استفاده از Google Colab برای آموزش شبکه‌ های عصبی عمیق

!pip install tensorflow  # برای TensorFlow
!pip install torch torchvision  # برای PyTorch

from google.colab import drive
drive.mount('/content/drive')

# حالا می‌توانید به فایل‌های خود در Google Drive دسترسی داشته باشید

import tensorflow as tf
from tensorflow.keras import datasets

# بارگذاری دیتاست MNIST
(x_train, y_train), (x_test, y_test) = datasets.mnist.load_data()

# نرمال سازی داده‌ها
x_train, x_test = x_train / 255., x_test / 255.

model = tf.keras.models.Sequential([
    tf.keras.layers.Flatten(input_shape=(28, 28)),  # لایه ورودی
    tf.keras.layers.Dense(128, activation='relu'),  # لایه مخفی
    tf.keras.layers.Dropout(.2),  # لایه Dropout
    tf.keras.layers.Dense(10, activation='softmax')  # لایه خروجی
])

model.compile(optimizer='adam',
              loss='sparse_categorical_crossentropy',
              metrics=['accuracy'])

import torch
import torch.nn as nn
import torch.optim as optim

class SimpleNN(nn.Module):
    def __init__(self):
        super(SimpleNN, self).__init__()
        self.fc1 = nn.Linear(28*28, 128)
        self.fc2 = nn.Linear(128, 10)

    def forward(self, x):
        x = x.view(-1, 28*28)
        x = torch.relu(self.fc1(x))
        x = self.fc2(x)
        return x

model = SimpleNN()

model.fit(x_train, y_train, epochs=5)

criterion = nn.CrossEntropyLoss()
optimizer = optim.Adam(model.parameters())

for epoch in range(5):
    model.train()
    optimizer.zero_grad()
    outputs = model(torch.tensor(x_train, dtype=torch.float32))
    loss = criterion(outputs, torch.tensor(y_train, dtype=torch.long))
    loss.backward()
    optimizer.step()
    print(f'Epoch [{epoch+1}/5], Loss: {loss.item():.4f}')

test_loss, test_acc = model.evaluate(x_test, y_test)
print('Test accuracy:', test_acc)

model.eval()
with torch.no_grad():
    inputs = torch.tensor(x_test, dtype=torch.float32)
    outputs = model(inputs.view(-1, 28*28))
    _, predicted = torch.max(outputs.data, 1)
    accuracy = (predicted == torch.tensor(y_test)).sum().item() / len(y_test)
    print(f'Test accuracy: {accuracy:.4f}')