Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

LPIPS with Alex net returns Nan #33

Merged
merged 2 commits into from
Sep 10, 2022
Merged

LPIPS with Alex net returns Nan #33

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
a000433
Add EPS to avoid Nan
ilpoli Sep 9, 2022
a1bd88d
Make epsilon an argument of LPIPS
francois-rozet Sep 10, 2022
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
9 changes: 5 additions & 4 deletions piqa/lpips.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,8 +11,6 @@
.. [Deng2009] ImageNet: A large-scale hierarchical image database (Deng et al, 2009)
"""

import inspect
import os
import torch
import torch.nn as nn
import torchvision.models as models
Expand Down Expand Up @@ -119,6 +117,7 @@ class LPIPS(nn.Module):
network: Specifies the perceptual network :math:`\mathcal{F}` to use:
`'alex'` | `'squeeze'` | `'vgg'`.
scaling: Whether the input and target need to be scaled w.r.t. [Deng2009]_.
epsilon: A numerical stability term.
dropout: Whether dropout is used or not.
pretrained: Whether the official weights :math:`w_l` are used or not.
eval: Whether to initialize the object in evaluation mode or not.
Expand All @@ -144,6 +143,7 @@ def __init__(
self,
network: str = 'alex',
scaling: bool = True,
epsilon: float = 1e-10,
dropout: bool = False,
pretrained: bool = True,
eval: bool = True,
Expand All @@ -155,6 +155,7 @@ def __init__(
self.scaling = scaling
self.register_buffer('shift', SHIFT.reshape(1, -1, 1, 1))
self.register_buffer('scale', SCALE.reshape(1, -1, 1, 1))
self.epsilon = epsilon

# Perception layers
if network == 'alex': # AlexNet
Expand Down Expand Up @@ -210,8 +211,8 @@ def forward(self, input: Tensor, target: Tensor) -> Tensor:
residuals = []

for lin, fx, fy in zip(self.lins, self.net(input), self.net(target)):
fx = fx / l2_norm(fx, dims=[1], keepdim=True)
fy = fy / l2_norm(fy, dims=[1], keepdim=True)
fx = fx / (l2_norm(fx, dims=[1], keepdim=True) + self.epsilon)
fy = fy / (l2_norm(fy, dims=[1], keepdim=True) + self.epsilon)

mse = ((fx - fy) ** 2).mean(dim=(-1, -2), keepdim=True)
residuals.append(lin(mse).flatten())
Expand Down