LocateAnything-3B-RK3588 / eval /preds_gpu_sampled.json
oliver0804's picture
Add RK3588 conversion of nvidia/LocateAnything-3B (RKLLM w8a8 + RKNN fp16)
0522016 verified
Raw History Blame Contribute Delete
37.7 kB
{"gpu_bidir_448": {"370818": {"text": "<ref>potted plant</ref><box>None</box><|im_end|>", "sec": 0.8}, "343453": {"text": "<ref>person</ref><box><395><123><681><998></box><|im_end|>", "sec": 0.11}, "119828": {"text": "<ref>cat</ref><box><224><398><880><998></box><|im_end|>", "sec": 0.14}, "47769": {"text": "<ref>chair</ref><box><625><726><775><998></box><|im_end|>", "sec": 0.09}, "438907": {"text": "<ref>person</ref><box><98><253><274><773></box><box><277><33><655><630></box><|im_end|>", "sec": 0.11}, "27972": {"text": "<ref>person</ref><box><567><206><783><574></box><|im_end|>", "sec": 0.09}, "64499": {"text": "<ref>zebra</ref><box><0><324><585><998></box><|im_end|>", "sec": 0.09}, "49810": {"text": "<ref>cat</ref><box><0><356><998><998></box><|im_end|>", "sec": 0.17}, "334530": {"text": "<ref>surfboard</ref><box><380><485><577><602></box><|im_end|>", "sec": 0.09}, "65350": {"text": "<ref>bicycle</ref><box><344><0><998><228></box><|im_end|>", "sec": 0.14}, "210030": {"text": "<ref>fork</ref><box><472><339><790><905></box><|im_end|>", "sec": 0.15}, "227985": {"text": "<ref>sandwich</ref><box><47><0><928><905></box><|im_end|>", "sec": 0.15}, "27932": {"text": "<ref>baseball glove</ref><box><77><317><770><925></box><|im_end|>", "sec": 0.09}, "185292": {"text": "<ref>person</ref><box><417><677><480><750></box><|im_end|>", "sec": 0.09}, "207728": {"text": "<ref>sheep</ref><box><142><590><650><998></box><box><212><148><740><755></box><|im_end|>", "sec": 0.11}, "165518": {"text": "<ref>motorcycle</ref><box><402><427><709><833></box><|im_end|>", "sec": 0.09}, "179285": {"text": "<ref>sports ball</ref><box><480><373><848><624></box><|im_end|>", "sec": 0.09}, "326541": {"text": "<ref>person</ref><box><0><5><441><998></box><box><265><410><507><1000></box><box><402><387><546><676></box><box><403><81><997><998></box><box><502><465><668><890></box><box><667><342><705><433></box><|im_end|>", "sec": 0.46}, "312586": {"text": "<ref>bear</ref><box><281><562><688><894></box><|im_end|>", "sec": 0.09}, "512194": {"text": "<ref>vase</ref><box><487><618><834><998></box><|im_end|>", "sec": 0.09}, "344100": {"text": "<ref>sandwich</ref><box><610><446><791><701></box><|im_end|>", "sec": 0.09}, "527784": {"text": "<ref>sandwich</ref><box><0><387><480><618></box><box><508><410><1000><882></box><|im_end|>", "sec": 0.19}, "231879": {"text": "<ref>person</ref><box><82><322><519><1000></box><box><186><0><461><702></box><box><333><300><520><1000></box><box><448><0><778><1000></box><box><679><0><874><1000></box><|im_end|>", "sec": 0.2}, "348045": {"text": "<ref>toilet</ref><box><7><639><235><924></box><box><407><634><612><926></box><box><768><628><992><904></box><|im_end|>", "sec": 0.13}, "33104": {"text": "<ref>person</ref><box><0><0><120><902></box><box><47><66><480><932></box><box><372><96><812><958></box><box><678><48><998><868></box><box><848><0><998><592></box><|im_end|>", "sec": 0.17}, "263860": {"text": "<ref>elephant</ref><box><0><127><479><998></box><box><409><195><998><998></box><|im_end|>", "sec": 0.16}, "367818": {"text": "<ref>horse</ref><box><220><127><848><890></box><|im_end|>", "sec": 0.09}, "448365": {"text": "<ref>person</ref><box><233><77><580><794></box><box><695><499><748><602></box><|im_end|>", "sec": 0.18}, "163640": {"text": "<ref>person</ref><box><132><293><452><1000></box><box><472><354><598><677></box><box><698><298><948><1000></box><|im_end|>", "sec": 0.13}, "556158": {"text": "<ref>person</ref><box><325><224><593><674></box><|im_end|>", "sec": 0.09}, "80413": {"text": "<ref>teddy bear</ref><box><348><231><616><544></box><|im_end|>", "sec": 0.09}, "110359": {"text": "<ref>airplane</ref><box><342><345><658><888></box><|im_end|>", "sec": 0.09}, "99810": {"text": "<ref>donut</ref><box><400><802><477><892></box><box><663><830><753><965></box><box><725><897><820><998></box><box><750><785><848><905></box><box><810><852><900><988></box><|im_end|>", "sec": 0.17}, "147518": {"text": "<ref>toilet</ref><box><241><500><650><970></box><|im_end|>", "sec": 0.09}, "80659": {"text": "<ref>horse</ref><box><0><208><849><880></box><box><478><225><998><967></box><|im_end|>", "sec": 0.18}, "41635": {"text": "<ref>cow</ref><box><0><325><398><703></box><box><320><333><648><674></box><box><516><310><998><642></box><|im_end|>", "sec": 0.18}, "448448": {"text": "<ref>giraffe</ref><box><158><0><998><998></box><|im_end|>", "sec": 0.12}, "80273": {"text": "<ref>person</ref><box><267><105><595><980></box><|im_end|>", "sec": 0.09}, "166166": {"text": "<ref>chair</ref><box><0><324><258><998></box><|im_end|>", "sec": 