Comments (3)
It requires CPU to process the queue of shadow masks (QueueMask). You can reduce the length of the queue of shadow masks (QueueMask(dataloader.len()/4)) to make it faster, and the performance is similar.
from mask-shadowgan.
the same question... Hey, Gavin666Github, how long did you train the code for 1 epoch?
from mask-shadowgan.
About a 0.33 hour per epoch on Tesla V100.
from mask-shadowgan.
Related Issues (16)
- Hi would you provide the model such as netG_A2B.pth and so on? HOT 1
- USR dataset
- Bad results HOT 2
- Evaluation code wanted HOT 3
- Can not reproduce the same results HOT 2
- Cross major layman ask for help
- Any pretrained model on USR dataset could be provided?
- Unable to convergence HOT 4
- ValueError: num_samples should be a positive integeral value, but got num_samples=0 HOT 16
- resume training problem
- Thank you for creating this. Can this be used to ADD shadows?
- got unpleasant result HOT 2
- RuntimeError: CUDA out of memory. HOT 1
- ValueError of train_Mask-ShadowGAN
- How to select the unpaired training data on ISTD and SRD, which contain paired shadow/shadow-free images?
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 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. 📊📈🎉
-
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 ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from mask-shadowgan.