[{"data":1,"prerenderedAt":669},["ShallowReactive",2],{"node-red-\u002Fnode-red\u002Fflowfuse\u002Fai\u002Fimage-classification":3},{"id":4,"title":5,"body":6,"description":661,"extension":662,"meta":663,"navigation":664,"path":665,"seo":666,"stem":667,"__hash__":668},"nodeRed\u002Fnode-red\u002Fflowfuse\u002Fai\u002Fimage-classification.md","Image Classification",{"type":7,"value":8,"toc":645},"minimark",[9,17,41,56,61,66,105,109,139,148,152,166,170,189,192,196,199,328,333,336,342,375,378,383,436,440,452,456,568,571,585,589,632,636,641],[10,11,13],"h1",{"id":12},"",[14,15],"binding",{"value":16},"meta.title",[18,19,20,21,24,25,28,29,32,33,36,37,40],"p",{},"The ",[22,23,5],"strong",{}," node enables you to classify images using ",[22,26,27],{},"ONNX models"," directly within ",[22,30,31],{},"Node-RED",".\nIt supports both ",[22,34,35],{},"pre-trained"," and ",[22,38,39],{},"custom"," models, allowing you to identify objects, detect scenes, or categorize images without requiring an external AI service.",[18,42,43,44,47,48,51,52,55],{},"This node is ideal for computer vision tasks such as ",[22,45,46],{},"image labeling",", ",[22,49,50],{},"content moderation",", or ",[22,53,54],{},"feature recognition"," at the edge.",[57,58,60],"h2",{"id":59},"inputs","Inputs",[62,63,65],"h3",{"id":64},"general","General",[67,68,69,80,95],"ul",{},[70,71,72,75,76],"li",{},[22,73,74],{},"Property:"," ",[77,78,79],"code",{},"input",[70,81,82,75,85,47,88,47,91,94],{},[22,83,84],{},"Type:",[77,86,87],{},"object",[77,89,90],{},"buffer",[77,92,93],{},"string"," or tensor.",[70,96,97,100,101,104],{},[22,98,99],{},"Description:"," The input image or tensor to classify. See the ",[22,102,103],{},"Details"," section for supported input formats.",[62,106,108],{"id":107},"model-selection","Model Selection",[67,110,111,121],{},[70,112,113,116,117,120],{},[22,114,115],{},"model:"," Path to a local ONNX model file or the name of a model to download from ",[22,118,119],{},"Hugging Face",".",[70,122,123,126,127,130,131,134,135,138],{},[22,124,125],{},"type:"," Data type used when loading the model (only applicable when using a model name). Supported types include ",[77,128,129],{},"q8"," (default, quantized Int8), ",[77,132,133],{},"fp16"," (Float16), ",[77,136,137],{},"fp32"," (Float32), and others.",[140,141,142],"blockquote",{},[18,143,144,147],{},[22,145,146],{},"Note:","\nWhen a model name is provided, the node automatically downloads and caches it locally if it is not already available.",[62,149,151],{"id":150},"configuration","Configuration",[67,153,154,160],{},[70,155,156,159],{},[22,157,158],{},"topK:"," The number of top predictions to return. This can be set manually or passed dynamically via a message property.",[70,161,162,165],{},[22,163,164],{},"threshold:"," Minimum confidence score (0.0–1.0) required for predictions to be included in the output. Predictions below this score are filtered out. This value can also be provided dynamically through a message property.",[57,167,169],{"id":168},"outputs","Outputs",[67,171,172,179,184],{},[70,173,174,75,176],{},[22,175,74],{},[77,177,178],{},"payload",[70,180,181,183],{},[22,182,84],{}," object or array",[70,185,186,188],{},[22,187,99],{}," Contains the classification results returned by the model. The structure of the output depends on the model used.",[57,190,103],{"id":191},"details",[62,193,195],{"id":194},"supported-input-formats","Supported Input Formats",[18,197,198],{},"The node supports multiple input formats depending on the model’s