0.12}, "24919": {"text": "<ref>elephant</ref><box><181><353><536><706></box><box><469><357><811><709></box><|im_end|>", "sec": 0.15}, "325347": {"text": "<ref>chair</ref><box><445><9><570><255></box><box><622><10><740><254></box><|im_end|>", "sec": 0.11}, "108026": {"text": "<ref>person</ref><box><176><0><998><998></box><|im_end|>", "sec": 0.09}, "14007": {"text": "<ref>cat</ref><box><536><369><654><698></box><|im_end|>", "sec": 0.17}, "328683": {"text": "<ref>parking meter</ref><box><345><51><608><362></box><|im_end|>", "sec": 0.09}, "427077": {"text": "<ref>person</ref><box><328><148><793><817></box><|im_end|>", "sec": 0.09}, "73702": {"text": "<ref>handbag</ref><box><538><365><995><905></box><|im_end|>", "sec": 0.15}, "357567": {"text": "<ref>toilet</ref><box><582><575><998><969></box><|im_end|>", "sec": 0.14}, "190756": {"text": "<ref>motorcycle</ref><box><182><94><769><882></box><|im_end|>", "sec": 0.09}, "311909": {"text": "<ref>bus</ref><box><0><94><979><905></box><|im_end|>", "sec": 0.09}, "19221": {"text": "<ref>person</ref><box><382><693><852><998></box><|im_end|>", "sec": 0.09}, "112626": {"text": "<ref>couch</ref><box><623><265><1000><732></box><|im_end|>", "sec": 0.09}, "187249": {"text": "<ref>person</ref><box><211><262><588><664></box><box><416><261><717><667></box><|im_end|>", "sec": 0.12}, "267434": {"text": "<ref>cow</ref><box><66><448><216><897></box><box><151><423><399><951></box><box><437><410><562><758></box><box><527><459><641><747></box><box><627><462><689><706></box><box><662><441><812><753></box><box><792><456><1000><688></box><|im_end|>", "sec": 0.21}, "422670": {"text": "<ref>person</ref><box><200><129><722><998></box><|im_end|>", "sec": 0.09}, "130566": {"text": "<ref>train</ref><box><28><272><906><740></box><|im_end|>", "sec": 0.09}, "365098": {"text": "<ref>boat</ref><box><67><228><999><912></box><|im_end|>", "sec": 0.16}, "253386": {"text": "<ref>person</ref><box><0><0><998><998></box><|im_end|>", "sec": 0.14}, "470779": {"text": "<ref>person</ref><box><83><199><276><844></box><box><211><143><490><865></box><box><405><115><625><793></box><box><511><86><708><849></box><box><648><62><843><857></box><|im_end|>", "sec": 0.17}, "335328": {"text": "<ref>person</ref><box><106><520><414><672></box><box><658><344><962><519></box><|im_end|>", "sec": 0.11}, "161397": {"text": "<ref>vase</ref><box><0><46><222><370></box><box><0><358><134><735></box><box><137><355><372><765></box><box><265><165><348><283></box><box><352><180><467><345></box><|im_end|>", "sec": 0.38}, "433980": {"text": "<ref>cell phone</ref><box><208><575><408><869></box><|im_end|>", "sec": 0.12}, "80057": {"text": "<ref>teddy bear</ref><box><0><15><892><655></box><|im_end|>", "sec": 0.09}, "336265": {"text": "<ref>person</ref><box><505><474><570><573></box><|im_end|>", "sec": 0.09}, "133567": {"text": "<ref>train</ref><box><0><200><897><694></box><|im_end|>", "sec": 0.09}, "231549": {"text": "<ref>bed</ref><box><179><733><808><999></box><|im_end|>", "sec": 0.09}, "502336": {"text": "<ref>person</ref><box><214><689><282><911></box><box><262><671><314><909></box><box><300><670><364><919></box><box><475><642><607><968></box><box><947><609><998><887></box><|im_end|>", "sec": 0.17}, "468632": {"text": "<ref>person</ref><box><111><411><298><859></box><box><116><381><225><819></box><box><455><301><653><856></box><box><745><385><908><883></box><|im_end|>", "sec": 0.15}, "156292": {"text": "<ref>clock</ref><box><317><373><637><585></box><|im_end|>", "sec": 0.09}, "115885": {"text": "<ref>cat</ref><box><694><0><998><661></box><|im_end|>", "sec": 0.12}, "581615": {"text": "<ref>toilet</ref><box><302><600><681><1000></box><|im_end|>", "sec": 0.09}, "556873": {"text": "<ref>cake</ref><box><239><523><575><778></box><|im_end|>", "sec": 0.09}, "575372": {"text": "<ref>traffic light</ref><box><191><791><242><918></box><box><416><347><474><547></box><box><636><153><705><397></box><box><927><792><998><932></box><|im_end|>", "sec": 0.18}, "394328": {"text": "<ref>toilet</ref><box><325><578><740><998></box><|im_end|>", "sec": 0.09}, "360943": {"text": "<ref>cat</ref><box><396><374><553><440></box><|im_end|>", "sec": 0.09}, "287545": {"text": "<ref>giraffe</ref><box><94><228><640><740></box><box><363><513><484><722></box><|im_end|>", "sec": 0.11}, "194506": {"text": "<ref>bear</ref><box><120><234><473><538></box><box><438><289><650><533></box><|im_end|>", "sec": 0.11}, "107087": {"text": "<ref>cat</ref><box><42><178><414><998></box><|im_end|>", "sec": 0.17}, "263474": {"text": "<ref>toilet</ref><box><38><315><798><974></box><|im_end|>", "sec": 0.09}, "407518": {"text": "<ref>bird</ref><box><580><209><868><887></box><|im_end|>", "sec": 