Follow the link

https://medium.com/analytics-vidhya/reducing-deep-learning-model-size-without-effecting-its-original-performance-and-accuracy-with-a809b49cf519

You should also check Knowledge Distillation.

You can use the following techniques:

Saif ul Islam

Downsizing a pre-trained CNN model to a smaller size without losing performance can be achieved by several techniques, including:

It's important to note that downsizing a pre-trained model may come with trade-offs in terms of performance, and the best approach will depend on the specific requirements of the application. It may also require multiple iterations of fine-tuning and experimentation to achieve the desired balance between size and accuracy.

This question can be answered in two parts. Firstly, (A) DOWNSIZING PRETRAINED MODEL is different compared to (B) CREATE SMALLER CNN THAT MIMIC LARGER ONE. (A) can be done by pruning or quantization, while (B) can be done by knowledge distillation.

For (A):

For (B):

In practice, method (A) is easier to implement. There are various tools like Intel's OpenVINO and Google's TensorFlow Lite that can perform pruning and quantization automatically with little to no effort. You only need to pass the pretrained model to any of the toolkits, to downsize the model. On the other hand, method (B) requires more efforts. You can search the limitation of knowledge distillation in the internet.

thanks Yi Jie Wong Janak Trivedi Saif ul Islam Daniel Coelho Sheikh Md. Razibul Hasan Raj for sharing useful information.