Comments (5)
Thanks so much for pointing this out @Hippogriff. Yup, I developed at the early stage directly with ONet's decoder, so forgot to change the comments. We don't use CBN at all now.
from convolutional_occupancy_networks.
@pengsongyou Hi! Thank you for your great work! I'm also very interested in why you didn't use CBN any more? Cause in ONet, CBN seems to work smoothly. Do you have any ablation study about the performance when using or not CBN in ConvONet? Or is it just an issue for GPU memory since you said "memory intensive batch normalization operation" in the paper?
from convolutional_occupancy_networks.
Hi @Wuziyi616 , thanks for your interest! We did an ablation study on this at the very beginning. We found that without CBN:
- It is more memory efficient (I don't remember the exact number, ~20% - 30% less memory)
- Training process becomes faster
- We don't find any performance drop, and in some cases, it can even reach slightly higher scores with a smaller number of iterations.
Hope this helps.
from convolutional_occupancy_networks.
@pengsongyou Thank you for your quick reply! Indeed I tried the code the training is faster and converged smoothly. BTW, just to make sure, the "configs/pointcloud/shapenet_3plane.yaml" is for training the "Ours-2D (3x64^2)" on Object-Level 3D Reconstruction from Point Clouds task (in which your model achieved an IoU of 0.861) right? That performance is amazing! Again this is really a great work!
from convolutional_occupancy_networks.
Hi @Wuziyi616 , thanks for the kind word! Yup, that is the model :) I think you might even get a little bit higher score because we continue training the model for a bit longer.
from convolutional_occupancy_networks.
Related Issues (20)
- train on outdoor LiDAR pointcloud HOT 1
- Noise during inference
- What's the difference between "points.npz" and "pointcloud.npz"? HOT 1
- How do I retrain the model HOT 1
- Finetune for pretrained model HOT 1
- How can I generate mesh with my own point cloud data HOT 7
- RuntimeError: cannot join current thread" by running "python generate.py configs/pointcloud_crop/demo_matterport.yaml" HOT 6
- How to transform a mesh to a occupancy mat? HOT 1
- Use *.pcd file as input to inference or inference without normals HOT 1
- How to train a new model for your own dataset HOT 4
- Which config file is to run 3D Volume input?
- out of memory error HOT 1
- on my own data HOT 2
- What is the resolution of surface reconstruction ? HOT 1
- unable to download shapenet, synthetic room datasets in colab
- RuntimeError: CUDA error: CUBLAS_STATUS_EXECUTION_FAILED when calling `cublasSgemm( handle, opa, opb, m, n, k, &alpha, a, lda, b, ldb, &beta, c, ldc)`
- what 's the difference between shape_1plane.pt and shape_3plane.pt??? HOT 1
- Question on initialized parameter values for point cloud crop generation
- pip install torch_scatter==2.0.2
- from cython.operator cimport dereference as drefεΊι
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
π 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. πππ
-
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 β€οΈ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from convolutional_occupancy_networks.