本篇博客代碼來自於《動手學深度學習》pytorch版，也是代碼較多，解釋較少的一篇。不過好多方法在我以前的博客都有提，所以這次沒提。還有一個原因是，這篇博客的代碼，只要好好看看肯定能看懂(前提是python語法大概了解)，這是我不加很多解釋的重要原因。
K折交叉驗證實現
def get_k_fold_data(k, i, X, y):
# 返回第i折交叉驗證時所需要的訓練和驗證數據，分開放，X_train為訓練數據，X_valid為驗證數據
assert k > 1
fold_size = X.shape[0] // k # 雙斜杠表示除完后再向下取整
X_train, y_train = None, None
for j in range(k):
idx = slice(j * fold_size, (j + 1) * fold_size) #slice(start,end,step)切片函數
X_part, y_part = X[idx, :], y[idx]
if j == i:
X_valid, y_valid = X_part, y_part
elif X_train is None:
X_train, y_train = X_part, y_part
else:
X_train = torch.cat((X_train, X_part), dim=0) #dim=0增加行數，豎着連接
y_train = torch.cat((y_train, y_part), dim=0)
return X_train, y_train, X_valid, y_valid
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) # 獲取k折交叉驗證的訓練和驗證數據
net = get_net(X_train.shape[1]) #get_net在這是一個基本的線性回歸模型，方法實現見附錄1
train_ls, valid_ls = train(net, *data, num_epochs, learning_rate,
weight_decay, batch_size) #train方法見后面附錄2
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']) #畫圖，且是對y求對數了，x未變。方法實現見附錄3
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
*args：表示接受任意長度的參數，然后存放入一個元組中；如def fun(*args) print(args)，‘fruit'，'animal'，'human'作為參數傳進去，輸出(‘fruit'，'animal'，'human')
**kwargs：表示接受任意長的參數，然后存放入一個字典中；如
def fun(**kwargs):
for key, value in kwargs.items():
print("%s:%s" % (key,value)
fun(a=1,b=2,c=3)會輸出 a=1 b=2 c=3
附錄1
loss = torch.nn.MSELoss()
def get_net(feature_num):
net = nn.Linear(feature_num, 1)
for param in net.parameters():
nn.init.normal_(param, mean=0, std=0.01)
return net
附錄2
def train(net, train_features, train_labels, test_features, test_labels, num_epochs, learning_rate,weight_decay, batch_size):
train_ls, test_ls = [], []
dataset = torch.utils.data.TensorDataset(train_features, train_labels)
train_iter = torch.utils.data.DataLoader(dataset, batch_size, shuffle=True) #TensorDataset和DataLoader的使用請查看我以前的博客
#這里使用了Adam優化算法
optimizer = torch.optim.Adam(params=net.parameters(), lr= learning_rate, weight_decay=weight_decay)
net = net.float()
for epoch in range(num_epochs):
for X, y in train_iter:
l = loss(net(X.float()), y.float())
optimizer.zero_grad()
l.backward()
optimizer.step()
train_ls.append(log_rmse(net, train_features, train_labels))
if test_labels is not None:
test_ls.append(log_rmse(net, test_features, test_labels))
return train_ls, test_ls
附錄3
def semilogy(x_vals, y_vals, x_label, y_label, x2_vals=None, y2_vals=None, legend=None, figsize=(3.5, 2.5)):
set_figsize(figsize)
plt.xlabel(x_label)
plt.ylabel(y_label)
plt.semilogy(x_vals, y_vals)
if x2_vals and y2_vals:
plt.semilogy(x2_vals, y2_vals, linestyle=':')
plt.legend(legend)
注：由於最近有其他任務，所以此博客寫的匆忙，等我有時間后會豐富，也可能加詳細解釋。