def fit_and_plot_pytorch(wd):
# 对权重参数衰减。权重名称一般是以weight结尾
net = nn.Linear(num_inputs, 1)
nn.init.normal_(net.weight, mean=0, std=1)
nn.init.normal_(net.bias, mean=0, std=1)
optimizer_w = torch.optim.SGD(params=[net.weight], lr=lr, weight_decay=wd) # 对权重参数衰减
optimizer_b = torch.optim.SGD(params=[net.bias], lr=lr) # 不对偏差参数衰减
train_ls, test_ls = [], []
for _ in range(num_epochs):
for X, y in train_iter:
l = loss(net(X), y).mean()
optimizer_w.zero_grad()
optimizer_b.zero_grad()
l.backward()
# 对两个optimizer实例分别调用step函数，从而分别更新权重和偏差
optimizer_w.step()
optimizer_b.step()
train_ls.append(loss(net(train_features), train_labels).mean().item())
test_ls.append(loss(net(test_features), test_labels).mean().item())
d2l.semilogy(range(1, num_epochs + 1), train_ls, 'epochs', 'loss',
range(1, num_epochs + 1), test_ls, ['train', 'test'])
print('L2 norm of w:', net.weight.data.norm().item())
def train_and_pred(train_features, test_features, train_labels, test_data,
num_epochs, lr, weight_decay, batch_size):
net = get_net(train_features.shape[1])
train_ls, _ = train(net, train_features, train_labels, None, None,
num_epochs, lr, weight_decay, batch_size)
d2l.semilogy(range(1, num_epochs + 1), train_ls, 'epochs', 'rmse')
print('train rmse %f' % train_ls[-1])
preds = net(test_features).detach().numpy()
test_data['SalePrice'] = pd.Series(preds.reshape(1, -1)[0])
submission = pd.concat([test_data['Id'], test_data['SalePrice']], axis=1)
submission.to_csv('./submission.csv', index=False)
def k_fold(k, X_train, y_train, num_epochs,
learning_rate, weight_decay, batch_size):
train_l_sum, valid_l_sum = 0, 0
for i in range(k):
data = get_k_fold_data(k, i, X_train, y_train)
net = get_net(X_train.shape[1])
train_ls, valid_ls = train(net, *data, num_epochs, learning_rate,
weight_decay, batch_size)
train_l_sum += train_ls[-1]
valid_l_sum += valid_ls[-1]
if i == 0:
d2l.semilogy(range(1, num_epochs + 1), train_ls, 'epochs', 'rmse',
range(1, num_epochs + 1), valid_ls,
['train', 'valid'])
print('fold %d, train rmse %f, valid rmse %f' % (i, train_ls[-1], valid_ls[-1]))
return train_l_sum / k, valid_l_sum / k
def fit_and_plot(lambd):
w,b = init_params()
train_ls,test_ls = [],[]
for _ in range(num_epochs):
for X,y in train_iter:
## 添加L2范数惩罚项
l = loss(net(X,w,b),y) + lambd *l2_penalty(w)
l = l.sum()
if w.grad is not None:
w.grad.data.zero_()
b.grad.data.zero_()
l.backward()
d2l.sgd([w,b],lr,batch_size)
train_ls.append(loss(net(train_features,w,b),train_labels).mean().item())
test_ls.append(loss(net(test_features,w,b),test_labels).mean().item())
d2l.semilogy(range(1, num_epochs + 1), train_ls, 'epochs', 'loss',
range(1, num_epochs + 1), test_ls, ['train', 'test'])
print('L2 norm of w:',w.norm().item())