Model training method and device, equipment and storage medium
The invention provides a model training method and device, equipment and a storage medium, relates to the technical field of artificial intelligence, in particular to the technical fields of machine vision, deep learning and the like, and can be applied to scenes such as target detection and neural...
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Patent |
| Sprache: | chi ; eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | |
|---|---|
| container_issue | |
| container_start_page | |
| container_title | |
| container_volume | |
| creator | LYU WENYU XU SHANGLIANG ZHAO YIAN WANG GUANZHONG DANG QINGQING |
| description | The invention provides a model training method and device, equipment and a storage medium, relates to the technical field of artificial intelligence, in particular to the technical fields of machine vision, deep learning and the like, and can be applied to scenes such as target detection and neural network optimization. According to the specific implementation scheme, the method comprises the steps of obtaining a level sequence number of each parameter transmission level in a decoding module of a to-be-trained neural network; a first transmission path set is generated according to the level sequence numbers, and in the first transmission path set, the level sequence number interval between adjacent levels in each transmission path does not exceed two levels; according to a preset path selection rule, selecting a target transmission path from the first transmission path set as a transmission path of a decoding module in the neural network; and training the neural network by using the training data according to |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN116468071A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN116468071A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN116468071A3</originalsourceid><addsrcrecordid>eNrjZLDzzU9JzVEoKUrMzMvMS1fITS3JyE9RSMxLUUhJLctMTtVRSC0szSzITc0rAYsWl-QXJaanAhWmZJbm8jCwpiXmFKfyQmluBkU31xBnD93Ugvz41OKCxOTUvNSSeGc_Q0MzEzMLA3NDR2Ni1AAANJAwRw</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Model training method and device, equipment and storage medium</title><source>esp@cenet</source><creator>LYU WENYU ; XU SHANGLIANG ; ZHAO YIAN ; WANG GUANZHONG ; DANG QINGQING</creator><creatorcontrib>LYU WENYU ; XU SHANGLIANG ; ZHAO YIAN ; WANG GUANZHONG ; DANG QINGQING</creatorcontrib><description>The invention provides a model training method and device, equipment and a storage medium, relates to the technical field of artificial intelligence, in particular to the technical fields of machine vision, deep learning and the like, and can be applied to scenes such as target detection and neural network optimization. According to the specific implementation scheme, the method comprises the steps of obtaining a level sequence number of each parameter transmission level in a decoding module of a to-be-trained neural network; a first transmission path set is generated according to the level sequence numbers, and in the first transmission path set, the level sequence number interval between adjacent levels in each transmission path does not exceed two levels; according to a preset path selection rule, selecting a target transmission path from the first transmission path set as a transmission path of a decoding module in the neural network; and training the neural network by using the training data according to</description><language>chi ; eng</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; ELECTRIC DIGITAL DATA PROCESSING ; PHYSICS</subject><creationdate>2023</creationdate><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20230721&DB=EPODOC&CC=CN&NR=116468071A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,776,881,25542,76289</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20230721&DB=EPODOC&CC=CN&NR=116468071A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>LYU WENYU</creatorcontrib><creatorcontrib>XU SHANGLIANG</creatorcontrib><creatorcontrib>ZHAO YIAN</creatorcontrib><creatorcontrib>WANG GUANZHONG</creatorcontrib><creatorcontrib>DANG QINGQING</creatorcontrib><title>Model training method and device, equipment and storage medium</title><description>The invention provides a model training method and device, equipment and a storage medium, relates to the technical field of artificial intelligence, in particular to the technical fields of machine vision, deep learning and the like, and can be applied to scenes such as target detection and neural network optimization. According to the specific implementation scheme, the method comprises the steps of obtaining a level sequence number of each parameter transmission level in a decoding module of a to-be-trained neural network; a first transmission path set is generated according to the level sequence numbers, and in the first transmission path set, the level sequence number interval between adjacent levels in each transmission path does not exceed two levels; according to a preset path selection rule, selecting a target transmission path from the first transmission path set as a transmission path of a decoding module in the neural network; and training the neural network by using the training data according to</description><subject>CALCULATING</subject><subject>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>ELECTRIC DIGITAL DATA PROCESSING</subject><subject>PHYSICS</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2023</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZLDzzU9JzVEoKUrMzMvMS1fITS3JyE9RSMxLUUhJLctMTtVRSC0szSzITc0rAYsWl-QXJaanAhWmZJbm8jCwpiXmFKfyQmluBkU31xBnD93Ugvz41OKCxOTUvNSSeGc_Q0MzEzMLA3NDR2Ni1AAANJAwRw</recordid><startdate>20230721</startdate><enddate>20230721</enddate><creator>LYU WENYU</creator><creator>XU SHANGLIANG</creator><creator>ZHAO YIAN</creator><creator>WANG GUANZHONG</creator><creator>DANG QINGQING</creator><scope>EVB</scope></search><sort><creationdate>20230721</creationdate><title>Model training method and device, equipment and storage medium</title><author>LYU WENYU ; XU SHANGLIANG ; ZHAO YIAN ; WANG GUANZHONG ; DANG QINGQING</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN116468071A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>chi ; eng</language><creationdate>2023</creationdate><topic>CALCULATING</topic><topic>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>ELECTRIC DIGITAL DATA PROCESSING</topic><topic>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>LYU WENYU</creatorcontrib><creatorcontrib>XU SHANGLIANG</creatorcontrib><creatorcontrib>ZHAO YIAN</creatorcontrib><creatorcontrib>WANG GUANZHONG</creatorcontrib><creatorcontrib>DANG QINGQING</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>LYU WENYU</au><au>XU SHANGLIANG</au><au>ZHAO YIAN</au><au>WANG GUANZHONG</au><au>DANG QINGQING</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Model training method and device, equipment and storage medium</title><date>2023-07-21</date><risdate>2023</risdate><abstract>The invention provides a model training method and device, equipment and a storage medium, relates to the technical field of artificial intelligence, in particular to the technical fields of machine vision, deep learning and the like, and can be applied to scenes such as target detection and neural network optimization. According to the specific implementation scheme, the method comprises the steps of obtaining a level sequence number of each parameter transmission level in a decoding module of a to-be-trained neural network; a first transmission path set is generated according to the level sequence numbers, and in the first transmission path set, the level sequence number interval between adjacent levels in each transmission path does not exceed two levels; according to a preset path selection rule, selecting a target transmission path from the first transmission path set as a transmission path of a decoding module in the neural network; and training the neural network by using the training data according to</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | chi ; eng |
| recordid | cdi_epo_espacenet_CN116468071A |
| source | esp@cenet |
| subjects | CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING ELECTRIC DIGITAL DATA PROCESSING PHYSICS |
| title | Model training method and device, equipment and storage medium |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-08T22%3A35%3A55IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-epo_EVB&rft_val_fmt=info:ofi/fmt:kev:mtx:patent&rft.genre=patent&rft.au=LYU%20WENYU&rft.date=2023-07-21&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN116468071A%3C/epo_EVB%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true |