0.09}, "31620": {"text": "<ref>person</ref><box><0><391><179><607></box><box><385><349><797><679></box><box><865><544><998><998></box><|im_end|>", "sec": 0.13}, "398237": {"text": "<ref>kite</ref><box><142><506><774><773></box><box><151><0><520><383></box><box><471><106><623><277></box><box><753><71><839><199></box><|im_end|>", "sec": 0.35}, "509403": {"text": "<ref>person</ref><box><565><135><750><870></box><|im_end|>", "sec": 0.14}, "292456": {"text": "<ref>person</ref><box><258><84><382><725></box><box><368><121><824><930></box><box><618><176><886><900></box><|im_end|>", "sec": 0.13}, "359833": {"text": "<ref>apple</ref><box><0><67><713><331></box><box><0><185><600><456></box><box><0><445><319><573></box><box><0><553><321><998></box><box><120><0><734><117></box><box><123><453><475><552></box><box><272><467><369><583></box><box><462><422><584><505></box><|im_end|>", "sec": 0.34}, "261982": {"text": "<ref>car</ref><box><0><16><551><356></box><|im_end|>", "sec": 0.14}, "429761": {"text": "<ref>person</ref><box><297><190><485><905></box><box><449><142><635><835></box><|im_end|>", "sec": 0.11}, "482719": {"text": "<ref>chair</ref><box><186><0><763><291></box><|im_end|>", "sec": 0.15}, "506178": {"text": "<ref>person</ref><box><176><184><869><1000></box><|im_end|>", "sec": 0.14}, "131131": {"text": "<ref>tv</ref><box><88><186><876><863></box><|im_end|>", "sec": 0.09}, "68286": {"text": "<ref>bed</ref><box><35><146><859><998></box><|im_end|>", "sec": 0.09}, "67896": {"text": "<ref>clock</ref><box><255><103><755><792></box><|im_end|>", "sec": 0.09}, "297830": {"text": "<ref>dog</ref><box><318><62><918><946></box><|im_end|>", "sec": 0.09}, "398810": {"text": "<ref>cat</ref><box><210><258><393><433></box><box><449><308><998><866></box><|im_end|>", "sec": 0.16}, "569565": {"text": "<ref>truck</ref><box><209><435><706><745></box><|im_end|>", "sec": 0.09}, "161879": {"text": "<ref>person</ref><box><94><0><366><606></box><|im_end|>", "sec": 0.09}, "333069": {"text": "<ref>giraffe</ref><box><220><306><629><908></box><box><539><305><922><642></box><|im_end|>", "sec": 0.19}, "544306": {"text": "<ref>clock</ref><box><534><663><632><823></box><box><712><667><820><824></box><|im_end|>", "sec": 0.11}, "455555": {"text": "<ref>person</ref><box><188><184><717><860></box><box><722><85><977><439></box><|im_end|>", "sec": 0.11}, "377575": {"text": "<ref>dog</ref><box><141><269><642><944></box><|im_end|>", "sec": 0.09}, "157213": {"text": "<ref>elephant</ref><box><434><208><618><625></box><|im_end|>", "sec": 0.09}}, "gpu_causal_448": {"370818": {"text": "<ref>potted plant</ref><box>None</box><|im_end|>", "sec": 0.09}, "343453": {"text": "<ref>person</ref><box><395><122><681><998></box><|im_end|>", "sec": 0.09}, "119828": {"text": "<ref>cat</ref><box><224><398><880><998></box><|im_end|>", "sec": 0.12}, "47769": {"text": "<ref>chair</ref><box><625><726><775><998></box><|im_end|>", "sec": 0.09}, "438907": {"text": "<ref>person</ref><box><118><254><274><773></box><box><277><33><655><630></box><|im_end|>", "sec": 0.11}, "27972": {"text": "<ref>person</ref><box><567><206><783><574></box><|im_end|>", "sec": 0.09}, "64499": {"text": "<ref>zebra</ref><box><0><324><585><998></box><|im_end|>", "sec": 0.09}, "49810": {"text": "<ref>cat</ref><box><0><356><998><998></box><|im_end|>", "sec": 0.17}, "334530": {"text": "<ref>surfboard</ref><box><382><485><578><602></box><|im_end|>", "sec": 0.09}, "65350": {"text": "<ref>bicycle</ref><box><344><0><998><228></box><|im_end|>", "sec": 0.14}, "210030": {"text": "<ref>fork</ref><box><472><344><792><902></box><|im_end|>", "sec": 0.09}, "227985": {"text": "<ref>sandwich</ref><box><47><0><928><905></box><|im_end|>", "sec": 0.15}, "27932": {"text": "<ref>baseball glove</ref><box><77><317><770><924></box><|im_end|>", "sec": 0.09}, "185292": {"text": "<ref>person</ref><box><417><677><480><750></box><|im_end|>", "sec": 0.09}, "207728": {"text": "<ref>sheep</ref><box><142><590><650><998></box><box><212><148><740><755></box><|im_end|>", "sec": 0.11}, "165518": {"text": "<ref>motorcycle</ref><box><402><427><709><833></box><|im_end|>", "sec": 0.09}, "179285": {"text": "<ref>sports ball</ref><box><480><373><848><624></box><|im_end|>", "sec": 0.09}, "326541": {"text": "<ref>person</ref><box><0><5><441><998></box><box><265><410><507><1000></box><box><402><387><546><676></box><box><502><465><748><1000></box><box><633><342><706><491></box><box><685><2><1000><1000></box><|im_end|>", "sec": 0.45}, "312586": {"text": "<ref>bear</ref><box><281><562><686><894></box><|im_end|>", "sec": 0.09}, "512194": {"text": "<ref>vase</ref><box><488><618><834><998></box><|im_end|>", "sec": 0.09}, "344100": {"text": "<ref>sandwich</ref><box><610><446><790><701></box><|im_end|>", "sec": 