{"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/netadapt-platform-aware-neural-network","title":"NetAdapt: Platform-Aware Neural Network Adaptation for Mobile Applications","arxiv_id":"1804.03230","date":"2018-04-09","proceeding":"ECCV 2018 9","authors":["Tien-Ju Yang","Andrew Howard","Bo Chen","Xiao Zhang","Alec Go","Mark Sandler","Vivienne Sze","Hartwig Adam"],"abstract":"This work proposes an algorithm, called NetAdapt, that automatically adapts a\npre-trained deep neural network to a mobile platform given a resource budget.\nWhile many existing algorithms simplify networks based on the number of MACs or\nweights, optimizing those indirect metrics may not necessarily reduce the\ndirect metrics, such as latency and energy consumption. To solve this problem,\nNetAdapt incorporates direct metrics into its adaptation algorithm. These\ndirect metrics are evaluated using empirical measurements, so that detailed\nknowledge of the platform and toolchain is not required. NetAdapt automatically\nand progressively simplifies a pre-trained network until the resource budget is\nmet while maximizing the accuracy. Experiment results show that NetAdapt\nachieves better accuracy versus latency trade-offs on both mobile CPU and\nmobile GPU, compared with the state-of-the-art automated network simplification\nalgorithms. For image classification on the ImageNet dataset, NetAdapt achieves\nup to a 1.7$\\times$ speedup in measured inference latency with equal or higher\naccuracy on MobileNets (V1&V2).","url_abs":"http://arxiv.org/abs/1804.03230v2","url_pdf":"http://arxiv.org/pdf/1804.03230v2.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":"netadapt-platform-aware-neural-network","repo_url":"https://github.com/NatGr/Master_Thesis","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"netadapt-platform-aware-neural-network","repo_url":"https://github.com/dwofk/fast-depth","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"netadapt-platform-aware-neural-network","repo_url":"https://github.com/madoibito80/NetAdapt","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"netadapt-platform-aware-neural-network","repo_url":"https://github.com/denru01/netadapt","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":null,"task_name":"CPU"},{"task_slug":null,"task_name":"GPU"},{"task_slug":"image-classification","task_name":"Image Classification"},{"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":"convolution","method_name":"Convolution"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"depthwise-convolution","method_name":"Depthwise Convolution"},{"method_slug":"depthwise-separable-convolution","method_name":"Depthwise Separable Convolution"},{"method_slug":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"mobilenetv1","method_name":"MobileNetV1"},{"method_slug":"netadapt","method_name":"NetAdapt"},{"method_slug":"pointwise-convolution","method_name":"Pointwise Convolution"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1804.03230","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1804.03230"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/NatGr/Master_Thesis","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/dwofk/fast-depth","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/madoibito80/NetAdapt","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/denru01/netadapt","reach":{"status":"unanswered"}}],"summary":{"ran_violates":1},"by_repo_kind":{"listed":{"samples":1,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":1,"samples":[{"code_sha256_prefix":"b084fed9f8158c59","entry":"ChooseNumFilters","repo":"madoibito80/NetAdapt","repo_kind":"listed","path":"netadapt.py","file_url":"https://github.com/madoibito80/NetAdapt/blob/HEAD/netadapt.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b084fed9f8158c59"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}