Seeking Pre-trained MobileNetV2 or Similar Lightweight Model Weights for Edge Devices

[Ching-Chien]

I am currently working on a project that involves deploying deep learning models on edge devices. Due to the computational constraints of these devices, I am in search of lightweight models, specifically pre-trained weights of MobileNetV2 or any related lightweight architecture that can efficiently run on such hardware.

Despite my efforts to train these models myself, I've encountered repeated failures and am hoping someone in the community might share their pre-trained weights or guide me to a repository where these might be available. The goal is to leverage these models for real-time inference on edge devices without compromising too much on accuracy.

If anyone has successfully used MobileNetV2 or a similar architecture for edge computing and is willing to share their model weights or insights, it would greatly help my project.Thank you in advance for any assistance or pointers you can provide.