• Dataset yaratish va tasvirlash
  • Tensorflow kutubxonasidan foydalanib neyron arxitekturasini qurish
  • Amaliy ish fan: Mashinali Oqitish Tayyorladi: Quvonch Toshtemirov




    Download 206,45 Kb.
    Sana27.05.2024
    Hajmi206,45 Kb.
    #255185
    Bog'liq
    4-amaliy



    MUHAMMAD AL-XORAZMIY NOMIDAGI TOSHKENT AXBOROT TEXNOLOGIYALARI UNIVERSITETI NURAFSHON FILIALI
    Kompyuter Injiniring Fakulteti
    3-kurs 210-21 gurux talabasi


    AMALIY ISH

    Fan:Mashinali Oqitish
    Tayyorladi: Quvonch Toshtemirov


    TOSHKENT-2023

    Dataset yaratish va tasvirlash:
    import matplotlib.pyplot as plt
    import random

    # Ixtiyoriy dataset yaratish


    random.seed(42)
    data_points = 50
    feature1 = [random.uniform(0, 10) for _ in range(data_points)]
    feature2 = [random.uniform(0, 10) for _ in range(data_points)]

    # Datasetni tasvirlash


    plt.scatter(feature1, feature2, color='blue', label='Dataset')

    # Grafikni tuzish


    plt.title('Ixtiyoriy Dataset Xususiyatlari')
    plt.xlabel('Xususiyat 1')
    plt.ylabel('Xususiyat 2')
    plt.legend()
    plt.grid(True)

    # Grafikni ko'rsatish


    plt.show()


    Tensorflow kutubxonasidan foydalanib neyron arxitekturasini qurish
    import tensorflow as tf
    import matplotlib.pyplot as plt
    import pandas as pd
    import numpy as np

    # Ixtiyoriy dataset yaratish


    np.random.seed(42)
    data_points = 50
    feature1 = np.random.uniform(0, 10, data_points)
    feature2 = np.random.uniform(0, 10, data_points)

    # Datasetni tasvirlash


    plt.scatter(feature1, feature2, color='blue', label='Dataset')
    plt.title('Ixtiyoriy Dataset Xususiyatlari')
    plt.xlabel('Xususiyat 1')
    plt.ylabel('Xususiyat 2')
    plt.legend()
    plt.grid(True)
    plt.show()

    # Neyron tarmoq arxitekturasi


    model = tf.keras.Sequential([
    tf.keras.layers.Dense(64, activation='relu', input_shape=(2,)),
    tf.keras.layers.Dense(64, activation='relu'),
    tf.keras.layers.Dense(1)
    ])

    # O'qitish parametrlarini tanlash


    model.compile(optimizer=tf.keras.optimizers.Adam(learning_rate=0.001),
    loss='mse',
    metrics=['mae'])

    # Tarmoqni o'qitish


    train_data = np.column_stack((feature1, feature2)) # Datasetni tayyorlash
    train_labels = np.random.rand(data_points, 1) # Natijalarni boshlash uchun tasodifiy generatsiya
    history = model.fit(train_data, train_labels, epochs=100, validation_split=0.2, verbose=0)

    # Natijalarni visual ko'rsatish


    train_loss = history.history['loss']
    val_loss = history.history['val_loss']
    epochs = range(1, len(train_loss) + 1)

    plt.plot(epochs, train_loss, 'bo', label='Train loss')


    plt.plot(epochs, val_loss, 'b', label='Validation loss')
    plt.title('O\'rtacha Sinov Tarmoqning O\'qitish Jarayoni')
    plt.xlabel('Epochs')
    plt.ylabel('Loss')
    plt.legend()
    plt.show()

    # Natijalarni jadvalga joylash


    results = pd.DataFrame({'Epoch': epochs, 'Train Loss': train_loss, 'Validation Loss': val_loss})
    print(results)
    Download 206,45 Kb.




    Download 206,45 Kb.

    Bosh sahifa
    Aloqalar

        Bosh sahifa



    Amaliy ish fan: Mashinali Oqitish Tayyorladi: Quvonch Toshtemirov

    Download 206,45 Kb.