Best sources to develop a single class thin/slim custom deep learning model for object detection?

I am working on a problem, where I need to detect a particular type of objects. I have tried with tensorflow ssd mobilenet model, but I their processing time is very high. Hence I am planning to develop my own object detection model for single class with a very few layers in Keras (Tensorflow). I need to know, is there any github repo, or tutorial that explains clear procedure about single class custom object detection model training.

Answer 1

[Kritika Bansal]

Hi,

You can follow the following links to know more about creating and training your own networks using MATLAB’s Deep Learning Toolbox:

https://in.mathworks.com/help/deeplearning/index.html?s_tid=CRUX_lftnav

https://in.mathworks.com/help/deeplearning/deep-learning-with-images.html?s_tid=CRUX_lftnav

https://in.mathworks.com/help/deeplearning/ug/define-custom-deep-learning-layer.html

In case you want to know about performing transfer learning in MATLAB, you can refer to the link below:

https://in.mathworks.com/help/deeplearning/examples/transfer-learning-using-alexnet.html