Training method of sketch generation model, sketch generation method, terminal and medium

The invention discloses a sketch generation model training method, a sketch generation method, a terminal and a medium, and the method comprises the steps: constructing a training data set, adding noise in the training data set, and obtaining a noise-added training data set, the training data set co...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: YAO BAOGANG, SUN WENYU, LIU XIANGDONG, JIANG PING, ZHANG NAN
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 YAO BAOGANG
SUN WENYU
LIU XIANGDONG
JIANG PING
ZHANG NAN
description The invention discloses a sketch generation model training method, a sketch generation method, a terminal and a medium, and the method comprises the steps: constructing a training data set, adding noise in the training data set, and obtaining a noise-added training data set, the training data set comprising discretized graph structure data or SDF data; the training data set after noise adding is input into a deep neural network model, prediction sketch structure data are obtained, and the deep neural network model is a network model with a Transform architecture as a core or a network model with a Unet architecture as a core; and determining a loss function based on the training data set and the predicted sketch structure data, and performing iterative training on the deep neural network model based on the loss function to obtain a sketch generation model. According to the method, the data structure characteristics are exerted, the sketch generation model obtained through training can effectively solve the pr
format Patent
fullrecord <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN117935291A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN117935291A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN117935291A3</originalsourceid><addsrcrecordid>eNrjZIgMKUrMzMvMS1fITS3JyE9RyE9TKM5OLUnOUEhPzUstSizJzM9TyM1PSc3RwSYB1qSjUJJalJuZl5ijkJiXAhRMySzN5WFgTUvMKU7lhdLcDIpuriHOHrqpBfnxqcUFiclAY0rinf0MDc0tjU2NLA0djYlRAwDW8TqU</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Training method of sketch generation model, sketch generation method, terminal and medium</title><source>esp@cenet</source><creator>YAO BAOGANG ; SUN WENYU ; LIU XIANGDONG ; JIANG PING ; ZHANG NAN</creator><creatorcontrib>YAO BAOGANG ; SUN WENYU ; LIU XIANGDONG ; JIANG PING ; ZHANG NAN</creatorcontrib><description>The invention discloses a sketch generation model training method, a sketch generation method, a terminal and a medium, and the method comprises the steps: constructing a training data set, adding noise in the training data set, and obtaining a noise-added training data set, the training data set comprising discretized graph structure data or SDF data; the training data set after noise adding is input into a deep neural network model, prediction sketch structure data are obtained, and the deep neural network model is a network model with a Transform architecture as a core or a network model with a Unet architecture as a core; and determining a loss function based on the training data set and the predicted sketch structure data, and performing iterative training on the deep neural network model based on the loss function to obtain a sketch generation model. According to the method, the data structure characteristics are exerted, the sketch generation model obtained through training can effectively solve the pr</description><language>chi ; eng</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; PHYSICS</subject><creationdate>2024</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&amp;date=20240426&amp;DB=EPODOC&amp;CC=CN&amp;NR=117935291A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,777,882,25545,76296</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20240426&amp;DB=EPODOC&amp;CC=CN&amp;NR=117935291A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>YAO BAOGANG</creatorcontrib><creatorcontrib>SUN WENYU</creatorcontrib><creatorcontrib>LIU XIANGDONG</creatorcontrib><creatorcontrib>JIANG PING</creatorcontrib><creatorcontrib>ZHANG NAN</creatorcontrib><title>Training method of sketch generation model, sketch generation method, terminal and medium</title><description>The invention discloses a sketch generation model training method, a sketch generation method, a terminal and a medium, and the method comprises the steps: constructing a training data set, adding noise in the training data set, and obtaining a noise-added training data set, the training data set comprising discretized graph structure data or SDF data; the training data set after noise adding is input into a deep neural network model, prediction sketch structure data are obtained, and the deep neural network model is a network model with a Transform architecture as a core or a network model with a Unet architecture as a core; and determining a loss function based on the training data set and the predicted sketch structure data, and performing iterative training on the deep neural network model based on the loss function to obtain a sketch generation model. According to the method, the data structure characteristics are exerted, the sketch generation model obtained through training can effectively solve the pr</description><subject>CALCULATING</subject><subject>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>PHYSICS</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2024</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZIgMKUrMzMvMS1fITS3JyE9RyE9TKM5OLUnOUEhPzUstSizJzM9TyM1PSc3RwSYB1qSjUJJalJuZl5ijkJiXAhRMySzN5WFgTUvMKU7lhdLcDIpuriHOHrqpBfnxqcUFiclAY0rinf0MDc0tjU2NLA0djYlRAwDW8TqU</recordid><startdate>20240426</startdate><enddate>20240426</enddate><creator>YAO BAOGANG</creator><creator>SUN WENYU</creator><creator>LIU XIANGDONG</creator><creator>JIANG PING</creator><creator>ZHANG NAN</creator><scope>EVB</scope></search><sort><creationdate>20240426</creationdate><title>Training method of sketch generation model, sketch generation method, terminal and medium</title><author>YAO BAOGANG ; SUN WENYU ; LIU XIANGDONG ; JIANG PING ; ZHANG NAN</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN117935291A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>chi ; eng</language><creationdate>2024</creationdate><topic>CALCULATING</topic><topic>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>YAO BAOGANG</creatorcontrib><creatorcontrib>SUN WENYU</creatorcontrib><creatorcontrib>LIU XIANGDONG</creatorcontrib><creatorcontrib>JIANG PING</creatorcontrib><creatorcontrib>ZHANG NAN</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>YAO BAOGANG</au><au>SUN WENYU</au><au>LIU XIANGDONG</au><au>JIANG PING</au><au>ZHANG NAN</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Training method of sketch generation model, sketch generation method, terminal and medium</title><date>2024-04-26</date><risdate>2024</risdate><abstract>The invention discloses a sketch generation model training method, a sketch generation method, a terminal and a medium, and the method comprises the steps: constructing a training data set, adding noise in the training data set, and obtaining a noise-added training data set, the training data set comprising discretized graph structure data or SDF data; the training data set after noise adding is input into a deep neural network model, prediction sketch structure data are obtained, and the deep neural network model is a network model with a Transform architecture as a core or a network model with a Unet architecture as a core; and determining a loss function based on the training data set and the predicted sketch structure data, and performing iterative training on the deep neural network model based on the loss function to obtain a sketch generation model. According to the method, the data structure characteristics are exerted, the sketch generation model obtained through training can effectively solve the pr</abstract><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier
ispartof
issn
language chi ; eng
recordid cdi_epo_espacenet_CN117935291A
source esp@cenet
subjects CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
PHYSICS
title Training method of sketch generation model, sketch generation method, terminal and medium
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-20T15%3A50%3A10IST&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=YAO%20BAOGANG&rft.date=2024-04-26&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN117935291A%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