Comments (5)
I got 92.3 for test acc and 88.9 for test avg acc
from dgcnn.
I also encountered such a problem, I used the tensorflow code, the experiment was repeated three times, the highest accuracy is only 91%, compared with the paper said 92.9% of the accuracy has a large gap. Excuse me, is something wrong there? hope to get your reply, thank you very much!
from dgcnn.
I also encountered such a problem, I used the tensorflow code, the experiment was repeated three times, the highest accuracy is only 91%, compared with the paper said 92.9% of the accuracy has a large gap. Excuse me, is something wrong there? hope to get your reply, thank you very much!
Hi,
Thank you for your question. The pytorch code is consistent with what we have in the paper. That said we didn't update the tensorflow code to reflect the new results.
from dgcnn.
I run the pytorch code with the script
python main.py --exp_name=dgcnn_1024 --model=dgcnn --num_points=1024 --k=20 --use_sgd=True
And I always get results slightly worse than the reported results in the paper.
I used the best test results in the training process. Especially, for average acc (mean class acc), the gap with the reported ones is larger.
Are there any special settings or tricks in running the code?
Thanks in advance.
Can you tell me how much is the gap you get? I re-run the code and can get the same number (even better).
from dgcnn.
Hi @cslxiao, we have released pretrained models and evaluation details here: https://github.com/princeton-vl/SimpleView. You might find them useful.
from dgcnn.
Related Issues (20)
- There was no model.2048.t7 file in pretrained folder.
- Can I get the final paper?
- pytorch part segmentation HOT 1
- Can we run this code in windows?
- Visualization issues
- getting 'Indexerror' in train_multi_gpu.py HOT 1
- Understanding equation #8 in research paper (Section 3.1)
- 请问你的分类模型到底是哪样的,有的有连接,有的没有!!!
- LiDAR Point Cloud Classification results not good with real data HOT 1
- Why does the pytorch version not have transform? HOT 2
- How to add more DGCNN layers in your implementation?
- Aborted (core dumped) if I process to many points at once HOT 2
- Is the input size of the first layer 6 because the input parameters are the point itself and its normals?? HOT 1
- Why is the accuracy rate so low? HOT 1
- Visualization
- ValueError: need at least one array to concatenate HOT 2
- What is the KNN distance formula implemented by pytorch HOT 1
- The network architecture in code is different from the paper?
- 数据可视化严重问题
- CUDA error
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 dgcnn.