{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/guidelines-and-benchmarks-for-deployment-of","title":"Guidelines and Benchmarks for Deployment of Deep Learning Models on Smartphones as Real-Time Apps","arxiv_id":"1901.02144","date":"2019-01-08","proceeding":null,"authors":["Abhishek Sehgal","Nasser Kehtarnavaz"],"abstract":"Deep learning solutions are being increasingly used in mobile applications.\nAlthough there are many open-source software tools for the development of deep\nlearning solutions, there are no guidelines in one place in a unified manner\nfor using these tools towards real-time deployment of these solutions on\nsmartphones. From the variety of available deep learning tools, the most suited\nones are used in this paper to enable real-time deployment of deep learning\ninference networks on smartphones. A uniform flow of implementation is devised\nfor both Android and iOS smartphones. The advantage of using multi-threading to\nachieve or improve real-time throughputs is also showcased. A benchmarking\nframework consisting of accuracy, CPU/GPU consumption and real-time throughput\nis considered for validation purposes. The developed deployment approach allows\ndeep learning models to be turned into real-time smartphone apps with ease\nbased on publicly available deep learning and smartphone software tools. This\napproach is applied to six popular or representative convolutional neural\nnetwork models and the validation results based on the benchmarking metrics are\nreported.","url_abs":"http://arxiv.org/abs/1901.02144v1","url_pdf":"http://arxiv.org/pdf/1901.02144v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"guidelines-and-benchmarks-for-deployment-of","repo_url":"https://github.com/SIP-Lab/Deep-Learning-Mobile","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"benchmarking","task_name":"Benchmarking"},{"task_slug":null,"task_name":"CPU"},{"task_slug":"deep-learning","task_name":"Deep Learning"},{"task_slug":"edge-computing","task_name":"Edge-computing"},{"task_slug":null,"task_name":"GPU"},{"task_slug":"image-classification","task_name":"Image Classification"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"bottleneck-residual-block","method_name":"Bottleneck Residual Block"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"kaiming-initialization","method_name":"Kaiming Initialization"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-block","method_name":"Residual Block"},{"method_slug":"residual-connection","method_name":"Residual Connection"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}