|
Rasa yordamida avtomatlashtirilgan chatbot
| | bet | 32/182 | | Sana | 19.05.2024 | | Hajmi | 5,69 Mb. | | #244351 |
Bog'liq Python sun\'iy intellekt texnologiyasi Dasrlik 2024Rasa yordamida avtomatlashtirilgan chatbot:
Rasa-ni o‘rnatish:
pip install rasa
Loyihani boshlash:
rasa init --no-prompt
Dialog faylini yaratish (domen.yml) va modelni o‘qitish:
rasa train
Chatbotni ishga tushirish:
rasa shell
Dialog fayliga misol (domen.yml):
intents:
- greet
- goodbye
- inform
responses:
utter_greet:
- text: " Salom! Sizga qanday yordam bera olaman?"
utter_goodbye:
- text: " Xayr! Agar sizda ko‘proq savollar bo‘lsa, so‘rang."
utter_default:
- text: " Kechirasiz, men to‘liq tushunmayapman. Siz aniqlik kiritishingiz mumkin?"
Namunaviy o‘quv fayli (data / nlu.yml):
nlu:
- intent: greet
examples: |
- Salom
- Salom
- Xayrli kun- intent: goodbye
examples: |
- Hozircha
- Xayr
- Xayr
- intent: inform
examples: |
- Menga yordam kerak
- Men ma’lumot izlayapman
- Menda muammo bor
Bu ilovalarning funksionalligini yaxshilash uchun Python-da Mashinali o‘qitishdan foydalanishning asosiy misollari. Albatta, har bir alohida holat loyiha talablari va vazifalariga muvofiq kodni moslashtirishni talab qiladi.
Python-da kod namunalari bilan dasturlarning ishlashini yaxshilash uchun Mashinali o‘qitishdan foydalanishning ba’zi misollari:
Tasvirlardagi ob’ektlarni avtomatik aniqlash:
Vazifa: fotosuratlardagi ob’ektlarni avtomatik ravishda tanib olish uchun funktsiyalarni ishlab chiqish.
Amaldagi kutubxona: Tensorflow oldindan o‘qitilgan MobileNet modeli bilan.
import tensorflow as tf
from tensorflow.keras.applications.mobilenet import MobileNet, preprocess_input, decode_predictions
from tensorflow.keras.preprocessing import image
import numpy as np
# Oldindan o‘qitilgan Mobile Net modelini yuklab olish
model = MobileNet(weights='imagenet’)
def predict_object(image_path):
img = image.load_img(image_path, target_size=(224, 224))
img_array = image.img_to_array(img)
img_array = np.expand_dims(img_array, axis=0)
img_array = preprocess_input(img_array)
predictions = model.predict(img_array)
decoded_predictions = decode_predictions(predictions, top=3)[0]
return decoded_predictions
# Foydalanish misoli
image_path = 'path/to/your/image.jpg’
predictions = predict_object(image_path)
print(predictions)
|
| |
