[GitHub] yjcn opened a new issue #11242: Same model with c_predict_api gets an incorrect result but it is right in python.

[GitBox <gi...@apache.org>]

yjcn opened a new issue #11242: Same model with c_predict_api gets an incorrect result but it is right in python.
URL: https://github.com/apache/incubator-mxnet/issues/11242
 
 
   I use my own dataset( 3 classes) to train a vgg16_reduced model. And it works well in [mxnet-ssd python](https://github.com/apache/incubator-mxnet/tree/master/example/ssd). And I want to use the c++ interface. First, I use deploy.py to deploy the model.  I test the depolyed model, it works well too in python. Then I test it in[ mxnet-ssd.cpp](https://github.com/zhreshold/mxnet-ssd.cpp) 
    and [single cpp file ssd](https://gist.github.com/shuokay/c8234fc5f2230ab79e89306a822f5edd).And there is no errors , but the result is incorrect(no detection).  I also trained inceptionv3 model, the result is same.

----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on GitHub and use the
URL above to go to the specific comment.
 
For queries about this service, please contact Infrastructure at:
users@infra.apache.org


With regards,
Apache Git Services