Comments (2)
Hi,
You should be able to train PointNetVLAD using the following command:
torchpack dist-run -np ${_NGPU} python training/train.py --train_pipeline 'PointNetVLAD' --point_loss_weight 0
by setting the dataset
parameter either KittiTupleDataset
or MulRanTupleDataset
. The point_loss_weight
parameter is set to zero as PointNetVLAD only uses the global loss during training.
Additionally, you can set the following parameters to the values used in the PointNetVLAD paper: lazy_loss
, ignore_zero_loss
, positives_per_query
, negatives_per_query
, loss_margin_1
, loss_margin_2
.
After training, you can generate results using the same evaluation commands given in the readme by providing the additional parameter --eval_pipeline 'PointNetVLAD'
and setting --checkpoint_name
to the path of the pretrained weights.
from logg3d-net.
Also, make sure to use the --pnv_preprocessing 'True'
parameter for PointNetVLAD.
from logg3d-net.
Related Issues (9)
- Sensor Requirement HOT 2
- Error SparseTensor during PointNetVLAD training HOT 3
- error when batch size larger than one HOT 9
- Issues with training KITTI datset HOT 7
- Train on a custom dataset HOT 2
- Channel value error when applying the checkpoint model to a custom point cloud HOT 2
- about visualization of t-SNE embeddings of the local features HOT 6
- Question about the construction of the is_revisit_D-3_T-30.json file? 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 logg3d-net.