0.09}, "527784": {"text": "<ref>sandwich</ref><box><0><387><480><618></box><box><508><410><1000><882></box><|im_end|>", "sec": 0.18}, "231879": {"text": "<ref>person</ref><box><83><323><519><1000></box><box><188><0><461><702></box><box><333><300><518><1000></box><box><448><0><778><1000></box><box><694><0><873><1000></box><|im_end|>", "sec": 0.2}, "348045": {"text": "<ref>toilet</ref><box><7><639><235><923></box><box><407><633><612><926></box><box><768><628><993><904></box><|im_end|>", "sec": 0.14}, "33104": {"text": "<ref>person</ref><box><0><0><120><902></box><box><47><66><480><932></box><box><372><96><811><958></box><box><678><48><998><868></box><box><845><0><998><592></box><|im_end|>", "sec": 0.17}, "263860": {"text": "<ref>elephant</ref><box><0><127><479><998></box><box><408><195><998><998></box><|im_end|>", "sec": 0.16}, "367818": {"text": "<ref>horse</ref><box><220><127><848><890></box><|im_end|>", "sec": 0.09}, "448365": {"text": "<ref>person</ref><box><233><77><580><794></box><box><695><499><748><602></box><|im_end|>", "sec": 0.19}, "163640": {"text": "<ref>person</ref><box><132><293><452><1000></box><box><472><354><598><677></box><box><698><298><948><1000></box><|im_end|>", "sec": 0.13}, "556158": {"text": "<ref>person</ref><box><327><224><593><674></box><|im_end|>", "sec": 0.09}, "80413": {"text": "<ref>teddy bear</ref><box><348><231><616><544></box><|im_end|>", "sec": 0.09}, "110359": {"text": "<ref>airplane</ref><box><342><345><658><888></box><|im_end|>", "sec": 0.09}, "99810": {"text": "<ref>donut</ref><box><400><801><477><889></box><box><663><829><753><966></box><box><725><896><822><998></box><box><750><784><848><904></box><box><810><852><901><988></box><|im_end|>", "sec": 0.2}, "147518": {"text": "<ref>toilet</ref><box><241><500><650><970></box><|im_end|>", "sec": 0.09}, "80659": {"text": "<ref>horse</ref><box><0><208><849><880></box><box><478><225><998><964></box><|im_end|>", "sec": 0.18}, "41635": {"text": "<ref>cow</ref><box><0><325><398><703></box><box><320><333><648><674></box><box><516><309><998><642></box><|im_end|>", "sec": 0.17}, "448448": {"text": "<ref>giraffe</ref><box><158><0><998><998></box><|im_end|>", "sec": 0.12}, "80273": {"text": "<ref>person</ref><box><267><105><595><980></box><|im_end|>", "sec": 0.09}, "166166": {"text": "<ref>chair</ref><box><0><324><258><998></box><|im_end|>", "sec": 0.12}, "24919": {"text": "<ref>elephant</ref><box><181><353><536><706></box><box><469><357><811><709></box><|im_end|>", "sec": 0.16}, "325347": {"text": "<ref>chair</ref><box><445><10><570><255></box><box><622><9><740><254></box><|im_end|>", "sec": 0.11}, "108026": {"text": "<ref>person</ref><box><174><0><998><998></box><|im_end|>", "sec": 0.09}, "14007": {"text": "<ref>cat</ref><box><536><369><654><698></box><|im_end|>", "sec": 0.17}, "328683": {"text": "<ref>parking meter</ref><box><345><51><608><362></box><|im_end|>", "sec": 0.1}, "427077": {"text": "<ref>person</ref><box><328><148><793><817></box><|im_end|>", "sec": 0.1}, "73702": {"text": "<ref>handbag</ref><box><538><362><998><902></box><|im_end|>", "sec": 0.1}, "357567": {"text": "<ref>toilet</ref><box><582><574><998><905></box><|im_end|>", "sec": 0.17}, "190756": {"text": "<ref>motorcycle</ref><box><183><94><767><882></box><|im_end|>", "sec": 0.1}, "311909": {"text": "<ref>bus</ref><box><0><94><979><905></box><|im_end|>", "sec": 0.1}, "19221": {"text": "<ref>person</ref><box><382><693><852><998></box><|im_end|>", "sec": 0.09}, "112626": {"text": "<ref>couch</ref><box><623><265><1000><732></box><|im_end|>", "sec": 0.09}, "187249": {"text": "<ref>person</ref><box><211><262><588><664></box><box><416><261><717><667></box><|im_end|>", "sec": 0.11}, "267434": {"text": "<ref>cow</ref><box><66><448><215><897></box><box><151><423><399><951></box><box><437><410><562><758></box><box><527><459><641><747></box><box><627><462><691><706></box><box><662><439><755><753></box><box><738><477><814><720></box><box><792><456><942><673></box><box><933><475><1000><689></box><|im_end|>", "sec": 0.24}, "422670": {"text": "<ref>person</ref><box><200><129><722><998></box><|im_end|>", "sec": 0.09}, "130566": {"text": "<ref>train</ref><box><28><272><906><740></box><|im_end|>", "sec": 0.09}, "365098": {"text": "<ref>boat</ref><box><67><228><999><912></box><|im_end|>", "sec": 0.17}, "253386": {"text": "<ref>person</ref><box><0><0><998><998></box><|im_end|>", "sec": 0.14}, "470779": {"text": "<ref>person</ref><box><83><199><276><848></box><box><211><143><490><865></box><box><405><114><625><793></box><box><511><86><708><849></box><box><648><62><843><858></box><|im_end|>", "sec": 0.17}, "335328": {"text": "<ref>person</ref><box><106><520><414><672></box><box><658><344><963><519></box><|im_end|>", "sec": 