{"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/fastnet","title":"FastNet","arxiv_id":"1802.02186","date":"2018-01-17","proceeding":null,"authors":["John Olafenwa","Moses Olafenwa"],"abstract":"Inception and the Resnet family of Convolutional Neural Network\narchi-tectures have broken records in the past few years, but recent state of\nthe art models have also incurred very high computational cost in terms of\ntraining, inference and model size. Making the deployment of these models on\nEdge devices, impractical. In light of this, we present a new novel\narchitecture that is designed for high computational efficiency on both GPUs\nand CPUs, and is highly suited for deployment on Mobile Applications, Smart\nCameras, Iot devices and controllers as well as low cost drones. Our\narchitecture boasts competitive accuracies on standard Datasets even\nout-performing the original Resnet. We present below the motivation for this\nresearch, the architecture of the network, single test accuracies on CIFAR 10\nand CIFAR 100 , a detailed comparison with other well-known architectures and\nlink to an implementation in Keras.","url_abs":"http://arxiv.org/abs/1802.02186v1","url_pdf":"http://arxiv.org/pdf/1802.02186v1.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":"fastnet","repo_url":"https://github.com/johnolafenwa/FastNet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"computational-efficiency","task_name":"Computational Efficiency"}],"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}