Tensor基础操作
简单的初始化
import torch as t Tensor基础操作 # 构建张量空间,不初始化
x = t.Tensor(5,3)
x
-2.4365e-20 -1.4335e-03 -2.4290e+25
-1.0283e-13 -2.8296e-07 -2.0769e+22
-1.3816e-33 -6.4672e-32 1.4497e-32
1.6020e-19 6.2625e+22 4.7428e+30
4.0095e-08 1.1943e-32 -3.5308e+35
[torch.FloatTensor of size 5x3]
# 构建张量空间,[0,1]均匀分布初始化
x = t.rand(5,3)
x
0.9618 0.0669 0.1458
0.3154 0.0680 0.1883
0.1795 0.4173 0.0395
0.7673 0.4906 0.6148
0.0949 0.2366 0.7571
[torch.FloatTensor of size 5x3
检查尺寸
# 查看矩阵形状,返回时tuple的子类,可以直接索引
print(x.shape)
print(x.size()) """
torch.Size([5, 3])
torch.Size([5, 3])
"""
Tensor加法操作
- 符号加
- torch.add(out=Tensor)
- Tensor.add(),方法后面不带有下划线时方法不会修改Tensor本身,仅仅返回新的值
- Tensor.add_(),方法后面带有下划线时方法会修改Tensor本身,同时返回新的值
Tensor加法操作 # 加法操作:t.add()
y = t.rand(5,3) print(x + y)
print(t.add(x, y))
result = t.Tensor(5,3)
t.add(x, y, out=result)
print(result)
输出,
1.6288 0.4566 0.9290
0.5943 0.4722 0.7359
0.4316 1.0932 0.7476
1.6499 1.3201 1.5611
0.3274 0.4651 1.5257
[torch.FloatTensor of size 5x3] 1.6288 0.4566 0.9290
0.5943 0.4722 0.7359
0.4316 1.0932 0.7476
1.6499 1.3201 1.5611
0.3274 0.4651 1.5257
[torch.FloatTensor of size 5x3] 1.6288 0.4566 0.9290
0.5943 0.4722 0.7359
0.4316 1.0932 0.7476
1.6499 1.3201 1.5611
0.3274 0.4651 1.5257
[torch.FloatTensor of size 5x3]
输入:
# 加法操作:Tensor自带方法
print(y)
# 不改变y本身
print("y.add():\n", y.add(x))
print(y)
print("y.add_():\n", y.add_(x))
print(y)
输出,
0.6670 0.3897 0.7832
0.2788 0.4042 0.5476
0.2521 0.6759 0.7081
0.8825 0.8295 0.9462
0.2325 0.2286 0.7686
[torch.FloatTensor of size 5x3] y.add(): 1.6288 0.4566 0.9290
0.5943 0.4722 0.7359
0.4316 1.0932 0.7476
1.6499 1.3201 1.5611
0.3274 0.4651 1.5257
[torch.FloatTensor of size 5x3] 0.6670 0.3897 0.7832
0.2788 0.4042 0.5476
0.2521 0.6759 0.7081
0.8825 0.8295 0.9462
0.2325 0.2286 0.7686
[torch.FloatTensor of size 5x3] y.add_(): 1.6288 0.4566 0.9290
0.5943 0.4722 0.7359
0.4316 1.0932 0.7476
1.6499 1.3201 1.5611
0.3274 0.4651 1.5257
[torch.FloatTensor of size 5x3] 1.6288 0.4566 0.9290
0.5943 0.4722 0.7359
0.4316 1.0932 0.7476
1.6499 1.3201 1.5611
0.3274 0.4651 1.5257
[torch.FloatTensor of size 5x3]
Tensor索引以及和Numpy.array转换
Tensor对象和numpy的array对象高度相似,不仅可以相互转换,而且:
- 转换前后的两者共享内存,所以他们之间的转换很快,而且几乎不会消耗资源,这意味着一个改变另一个也随之改变
- 两者在调用时可以相互取代(应该是由于两者的内置方法高度相似)
虽然有Tensor.numpy()和t.from_numpy(),但是记不住的话使用np.array(Tensor)和t.Tensor(array)即可,同样可以共享内存。
Tensor索引
# Tensor索引和numpy的array类似
x[:, 1]
0.0669
0.0680
0.4173
0.4906
0.2366
[torch.FloatTensor of size 5]
Tensor->array
Tensor和numpy转换 a = t.ones_like(x)
b = a.numpy() # Tensor->array
b
array([[ 1., 1., 1.],
[ 1., 1., 1.],
[ 1., 1., 1.],
[ 1., 1., 1.],
[ 1., 1., 1.]], dtype=float32)
Tensor和array的交互
import numpy as np print(x) # Tensor和array的交互很强,一定程度上可以相互替代 a = np.ones_like(x)
print(a)
0.9618 0.0669 0.1458
0.3154 0.0680 0.1883
0.1795 0.4173 0.0395
0.7673 0.4906 0.6148
0.0949 0.2366 0.7571
[torch.FloatTensor of size 5x3] [[ 1. 1. 1.]
[ 1. 1. 1.]
[ 1. 1. 1.]
[ 1. 1. 1.]
[ 1. 1. 1.]]
array->Tensor(两者共享内存的验证)
b = t.from_numpy(a) # array->Tensor
print(a)
print(b)
b.add_(1) # 两者共享内存
print(a)
print(b)
[[ 1. 1. 1.]
[ 1. 1. 1.]
[ 1. 1. 1.]
[ 1. 1. 1.]
[ 1. 1. 1.]] 1 1 1
1 1 1
1 1 1
1 1 1
1 1 1
[torch.FloatTensor of size 5x3] [[ 2. 2. 2.]
[ 2. 2. 2.]
[ 2. 2. 2.]
[ 2. 2. 2.]
[ 2. 2. 2.]] 2 2 2
2 2 2
2 2 2
2 2 2
2 2 2
[torch.FloatTensor of size 5x3]
试验np.array(Tensor)和t.Tensor(array),
import numpy as np
x = t.rand(5,3)
# Tensor和array的交互很强,一定程度上可以相互替代
a = np.ones_like(x)
print(a)
b = t.Tensor(a) # array->Tensor
print(a)
print(b)
b.add_(1) # 两者共享内存
print(a)
print(b)
print(np.array(x))
[[ 1. 1. 1.]
[ 1. 1. 1.]
[ 1. 1. 1.]
[ 1. 1. 1.]
[ 1. 1. 1.]]
[[ 1. 1. 1.]
[ 1. 1. 1.]
[ 1. 1. 1.]
[ 1. 1. 1.]
[ 1. 1. 1.]] 1 1 1
1 1 1
1 1 1
1 1 1
1 1 1
[torch.FloatTensor of size 5x3] [[ 2. 2. 2.]
[ 2. 2. 2.]
[ 2. 2. 2.]
[ 2. 2. 2.]
[ 2. 2. 2.]] 2 2 2
2 2 2
2 2 2
2 2 2
2 2 2
[torch.FloatTensor of size 5x3] [[ 0.95334041 0.48346853 0.86516887]
[ 0.0904668 0.05142063 0.42738861]
[ 0.7112515 0.45674682 0.39708138]
[ 0.06700033 0.90959501 0.4757393 ]
[ 0.6760695 0.83767009 0.1341657 ]]
最后,实验以下cpu加速,当然,由于我的笔记本没有加速,所以条件是不满足的。
if t.cuda.is_available():
x = x.cuda()
y = y.cuda()
x+y