2-misol: o‘qitish
O‘qitish funksiyasi
async function trainModel(model, inputs, labels, surface) {
const batchSize = 25;
const epochs = 100;
const callbacks = tfvis.show.fitCallbacks(surface, ['loss'], {callbacks:['onEpochEnd']})
return await model.fit(inputs, labels,
{batchSize, epochs, shuffle:true, callbacks:callbacks}
);
}
epochs model nechta iteratsiya (sikl) bajarishini belgilaydi.
model.fit — sikllarni ishga tushiruvchi funksiya.
callbacks model grafikani qayta chizmoqchi bo‘lganda chaqiriladigan callback funksiyasini belgilaydi.
Modelni testlash
Model o‘qitilgandan so‘ng uni testlash va baholash muhim.
Buni model turli kirish qiymatlari oralig‘i uchun nimani bashorat qilishini tekshirish orqali amalga oshiramiz.
Ammo buni qilishdan oldin ma’lumotlarni normallashtirilgan holatdan qaytarishimiz (un-normalize) kerak:
Normallashtirishni bekor qilish
let unX = tf.linspace(0, 1, 100);
let unY = model.predict(unX.reshape([100, 1]));
const unNormunX = unX.mul(inputMax.sub(inputMin)).add(inputMin);
const unNormunY = unY.mul(labelMax.sub(labelMin)).add(labelMin);
unX = unNormunX.dataSync();
unY = unNormunY.dataSync();
So‘ngra natijani ko‘rib chiqishimiz mumkin:
Natijani grafikda tasvirlash
const predicted = Array.from(unX).map((val, i) => {
return {x: val, y: unY[i]}
});
// Plot the Result
tfPlot([values, predicted], surface1)
W3Schools Pathfinder
Yutuqlaringizni kuzating – bu bepul!