Comments (6)
@a18700 Hi, I actually use default setting in code for voting test. Voting exactly will introduce randomness to experiment results, but it just a slight change. Furthermore, voting test will not increase the performance and it works for more stable results, Finally, I add randomly drop points in trianing processing, which already used in official PointNet++ :)
from pointnet_pointnet2_pytorch.
@ZJU-PLP @yanx27 I also encountered this issue (memory leaks) when setting num_workers > 0
. The worker process will be killed after some iterations, especially because I don't have a large memory. This seems to be an issue introduced by the reference counting of Python. To mitigate it you can set num_workers = 0
, which slows down your data IO for sure. See pytorch/pytorch#13246.
from pointnet_pointnet2_pytorch.
How kind you are!
One thing what i want to clarify remaining, how does the performance of pointnet++(ssg, msg) is better than official version?
For ssg, 92.4 and 90.9(in paper) is huge difference.
So at first i thought it's heavily depending on augmentations, but you replied as you continue to use same augmentations in paper.
Can you explain more about this enhancement in performance?
Thanks.
from pointnet_pointnet2_pytorch.
@a18700 This work uses almost all the settings of the official version except:
(1) The ball query function maybe slightly different from official one
(2) I use both group normalized xyz and raw xyz to aggregate local group's features.
So I really do not sure that which one will enhance the performance :)
from pointnet_pointnet2_pytorch.
@yanx27 Hi, could you mind sharing the memory usage when you train pointnet2_sem_seg? I find that the memeory need 20GB while offiical tensorflow version only 6GB!
Ps:the batch_size=16
from pointnet_pointnet2_pytorch.
@ZJU-PLP Do you use same CUDA version and torch version with me?
from pointnet_pointnet2_pytorch.
Related Issues (20)
- 背景需不需要加标签
- Add codes for offline data preprocessing to accelerate training. Using setting of --process_data
- 球采样(query_ball_point)逻辑错误 HOT 5
- Different number of points in each class HOT 2
- Result file of classification
- Where did the pointnet.py file go?
- Tested with Torch 2.1 and CUDA 11.8, it works! HOT 1
- Some doubt in backpropagation of PointNet++ while solving it manually.
- 为什么这里卡住了,没有继续训练 HOT 4
- shape invalid issue
- pointnet2_part_seg应该如何部署
- S3DISDataLoader not using the Z axis when extracting a random block
- ForkingPickler(file, protocol).dump(obj) AttributeError: Can't pickle local object 'main.<locals>.<lambda>'
- How to perform semantic segmentation on the SemanticKITTI dataset?
- why dose this msg implemention performs better(92.8) than official 91.9?
- Question about ModelNetDataLoader.py
- Converting model to rknn format
- ValueError: cannot reshape array of size 0 into shape (1067709,7)
- Nvidia RTX 4060 mobile can't work with pytorch==1.6.0 cudatoolkit=10.1
- Help!!! in_channels of sem_seg
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 pointnet_pointnet2_pytorch.