requirements:",[67,200,201,207,213,223],{},[70,202,203,206],{},[22,204,205],{},"Buffer"," — Binary image data, typically from a file or camera input.",[70,208,209,212],{},[22,210,211],{},"Base64 string"," — Base64-encoded image data.",[70,214,215,218,219,222],{},[22,216,217],{},"Jimp Image Object"," — An image object (e.g, output from ",[77,220,221],{},"node-red-contrib-image-tools",").",[70,224,225,228,229],{},[22,226,227],{},"Tensor"," — A pre-processed tensor object in the following format:",[230,231,235],"pre",{"className":232,"code":233,"language":234,"meta":12,"style":12},"language-json shiki shiki-themes github-light github-dark","{\n  \"data\": [0.0, 0.1, 0.2, ...],\n  \"type\": \"float32\",\n  \"dim\": [1, 3, 224, 224]\n}\n","json",[77,236,237,246,278,294,322],{"__ignoreMap":12},[238,239,242],"span",{"class":240,"line":241},"line",1,[238,243,245],{"class":244},"sVt8B","{\n",[238,247,249,253,256,259,261,264,266,269,271,275],{"class":240,"line":248},2,[238,250,252],{"class":251},"sj4cs","  \"data\"",[238,254,255],{"class":244},": [",[238,257,258],{"class":251},"0.0",[238,260,47],{"class":244},[238,262,263],{"class":251},"0.1",[238,265,47],{"class":244},[238,267,268],{"class":251},"0.2",[238,270,47],{"class":244},[238,272,274],{"class":273},"s7hpK","...",[238,276,277],{"class":244},"],\n",[238,279,281,284,287,291],{"class":240,"line":280},3,[238,282,283],{"class":251},"  \"type\"",[238,285,286],{"class":244},": ",[238,288,290],{"class":289},"sZZnC","\"float32\"",[238,292,293],{"class":244},",\n",[238,295,297,300,302,305,307,310,312,315,317,319],{"class":240,"line":296},4,[238,298,299],{"class":251},"  \"dim\"",[238,301,255],{"class":244},[238,303,304],{"class":251},"1",[238,306,47],{"class":244},[238,308,309],{"class":251},"3",[238,311,47],{"class":244},[238,313,314],{"class":251},"224",[238,316,47],{"class":244},[238,318,314],{"class":251},[238,320,321],{"class":244},"]\n",[238,323,325],{"class":240,"line":324},5,[238,326,327],{"class":244},"}\n",[140,329,330],{},[18,331,332],{},"TIP: If the model supports batching, the input can be an array of images in one of the supported formats.",[62,334,108],{"id":335},"model-selection-1",[18,337,20,338,341],{},[22,339,340],{},"model"," property defines which ONNX model to use. You can either:",[67,343,344,355],{},[70,345,346,347,350,351,354],{},"Provide a ",[22,348,349],{},"local path"," (for example, ",[77,352,353],{},"\u002Fdata\u002Fmodels\u002Fresnet50.onnx","), or",[70,356,357,358,361,362,350,370,222],{},"Specify a ",[22,359,360],{},"model name"," available on ",[22,363,364],{},[365,366,119],"a",{"href":367,"rel":368},"https:\u002F\u002Fhuggingface.co\u002Fmodels?pipeline_tag=image-classification&library=transformers.js,onnx&sort=trending",[369],"nofollow",[365,371,374],{"href":372,"rel":373},"https:\u002F\u002Fhuggingface.co\u002Fqualcomm\u002FMobileNet-v3-Large",[369],"MobileNet-v3-Large",[18,376,377],{},"When a model name is used, the node automatically downloads and caches it locally for reuse.",[379,380,382],"h4",{"id":381},"model-type-options","Model Type Options",[67,384,385,391,396,401,407,413,418,424,430],{},[70,386,387,390],{},[77,388,389],{},"auto"," — Automatically selects the most suitable type.",[70,392,393,395],{},[77,394,137],{}," — Standard 32-bit floating-point model.",[70,397,398,400],{},[77,399,133],{}," — Half-precision 16-bit floating-point model.",[70,402,403,406],{},[77,404,405],{},"int8"," — 8-bit integer quantized model.",[70,408,409,412],{},[77,410,411],{},"uint8"," — 8-bit unsigned integer model.",[70,414,415,417],{},[77,416,129],{}," — Quantized Int8 model (default).",[70,419,420,423],{},[77,421,422],{},"q4"," — Quantized Int4 model.",[70,425,426,429],{},[77,427,428],{},"q4f16"," — Quantized Int4 with Float16 model.",[70,431,432,435],{},[77,433,434],{},"bnb4"," — BNB4 quantized model.",[62,437,439],{"id":438},"configuration-options","Configuration Options",[67,441,442,447],{},[70,443,444,446],{},[22,445,158],{}," Defines how many top predictions to return in the output. Use this to limit results to the most relevant classes.",[70,448,449,451],{},[22,450,164],{}," Filters predictions by their confidence score. Only predictions above the threshold are included.",[57,453,455],{"id":454},"example-output","Example Output",[230,457,459],{"className":232,"code":458,"language":234,"meta":12,"style":12},"[\n  {\n    \"label\": \"golden retriever\",\n    \"score\": 0.9812\n  },\n  {\n    \"label\": \"labrador retriever\",\n    \"score\": 0.0143\n  },\n  {\n    \"label\": \"cocker spaniel\",\n    \"score\": 0.0021\n  }\n]\n",[77,460,461,466,471,483,493,498,503,515,525,530,535,547,557,563],{"__ignoreMap":12},[238,462,463],{"class":240,"line":241},[238,464,465],{"class":244},"[\n",[238,467,468],{"class":240,"line":248},[238,469,470],{"class":244},"  {\n",[238,472,473,476,478,481],{"class":240,"line":280},[238,474,475],{"class":251},"    \"label\"",[238,477,286],{"class":244},[238,479,480],{"class":289},"\"golden retriever\"",[238,482,293],{"class":244},[238,484,485,488,490],{"class":240,"line":296},[238,486,487],{"class":251},"    \"score\"",[238,489,286],{"class":244},[238,491,492],{"class":251},"0.9812\n",[238,494,495],{"class":240,"line":324},[238,496,497],{"class":244},"  },\n",[238,499,501],{"class":240,"line":500},6,[238,502,470],{"class":244},[238,504,506,508,510,513],{"class":240,"line":505},7,[238,507,475],{"class":251},[238,509,286],{"class":244},[238,511,512],{"class":289},"\"labrador retriever\"",[238,514,293],{"class":244},[238,516,518,520,522],{"class":240,"line":517},8,[238,519,487],{"class":251},[238,521,286],{"class":244},[238,523,524],{"class":251},"0.0143\n",[238,526,528],{"class":240,"line":527},9,[238,529,497],{"class":244},[238,531,533],{"class":240,"line":532},10,[238,534,470],{"class":244},[238,536,538,540,542,545],{"class":240,"line":537},11,[238,539,475],{"class":251},[238,541,286],{"class":244},[238,543,544],{"class":289},"\"cocker spaniel\"",[238,546,293],{"class":244},[238,548,550,552,554],{"class":240,"line":549},12,[238,551,487],{"class":251},[238,553,286],{"class":244},[238,555,556],{"class":251},"0.0021\n",[238,558,560],{"class":240,"line":559},13,[238,561,562],{"class":244},"  }\n",[238,564,566],{"class":240,"line":565},14,[238,567,321],{"class":244},[18,569,570],{},"Each object in the output array includes:",[67,572,573,579],{},[70,574,575,578],{},[22,576,577],{},"label:"," The predicted class name.",[70,580,581,584],{},[22,582,583],{},"score:"," The confidence score for that prediction.",[57,586,588],{"id":587},"notes","Notes",[67,590,591,607,619,629],{},[70,592,593,594,597,598,47,601,51,604,120],{},"The node supports any ",[22,595,596],{},"ONNX-compatible image classification model",", such as ",[22,599,600],{},"ResNet",[22,602,603],{},"MobileNet",[22,605,606],{},"Vision Transformer (ViT)",[70,608,609,610,47,612,614,615,618],{},"Quantized models (",[77,611,129],{},[77,613,405],{},") are recommended for ",[22,616,617],{},"edge deployments"," due to improved performance and lower memory usage.",[70,620,621,622,625,626,120],{},"Ensure that your ONNX model is trained for ",[22,623,624],{},"image classification"," and compatible with ",[22,627,628],{},"ONNX