כתיבת VGG מאפס ב-PyTorch

import numpy as np
import torch
import torch.nn as nn
from torchvision import datasets
from torchvision import transforms
from torch.utils.data.sampler import SubsetRandomSampler


# הגדרת המכשיר
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')

def data_loader(data_dir,
                batch_size,
                random_seed=42,
                valid_size=0.1,
                shuffle=True,
                test=False):
  
    normalize = transforms.Normalize(
        mean=[0.4914, 0.4822, 0.4465],
        std=[0.2023, 0.1994, 0.2010],
    )

    הגדרות ממערכת מסויימת
    transform = transforms.Compose([
            transforms.Resize((227,227)),
            transforms.ToTensor(),
            normalize,
    ])

    if test:
        dataset = datasets.CIFAR100(
          root=data_dir, train=False,
          download=True, transform=transform,
        )

        data_loader = torch.utils.data.DataLoader(
            dataset, batch_size=batch_size, shuffle=shuffle
        )

        return data_loader

    טעינת נתונים
    train_dataset = datasets.CIFAR100(
        root=data_dir, train=True,
        download=True, transform=transform,
    )

    valid_dataset = datasets.CIFAR10(
        root=data_dir, train=True,
        download=True, transform=transform,
    )

    num_train = len(train_dataset)
    indices = list(range(num_train))
    split = int(np.floor(valid_size * num_train))

    if shuffle:
        np.random.seed(random_seed)
        np.random.shuffle(indices)

    train_idx, valid_idx = indices[split:], indices[:split]
    train_sampler = SubsetRandomSampler(train_idx)
    valid_sampler = SubsetRandomSampler(valid_idx)

    train_loader = torch.utils.data.DataLoader(
        train_dataset, batch_size=batch_size, sampler=train_sampler)
 
    valid_loader = torch.utils.data.DataLoader(
        valid_dataset, batch_size=batch_size, sampler=valid_sampler)

    return (train_loader, valid_loader)


נתונית CIFAR100
train_loader, valid_loader = data_loader(data_dir='./data',
                                         batch_size=64)

test_loader = data_loader(data_dir='./data',
                              batch_size=64,
                              test=True)

class VGG16(nn.Module):
    def __init__(self, num_classes=10):
        super(VGG16, self).__init__()
        self.layer1 = nn.Sequential(
            nn.Conv2d(3, 64, kernel_size=3, stride=1, padding=1),
            nn.BatchNorm2d(64),
            nn.ReLU())
        self.layer2 = nn.Sequential(
            nn.Conv2d(64, 64, kernel_size=3, stride=1, padding=1),
            nn.BatchNorm2d(64),
            nn.ReLU(), 
            nn.MaxPool2d(kernel_size = 2, stride = 2))
        self.layer3 = nn.Sequential(
            nn.Conv2d(64, 128, kernel_size=3, stride=1, padding=1),
            nn.BatchNorm2d(128),
            nn.ReLU())
        self.layer4 = nn.Sequential(
            nn.Conv2d(128, 128, kernel_size=3, stride=1, padding=1),
            nn.BatchNorm2d(128),
            nn.ReLU(),
            nn.MaxPool2d(kernel_size = 2, stride = 2))
        self.layer5 = nn.Sequential(
            nn.Conv2d(128, 256, kernel_size=3, stride=1, padding=1),
            nn.BatchNorm2d(256),
            nn.ReLU())
        self.layer6 = nn.Sequential(
            nn.Conv2d(256, 256, kernel_size=3, stride=1, padding=1),
            nn.BatchNorm2d(256),
            nn.ReLU())
        self.layer7 = nn.Sequential(
            nn.Conv2d(256, 256, kernel_size=3, stride=1, padding=1),
            nn.BatchNorm2d(256),
            nn.ReLU(),
            nn.MaxPool2d(kernel_size = 2, stride = 2))
        self.layer8 = nn.Sequential(
            nn.Conv2d(256, 512, kernel_size=3, stride=1, padding=1),
            nn.BatchNorm2d(512),
            nn.ReLU())
        self.layer9 = nn.Sequential(
            nn.Conv2d(512, 512, kernel_size=3, stride=1, padding=1),
            nn.BatchNorm2d(512),
            nn.ReLU())
        self.layer10 = nn.Sequential(
            nn.Conv2d(512, 512, kernel_size=3, stride=1, padding=1),
            nn.BatchNorm2d(512),
            nn.ReLU(),
            nn.MaxPool2d(kernel_size = 2, stride = 2))
        self.layer11 = nn.Sequential(
            nn.Conv2d(512, 512, kernel_size=3, stride=1, padding=1),
            nn.BatchNorm2d(512),
            nn.ReLU())
        self.layer12 = nn.Sequential(
            nn.Conv2d(512, 512, kernel_size=3, stride=1, padding=1),
            nn.BatchNorm2d(512),
            nn.ReLU())
        self.layer13 = nn.Sequential(
            nn.Conv2d(512, 512, kernel_size=3, stride=1, padding=1),
            nn.BatchNorm2d(512),
            nn.ReLU(),
            nn.MaxPool2d(kernel_size = 2, stride = 2))
        self.fc = nn.Sequential(
            nn.Dropout(0.5),
            nn.Linear(7*7*512, 4096),
            nn.ReLU())
        self.fc1 = nn.Sequential(
            nn.Dropout(0.5),
            nn.Linear(4096, 4096),
            nn.ReLU())
        self.fc2= nn.Sequential(
            nn.Linear(4096, num_classes))
        
