查看“︁PyTorch get started”︁的源代码

= Installation =
== Conda Installation== 

<syntaxhighlight lang="bash">
conda create --name deeplearning python=3.11
conda activate deeplearning
python --version
// 3.11.5
</syntaxhighlight>

== Install pytorch ==

<syntaxhighlight lang="bash">
conda install pytorch::pytorch torchvision torchaudio -c pytorch
</syntaxhighlight>

To verify:

<syntaxhighlight lang="python">
import torch
x = torch.rand(5, 3)
print(x)
</syntaxhighlight>

Output:
<syntaxhighlight lang="bash">
tensor([[0.2162, 0.2653, 0.6725],
        [0.5371, 0.4180, 0.1353],
        [0.3697, 0.5238, 0.0332],
        [0.6179, 0.5008, 0.9435],
        [0.1182, 0.3233, 0.9071]])
</syntaxhighlight>

= Concepts =
== Tensor（张量） ==
Tensors are a specialized data structure that are very similar to arrays and matrices. In PyTorch, we use tensors to encode the inputs and outputs of a model, as well as the model’s parameters.

Tensors are similar to NumPy’s ndarrays, except that ：
* tensors can run on GPUs or other hardware accelerators
* tensors are also optimized for automatic differentiation（自动微分）

<syntaxhighlight lang="python">
>>> import torch
>>> x = torch.arange(10)
>>> x
tensor([0, 1, 2, 3, 4, 5, 6, 7, 8, 9])
>>> x.shape
torch.Size([10])
>>> x.numel()
10
>>> X = x.reshape(3,4)
Traceback (most recent call last):
  File "<stdin>", line 1, in <module>
RuntimeError: shape '[3, 4]' is invalid for input of size 10
>>> X = x.reshape(2,5)
>>> X
tensor([[0, 1, 2, 3, 4],
        [5, 6, 7, 8, 9]])
</syntaxhighlight>


[[Category:Deep Learning]]
[[Category:PyTorch]]