Runtime",[70,630,631],{},"When using a Hugging Face model name, ensure network connectivity during the first run so that the model can be downloaded and cached locally.",[57,633,635],{"id":634},"example-flow","Example Flow",[637,638],"render-flow",{":height":639,"flow":640},"400","[{"id":"80afcb4f0920c6ce","type":"http request","z":"e1ceeedf31ce1ebd","name":"","method":"GET","ret":"bin","paytoqs":"ignore","url":"","tls":"","persist":false,"proxy":"","insecureHTTPParser":false,"authType":"","senderr":false,"headers":[],"x":670,"y":3160,"wires":[["cef35d49d8f7e529"]]},{"id":"cef35d49d8f7e529","type":"change","z":"e1ceeedf31ce1ebd","name":"topK 3, thres: 5%","rules":[{"t":"move","p":"payload","pt":"msg","to":"image","tot":"msg"},{"t":"set","p":"topK","pt":"msg","to":"3","tot":"num"},{"t":"set","p":"thres","pt":"msg","to":"0.05","tot":"num"}],"action":"","property":"","from":"","to":"","reg":false,"x":850,"y":3160,"wires":[["d76d57912ca9fd3f"]]},{"id":"d76d57912ca9fd3f","type":"image viewer","z":"e1ceeedf31ce1ebd","name":"","width":"224","data":"image","dataType":"msg","active":true,"x":1010,"y":3160,"wires":[["903b8d0c4750e324"]]},{"id":"fb880704ba86d144","type":"debug","z":"e1ceeedf31ce1ebd","name":"class","active":true,"tosidebar":true,"console":false,"tostatus":true,"complete":"payload","targetType":"msg","statusVal":"payload[0].label & \"(\" & $round(payload[0].score * 100,2)  & \"%)\"","statusType":"jsonata","x":870,"y":3220,"wires":[]},{"id":"a8e34856bea9f3cd","type":"image-classification","z":"e1ceeedf31ce1ebd","name":"","property":"images","propertyType":"msg","model":"onnx-community/resnet-50-ONNX","modelType":"name","dtype":"fp16","topK":"1","topKType":"num","threshold":"0.1","thresholdType":"num","x":1080,"y":3800,"wires":[["7bd09a7daa0d5dae","0b07230327b5689c"]]},{"id":"903b8d0c4750e324","type":"image-classification","z":"e1ceeedf31ce1ebd","name":"","property":"image","propertyType":"msg","model":"Xenova/vit-base-patch16-224","modelType":"name","dtype":"q8","topK":"topK","topKType":"msg","threshold":"thres","thresholdType":"msg","x":700,"y":3220,"wires":[["fb880704ba86d144"]]},{"id":"e21197eababa2618","type":"image viewer","z":"e1ceeedf31ce1ebd","name":"images[0]","width":"224","data":"images[0]","dataType":"msg","active":true,"x":660,"y":3800,"wires":[["d2b756bb0a700a0e"]]},{"id":"d2b756bb0a700a0e","type":"image viewer","z":"e1ceeedf31ce1ebd","name":"images[1]","width":"224","data":"images[1]","dataType":"msg","active":true,"x":860,"y":3800,"wires":[["a8e34856bea9f3cd"]]},{"id":"b5768dffc25bf899","type":"inject","z":"e1ceeedf31ce1ebd","name":"beer","props":[{"p":"url","v":"https://stoelzle-lausitz.com/cdn/shop/files/stoelzle-lausitz-bierglaeser-glass-mug-full-beer-foam.png","vt":"str"}],"repeat":"","crontab":"","once":false,"onceDelay":0.1,"topic":"","x":450,"y":3200,"wires":[["49f8de9173d09a2f"]]},{"id":"0ff2faa6328f5e8c","type":"inject","z":"e1ceeedf31ce1ebd","name":"wolf","props":[{"p":"url","v":"https://upload.wikimedia.org/wikipedia/commons/thumb/6/68/Eurasian_wolf_2.jpg/1920px-Eurasian_wolf_2.jpg","vt":"str"}],"repeat":"","crontab":"","once":false,"onceDelay":0.1,"topic":"","x":450,"y":3160,"wires":[["49f8de9173d09a2f"]]},{"id":"5833b4f0c1928af6","type":"inject","z":"e1ceeedf31ce1ebd","name":"owl","props":[{"p":"url","v":"https://upload.wikimedia.org/wikipedia/commons/thumb/5/56/Bubo_bubo_sibiricus_-_01.JPG/1024px-Bubo_bubo_sibiricus_-_01.JPG","vt":"str"}],"repeat":"","crontab":"","once":false,"onceDelay":0.1,"topic":"","x":450,"y":3240,"wires":[["49f8de9173d09a2f"]]},{"id":"7bd09a7daa0d5dae","type":"debug","z":"e1ceeedf31ce1ebd","name":"class","active":true,"tosidebar":true,"console":false,"tostatus":true,"complete":"true","targetType":"full","statusVal":"payload[0][0].label & \"(\" & $round(payload[0][0].score * 100,2)  & \"%)\"","statusType":"jsonata","x":1270,"y":3760,"wires":[]},{"id":"0b07230327b5689c","type":"debug","z":"e1ceeedf31ce1ebd","name":"class","active":true,"tosidebar":false,"console":false,"tostatus":true,"complete":"payload","targetType":"msg","statusVal":"payload[1][0].label & \"(\" & $round(payload[1][0].score * 100,2)  & \"%)\"","statusType":"jsonata","x":1270,"y":3820,"wires":[]},{"id":"c799ffb88823e69c","type":"comment","z":"e1ceeedf31ce1ebd","name":"Image Classification","info":"","x":470,"y":3060,"wires":[]},{"id":"99eb75b743ba98ea","type":"comment","z":"e1ceeedf31ce1ebd","name":"Batch Image Classification","info":"","x":510,"y":3700,"wires":[]},{"id":"55506dfb9dc40daf","type":"change","z":"e1ceeedf31ce1ebd","name":"move payload images array","rules":[{"t":"set","p":"images","pt":"msg","to":"[]","tot":"json"},{"t":"move","p":"payload","pt":"msg","to":"images[0]","tot":"msg"},{"t":"set","p":"url","pt":"msg","to":"urls[1]","tot":"msg"}],"action":"","property":"","from":"","to":"","reg":false,"x":775,"y":3740,"wires":[["2b8af48bb3f824bc"]],"l":false},{"id":"c9b1c4ff34ec7d02","type":"change","z":"e1ceeedf31ce1ebd","name":"move payload images array","rules":[{"t":"move","p":"payload","pt":"msg","to":"images[1]","tot":"msg"}],"action":"","property":"","from":"","to":"","reg":false,"x":995,"y":3740,"wires":[["e21197eababa2618"]],"l":false},{"id":"c7c8d609c2bfaffc","type":"inject","z":"e1ceeedf31ce1ebd","name":"wolf+clock","props":[{"p":"urls","v":"[]","vt":"json"},{"p":"urls[0]","v":"https://upload.wikimedia.org/wikipedia/commons/thumb/6/68/Eurasian_wolf_2.jpg/1920px-Eurasian_wolf_2.jpg","vt":"str"},{"p":"urls[1]","v":"https://upload.wikimedia.org/wikipedia/commons/thumb/c/cf/Pendulum_clock_by_Jacob_Kock%2C_antique_furniture_photography%2C_IMG_0931_edit.jpg/250px-Pendulum_clock_by_Jacob_Kock%2C_antique_furniture_photography%2C_IMG_0931_edit.jpg","vt":"str"},{"p":"url","v":"urls[0]","vt":"msg"},{"p":"preprocessorConfigOverrides","v":"{\"size\": {\"width\":224, \"height\":224}}","vt":"json"}],"repeat":"","crontab":"","once":false,"onceDelay":0.1,"topic":"","x":460,"y":3740,"wires":[["2dd6833f25e7a905"]]},{"id":"2dd6833f25e7a905","type":"http request","z":"e1ceeedf31ce1ebd","name":"","method":"GET","ret":"bin","paytoqs":"ignore","url":"","tls":"","persist":false,"proxy":"","insecureHTTPParser":false,"authType":"","senderr":false,"headers":[],"x":670,"y":3740,"wires":[["55506dfb9dc40daf"]]},{"id":"2b8af48bb3f824bc","type":"http request","z":"e1ceeedf31ce1ebd","name":"","method":"GET","ret":"bin","paytoqs":"ignore","url":"","tls":"","persist":false,"proxy":"","insecureHTTPParser":false,"authType":"","senderr":false,"headers":[],"x":890,"y":3740,"wires":[["c9b1c4ff34ec7d02"]]},{"id":"79f068f1e84fdef2","type":"inject","z":"e1ceeedf31ce1ebd","name":"","props":[{"p":"topic","vt":"str"}],"repeat":"","crontab":"","once":false,"onceDelay":0.1,"topic":"","x":450,"y":3480,"wires":[["c7b482660e93f645"]]},{"id":"c7b482660e93f645","type":"file in","z":"e1ceeedf31ce1ebd","name":"","filename":"dog.jpg","filenameType":"str","format":"","chunk":false,"sendError":false,"encoding":"none","allProps":false,"x":660,"y":3480,"wires":[["64b15839a5d33ad4"]]},{"id":"70d9f015166b7f63","type":"comment","z":"e1ceeedf31ce1ebd","name":"Auto preprocessing: Using Image as