The demand for applications deploying deep learning models in resource-constrained environments is on the rise today, driven by the need for low latency and real-time inference. However, many deep learning models are too large and complex to perform effectively on such devices, posing challenges for scaling and model deployment.
Therefore, striking a compromise between maintaining high accuracy and reducing inference time and model size becomes essential. In the study presented in this white paper, three different models—Custom, VGG16[2], MobileNET[3]—are compressed using tiny machine learning or TinyML, a framework for model optimization and compression. The primary goal is to preserve optimal accuracy while significantly reducing inference time and model size.
The study will assess the trade-offs between accuracy, size reduction, and inference time by comparing the compressed models by tailoring and comparing the performance with the original models. Additionally, the study intends to explore TinyML's potential to enhance user experience and enable edge computing in medical applications.