Learn practical skills, build real-world projects, and advance your career
Updated 3 years ago
Starting with PyTorch functions
PyTorch has long been the preferred deep-learning library for researchers, used primarily for applications such as computer vision and natural language processing.
- torch.as_tensor
- torch.set_default_tensor_type()
- torch.where(condition, t1, t2)
- torch.reshape()
- torch.from_numpy(ndarray)
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 - torch.as_tensor
Converts any data type to tensor type
torch.as_tensor(data, dtype=None, device=None)
# Example 1 - working
list1=[1,2,3,4]
list1=torch.as_tensor(list1)
type(list1)
torch.Tensor