الشبكات العصبية — الانتشار الأمامي والخلفي

import torch
import torch.nn as nn
import torch.optim as optim
from torch.utils.data import TensorDataset, DataLoader

class="tok-comment"># ── Sample dataloader ──────────────────────────────────────────────────
X_data = torch.randn(class="tok-num">1000, class="tok-num">128)
y_data = torch.randint(class="tok-num">0, class="tok-num">2, (class="tok-num">1000,)).float()
dataloader = DataLoader(TensorDataset(X_data, y_data), batch_size=class="tok-num">64, shuffle=True)

class MLP(nn.Module):
    def __init__(self, input_dim, hidden_dims, output_dim, dropout=class="tok-num">0.3):
        super().__init__()
        layers = []
        dims = [input_dim] + hidden_dims
        for i in range(len(hidden_dims)):
            layers += [
                nn.Linear(dims[i], dims[i+class="tok-num">1]),
                nn.BatchNorm1d(dims[i+class="tok-num">1]),
                nn.ReLU(),
                nn.Dropout(dropout)
            ]
        layers.append(nn.Linear(hidden_dims[-class="tok-num">1], output_dim))
        self.net = nn.Sequential(*layers)

    def forward(self, x):
        return self.net(x)

model = MLP(input_dim=class="tok-num">128, hidden_dims=[class="tok-num">256, class="tok-num">128, class="tok-num">64], output_dim=class="tok-num">1)
optimizer = optim.AdamW(model.parameters(), lr=class="tok-num">1e-3, weight_decay=class="tok-num">1e-4)
scheduler = optim.lr_scheduler.CosineAnnealingLR(optimizer, T_max=class="tok-num">100)

class="tok-comment"># Training step
for x_batch, y_batch in dataloader:
    optimizer.zero_grad()
    logits = model(x_batch).squeeze()
    loss = nn.BCEWithLogitsLoss()(logits, y_batch.float())
    loss.backward()
    nn.utils.clip_grad_norm_(model.parameters(), class="tok-num">1.0)
    optimizer.step()
    scheduler.step()