input","info":"","x":560,"y":3120,"wires":[]},{"id":"0c1b6f94772cf829","type":"inject","z":"e1ceeedf31ce1ebd","name":"plane","props":[{"p":"url","v":"https://upload.wikimedia.org/wikipedia/commons/e/eb/British_Airways_Concorde_G-BOAC_03.jpg","vt":"str"}],"repeat":"","crontab":"","once":false,"onceDelay":0.1,"topic":"","x":450,"y":3280,"wires":[["49f8de9173d09a2f"]]},{"id":"584b4e035f0e91dd","type":"comment","z":"e1ceeedf31ce1ebd","name":"Auto preprocessing: Using local file Image as input. \\n NOTE: You will need to add a dog.jpg image to test this","info":"","x":600,"y":3420,"wires":[]},{"id":"25a103fa3e5ced6e","type":"image-classification","z":"e1ceeedf31ce1ebd","name":"","property":"payload","propertyType":"msg","model":"onnx-community/resnet-50-ONNX","modelType":"name","dtype":"fp16","topK":"1","topKType":"num","threshold":"0.5","thresholdType":"num","x":700,"y":3540,"wires":[["7af6dd11b8160481"]]},{"id":"7af6dd11b8160481","type":"debug","z":"e1ceeedf31ce1ebd","name":"class","active":true,"tosidebar":true,"console":false,"tostatus":true,"complete":"payload","targetType":"msg","statusVal":"payload[0].label & \"(\" & $round(payload[0].score * 100,2)  & \"%)\"","statusType":"jsonata","x":870,"y":3540,"wires":[]},{"id":"64b15839a5d33ad4","type":"image viewer","z":"e1ceeedf31ce1ebd","name":"","width":"180","data":"payload","dataType":"msg","active":true,"x":1010,"y":3480,"wires":[["25a103fa3e5ced6e"]]},{"id":"49f8de9173d09a2f","type":"junction","z":"e1ceeedf31ce1ebd","x":560,"y":3160,"wires":[["80afcb4f0920c6ce"]]},{"id":"1012c4c8ef915cdd","type":"global-config","env":[],"modules":{"node-red-contrib-image-tools":"2.1.1","@flowfuse-nodes/nr-ai-nodes":"0.1.6","@flowfuse/nr-file-nodes":"0.0.8"}}]",[642,643,644],"style",{},"html pre.shiki code .sVt8B, html code.shiki .sVt8B{--shiki-default:#24292E;--shiki-dark:#E1E4E8}html pre.shiki code .sj4cs, html code.shiki .sj4cs{--shiki-default:#005CC5;--shiki-dark:#79B8FF}html pre.shiki code .s7hpK, html code.shiki .s7hpK{--shiki-default:#B31D28;--shiki-default-font-style:italic;--shiki-dark:#FDAEB7;--shiki-dark-font-style:italic}html pre.shiki code .sZZnC, html code.shiki .sZZnC{--shiki-default:#032F62;--shiki-dark:#9ECBFF}html .default .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .dark .shiki span {color: var(--shiki-dark);background: var(--shiki-dark-bg);font-style: var(--shiki-dark-font-style);font-weight: var(--shiki-dark-font-weight);text-decoration: var(--shiki-dark-text-decoration);}html.dark .shiki span {color: var(--shiki-dark);background: var(--shiki-dark-bg);font-style: var(--shiki-dark-font-style);font-weight: var(--shiki-dark-font-weight);text-decoration: var(--shiki-dark-text-decoration);}",{"title":12,"searchDepth":248,"depth":248,"links":646},[647,652,653,658,659,660],{"id":59,"depth":248,"text":60,"children":648},[649,650,651],{"id":64,"depth":280,"text":65},{"id":107,"depth":280,"text":108},{"id":150,"depth":280,"text":151},{"id":168,"depth":248,"text":169},{"id":191,"depth":248,"text":103,"children":654},[655,656,657],{"id":194,"depth":280,"text":195},{"id":335,"depth":280,"text":108},{"id":438,"depth":280,"text":439},{"id":454,"depth":248,"text":455},{"id":587,"depth":248,"text":588},{"id":634,"depth":248,"text":635},"Classify images using ONNX models directly in Node-RED. Supports pre-trained and custom models for tasks like labeling, content moderation, and object recognition.","md",{},true,"\u002Fnode-red\u002Fflowfuse\u002Fai\u002Fimage-classification",{"title":5,"description":661},"node-red\u002Fflowfuse\u002Fai\u002Fimage-classification","vnqPc0TA9-c_VhKI-zjHH3UlJURNFRVhtGIMk-Vv0Aw",1780070556763]