0.11}, "161397": {"text": "<ref>vase</ref><box><0><46><222><370></box><box><0><358><134><735></box><box><23><359><218><513></box><box><137><537><372><763></box><box><350><174><466><355></box><|im_end|>", "sec": 0.39}, "433980": {"text": "<ref>cell phone</ref><box><208><577><408><869></box><|im_end|>", "sec": 0.12}, "80057": {"text": "<ref>teddy bear</ref><box><0><15><892><655></box><|im_end|>", "sec": 0.09}, "336265": {"text": "<ref>person</ref><box><505><475><570><573></box><|im_end|>", "sec": 0.09}, "133567": {"text": "<ref>train</ref><box><0><200><897><694></box><|im_end|>", "sec": 0.09}, "231549": {"text": "<ref>bed</ref><box><175><730><807><999></box><|im_end|>", "sec": 0.17}, "502336": {"text": "<ref>person</ref><box><214><689><282><912></box><box><265><671><314><910></box><box><299><670><362><920></box><box><475><642><607><968></box><box><947><608><998><888></box><|im_end|>", "sec": 0.17}, "468632": {"text": "<ref>person</ref><box><111><411><298><859></box><box><115><381><225><819></box><box><455><301><653><856></box><box><745><385><908><883></box><|im_end|>", "sec": 0.15}, "156292": {"text": "<ref>clock</ref><box><317><374><637><585></box><|im_end|>", "sec": 0.09}, "115885": {"text": "<ref>cat</ref><box><694><0><998><661></box><|im_end|>", "sec": 0.12}, "581615": {"text": "<ref>toilet</ref><box><302><600><681><1000></box><|im_end|>", "sec": 0.09}, "556873": {"text": "<ref>cake</ref><box><239><523><575><777></box><|im_end|>", "sec": 0.09}, "575372": {"text": "<ref>traffic light</ref><box><191><793><242><918></box><box><416><347><474><547></box><box><634><153><705><397></box><box><927><791><998><930></box><|im_end|>", "sec": 0.18}, "394328": {"text": "<ref>toilet</ref><box><325><580><740><998></box><|im_end|>", "sec": 0.09}, "360943": {"text": "<ref>cat</ref><box><396><374><551><440></box><|im_end|>", "sec": 0.09}, "287545": {"text": "<ref>giraffe</ref><box><94><228><640><742></box><box><362><513><484><722></box><|im_end|>", "sec": 0.11}, "194506": {"text": "<ref>bear</ref><box><120><234><473><545></box><box><438><289><650><533></box><|im_end|>", "sec": 0.11}, "107087": {"text": "<ref>cat</ref><box><42><178><414><998></box><|im_end|>", "sec": 0.17}, "263474": {"text": "<ref>toilet</ref><box><38><315><798><974></box><|im_end|>", "sec": 0.09}, "407518": {"text": "<ref>bird</ref><box><580><209><868><887></box><|im_end|>", "sec": 0.09}, "31620": {"text": "<ref>person</ref><box><0><391><179><607></box><box><386><349><797><679></box><box><865><544><998><998></box><|im_end|>", "sec": 0.13}, "398237": {"text": "<ref>kite</ref><box><142><506><774><773></box><box><151><75><446><393></box><box><471><105><622><275></box><box><753><71><839><199></box><|im_end|>", "sec": 0.33}, "509403": {"text": "<ref>person</ref><box><567><135><750><870></box><|im_end|>", "sec": 0.14}, "292456": {"text": "<ref>person</ref><box><258><84><382><725></box><box><368><121><824><930></box><box><618><176><886><900></box><|im_end|>", "sec": 0.13}, "359833": {"text": "<ref>apple</ref><box><0><67><713><331></box><box><0><309><54><456></box><box><0><673><189><835></box><box><2><819><34><881></box><box><5><309><143><413></box><box><7><444><122><552></box><box><23><596><179><698></box><box><50><289><158><355></box><box><100><793><311><951></box><box><103><404><194><461></box><box><113><188><219><255></box><box><125><453><294><556></box><box><132><245><227><302></box><box><137><273><257><346></box><box><150><336><267><422></box><box><193><646><319><763></box><box><253><299><395><380></box><box><272><375><372><526></box><box><275><468><373><553></box><box><333><268><445><328></box><box><343><451><477><547></box><box><387><366><498><460></box><box><420><297><541><382></box><box><463><423><585><502></box><box><485><350><600><448></box><|im_end|>", "sec": 1.0}, "261982": {"text": "<ref>car</ref><box><0><15><551><356></box><|im_end|>", "sec": 0.14}, "429761": {"text": "<ref>person</ref><box><297><190><485><906></box><box><449><142><636><836></box><|im_end|>", "sec": 0.11}, "482719": {"text": "<ref>chair</ref><box><186><0><763><291></box><|im_end|>", "sec": 0.15}, "506178": {"text": "<ref>person</ref><box><178><184><869><1000></box><|im_end|>", "sec": 0.14}, "131131": {"text": "<ref>tv</ref><box><88><186><876><863></box><|im_end|>", "sec": 0.09}, "68286": {"text": "<ref>bed</ref><box><35><146><858><998></box><|im_end|>", "sec": 0.1}, "67896": {"text": "<ref>clock</ref><box><256><104><763><742></box><|im_end|>", "sec": 0.15}, "297830": {"text": "<ref>dog</ref><box><317><62><918><946></box><|im_end|>", "sec": 0.09}, "398810": {"text": "<ref>cat</ref><box><210><259><393><433></box><box><449><307><998><866></box><|im_end|>", "sec": 0.16}, "569565": {"text": "<ref>truck</ref><box><209><431><706><745></box><|im_end|>", "sec": 