Learn practical skills, build real-world projects, and advance your career
Updated 3 years ago
Creating Tensor data
An short introduction about PyTorch and about the chosen functions.
- function 1 : creating tonsr data and fill it by zero or random
- function 2 : Concatenates the given sequence of seq tensors in the given dimension.
- function 3 : Splits the tensor into chunks
- function 4 : Convert the data into a torch.Tensor.
- function 5 : Returns a tensor of random numbers drawn from separate normal distributions
Before we begin, let's install and import PyTorch
# Uncomment and run the appropriate command for your operating system, if required
# Linux / Binder
# !pip install numpy torch==1.7.0+cpu torchvision==0.8.1+cpu torchaudio==0.7.0 -f https://download.pytorch.org/whl/torch_stable.html
# Windows
# !pip install numpy torch==1.7.0+cpu torchvision==0.8.1+cpu torchaudio==0.7.0 -f https://download.pytorch.org/whl/torch_stable.html
# MacOS
# !pip install numpy torch torchvision torchaudio
# Import torch and other required modules
import torch
Function 1 - Create data with random function
torch.randn give you the ability to create data with given size. it's very useful when you don't have a data and want to create a random data.
# Example 1 - working with Randn function
#Function 1 (create a data) #https://pytorch.org/docs/stable/generated/torch.randn.html#torch.randn
inputs = torch.zeros(3,4)
display (inputs)
inputs = torch.randn(3,4)
display(inputs)
tensor([[0., 0., 0., 0.],
[0., 0., 0., 0.],
[0., 0., 0., 0.]])
tensor([[ 0.3443, 0.5673, 0.6769, -0.6091],
[-0.0864, -1.1892, 1.4165, 0.7665],
[ 0.9718, 1.0737, -0.5271, 1.3133]])