Jovian
Sign In
Learn practical skills, build real-world projects, and advance your career
import numpy as np
import torch 
# create tensors 
x = torch.tensor(3.)
w = torch.tensor(4., requires_grad=True)
b = torch.tensor(5., requires_grad=True)
y = w * x + b
y
tensor(17., grad_fn=<AddBackward0>)

calculate derivative

used for calculating gradient

gradients use when dealing with metrices , derivative use when deaking with numbers

y.backward()