0.09}, "161879": {"text": "<ref>person</ref><box><94><0><366><605></box><|im_end|>", "sec": 0.09}, "333069": {"text": "<ref>giraffe</ref><box><220><307><630><908></box><box><539><305><922><642></box><|im_end|>", "sec": 0.19}, "544306": {"text": "<ref>clock</ref><box><534><663><630><806></box><box><714><667><817><810></box><|im_end|>", "sec": 0.11}, "455555": {"text": "<ref>person</ref><box><188><184><717><860></box><box><722><85><977><439></box><|im_end|>", "sec": 0.11}, "377575": {"text": "<ref>dog</ref><box><141><269><642><944></box><|im_end|>", "sec": 0.09}, "157213": {"text": "<ref>elephant</ref><box><434><208><618><625></box><|im_end|>", "sec": 0.09}}, "gpu_bidir_native": {"370818": {"text": "<ref>potted plant</ref><box>None</box><|im_end|>", "sec": 0.13}, "343453": {"text": "<ref>person</ref><box><395><123><680><998></box><|im_end|>", "sec": 0.12}, "119828": {"text": "<ref>cat</ref><box><224><397><880><997></box><|im_end|>", "sec": 0.09}, "47769": {"text": "<ref>chair</ref><box><628><728><776><1000></box><|im_end|>", "sec": 0.09}, "438907": {"text": "<ref>person</ref><box><114><255><277><773></box><box><279><34><656><627></box><|im_end|>", "sec": 0.2}, "27972": {"text": "<ref>person</ref><box><567><207><758><561></box><|im_end|>", "sec": 0.12}, "64499": {"text": "<ref>zebra</ref><box><0><317><586><998></box><box><169><362><588><927></box><|im_end|>", "sec": 0.14}, "49810": {"text": "<ref>cat</ref><box><202><350><998><1000></box><|im_end|>", "sec": 0.12}, "334530": {"text": "<ref>surfboard</ref><box><367><488><581><602></box><|im_end|>", "sec": 0.12}, "65350": {"text": "<ref>bicycle</ref><box><347><0><998><218></box><|im_end|>", "sec": 0.16}, "210030": {"text": "<ref>fork</ref><box><472><340><792><902></box><|im_end|>", "sec": 0.1}, "227985": {"text": "<ref>sandwich</ref><box><50><2><928><898></box><|im_end|>", "sec": 0.18}, "27932": {"text": "<ref>baseball glove</ref><box><88><90><873><923></box><|im_end|>", "sec": 0.07}, "185292": {"text": "<ref>person</ref><box><415><677><478><753></box><|im_end|>", "sec": 0.12}, "207728": {"text": "<ref>sheep</ref><box><144><502><652><997></box><box><212><150><742><757></box><|im_end|>", "sec": 0.12}, "165518": {"text": "<ref>motorcycle</ref><box><402><425><709><835></box><|im_end|>", "sec": 0.15}, "179285": {"text": "<ref>sports ball</ref><box><480><373><848><623></box><|im_end|>", "sec": 0.12}, "326541": {"text": "<ref>person</ref><box><0><11><406><997></box><box><275><411><748><997></box><box><466><392><541><678></box><box><509><472><666><886></box><box><669><347><698><422></box><box><684><83><998><997></box><|im_end|>", "sec": 0.45}, "312586": {"text": "<ref>bear</ref><box><283><560><684><892></box><|im_end|>", "sec": 0.12}, "512194": {"text": "<ref>vase</ref><box><488><616><836><998></box><|im_end|>", "sec": 0.12}, "344100": {"text": "<ref>sandwich</ref><box><609><445><791><700></box><|im_end|>", "sec": 0.12}, "527784": {"text": "<ref>sandwich</ref><box><512><420><1000><880></box><|im_end|>", "sec": 0.2}, "231879": {"text": "<ref>person</ref><box><88><326><483><998></box><box><191><0><458><700></box><box><331><304><516><998></box><box><452><0><809><998></box><box><697><0><872><859></box><|im_end|>", "sec": 0.25}, "348045": {"text": "<ref>toilet</ref><box><9><639><236><928></box><box><406><634><610><927></box><box><768><628><992><906></box><|im_end|>", "sec": 0.18}, "33104": {"text": "<ref>person</ref><box><0><20><118><898></box><box><50><66><493><932></box><box><370><96><812><960></box><box><680><46><998><876></box><box><845><0><998><608></box><|im_end|>", "sec": 0.17}, "263860": {"text": "<ref>elephant</ref><box><0><124><472><998></box><box><405><194><998><998></box><|im_end|>", "sec": 0.18}, "367818": {"text": "<ref>horse</ref><box><222><126><848><890></box><|im_end|>", "sec": 0.12}, "448365": {"text": "<ref>person</ref><box><234><77><580><794></box><|im_end|>", "sec": 0.12}, "163640": {"text": "<ref>person</ref><box><134><294><452><998></box><box><475><354><598><682></box><box><698><298><950><1000></box><|im_end|>", "sec": 0.16}, "556158": {"text": "<ref>person</ref><box><325><225><594><677></box><|im_end|>", "sec": 0.12}, "80413": {"text": "<ref>teddy bear</ref><box><350><231><616><546></box><|im_end|>", "sec": 0.12}, "110359": {"text": "<ref>airplane</ref><box><342><342><658><888></box><|im_end|>", "sec": 0.12}, "99810": {"text": "<ref>donut</ref><box><396><817><474><895></box><box><662><829><752><964></box><box><728><898><822><997></box><box><750><787><846><907></box><box><808><853><900><985></box><|im_end|>", "sec": 0.3}, "147518": {"text": "<ref>toilet</ref><box><240><502><650><972></box><|im_end|>", "sec": 0.12}, "80659": {"text": "<ref>horse</ref><box><67><208><567><880></box><|im_end|>", "sec": 