Comments (4)
hi,
I once trained using 1 RTX 2080Ti/RTX 3090, each epoch took around 2/1.5 hours, so in total around 2 days.
from overlappredator.
Thank you!
from overlappredator.
Hey, there
I also noticed that the param: max_epoches of this KPConv version differs from the other MinkConv-based version:
KPConv-based : ~40 epoches
MinkConv-baed: ~100 epoches
And they both need about 2 hours to finish training one single epoch, there is a HUGE time difference between these two versions, it's a little bit strange to me, but anyway, the final performance of these two seems to be the same.
:)
from overlappredator.
hi,
- I train ME version after CVPR, I don't have time pressure and it's a single experiment, so I just train it for 100 epochs, as FCGF did.
- The message of this experiment is that "Predator is flexible regarding the backbone networks". So training two backbones differently doesn't harm this argument. To really compare two backbones, we need to design fair experiments.
from overlappredator.
Related Issues (20)
- Inference does not get applied HOT 3
- ModelLoNet dataset HOT 1
- Demo .py [Alignment ouptuts identity transfortmation matrix] HOT 1
- Ambiguous overlap ratio for Modelnet and ModelLoNet
- how to get ground truth transformation?
- The content of the pth file HOT 1
- The gt-info and gt.log files HOT 1
- Coordinate system of data HOT 3
- The role of cal_overlap.py
- Question about overlap ratio in 3DMatch.pkl
- I want to know where to download 3dmatch dataset in .pth format? HOT 2
- how to generate the format of the pth file HOT 1
- How to creat gt.info and gt.log files HOT 8
- Run with Rotated 3DMatch and 3DLomatch Dataset
- Questions about producing the newest results with the newest codes
- export the model to torchscript?
- Cannot download dataset or model weights HOT 2
- Training is done with a warning message from the Scikit-Learn library
- There is no .pth file in the checkpoints folder HOT 1
- Requirements not match
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 overlappredator.