In deepstream app primary model is peoplenet and after detecting face, applying on it secondary model to classify the mask on face. But result i am getting always first entry of the label.txt file. I am not getting the reason. tlt model is working fine on new testing images and after converting it to etlt, i added it as secondary model then having result issues.
Please provide complete information as applicable to your setup.
• Hardware Platform (Jetson / GPU)
• DeepStream Version
• JetPack Version (valid for Jetson only)
• TensorRT Version
• NVIDIA GPU Driver Version (valid for GPU only)
• Issue Type( questions, new requirements, bugs)
• How to reproduce the issue ? (This is for bugs. Including which sample app is using, the configuration files content, the command line used and other details for reproducing)
• Requirement details( This is for new requirement. Including the module name-for which plugin or for which sample application, the function description)
There is no update from you for a period, assuming this is not an issue any more.
Hence we are closing this topic. If need further support, please open a new one.
Hey, can you share your configs with us.
And always keep in mind to share your setup with us.
For future reference (since I faced a similar issue for a long time), the problem that I did was that the label file was like this:
Instead, for secondary classifiers it need to be like this :
Hi,I have similar issue,but change label still exist same error
In my case, there was formatting issue with training data on which model was trained. You can also check the training/ validation text/csv data are in proper format and then training is running properly. see if this work for you.
I will try it,thanks
by the way, what is your deepstream sdk version?