Comments (9)
According to your description, it seems that the normal regression is not good enough.
Please send the one of the generated octree file and the trained caffe model to me ([email protected]) so that I can figure out the reason.
from o-cnn.
Thank you very much for looking! I have sent the caffe model and octrees to your email.
from o-cnn.
I saw your results. According to your caffemodel, the network is only trained for 22000 iterations. Please follow the solver we provided (https://github.com/Microsoft/O-CNN/blob/master/caffe/examples/ao-cnn/image2shape.solver.prototxt), and train the network for 350000 iterations.
from o-cnn.
from o-cnn.
If the hyper-parameters are changed, the results may be quite different.
Please follow the solver and paramters we provided to reproduce our results.
from o-cnn.
Ok, running it now without batch_size increase + iteration decrease. I.e., i'm using the exact solver parameters unchanged.
However, I notice in the solver parameters, the net source is image2shape_resnet.train.prototxt, while in the repository, there is only image2shape.train.prototxt. So I changed it to image2shape.train.prototxt.
Will this be ok?
from o-cnn.
Yes, it is a typo, and I have fixed it. Thank you!
from o-cnn.
Hi, so I ran at batchsize 32 with all your default hyper-parameters and it works great! It's a duplicate of your paper.
However if I try different batch sizes, the "normal regression" as you say seems to fail and I get the problem I mentioned, only horizontal and 45 degree patches.
Is this to do with the the learning rate and step value hyper-parameters? e.g. do the following hyperparameters need to be refined to increase batchsize and have the normal regression proceed properly:
base_lr: 0.1
momentum: 0.9
weight_decay: 0.0005
lr_policy: "multistep"
gamma: 0.1
stepvalue: 150000
stepvalue: 300000
stepvalue: 350000
or is it something more fundamental about the batchsize?
Thanks again.
from o-cnn.
As far as I know, it seems that there is on solid theory about the batchsize.
If the batch size is changed, the learning rate and step value should also be properly tuned, and perhaps better results can be acheived.
For our network, you can try to remove the caffe layers whose type are "Normalize". The "Normalize" layers are used to normalize the length of normal to be 1, I have observed that after removing the "Normalize" layers, the normal regression converges faster. You can add back these "Normalize" layers in the testing stage.
If you want to use multi-GPUs, this paper (https://arxiv.org/pdf/1706.02677.pdf) decribes some guidelines to tune the batch size and learning rate based the single-GPU paramters.
from o-cnn.
Related Issues (20)
- git checkout 6bfc5ca error HOT 4
- It requires either way Nvidia graphics card right? HOT 1
- pytorch installation error on Ubuntu 20.04, gcc 9.3.0 HOT 2
- Any plan for releasing a pytorch implementation of the Adaptive O-CNN? HOT 1
- error testing O-CNN under pytorch after building HOT 3
- error in installation HOT 2
- How to use pretrained pytorch O-CNN model in C++? HOT 3
- Point cloud -> octree -> point cloud
- How to split a batched octree to raw octree HOT 4
- Inference using my own point cloud on Scannet dataset HOT 1
- How long does it take to use ScanNet dataset training model? HOT 2
- Inference HOT 1
- Met cublas error when running test_all.py after a pytorch build HOT 3
- Got low accuracy results for Scannet per-point prediction HOT 1
- cmake installation error HOT 1
- Tensorflow.python.framework.errors_impl.NotFoundError HOT 1
- This repo is missing important files
- Understanding about 3D convolution and pool process on octree HOT 2
- Need to process individual shape features and merge them again according to batched merged octrees
- Octree->Points/Volume in Pytorch
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 o-cnn.