0.19}, "41635": {"text": "<ref>cow</ref><box><0><329><395><725></box><box><320><327><648><679></box><box><519><308><998><654></box><|im_end|>", "sec": 0.16}, "448448": {"text": "<ref>giraffe</ref><box><161><0><998><581></box><box><216><65><998><998></box><|im_end|>", "sec": 0.2}, "80273": {"text": "<ref>person</ref><box><266><106><594><979></box><|im_end|>", "sec": 0.12}, "166166": {"text": "<ref>chair</ref><box><0><325><248><997></box><|im_end|>", "sec": 0.12}, "24919": {"text": "<ref>elephant</ref><box><178><351><530><705></box><box><431><356><812><707></box><|im_end|>", "sec": 0.18}, "325347": {"text": "<ref>chair</ref><box><452><11><569><261></box><box><623><6><739><256></box><|im_end|>", "sec": 0.12}, "108026": {"text": "<ref>person</ref><box><175><0><998><998></box><|im_end|>", "sec": 0.12}, "14007": {"text": "<ref>cat</ref><box><0><70><480><998></box><|im_end|>", "sec": 0.19}, "328683": {"text": "<ref>parking meter</ref><box><344><50><608><934></box><|im_end|>", "sec": 0.15}, "427077": {"text": "<ref>person</ref><box><331><148><794><816></box><|im_end|>", "sec": 0.09}, "73702": {"text": "<ref>handbag</ref><box><625><531><998><898></box><|im_end|>", "sec": 0.12}, "357567": {"text": "<ref>toilet</ref><box><581><577><998><969></box><|im_end|>", "sec": 0.12}, "190756": {"text": "<ref>motorcycle</ref><box><184><256><769><883></box><|im_end|>", "sec": 0.12}, "311909": {"text": "<ref>bus</ref><box><0><94><988><906></box><|im_end|>", "sec": 0.12}, "19221": {"text": "<ref>person</ref><box><377><694><852><998></box><|im_end|>", "sec": 0.12}, "112626": {"text": "<ref>couch</ref><box><624><266><998><730></box><|im_end|>", "sec": 0.12}, "187249": {"text": "<ref>person</ref><box><211><262><589><662></box><box><400><260><716><665></box><|im_end|>", "sec": 0.14}, "267434": {"text": "<ref>cow</ref><box><59><446><214><894></box><box><152><427><398><952></box><box><436><412><559><758></box><box><527><460><638><744></box><box><627><448><716><706></box><box><661><429><770><752></box><box><741><473><816><719></box><box><792><456><998><694></box><|im_end|>", "sec": 0.3}, "422670": {"text": "<ref>person</ref><box><200><129><722><998></box><box><405><267><967><998></box><|im_end|>", "sec": 0.21}, "130566": {"text": "<ref>train</ref><box><28><272><905><738></box><|im_end|>", "sec": 0.12}, "365098": {"text": "<ref>boat</ref><box><70><230><1000><911></box><|im_end|>", "sec": 0.12}, "253386": {"text": "<ref>person</ref><box><0><0><166><997></box><box><614><0><730><186></box><box><830><0><998><997></box><|im_end|>", "sec": 0.22}, "470779": {"text": "<ref>person</ref><box><84><200><275><848></box><box><155><144><475><867></box><box><406><115><625><798></box><box><545><90><703><873></box><box><650><62><844><846></box><|im_end|>", "sec": 0.2}, "335328": {"text": "<ref>person</ref><box><109><520><416><669></box><box><658><344><963><519></box><|im_end|>", "sec": 0.15}, "161397": {"text": "<ref>vase</ref><box><134><580><372><762></box><|im_end|>", "sec": 0.2}, "433980": {"text": "<ref>cell phone</ref><box><208><578><408><852></box><|im_end|>", "sec": 0.12}, "80057": {"text": "<ref>teddy bear</ref><box><0><12><892><652></box><|im_end|>", "sec": 0.12}, "336265": {"text": "<ref>person</ref><box><504><473><569><575></box><|im_end|>", "sec": 0.12}, "133567": {"text": "<ref>train</ref><box><0><198><903><686></box><|im_end|>", "sec": 0.28}, "231549": {"text": "<ref>bed</ref><box><173><731><808><998></box><|im_end|>", "sec": 0.15}, "502336": {"text": "<ref>person</ref><box><181><564><227><693></box><box><216><694><289><911></box><box><223><581><252><691></box><box><264><671><261><911></box><box><267><669><311><911></box><box><302><671><359><911></box><box><478><643><606><969></box><box><948><607><998><887></box><|im_end|>", "sec": 0.42}, "468632": {"text": "<ref>person</ref><box><108><429><300><856></box><box><114><379><280><827></box><box><456><302><653><854></box><box><745><385><908><881></box><|im_end|>", "sec": 0.19}, "156292": {"text": "<ref>clock</ref><box><315><375><637><586></box><|im_end|>", "sec": 0.12}, "115885": {"text": "<ref>cat</ref><box><694><0><998><664></box><|im_end|>", "sec": 0.1}, "581615": {"text": "<ref>toilet</ref><box><299><600><682><998></box><|im_end|>", "sec": 0.13}, "556873": {"text": "<ref>cake</ref><box><239><523><593><816></box><|im_end|>", "sec": 0.12}, "575372": {"text": "<ref>traffic light</ref><box><191><794><238><923></box><box><417><348><472><546></box><box><636><154><705><396></box><box><948><796><998><933></box><|im_end|>", "sec": 0.19}, "394328": {"text": "<ref>toilet</ref><box><327><581><742><998></box><|im_end|>", "sec": 0.13}, "360943": {"text": "<ref>cat</ref><box><394><375><552><439></box><|im_end|>", "sec": 