{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/gpunet-searching-the-deployable-convolution","title":"GPUNet: Searching the Deployable Convolution Neural Networks for GPUs","arxiv_id":"2205.00841","date":"2022-04-26","proceeding":null,"authors":["Linnan Wang","Chenhan Yu","Satish Salian","Slawomir Kierat","Szymon Migacz","Alex Fit Florea"],"abstract":"Customizing Convolution Neural Networks (CNN) for production use has been a challenging task for DL practitioners. This paper intends to expedite the model customization with a model hub that contains the optimized models tiered by their inference latency using Neural Architecture Search (NAS). To achieve this goal, we build a distributed NAS system to search on a novel search space that consists of prominent factors to impact latency and accuracy. Since we target GPU, we name the NAS optimized models as GPUNet, which establishes a new SOTA Pareto frontier in inference latency and accuracy. Within 1$ms$, GPUNet is 2x faster than EfficientNet-X and FBNetV3 with even better accuracy. We also validate GPUNet on detection tasks, and GPUNet consistently outperforms EfficientNet-X and FBNetV3 on COCO detection tasks in both latency and accuracy. All of these data validate that our NAS system is effective and generic to handle different design tasks. With this NAS system, we expand GPUNet to cover a wide range of latency targets such that DL practitioners can deploy our models directly in different scenarios.","url_abs":"https://arxiv.org/abs/2205.00841v1","url_pdf":"https://arxiv.org/pdf/2205.00841v1.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":"gpunet-searching-the-deployable-convolution","repo_url":"https://github.com/NVIDIA/DeepLearningExamples","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":null,"task_name":"GPU"},{"task_slug":"architecture-search","task_name":"Neural Architecture Search"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/neural-architecture-search-on-imagenet","task":"Neural Architecture Search","dataset":"ImageNet","model":"GPUNet-D3","rank_in_archive_order":3,"of":135,"metrics":{"FLOPs":"15.6G","Params":"19M","Top-1 Error Rate":"16.4"},"uses_additional_data":false},{"leaderboard":"/sota/neural-architecture-search-on-imagenet","task":"Neural Architecture Search","dataset":"ImageNet","model":"GPUNet-D1","rank_in_archive_order":4,"of":135,"metrics":{"FLOPs":"3.66G","Params":"10.6M","Top-1 Error Rate":"17.5"},"uses_additional_data":false},{"leaderboard":"/sota/neural-architecture-search-on-imagenet","task":"Neural Architecture Search","dataset":"ImageNet","model":"GPUNet-D0","rank_in_archive_order":28,"of":135,"metrics":{"FLOPs":"720M","Params":"6.2M","Top-1 Error Rate":"20.3"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2205.00841","atlas_url":"https://app.syntology.ai/?focus=2205.00841","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2205.00841"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2205.00841\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2205.00841"},"call":"get_concepts_for_paper(arxiv_id=\"2205.00841\")"}],"by_repo":[{"repo":"NVIDIA/DeepLearningExamples","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":2,"harvested_for":["1901.02860","2010.05646"],"harvested_for_calls":[{"arxiv_id":"1901.02860","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1901.02860"},"call":"get_harvested_code_for_paper(arxiv_id=\"1901.02860\")"},{"arxiv_id":"2010.05646","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2010.05646"},"call":"get_harvested_code_for_paper(arxiv_id=\"2010.05646\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"1cee1b7af1cd4043b9da50680ddcddda1a07c9a7338b276e7ef0492a8a28ccb5","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}