• Topshiriqni baholash. MAX 5 ball.
  • Chuqur o‘qitish algoritmlari asosida masalalar yechish




    Download 52.42 Kb.
    Sana22.12.2023
    Hajmi52.42 Kb.
    #127101
    Bog'liq
    oksidlanish-va-qaytarilish-reaksiyalari, 01-10-1254, Kamron elektironika, 13.Бланк ответов на тест, 2-ma\'ruza, SaidAziz, hs fast food powerpoint 7 29 11 (1), 1702997833, Кратные интегралы

    6-Topshiriq
    Chuqur o‘qitish algoritmlari asosida masalalar yechish
    Ishdan maqsad. Talabalar neyron tarmog‘i, ularning ishlash prinsiplari, ishlash texnologiyalarini o‘rganish, ular asosida chuqur o‘qitish algoritmlari asosida neyron tarmog‘ini ishlab chiqish.
    Vazifalar:

    1. Chuqur o‘qitish algoritmlarini o‘rganish

    2. chuqur o‘qitish algoritmlari asosida neyron tarmog‘ini ishlab Topshiriqni baholash. MAX 5 ball.

    1. Berilgan topshiriqqa optimal yondoshish – 2 ball;

    2. Xulosa va foydalangan adabiyotlarni yoritilganlik – 1 ball;

    3. Topshiriqni himoya qilish – 2 ball.

    import torch
    import torch.nn as nn
    import torch.optim as optim
    from torch.utils.data import Dataset, DataLoader
    class UyHayvonlarDataset(Dataset):
    def __init__(self, data_path):
    self.data = torch.tensor(data_path, dtype=torch.float32)
    def __len__(self):
    return len(self.data)
    def __getitem__(self, idx):
    sample = self.data[idx, :-1]
    label = int(self.data[idx, -1])
    return sample, label
    class UyHayvonlarModel(nn.Module):
    def __init__(self, input_size, hidden_size, output_size):
    super(UyHayvonlarModel, self).__init__()
    self.fc1 = nn.Linear(input_size, hidden_size)
    self.relu = nn.ReLU()
    self.fc2 = nn.Linear(hidden_size, output_size)
    def forward(self, x):
    x = self.fc1(x)
    x = self.relu(x)
    x = self.fc2(x)
    return x
    def train(model, dataloader, criterion, optimizer, num_epochs=1000):
    for epoch in range(num_epochs):
    for inputs, labels in dataloader:
    outputs = model(inputs)
    loss = criterion(outputs, labels)
    optimizer.zero_grad()
    loss.backward()
    optimizer.step()
    if (epoch + 1) % 100 == 0:
    print(f'Epoch [{epoch+1}/{num_epochs}], Loss: {loss.item():.4f}')
    data_path = [
    [200, 150, 350, 0],
    [205, 165, 340, 0],
    [210, 160, 330, 0],
    [110, 100, 50, 1],
    [100, 90, 40, 1],
    [90, 90, 40, 1],
    [40, 35, 10, 2],
    [35, 35, 9, 2],
    [30, 25, 7, 2],

    ]
    dataset = UyHayvonlarDataset(data_path)


    dataloader = DataLoader(dataset, batch_size=8, shuffle=True)
    input_size = 3 # Uzunlik, balandlik, og'irlik
    hidden_size = 16
    output_size = 3
    model = UyHayvonlarModel(input_size, hidden_size, output_size)
    criterion = nn.CrossEntropyLoss()
    optimizer = optim.SGD(model.parameters(), lr=0.01)
    train(model, dataloader, criterion, optimizer, num_epochs=1000)
    with torch.no_grad():
    test_data = torch.tensor([[210,170,395]], dtype=torch.float32)
    predicted_class = torch.argmax(model(test_data))
    print(f'Predicted Class: {predicted_class.item()}')



    Download 52.42 Kb.




    Download 52.42 Kb.

    Bosh sahifa
    Aloqalar

        Bosh sahifa



    Chuqur o‘qitish algoritmlari asosida masalalar yechish

    Download 52.42 Kb.