Given a trained network, how can we accelerate it to meet efficiency needs for deployment on particular hardware? The commonly used hardware-aware network compression techniques address this question with pruning, kernel fusion, quantization and lowering precision. However, these approaches do not change the underlying network operations. In this paper, we propose hardware-aware network transformation (HANT), which accelerates a network by replacing inefficient operations with more efficient alternatives using a neural architecture search like approach. HANT tackles the problem in two phase: In the first phase, a large number of alternative operations per every layer of the teacher model is trained using layer-wise feature map distillation. In the second phase, the combinatorial selection of efficient operations is relaxed to an integer optimization problem that can be solved in a few seconds. We extend HANT with kernel fusion and quantization to improve throughput even further. Our experimental results on accelerating the EfficientNet family show that HANT can accelerate them by up to 3.6x with <0.4% drop in the top-1 accuracy on the ImageNet dataset. When comparing the same latency level, HANT can accelerate EfficientNet-B4 to the same latency as EfficientNet-B1 while having 3% higher accuracy. We examine a large pool of operations, up to 197 per layer, and we provide insights into the selected operations and final architectures.<\/p>\n","protected":false},"excerpt":{"rendered":"
Given a trained network, how can we accelerate it to meet efficiency needs for deployment on particular hardware? The commonly used hardware-aware network compression techniques address this question with pruning, kernel fusion, quantization and lowering precision. However, these approaches do not change the underlying network operations. In this paper, we propose hardware-aware network transformation (HANT), […]<\/p>\n","protected":false},"featured_media":0,"template":"","meta":{"msr-url-field":"","msr-podcast-episode":"","msrModifiedDate":"","msrModifiedDateEnabled":false,"ep_exclude_from_search":false,"_classifai_error":"","footnotes":""},"msr-content-type":[3],"msr-research-highlight":[],"research-area":[13556,13562],"msr-publication-type":[193724],"msr-product-type":[],"msr-focus-area":[],"msr-platform":[],"msr-download-source":[],"msr-locale":[268875],"msr-post-option":[],"msr-field-of-study":[],"msr-conference":[],"msr-journal":[],"msr-impact-theme":[],"msr-pillar":[],"class_list":["post-764053","msr-research-item","type-msr-research-item","status-publish","hentry","msr-research-area-artificial-intelligence","msr-research-area-computer-vision","msr-locale-en_us"],"msr_publishername":"","msr_edition":"","msr_affiliation":"","msr_published_date":"2021-7-1","msr_host":"","msr_duration":"","msr_version":"","msr_speaker":"","msr_other_contributors":"","msr_booktitle":"","msr_pages_string":"","msr_chapter":"","msr_isbn":"","msr_journal":"","msr_volume":"","msr_number":"","msr_editors":"","msr_series":"","msr_issue":"","msr_organization":"","msr_how_published":"arXiv","msr_notes":"","msr_highlight_text":"","msr_release_tracker_id":"","msr_original_fields_of_study":"","msr_download_urls":"","msr_external_url":"","msr_secondary_video_url":"","msr_longbiography":"","msr_microsoftintellectualproperty":1,"msr_main_download":"","msr_publicationurl":"","msr_doi":"","msr_publication_uploader":[{"type":"url","viewUrl":"false","id":"false","title":"https:\/\/arxiv.org\/abs\/2107.10624","label_id":"243109","label":0}],"msr_related_uploader":"","msr_attachments":[],"msr-author-ordering":[{"type":"text","value":"Pavlo Molchanov","user_id":0,"rest_url":false},{"type":"user_nicename","value":"Jimmy Hall","user_id":38148,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Jimmy Hall"},{"type":"text","value":"Hongxu Yin","user_id":0,"rest_url":false},{"type":"text","value":"Jan Kautz","user_id":0,"rest_url":false},{"type":"user_nicename","value":"Nicolo Fusi","user_id":31829,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Nicolo Fusi"},{"type":"text","value":"Arash Vahdat","user_id":0,"rest_url":false}],"msr_impact_theme":[],"msr_research_lab":[199563],"msr_event":[],"msr_group":[330695],"msr_project":[804847,545241],"publication":[],"video":[],"download":[],"msr_publication_type":"miscellaneous","related_content":{"projects":[{"ID":804847,"post_title":"Reducing AI's Carbon Footprint","post_name":"reducing-ais-carbon-footprint","post_type":"msr-project","post_date":"2022-05-24 08:56:55","post_modified":"2024-01-16 11:11:59","post_status":"publish","permalink":"https:\/\/www.microsoft.com\/en-us\/research\/project\/reducing-ais-carbon-footprint\/","post_excerpt":"This project develops techniques that enable AI to use computing infrastructure more efficiently. The goals are to maintain predictive accuracy while reducing carbon emissions, whether embodied in manufactured hardware, or produced from electricity usage when green energy is not available.","_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/804847"}]}},{"ID":545241,"post_title":"AutoML","post_name":"automl","post_type":"msr-project","post_date":"2018-11-20 10:10:06","post_modified":"2022-10-27 11:29:20","post_status":"publish","permalink":"https:\/\/www.microsoft.com\/en-us\/research\/project\/automl\/","post_excerpt":"State-of-the-art machine learning\/AI systems consist of complex pipelines with choices of hyperparameters, models and configuration details that need to be tuned for optimal performance. The AutoML project develops automated methods for optimizing AI pipelines, making AI development more broadly accessible. Core AutoML technology is already live in Azure Machine Learning, Power BI and other Microsoft products. Our AutoML research is advancing the state of the art in neural architecture search, model compression and more.","_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/545241"}]}}]},"_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/764053"}],"collection":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item"}],"about":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/types\/msr-research-item"}],"version-history":[{"count":2,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/764053\/revisions"}],"predecessor-version":[{"id":766996,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/764053\/revisions\/766996"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media?parent=764053"}],"wp:term":[{"taxonomy":"msr-content-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-content-type?post=764053"},{"taxonomy":"msr-research-highlight","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-highlight?post=764053"},{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=764053"},{"taxonomy":"msr-publication-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-publication-type?post=764053"},{"taxonomy":"msr-product-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-product-type?post=764053"},{"taxonomy":"msr-focus-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-focus-area?post=764053"},{"taxonomy":"msr-platform","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-platform?post=764053"},{"taxonomy":"msr-download-source","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-download-source?post=764053"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=764053"},{"taxonomy":"msr-post-option","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-post-option?post=764053"},{"taxonomy":"msr-field-of-study","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-field-of-study?post=764053"},{"taxonomy":"msr-conference","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-conference?post=764053"},{"taxonomy":"msr-journal","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-journal?post=764053"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=764053"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=764053"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}