模型训练常用函数

1. 多元素累加器

class Accumulator: #@save
	"""在n个变量上累加"""
	def __init__(self, n):
		self.data = [0.0] * n
	def add(self, *args):
		self.data = [a + float(b) for a, b in zip(self.data, args)]
	def reset(self):
		self.data = [0.0] * len(self.data)
	def __getitem__(self, idx):
		return self.data[idx]

metric = Accumulator(2)
metric.add(1, 1)

2. 准确率计算

def accuracy(y_hat, y): #@save
	"""计算预测正确的数量"""
	if len(y_hat.shape) > 1 and y_hat.shape[1] > 1:
		y_hat = y_hat.argmax(axis=1)
	cmp = y_hat.type(y.dtype) == y
	return float(cmp.type(y.dtype).sum())

3. 计算模型在某数据集上的精度(pytorch)

def evaluate_accuracy(net, data_iter): #@save
	"""计算在指定数据集上模型的精度"""
	if isinstance(net, torch.nn.Module):
		net.eval() # 将模型设置为评估模式
	metric = Accumulator(2) # 正确预测数、预测总数
	with torch.no_grad():
		for X, y in data_iter:
			metric.add(accuracy(net(X), y), y.numel())
	return metric[0] / metric[1]

4. 网络参数初始化(pytorch)

def init_weights(m):
	if type(m) == nn.Linear:
		nn.init.normal_(m.weight, std=0.01)
		
net.apply(init_weights);