-
**Describe the bug**
The `runner.sh` script parses out the output from `jupytext` into something for feeding into pep8. `sed` is used in places to pick parts out, however for some weirdly formatting …
-
Hi ChrisDud0257,
Thank you for your open source project! I encountered some issues while fine-tuning the RRDB model using SSL-loss. Specifically, the results from the model show a lot of artifacts,…
-
Hello, it's a great project!
I encountered some errors when execute script : bash scripts/text_condition/gpu/sample_t2v.sh
Anyone can help me ~
```
(opensora-plan) root@DESKTOP-KLL8FM3:~/project/O…
-
-
In the paper,
the authors describe that the recon loss is replaced with perceptual loss.
However, in the code, the actual recon loss is L1 (not L2) + perceptual loss.
https://github.com/LeeDoYu…
-
Hi
I had run the model with provided images and with a couple of my images, but the output is always simply black images.
There are no critical errors in the script output, warnings only.
How d…
-
The chainer implementation of Justin's paper "Perceptual Losses for Real-Time Style Transfer and Super-Resolution" uses a script that reduces the model to just the convolutional layers, creating a mod…
-
Hi,
I have pruned fast neural net based on the magnitude of the weights. Now, I want to evaluate the prediction loss. I have gone through slow_neural_style.lua and train.lua to figure out how the …
-
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…
-
The architecture of kp_detector defined in 'modules/keypoint_detector.py', and applied in 'GeneratorFullModel'. Loss function contains 'perceptual', 'generator_gan', 'feature_matching', 'equivariance_…