hpp:71

I've search the text-recognition-0012.xml file and I didn't find the shadow/LSTMLayers/encoder/stack_bidirectional_rnn/cell_0/bidirectional_rnn/bw/bw/while/lstm_cell/concat/LSTMCell_sequence layer.

Best regards,

Felipe Ximenes

 

 

 

 

 

 

0 Kudos
3 Replies
JesusE_Intel
Moderator
782 Views

Hi Felipe Ximenes,

Are you using our text_detection_demo? I was able to load both the text detection and text recognition model without any issues. Could you please try to run the demo with the following command and let me know if it works for you?

./text_detection_demo -i input.png -dt image -m_td intel/text-detection-0004/FP32/text-detection-0004.xml -m_tr intel/text-recognition-0012/FP32/text-recognition-0012.xml

Regards,

Jesus

 

0 Kudos
FVian
Beginner
782 Views

Hi Jesus,

Thanks for your reply. Unfortunately, I'm not using the text_detection_demo. I'm working to implement a new application. I ran the command that you request and worked. I'll revise my code to understand why this error appears. But did you see this error before?

Best regards,

Felipe Ximenes

0 Kudos
JesusE_Intel
Moderator
782 Views

Hi Felipe Ximenes,

I have not seen the error message before, take a look at the demo application for guidance on how to inference with the model. The description of the text-recognition-0012 will also help understand what is expected as input and output.

Regards,

Jesus

0 Kudos
Reply