-
## Width
- [x] Fix width defaulting to 0 -> #66
- [x] Change width -> equalize width checkbox/number input instead -> #66
- [x] Factor width out of load_images -> #66
- [ ] Check if cropping …
-
```
This is only important when using the perceptual metric. The solution is just
to flip the luminance
calculation components and to relabel all rgba variables and documentation
appropriately. Als…
-
The manipulation of images could be seen as a conditioned generation. Therefore, the commonly used perceptual loss in style transfer is essential in some generation tasks. However, the mmgeneration on…
-
Dear authors,
Thank you for sharing the code. I would suggest to add small constant to operations where **torch.sqrt is involved** to avoid **NaN** during gradient calculation and hence backpropaga…
-
```
This is only important when using the perceptual metric. The solution is just
to flip the luminance
calculation components and to relabel all rgba variables and documentation
appropriately. Als…
-
```
This is only important when using the perceptual metric. The solution is just
to flip the luminance
calculation components and to relabel all rgba variables and documentation
appropriately. Als…
-
See the [similar issue](https://github.com/libjxl/libjxl/issues/202) in libjxl.
It would be great to evaluate DSSIM on the CLIC-2021 perceptual quality task. This should provide additional informat…
-
```
This is only important when using the perceptual metric. The solution is just
to flip the luminance
calculation components and to relabel all rgba variables and documentation
appropriately. Als…
-
# Speech Separation
Speech separation is the task of obtaining clean, single-speaker speech from a speech mixture of multiple overlapping speakers.
## Task Objective
**Why is this task needed…
-
Hi,
First, I want to say thank you for your great work!
I have a question about the lpips networks (alex, squeeze, vgg)
[The Unreasonable Effectiveness of Deep Features as a Perceptual Metric…