Comments (2)
These numbers are super helpful! Thanks!!
from ocvp-object-centric-video-prediction.
Hi Zhanghan,
Below you can find the number of iterations (batches) that the modes were trained for, as well as the number of epochs these iterations correspond to.
Additionally, I report the training time that our experiments took the following using an NVIDIA A6000 with 48Gb
Dataset | Model | Iters. | Epochs | Time |
---|---|---|---|---|
Ojb3D | SAVi | 100k | 2000 | 26h |
Obj3D | OCVP-Seq | 70k | 1500 | 34h |
MOVi-A | SAVi | 150k | 2000 | 120h |
MOVi-A | OCVP-Seq | 50k | 300 | 18h |
You can find these numbers and further hyper-parameters in the configuration files.
The number of epochs need not match the exact configuration, since the experiments might have been stopped earlier if the model had already converged.
I hope this answers your question.
Do not hesitate to follow up if you still have any questions.
from ocvp-object-centric-video-prediction.
Related Issues (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 ocvp-object-centric-video-prediction.