Comments (6)
Hi @g1y5x3 ,
It is hard to say what the right duration is, as it highly depends on the chosen learning-rate.
But for sure I never trained it for more than 200 epochs (you will also see that the loss kinda converges after that amount of time).
Best,
from delora.
Thank you for your clarification. So the 10,000 epochs that was in deployer/trainer.py was just a generic configuration but not necessarily the one used for reproducing the results right?
from delora.
Actually, would you mind share the training parameters that you used in the paper?
from delora.
yeah, usually I deployed it on servers and wanted to run it as long as possible rather than being killed by an internal epoch limit.
from delora.
Which parameters do you mean? model parameters (i.e. weights)?
from delora.
There is an example checkpoint for kitti provided here: https://github.com/leggedrobotics/DeLORA/tree/main/checkpoints
from delora.
Related Issues (20)
- can not find ./config/config_datasets_preprocessing.yaml HOT 2
- Failed to load Python extension for LZ4 support HOT 2
- About Scan2Map HOT 3
- TypeError: load() missing 1 required positional argument: 'Loader' HOT 2
- ValueError: axes don't match array
- ValueError: axes don't match array only for ouster lidar HOT 3
- multiple gpus error HOT 1
- reproduce the results of DARPA HOT 5
- About yaml error HOT 1
- Question about the set of epoch HOT 3
- Does darpa subT dataset support mini-batch on delora?
- Question aboult the 'normalization_scaling' parameter
- datasets about 'Airborne Particle Classification in LiDAR Point Clouds Using Deep Learning'
- About Odom data HOT 2
- Issue with pip3 install -e . HOT 4
- About Preprocessing scan HOT 1
- Can I make this model only fully supervised? HOT 2
- Training a different Lidar dataset with uneven vertical resolution/angular subdivisions. HOT 1
- Calculation of the parameters 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 delora.