Comments (7)
May I ask if you can directly test with the weights you provide? The accuracy of the test in pointmamba is only 7%~8%, and the weight files provided by them are also used in point-MAE, with about 93.5%
I just re-cloned the repository, downloaded the open-sourced checkpoint, and achieved the exact same results as reported. The test command should be CUDA_VISIBLE_DEVICES=0 python main.py --test --config cfgs/finetune_modelnet.yaml --ckpts modelnet_scratch.pth
.
from pointmamba.
I'm sorry, we never encountered an issue with NaN.
from pointmamba.
Thank you for your interest in our work!
The code currently open-sourced from the repository aligns with the paper's current version. Our models are all trained and tested using a single RTX 4090, which may differ across hardware platforms. Also please refer to this issue and the explanation here.
Feel free to evaluate our open-sourced weight for ModelNet40.
from pointmamba.
May I ask if you can directly test with the weights you provide? The accuracy of the test in pointmamba is only 7%~8%, and the weight files provided by them are also used in point-MAE, with about 93.5%
from pointmamba.
并且当我训练的时候
会nan
同样的数据,在mae中可以正常训练
请问可以直接使用代码中的超参数吗,需要针对性调整?
from pointmamba.
I'm sorry, we never encountered an issue with NaN.
Thank you very much for your answer~
from pointmamba.
I am closing this issue. Please feel free to reopen it if necessary.
from pointmamba.
Related Issues (20)
- Problems when installing Chamfer Distance HOT 9
- A question about reported experimental results HOT 2
- about semantic segmentation HOT 1
- Pretraining HOT 1
- What is the use of `inference_params` in Mamba and how to set it? HOT 4
- 关于部件分割和分类任务中的特征最大值池化问题 HOT 6
- about the ModelNet40 Dataset HOT 1
- Testing HOT 1
- Visualization HOT 4
- Excuse me, if this box is not checked, does it mean that the code for splitting and splitting has not been released yet? HOT 4
- Anybody observe slow training speed for mamba compared to transformer model? HOT 2
- Problems when installing pointnet2_ops HOT 2
- update of the code HOT 1
- Serialization / Hilbert ordering. HOT 4
- Hilbert space-filling curves HOT 4
- Trying to backward through the graph a second time HOT 3
- windows reproduce HOT 2
- GPU not being utilized
- How much GPU memory is used during pre-training
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 pointmamba.