Comments (5)
Did you find out how they set these weights? I am curious too!
from super-slomo.
In my opinion, these weights are set based on your training losses.
A loss represents its target, also has different difficulty to be converged. Therefore, I always ask myself a question about which loss will be useful (improve PSNR) for my final output, and how much the loss is enough? I might have to tune the weights too many times to figure out. Why don't you train the model and see what will happen :))
For example, empirically, in training, I observed that loss_smooth is easier to be converged, more than other losses, we set its weight of 1 might be okay. Meanwhile, prcpLoss is high. If we set the weight of that loss is too high, it would cause worse on final output because your network only concentrates on updating the network's params based on that loss. But if we set it as 0.005, it will improve the quality as well as the perceptual aspect.
It is too confused; therefore, they used the term "empirically" in the paper.
I usually balance the trade-off between losses (all values are approximate), which also makes a balance in backpropagating error as well as updating weights for your target.
from super-slomo.
Thanks for your kindly reply! Actually I have been training this model since yesterday, the loss decreases gradually, but the ValPSNR is always negative, can you give me a hint? Any suggests will be so helpful!
from super-slomo.
You could check:
- Is your PSNR calculation correct?
- (important) Run eval and check the interpolated video directly, is it good and satisfy you? If not, the model must be failed and negative PSNR is reasonable because MSE is extremely huge (more than 256*256). Negative PSNR is ... I think it's hard to appear unless there is a bug.
from super-slomo.
Thank you very much!!! I will look into that.
from super-slomo.
Related Issues (20)
- ffmpeg error while running evaluation code. HOT 1
- Output interpolated image frames are of different size then input frames?
- What is the function of transforms.Normalize(mean=negmean, std=std)? Why use a negative mean๏ผ
- Error converting file:D:\Coding\JAVASCRIPT\recless\out\4fpsRecording.mkv. Exiting.
- PackagesNotFoundError: torchvision-cpu==0.2.0 HOT 3
- Runtime Error (Traceback Attached) HOT 23
- Frames are not extracted for any input video
- Differences with butterflow
- Slowdown a point of the video HOT 1
- It does not seem to work for scale value below 4 HOT 1
- "index 1 is out of bounds for dimension 0 with size 1" HOT 2
- Reference frames are different from the original ones. HOT 1
- sh: /Users/*/Downloads/ffmpeg/ffmpeg: No such file or directory HOT 2
- Add local file to Google Colab?? Or change length??
- How can I find the dataset of 240-fps video from YouTube HOT 1
- Training
- Objective metrics
- Could be faster by not saving PNG frames
- Image edge flicker
- low rate of utilization in test video
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. ๐๐๐
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google โค๏ธ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from super-slomo.