Challenges and Obstacles Towards Deploying Deep Learning Models on Mobile Devices
This work addresses deployment obstacles for developers and researchers aiming to run deep learning on resource-constrained mobile platforms, but it is incremental as it reviews existing challenges and solutions.
The paper identifies challenges in deploying deep learning models on mobile devices, such as hardware-aware optimizations and model conversion, and presents practical solutions to address these issues.
From computer vision and speech recognition to forecasting trajectories in autonomous vehicles, deep learning approaches are at the forefront of so many domains. Deep learning models are developed using plethora of high-level, generic frameworks and libraries. Running those models on the mobile devices require hardware-aware optimizations and in most cases converting the models to other formats or using a third-party framework. In reality, most of the developed models need to undergo a process of conversion, adaptation, and, in some cases, full retraining to match the requirements and features of the framework that is deploying the model on the target platform. Variety of hardware platforms with heterogeneous computing elements, from wearable devices to high-performance GPU clusters are used to run deep learning models. In this paper, we present the existing challenges, obstacles, and practical solutions towards deploying deep learning models on mobile devices.