    def forward(self, x):
        out = self.layer1(x)
        out = self.layer2(out)
        out = self.layer3(out)
        out = self.layer4(out)
        out = self.layer5(out)
        out = self.layer6(out)
        out = self.layer7(out)
        out = self.layer8(out)
        out = self.layer9(out)
        out = self.layer10(out)
        out = self.layer11(out)
        out = self.layer12(out)
        out = self.layer13(out)
        out = out.reshape(out.size(0), -1)
        out = self.fc(out)
        out = self.fc1(out)
        out = self.fc2(out)
        return out

num_classes = 100
num_epochs = 20
batch_size = 16
learning_rate = 0.005

model = VGG16(num_classes).to(device)


# אובדן ואופטימיזר
criterion = nn.CrossEntropyLoss()
optimizer = torch.optim.SGD(model.parameters(), lr=learning_rate, weight_decay = 0.005, momentum = 0.9)  


# למידת המודל
total_step = len(train_loader)

total_step = len(train_loader)

for epoch in range(num_epochs):
    for i, (images, labels) in enumerate(train_loader):  
        # מעביר טנסורים למכשיר המותאם
        images = images.to(device)
        labels = labels.to(device)
        
        # העברה קדימה
        outputs = model(images)
        loss = criterion(outputs, labels)
        
        # בקפרופוגרציה והוטיבציה
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()

    print ('Epoch [{}/{}], Step [{}/{}], Loss: {:.4f}' 
                   .format(epoch+1, num_epochs, i+1, total_step, loss.item()))
            
    # ולידציה
    with torch.no_grad():
        correct = 0
        total = 0
        for images, labels in valid_loader:
            images = images.to(device)
            labels = labels.to(device)
            outputs = model(images)
            _, predicted = torch.max(outputs.data, 1)
            total += labels.size(0)
            correct += (predicted == labels).sum().item()
            del images, labels, outputs
    
        print('Accuracy of the network on the {} validation images: {} %'.format(5000, 100 * correct / total)) 

with torch.no_grad():
    correct = 0
    total = 0
    for images, labels in test_loader:
        images = images.to(device)
        labels = labels.to(device)
        outputs = model(images)
        _, predicted = torch.max(outputs.data, 1)
        total += labels.size(0)
        correct += (predicted == labels).sum().item()
        del images, labels, outputs

    print('Accuracy of the network on the {} test images: {} %'.format(10000, 100 * correct / total))