AI Pytorch - freecodecamp.org

<JS C C++ Python><coding Robotics CNC>

<Robotics CNC Links>

<CNC><CNC tutorial><3d printing><Azure MongoDB Spark><AI Pytorch><Ship building><GIT> 

source: https://www.freecodecamp.org/news/learn-pytorch-for-deep-learning-in-day/

Main elements

name	dimension	application tensor
Scalar	0 dimension	scalar = torch.tensor(7)
vector	single dimension tensor	vector = torch.tensor([7, 7])
	can contain many numbers
matrix	Matrices are as flexible as vectors, except they've got an extra dimension	MATRIX = torch.tensor([[7, 8], [9, 10], [6.5, 7.2]])
Tensor	tensors can represent almost anything	TENSOR = torch.tensor([[[1, 2, 3], [3, 6, 9], [2, 4, 5]]])

 Attributes and methods

name	type	example	result	explanation
ndim	attribute	scalar.ndim	0	checks dimension
		vector.ndim	1
		MATRIX.ndim	2
		TENSOR.ndim	3
item	method	scalar.item()	7	retrieve the number from tensor
shape	attribute	vector.shape	torch.Size([2])	How the elements inside tensors are arranged
		MATRIX.shape	torch.Size([3, 2])
		TENSOR.shape	torch.Size([1, 3, 3])	1 for overall group, 3 for 3 brackets,and 3 is elements in each brackets

Some operations

# Create a random tensor of size (3, 4) random_tensor = torch.rand(size=(3, 4)) random_tensor, random_tensor.dtype		(tensor([[0.5949, 0.6433, 0.3059, 0.6293], [0.0861, 0.6876, 0.9790, 0.4856], [0.3752, 0.6620, 0.7464, 0.5335]])
# Create a tensor of all zeros zeros = torch.zeros(size=(3, 4)) zeros, zeros.dtype		(tensor([[0., 0., 0., 0.], [0., 0., 0., 0.], [0., 0., 0., 0.]]), torch.float32)
# Create a tensor of all ones ones = torch.ones(size=(3, 4)) ones, ones.dtype		(tensor([[1., 1., 1., 1.], [1., 1., 1., 1.], [1., 1., 1., 1.]]), torch.float32)
# Create a range of values 0 to 10 zero_to_ten = torch.arange(start=0, end=10, step=1) zero_to_ten	range of numbers, such as 1 to 10 or 0 to 100. You can use torch.arange(start, end, step) to do so.	tensor([0, 1, 2, 3, 4, 5, 6, 7, 8, 9])
ten_zeros = torch.zeros_like(input=zero_to_ten)	a tensor of all zeros with the same shape as a previous tensor	tensor([0, 0, 0, 0, 0, 0, 0, 0, 0, 0])
float_16_tensor = torch.tensor([3.0, 6.0, 9.0], dtype=torch.float16)	data type float 16

source:

https://www.learnpytorch.io/pytorch_2_intro/

https://pytorch.org/tutorials/beginner/basics/saveloadrun_tutorial.html

for running pytorch code

https://jupyter.org/try-jupyter/lab/

jupyter docs:

https://jupyterlab.readthedocs.io/en/latest/