Search Results
| Search type | Search syntax |
|---|---|
| Tags | [tag] |
| Exact | "words here" |
| Author |
user:1234 user:me (yours) |
| Score |
score:3 (3+) score:0 (none) |
| Answers |
answers:3 (3+) answers:0 (none) isaccepted:yes hasaccepted:no inquestion:1234 |
| Views | views:250 |
| Code | code:"if (foo != bar)" |
| Sections |
title:apples body:"apples oranges" |
| URL | url:"*.example.com" |
| Saves | in:saves |
| Status |
closed:yes duplicate:no migrated:no wiki:no |
| Types |
is:question is:answer |
| Exclude |
-[tag] -apples |
| For more details on advanced search visit our help page | |
Results tagged with lpips
Search options not deleted
user 50897
For questions about the Learned Perceptual Image Patch Similarity (LPIPS) metric. See the paper "The Unreasonable Effectiveness of Deep Features as a Perceptual Metric" (2018) by Richard Zhang et al. for more info.
4
votes
1
answer
2k
views
To assess the quality of the reconstructed images, which metric is more reliable: PSNR or LP...
LPIPS is decreasing, which is good. PSNR goes up and down, but the L1 loss and SSIM loss are increasing.
So, which metric should I care more about?
My datasets are Paris Street View and CelebA. … I'm not sure if the VGG that extracts features for LPIPS is reliable here or not. …
- 43