pyTorch深入学习梯度和Linear Regression实现

tensor(data, *, dtype=None, device=None, requires_grad=False, pin_memory=False) -> Tensor
#require_grad默认是false，下面我们将显式的开启
x = torch.tensor([1,2,3],requires_grad=True,dtype=torch.float)

x = torch.tensor([1,2,3],requires_grad=True,dtype=torch.float32)
> tensor([1.,2.,3.],grad_fn=None)
y = x + 2
> tensor([3.,4.,5.],grad_fn=<AddBackward0>)
z = y * y * 3
> tensor([3.,4.,5.],grad_fn=<MulBackward0>)

x = torch.ones((2,2),requires_grad=True)
> tensor([[1.,1.],
> 		   [1.,1.]],requires_grad=True)
y = x + 2
z = y * y * 3
out = z.mean()
#out是一个标量，无需指定求偏导的变量
out.backward()
x.grad
> tensor([[4.500,4.500],
> 		  [4.500,4.500]])
#每次计算梯度前，需要将梯度清零,否则会累加
x.grad.data.zero_()

x = torch.tensor(1.,requires_grad=True)
y1 = x ** 2
with torch.no_grad()
	y2 = x ** 3
y3 = y1 + y2
y3.backward()
print(x.grad)
> 2

num_features = 2#两个特征
num_examples = 1000 #样本个数
w = torch.normal(0,1,(num_features,1))
b = torch.tensor(4.2)
samples = torch.normal(0,1,(num_examples,num_features))
labels = samples.matmul(w) + b
noise = torch.normal(0,.01,labels.shape)
labels += noise

import random
def data_iter(samples,labels,batch_size):
	num_samples = samples.shape[0] #获得batch轴的长度
	indices = [i for i in range(num_samples)]
	random.shuffle(indices)#将索引数组原地打乱
	for i in range(0,num_samples,batch_size):
	j = torch.LongTensor(indices[i:min(i+batch_size,num_samples)])
	yield samples.index_select(0,j),labels(0,j)

def loss_function(predict,labels):
	loss = (predict,labels)** 2 / 2
	return loss.mean()

def loss_function(predict,labels):
	loss = (predict,labels)** 2 / 2
	return loss.mean()

w = torch.normal(0.,1.,(num_features,1),requires_grad=True)
b = torch.zero(0.,dtype=torch.float32,requires_grad=True)
batch_size = 100
for epoch in range(10):
	for data, label in data_iter(samples,labels,batch_size):
		predict = data.matmul(w) + b
		loss = loss_function(predict,label)
		loss.backward()
		optimizer([w,b],0.05)
		w.grad.data.zero_()
		b.grad.data.zero_()