使用pytorch构建神经网络系列
第二章 第二节 pytorch进阶
目录
1.Broadcasting
key idea:
-Insert 1 dim ahead
-Expand dims with size 1 to same size
-Feature maps:[4,32, 14,14]
-Bias:[32,1,1] ==> [1,32,1,1] ==>[4,32, 14,14]
Match from Last dim！！
- If current dim = 1， expand to same
- if either has no dim， insert one dim and expand to same
- otherwise，NOT broadcasting-able
2.Merge/split
cat
合并（其他dim必须一致）
a = torch.rand(4,28,28)
b = torch.rand(5,28,28)
torch.cat([a,b],dim = 0).shape
torch.Size([9, 28, 28])
stack
creat new dim：
a = torch.rand(28,28)
b = torch.rand(28,28)
torch.stack([a,b],dim = 0).shape
torch.Size([2, 28, 28])
split
a = torch.rand(5,28,28)
aa, bb = a.split([2,3], dim = 0)
aa.shape, bb.shape
(torch.Size([2, 28, 28]), torch.Size([3, 28, 28]))
Chunk: by num
a = torch.rand(6,28,28)
aa, bb = a.chunk(2, dim = 0)
aa.shape, bb.shape
(torch.Size([3, 28, 28]), torch.Size([3, 28, 28]))
3.数学运算
matmul
=@
a = torch.full([2,2],8, dtype = torch.float)
b = torch.ones(2,2)
torch.matmul(a, b)
a@b
tensor([[16., 16.],
[16., 16.]])
a = torch.rand(4, 784)
w = torch.rand(512, 784)
(a@w.t()).shape
torch.Size([4, 512])
实现并行相乘
a = torch.rand(4, 3, 28, 32)
b = torch.rand(4, 3, 32, 28)
torch.matmul(a, b).shape
torch.Size([4, 3, 28, 28])
Power
a = torch.full([2,2], 3, dtype = float)
a.pow(2)
tensor([[9., 9.],
[9., 9.]], dtype=torch.float64)
aa = a**2
aa
tensor([[9., 9.],
[9., 9.]], dtype=torch.float64)
aa.sqrt()
aa**(0.5)
tensor([[3., 3.],
[3., 3.]], dtype=torch.float64)
aa.rsqrt() #平方根倒数
tensor([[0.3333, 0.3333],
[0.3333, 0.3333]], dtype=torch.float64)
Exp / log
a = torch.exp(torch.ones(2,2)) # e的1次方
a
tensor([[2.7183, 2.7183],
[2.7183, 2.7183]])
torch.log(a) #默认以e为底
tensor([[1.0000, 1.0000],
[1.0000, 1.0000]])
Approximation
- .floor() .ceil() 向下取整 和向上取整
- .round() 四舍五入
- .trunc() .frac()整数部分与小数部分
a = torch.tensor(3.1415)
a.floor(),a.ceil(),a.trunc(),a.frac(),a.round()
(tensor(3.), tensor(4.), tensor(3.), tensor(0.1415), tensor(3.))
clamp
grad = torch.rand(2,3)*19
grad
tensor([[ 0.2305, 0.0978, 0.6458],
[ 4.6174, 9.2011, 11.8627]])
最小值设置为10
grad.clamp(10)
tensor([[10.0000, 10.0000, 10.0000],
[10.0000, 10.0000, 11.8627]])
设置在（0，10）区间
grad.clamp(5,10)
tensor([[ 5.0000, 5.0000, 5.0000],
[ 5.0000, 9.2011, 10.0000]])
4.属性统计
norm
a = torch.full([8],1, dtype = float)
b = a.view(2,4)
c = a.view(2,2,2)
a,b,c
(tensor([1., 1., 1., 1., 1., 1., 1., 1.], dtype=torch.float64),
tensor([[1., 1., 1., 1.],
[1., 1., 1., 1.]], dtype=torch.float64),
tensor([[[1., 1.],
[1., 1.]],
[[1., 1.],
[1., 1.]]], dtype=torch.float64))
L1范数
a.norm(1),b.norm(1),c.norm(1)
(tensor(8., dtype=torch.float64),
tensor(8., dtype=torch.float64),
tensor(8., dtype=torch.float64))
L2范数
a.norm(2),b.norm(2),c.norm(2)
(tensor(2.8284, dtype=torch.float64),
tensor(2.8284, dtype=torch.float64),
tensor(2.8284, dtype=torch.float64))
指定维度：
b.norm(2,dim = 0)
tensor([1.4142, 1.4142, 1.4142, 1.4142], dtype=torch.float64)
mean, sum, min, max, prod(累积)
a = torch.arange(1,9).view(2,4).float()
a
tensor([[1., 2., 3., 4.],
[5., 6., 7., 8.]])
a.mean(), a.sum(), a.min(), a.max(), a.prod()
(tensor(4.5000), tensor(36.), tensor(1.), tensor(8.), tensor(40320.))
最大值最小值索引
a.argmax(), a.argmin() #默认铺平 可以加上dim = ，指定维度
(tensor(7), tensor(0))
dim / keepdim
a = torch.rand(4,10)
a.max(dim = 1)
torch.return_types.max(
values=tensor([0.8951, 0.9522, 0.6955, 0.9705]),
indices=tensor([1, 6, 0, 9]))
a.max(dim = 1, keepdim = True)
torch.return_types.max(
values=tensor([[0.8951],
[0.9522],
[0.6955],
[0.9705]]),
indices=tensor([[1],
[6],
[0],
[9]]))
top-k/k-th
a.topk(3, dim =1, largest = True)
torch.return_types.topk(
values=tensor([[0.8951, 0.8779, 0.8563],
[0.9522, 0.9264, 0.8587],
[0.6955, 0.6641, 0.5106],
[0.9705, 0.9102, 0.7651]]),
indices=tensor([[1, 0, 5],
[6, 4, 9],
[0, 7, 1],
[9, 5, 8]]))
第k小
a.kthvalue(10, dim =1)
torch.return_types.kthvalue(
values=tensor([0.8951, 0.9522, 0.6955, 0.9705]),
indices=tensor([1, 6, 0, 9]))
compare
<,<=,>=,>,!=,==
返回1或0
5.Tensor advanced operation
where
torch.where(condition, x, y) ⇒ tensor
probility = torch.rand(2,2)
a = torch.zeros(2, 2)
b = torch.ones(2, 2)
probility,a,b
(tensor([[0.9443, 0.5826],
[0.3918, 0.5968]]),
tensor([[0., 0.],
[0., 0.]]),
tensor([[1., 1.],
[1., 1.]]))
torch.where(probility > 0.5, b, a)
tensor([[1., 1.],
[0., 1.]])
gather
查表
torch.gather(input, dim, index, out = None) ==> Tensor
prob = torch.randn(4,10)
idx = prob.topk(dim = 1, k = 2)
idx[1]
tensor([[3, 4],
[5, 2],
[1, 4],
[6, 3]])
label = torch.arange(10) + 50
label
tensor([50, 51, 52, 53, 54, 55, 56, 57, 58, 59])
torch.gather(label.expand(4,10), dim = 1, index = idx[1])
tensor([[53, 54],
[55, 52],
[51, 54],
[56, 53]])