I have SSD model with good accuracy above 80per and detection will happen in 0.20 seconds. However, I want to reduce the detection period to about 0.05-0.08seconds and reduce model size.
I came to know that quantization is the process to reduce the detection period.
Tried with post quantization, however it is not working as expected.
I want to perform quantization while training, which I'm not able to get any resources. Can anyone suggest how to use quantization for Single shot detector model.