METHOD AND APPARATUS FOR QUANTIZING NEURAL NETWORK MODEL, AND METHOD AND APPARATUS FOR PROCESSING DATA
A method and apparatus for quantizing a neural network model, and a method and apparatus for processing data, which belong to the field of artificial intelligence. An original neural network model comprises a first operator, a second operator and a first operation module, the first operation module...
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Patent |
| Sprache: | chi ; eng ; fre |
| 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 | SUN, Fangxuan LIAN, Shuo CHANG, Jing ZHOU, Jun WANG, Chenxi |
| description | A method and apparatus for quantizing a neural network model, and a method and apparatus for processing data, which belong to the field of artificial intelligence. An original neural network model comprises a first operator, a second operator and a first operation module, the first operation module being used for performing operation on an output of the first operator and an output of the second operator. The method for quantizing a neural network model comprises: determining a data quantization parameter according to the range of first training input data of a first operator and the range of second training input data of a second operator; and determining a quantized neural network model, and the quantized neural network model respectively quantizing quantized first input data of the first operator and quantized second input data of the second operator by using the data quantization parameter. A quantized processing result of a first operator and a quantized processing result of a second operator can be dire |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_WO2022088063A1</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>WO2022088063A1</sourcerecordid><originalsourceid>FETCH-epo_espacenet_WO2022088063A13</originalsourceid><addsrcrecordid>eNrjZEjzdQ3x8HdRcPQD4oAAxyDHkNBgBTf_IIXAUEe_EM8oTz93BT_X0CBHHyAVEu4f5K3g6-_i6qMD1oJTd0CQv7NrcDBIt4tjiCMPA2taYk5xKi-U5mZQdnMNcfbQTS3Ij08tLkhMTs1LLYkP9zcyMDIysLAwMDN2NDQmThUAeqs11Q</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>METHOD AND APPARATUS FOR QUANTIZING NEURAL NETWORK MODEL, AND METHOD AND APPARATUS FOR PROCESSING DATA</title><source>esp@cenet</source><creator>SUN, Fangxuan ; LIAN, Shuo ; CHANG, Jing ; ZHOU, Jun ; WANG, Chenxi</creator><creatorcontrib>SUN, Fangxuan ; LIAN, Shuo ; CHANG, Jing ; ZHOU, Jun ; WANG, Chenxi</creatorcontrib><description>A method and apparatus for quantizing a neural network model, and a method and apparatus for processing data, which belong to the field of artificial intelligence. An original neural network model comprises a first operator, a second operator and a first operation module, the first operation module being used for performing operation on an output of the first operator and an output of the second operator. The method for quantizing a neural network model comprises: determining a data quantization parameter according to the range of first training input data of a first operator and the range of second training input data of a second operator; and determining a quantized neural network model, and the quantized neural network model respectively quantizing quantized first input data of the first operator and quantized second input data of the second operator by using the data quantization parameter. A quantized processing result of a first operator and a quantized processing result of a second operator can be dire</description><language>chi ; eng ; fre</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; PHYSICS</subject><creationdate>2022</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=20220505&DB=EPODOC&CC=WO&NR=2022088063A1$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,776,881,25542,76289</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20220505&DB=EPODOC&CC=WO&NR=2022088063A1$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>SUN, Fangxuan</creatorcontrib><creatorcontrib>LIAN, Shuo</creatorcontrib><creatorcontrib>CHANG, Jing</creatorcontrib><creatorcontrib>ZHOU, Jun</creatorcontrib><creatorcontrib>WANG, Chenxi</creatorcontrib><title>METHOD AND APPARATUS FOR QUANTIZING NEURAL NETWORK MODEL, AND METHOD AND APPARATUS FOR PROCESSING DATA</title><description>A method and apparatus for quantizing a neural network model, and a method and apparatus for processing data, which belong to the field of artificial intelligence. An original neural network model comprises a first operator, a second operator and a first operation module, the first operation module being used for performing operation on an output of the first operator and an output of the second operator. The method for quantizing a neural network model comprises: determining a data quantization parameter according to the range of first training input data of a first operator and the range of second training input data of a second operator; and determining a quantized neural network model, and the quantized neural network model respectively quantizing quantized first input data of the first operator and quantized second input data of the second operator by using the data quantization parameter. A quantized processing result of a first operator and a quantized processing result of a second operator can be dire</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>2022</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZEjzdQ3x8HdRcPQD4oAAxyDHkNBgBTf_IIXAUEe_EM8oTz93BT_X0CBHHyAVEu4f5K3g6-_i6qMD1oJTd0CQv7NrcDBIt4tjiCMPA2taYk5xKi-U5mZQdnMNcfbQTS3Ij08tLkhMTs1LLYkP9zcyMDIysLAwMDN2NDQmThUAeqs11Q</recordid><startdate>20220505</startdate><enddate>20220505</enddate><creator>SUN, Fangxuan</creator><creator>LIAN, Shuo</creator><creator>CHANG, Jing</creator><creator>ZHOU, Jun</creator><creator>WANG, Chenxi</creator><scope>EVB</scope></search><sort><creationdate>20220505</creationdate><title>METHOD AND APPARATUS FOR QUANTIZING NEURAL NETWORK MODEL, AND METHOD AND APPARATUS FOR PROCESSING DATA</title><author>SUN, Fangxuan ; LIAN, Shuo ; CHANG, Jing ; ZHOU, Jun ; WANG, Chenxi</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_WO2022088063A13</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>chi ; eng ; fre</language><creationdate>2022</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>SUN, Fangxuan</creatorcontrib><creatorcontrib>LIAN, Shuo</creatorcontrib><creatorcontrib>CHANG, Jing</creatorcontrib><creatorcontrib>ZHOU, Jun</creatorcontrib><creatorcontrib>WANG, Chenxi</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>SUN, Fangxuan</au><au>LIAN, Shuo</au><au>CHANG, Jing</au><au>ZHOU, Jun</au><au>WANG, Chenxi</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>METHOD AND APPARATUS FOR QUANTIZING NEURAL NETWORK MODEL, AND METHOD AND APPARATUS FOR PROCESSING DATA</title><date>2022-05-05</date><risdate>2022</risdate><abstract>A method and apparatus for quantizing a neural network model, and a method and apparatus for processing data, which belong to the field of artificial intelligence. An original neural network model comprises a first operator, a second operator and a first operation module, the first operation module being used for performing operation on an output of the first operator and an output of the second operator. The method for quantizing a neural network model comprises: determining a data quantization parameter according to the range of first training input data of a first operator and the range of second training input data of a second operator; and determining a quantized neural network model, and the quantized neural network model respectively quantizing quantized first input data of the first operator and quantized second input data of the second operator by using the data quantization parameter. A quantized processing result of a first operator and a quantized processing result of a second operator can be dire</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | chi ; eng ; fre |
| recordid | cdi_epo_espacenet_WO2022088063A1 |
| source | esp@cenet |
| subjects | CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING PHYSICS |
| title | METHOD AND APPARATUS FOR QUANTIZING NEURAL NETWORK MODEL, AND METHOD AND APPARATUS FOR PROCESSING DATA |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-10T21%3A40%3A57IST&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=SUN,%20Fangxuan&rft.date=2022-05-05&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EWO2022088063A1%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 |