23:null 24:["$","title",null,{"children":"เริ่มใช้งาน Machine Learning บนเว็บด้วย TensorFlow.js | \"Ta\" Virot C. | Observable"}] 29:T400,{ const score = []; let tbody = ''; for (let i = 0; i < sentences.length; i++) { tbody += `${i+1}`; const s = []; for (let j = 0; j < i; j++) { s.push(score[j][i]); tbody += `${score[j][i].toFixed(2)}`; } for (let j = i; j < sentences.length; j++) { const embI = embeddings.slice([i,0],[1]); const embJ = embeddings.slice([j,0],[1]); // Cosine Similarity s.push(embI.matMul(embJ, false, true).dataSync()[0]); // Euclidean Distance // s.push(embJ.sub(embI).norm('euclidean').dataSync()[0]); tbody += `${s[j].toFixed(2)}`; } score.push(s); tbody += ''; } return html` ${tbody}

sentence	1	2	3	4	5

` }2a:[] 27:{"id":"e12fbb8720a11744","slug":"machine-learning-tensorflow-js/2","title":"เริ่มใช้งาน Machine Learning บนเว็บด้วย TensorFlow.js","thumbnail":"a589d51e99bec28f07cc95ce1a17443fe285c7ee424d4858ea24611083b96ab4","access_level":"public","create_time":"$D2021-01-15T16:29:28.333Z","update_time":"$D2021-01-15T16:29:28.333Z","view_time":null,"first_public_time":"$D2021-01-15T16:29:41.208Z","has_unpublished_edits":null,"fork":{"id":"b389754a48c30d89","slug":"machine-learning-tensorflow-js","title":"เริ่มใช้งาน Machine Learning บนเว็บด้วย TensorFlow.js","owner":{"id":"05fe87ce00c24684","login":"tvirot","name":"\"Ta\" Virot C."}},"stars":0,"starred":false,"owner":{"type":"team","id":"05fe87ce00c24684","login":"tvirot","name":"\"Ta\" Virot C.","avatar_url":"https://avatars-next.observableusercontent.com/a2b53d057ac064ea2a178f61376d79ebffd11284cadbef50588e520a74a730b2","tier":"starter_2024"},"version":530,"publish_version":530,"role":null,"authored":false,"authors":[{"type":"individual","id":"679d00b8a8620131","login":"tvirot","name":"\"Ta\" Virot C.","avatar_url":"https://avatars-next.observableusercontent.com/a2b53d057ac064ea2a178f61376d79ebffd11284cadbef50588e520a74a730b2","tier":null}],"members":[{"type":"individual","id":"679d00b8a8620131","login":"tvirot","name":"\"Ta\" Virot C.","avatar_url":"https://avatars-next.observableusercontent.com/a2b53d057ac064ea2a178f61376d79ebffd11284cadbef50588e520a74a730b2","tier":null,"role":"editor"}],"comments":[],"custom_thumbnail":false,"trashed":false,"lapsed":null,"subscribed":null,"forks":0,"collection":null,"type":"notebook","body":{"titling":"auto","title":"เริ่มใช้งาน Machine Learning บนเว็บด้วย TensorFlow.js","cells":[{"id":11,"value":"md`# เริ่มใช้งาน Machine Learning บนเว็บด้วย TensorFlow.js\n\nใน Notebook นี้เราจะมาลองดูตัวอย่างการนำโมเดล Machine Learning สำเร็จรูป (Pre-Trained Models) จาก TensorFlow.js มาใช้งานบนเว็บกัน ใครที่ขี้เกียจอ่าน สามารถชมวีดีโอประกอบได้ที่ [Skooldio Tutorials](https://tutorials.skooldio.com/content/machine-learning-with-tensorflowjs)\n`","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":40,"value":"md`## 1. Image Classification\nในตัวอย่างแรกเราจะมาลองทำนายวัตถุในรูปภาพด้วย [MobileNet](https://github.com/tensorflow/tfjs-models/tree/master/mobilenet) ซึ่งเป็นโมเดล Deep Learning สำหรับรูปภาพที่มีขนาดไฟล์เล็กและประมวลผลได้ไว จึงมักถูกนำมาใช้งานบนเว็บหรืออุปกรณ์พกพาต่างๆ \n\nเริ่มจากการ import npm module [@tensorflow-models/mobilenet](https://www.npmjs.com/package/@tensorflow-models/mobilenet) กันก่อน\n`","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":49,"value":"mobilenet = require('@tensorflow-models/mobilenet@1.0.0');","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":238,"value":"md`หรือจะ import โดยการใส่ script tag ใน HTML ก็ได้ \n\n\\`\\`\\`\n\n\n\n\\`\\`\\`\n`","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":189,"value":"md`จากนั้นก็ทำการโหลดโมเดล ด้วยคำสั่ง [\\`load()\\`](https://github.com/tensorflow/tfjs-models/tree/master/mobilenet#loading-the-model)`","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":191,"value":"img_classifier = mobilenet.load();","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":215,"value":"md`เมื่อได้โมเดลมาพร้อมแล้ว การใช้งานก็สุดแสนจะง่ายดาย เพียงเรียกใช้คำสั่ง [\\`classify(img)\\`](https://github.com/tensorflow/tfjs-models/tree/master/mobilenet#making-a-classification) โดย \\`img\\` นั้นจะเป็นรูปภาพที่มาจาก \\`\\` \\`