Importing retinaface causes all torch tensors to lack gradient function

[yhu9]

Expected behavior of torch Tensors is to have a gradient function if it requires gradient.

Shortest example I have on what is happening for me.

import torch
x = torch.randn(1, requires_grad=True)
print(x + 1)

tensor([1.3468], grad_fn=<AddBackward0>)

import torch
import retinaface
x = torch.randn(1, requires_grad=True)
print(x + 1)

tensor([1.3468])

[aixiaodewugege]

This problem waste a lot of my time.....It took me half a day to fix it.