0.13}, "287545": {"text": "<ref>giraffe</ref><box><94><227><641><740></box><box><364><512><483><723></box><|im_end|>", "sec": 0.15}, "194506": {"text": "<ref>bear</ref><box><120><233><470><538></box><box><439><288><647><535></box><|im_end|>", "sec": 0.15}, "107087": {"text": "<ref>cat</ref><box><67><178><405><998></box><|im_end|>", "sec": 0.21}, "263474": {"text": "<ref>toilet</ref><box><38><316><800><977></box><|im_end|>", "sec": 0.13}, "407518": {"text": "<ref>bird</ref><box><583><208><867><888></box><|im_end|>", "sec": 0.12}, "31620": {"text": "<ref>person</ref><box><0><391><175><603></box><box><385><350><562><516></box><box><390><372><796><678></box><|im_end|>", "sec": 0.28}, "398237": {"text": "<ref>kite</ref><box><141><502><398><698></box><box><152><75><389><217></box><box><470><102><619><279></box><box><755><71><841><202></box><|im_end|>", "sec": 0.36}, "509403": {"text": "<ref>person</ref><box><564><138><750><873></box><|im_end|>", "sec": 0.21}, "292456": {"text": "<ref>person</ref><box><260><85><382><725></box><box><356><120><824><931></box><box><628><176><886><901></box><|im_end|>", "sec": 0.14}, "359833": {"text": "<ref>apple</ref><box><0><150><44><209></box><box><0><355><42><464></box><box><0><561><35><661></box><box><0><678><183><836></box><box><0><820><33><889></box><box><0><903><144><998></box><box><2><106><60><153></box><box><4><308><148><405></box><box><6><444><140><559></box><box><15><212><131><284></box><box><23><75><96><112></box><box><27><603><179><695></box><box><38><184><110><225></box><box><46><288><160><347></box><box><56><133><133><180></box><box><62><73><125><109></box><box><92><97><152><134></box><box><100><797><298><953></box><box><108><69><231><105></box><box><117><403><229><469></box><box><119><191><217><250></box><box><123><245><208><297></box><box><123><453><279><566></box><box><129><72><190><116></box><box><135><275><235><345></box><box><138><158><233><228></box><box><146><336><271><427></box><box><154><120><202><103></box><box><156><94><210><122></box><box><175><650><319><770></box><box><177><66><246><102></box><box><196><80><265><111></box><box><204><189><310><244></box><box><206><230><300><127></box><box><215><280><294><322></box><box><223><100><296><141></box><box><227><3><267><22></box><box><242><17><302><98></box><box><248><155><325><211></box><box><254><303><390><389></box><box><262><88><331><128></box><box><269><467><352><525></box><box><273><377><410><477></box><box><277><9><329><50></box><box><281><114><348><161></box><box><292><517><360><575></box><box><294><184><362><236></box><box><298><34><350><78></box><box><304><247><371><295></box><box><315><206><417><258></box><box><321><67><379><105></box><box><327><269><440><330></box><box><333><136><396><181></box><box><338><455><481><544></box><box><342><86><406><130></box><box><346><41><398><77></box><box><354><159><435><216></box><box><365><314><446><366></box><box><369><0><425><28></box><box><375><70><438><147></box><box><385><367><498><459></box><box><388><36><456><166></box><box><404><222><471><256></box><box><408><259><483><305></box><box><419><297><546><380></box><box><423><0><473><39></box><box><429><203><500>", "sec": 3.67}, "261982": {"text": "<ref>car</ref><box><0><16><551><344></box><|im_end|>", "sec": 0.12}, "429761": {"text": "<ref>person</ref><box><297><190><484><904></box><box><455><141><634><835></box><|im_end|>", "sec": 0.14}, "482719": {"text": "<ref>chair</ref><box><372><0><762><300></box><|im_end|>", "sec": 0.21}, "506178": {"text": "<ref>person</ref><box><176><184><803><998></box><|im_end|>", "sec": 0.1}, "131131": {"text": "<ref>tv</ref><box><88><187><876><863></box><|im_end|>", "sec": 0.13}, "68286": {"text": "<ref>bed</ref><box><38><146><858><997></box><|im_end|>", "sec": 0.11}, "67896": {"text": "<ref>clock</ref><box><258><104><756><790></box><|im_end|>", "sec": 0.13}, "297830": {"text": "<ref>dog</ref><box><318><88><919><948></box><|im_end|>", "sec": 0.13}, "398810": {"text": "<ref>cat</ref><box><444><302><998><866></box><|im_end|>", "sec": 0.2}, "569565": {"text": "<ref>truck</ref><box><181><433><706><745></box><|im_end|>", "sec": 0.12}, "161879": {"text": "<ref>person</ref><box><84><0><364><605></box><|im_end|>", "sec": 0.14}, "333069": {"text": "<ref>giraffe</ref><box><222><306><631><908></box><|im_end|>", "sec": 0.12}, "544306": {"text": "<ref>clock</ref><box><534><668><634><806></box><box><716><670><820><807></box><|im_end|>", "sec": 0.16}, "455555": {"text": "<ref>person</ref><box><191><182><716><858></box><box><723><86><978><438></box><|im_end|>", "sec": 0.16}, "377575": {"text": "<ref>dog</ref><box><141><270><642><947></box><|im_end|>", "sec": 0.12}, "157213": {"text": "<ref>elephant</ref><box><436><208><617><619></box><|im_end|>", "sec": 0.1}}}