Comments (6)
Hi, thanks for your interest1
we set the batch size to be 24 in the paper. I think the main reason is the small batch size you adapted. Dataparallel or distributed shouldn't influence the performance but just the consumed time for each epoch.
Hope this solves your problem :)
from zooming-slow-mo-cvpr-2020.
Thank you for your information! One more question, how many iterations does your model achieve the convergence? I saw in the yaml file the number of iterations is 600k? But 600K will take a long time to run. In your paper, you mentioned it took you a day and half to train the model.
from zooming-slow-mo-cvpr-2020.
Hi, the 600k is split into 4 periods. The model will converge within each period, and achieve better results when finishing the next period. So you can choose where to stop to reach a balance between the training time and model performance in actual application. I didn't mention anything like "a day and half" in the paper. It usually takes more than 2 days to finish each period.
from zooming-slow-mo-cvpr-2020.
Thanks for your patience and explanation. It indeed helps. I must remember the training time wrong. Sorry for that. When transiting from one period to the next what do I need to change? Do I need to change batch size, learning rate or other params?
from zooming-slow-mo-cvpr-2020.
It's fine. I just edited the train.yml so that you don't need to change anything if you follow the default setting given on the github,.
The setting of training periods can be found here: https://github.com/Mukosame/Zooming-Slow-Mo-CVPR-2020/blob/master/codes/options/train/train_zsm.yml#L56
from zooming-slow-mo-cvpr-2020.
Thanks for your replying. This project is a great work.
from zooming-slow-mo-cvpr-2020.
Related Issues (20)
- about the training phase HOT 8
- Windows support
- ValueError: Unknown CUDA arch (8.0) or GPU not supported HOT 1
- Zooming-Slow-Mo-CVPR-2020/codes/models/modules/DCNv2/_ext.cpython-37m-x86_64-linux-gnu.so: undefined symbol: HOT 1
- question about create_lmdb_mp.py HOT 2
- Regarding downsampling HOT 1
- Shared cells for bidirectional lstm HOT 2
- SSIM results HOT 1
- Change scale in video_to_zsm? HOT 4
- about video_to_zsm.py output HOT 1
- How can i train and test my datasets? HOT 7
- OOM HOT 11
- inference device HOT 1
- Offset mean is 145.10989379882812, larger than 100 HOT 1
- list object has no attribute 'add' HOT 2
- Custom Dataset Format
- Questions about Zooming Slow-mo validation on Vid4
- About Image Down Sampling
- OOM in train.py .
- some questions about testing HOT 1
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 zooming-slow-mo-cvpr-2020.