Comments (7)
Semantic3D is large in terms of point number, but rather small in terms of diverse scene. Due to this reason, we observed strong overfitting on Semantic3d. Nevertheless, we managed to achieve results that would reach 2nd place on the leader board. We believe the results can be further improved if we try some more data augmentation tricks, so we decided not to release our results on the leader board. Then we joined Alibaba and do not have enough time to play on this dataset (we have larger datasets to play with ;-).
In short, we believe PointCNN should perform well on Semantic3D, if you have time/patience in fighting against the overfitting.
from pointcnn.
We are working on this dataset. The code for processing semantic3d at the moment probably is not a good solution. It just serves as an exemplar to demonstrate that semantic3d could be processed in a very similar way as that for ScanNet and S3DIS, though it won't lead to the best performance.
Compared with ScanNet and S3DIS, semantic3d is extremely dense (and yes, it takes longer to train/eval), and we are working on a way to better leverage all the training data, which is likely doable through a proper preprocessing, without touch the PointCNN core code.
So, please stay tuned ;-)
from pointcnn.
How long does it need to train the cls/seg network? What is your device?
from pointcnn.
I find that it may be overfitting using 1024 epoch in S3DIS. Do you have such problem?
from pointcnn.
Hi, @LZDSJTU
We also have this problem. We can get almost 100 percision on training set, but only 80-90 acc on val. We still try to reslove this problem~~
from pointcnn.
any update on semantic segmentation? I'm happy to chase preprocessing ideas. Are people seeing improvement over pointnet? I have that up and running and am decently happy with results. I'm debating trying pointnet++ or pointcnn.
from pointcnn.
from pointcnn.
Related Issues (20)
- About “Note that S is an unordered set” in the paper
- Own data segmentation
- question about xforms
- model color HOT 1
- unable to download s3dis HOT 1
- Addition of comments or a video tutorial to better undertsand the code HOT 1
- ShapeNet Partsegmentation HOT 1
- Creating Confusion matrix from predicted results
- How to run PointCNN
- Regarding custom dataset HOT 7
- PointCNN Part segmentation model details
- ScannetV2 for point cloud Classification get too high performace
- another dataset
- Cannot compile tf_sampling_compile HOT 1
- Can't run train_val_seg.py for S3DIS dataset
- Can't run the code HOT 1
- Hanging on when running S3DIS and ShapeNetPart
- done
- How to set the path? python3 s3dis_merge.py -d <path to *_pred.h5>
- Which command to obtain the pred.npy in S3DIS dataset?
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 pointcnn.