Snippet record of my best accuracy

titanic.py

# 69%
# 1. Design model
class Net(torch.nn.Module):
    def __init__(self):
        super().__init__()
        self.fc1 = torch.nn.Linear(11, 40)
        self.fc2 = torch.nn.Linear(40, 40)
        self.fc3 = torch.nn.Linear(40, 40)
        self.fc4 = torch.nn.Linear(40, 15)
        self.fc5 = torch.nn.Linear(15, 1)
        self.dropout = torch.nn.Dropout(p=0.5)
        self.tanh = torch.nn.Tanh()
#         self.sigmoid = torch.nn.Sigmoid()
        self.relu = torch.nn.ReLU()
    def forward(self, x):
        x = self.tanh(self.fc1(x))
        x = self.dropout(x)
        x = self.tanh(self.fc2(x))
        x = self.dropout(x)
        x = self.tanh(self.fc3(x))
        x = self.dropout(x)
        x = self.tanh(self.fc4(x))
        x = self.dropout(x)
        x = self.tanh(self.fc5(x))
        x = self.relu(x)
        return x
        
# 2. Define criterion and optimizer
model = Net()
criterion = torch.nn.BCEWithLogitsLoss()
# optimizer = torch.optim.Adadelta(model.parameters(), lr=0.01)
# optimizer = torch.optim.Adam(model.parameters(), lr=0.01)
optimizer = torch.optim.SGD(model.parameters(), lr=0.01, momentum=0.9)

def train(model, device, train_loader, optimizer, epoch):
    model.train()
    for batch_idx, (data, target) in enumerate(train_loader):
        optimizer.zero_grad()
        output = model(data)
        from pprint import pprint
#         import ipdb; ipdb.set_trace()
        loss = criterion(output, target)
        loss.backward()
        optimizer.step()
        if batch_idx % 10 == 0:
            print('Train Epoch: {} [{}/{} ({:.0f}%)]\tLoss: {:.6f}'.format(
                epoch, batch_idx * len(data), len(train_loader.dataset),
                100. * batch_idx / len(train_loader), loss.item()))
                
def test(model, device, test_loader):
    model.eval()
    test_loss = 0
    correct = 0
    with torch.no_grad():
        for data, target in test_loader:
            output = model(data)
            test_loss += criterion(output, target).item() # sum up batch loss
            pred = output.max(1, keepdim=True)[1] # get the index of the max log-probability
#             import ipdb; ipdb.set_trace()
            correct += pred.eq(target.long().view_as(pred)).sum().item()

    test_loss /= len(test_loader.dataset)
    print('\nTest set: Average loss: {:.4f}, Accuracy: {}/{} ({:.0f}%)\n'.format(
        test_loss, correct, len(test_loader.dataset),
        100. * correct / len(test_loader.dataset)))
        
# 3. Train
for epoch in range(1, 30):
    train(model, device, train_loader, optimizer, epoch)
    test(model, device, test_loader)