Comments (8)
您好,我没有尝试过多卡训练,看起来可能是模型上一部分参数的device不对,可以检查一下
from graspnet-baseline.
感谢您的回答,我会在尝试修改代码;如果修改产生效果,我会向您回复的。
from graspnet-baseline.
您好,在阅读论文的过程中,产生一些疑问:
关于评价精度AP,以 u = 0.8 为例 ,对应的抓取分数应该是 s = 1.1 -u = 0.3,假设排名前50的抓取位姿分数都是0.3,总的分数是15,为什么您论文中报告的是 33.43/36.19,我对此不太理解?AP是如何计算的?期待您的回复
from graspnet-baseline.
对于u=0.8时,夹爪预测的分数是 s = 0.3或者s = 0吗?在您的论文中,我看到Operation Network的损失函数是:
对于分数Sij的预测,我理解可以设计为分类损失函数,您为何选择回归预测呢?
from graspnet-baseline.
你好,抓取分数不是50*0.3这么算的,具体可以看我们论文中的阐述,或者网页的解释:https://graspnet.net/evaluation.html
分数的预测也可以使用分类损失,回归是为了兼容未来可能出现的其他度量。
from graspnet-baseline.
感谢您及时的回复,根据您的建议,我在论文中看到: the percentage of true positive is more important.,是否可以这样理解:在 u = 0.8 是,AP代表的是排名前50个抓取位姿中,真阳性的比例?比如说真阳性的比例是33.43%?
from graspnet-baseline.
您好,是这样的
from graspnet-baseline.
十分感谢您的回复,解答了疑惑,再次感谢您出色的工作!
from graspnet-baseline.
Related Issues (20)
- Clarification on Scores within the Dataset HOT 1
- 对于6D grasp的一些疑问 HOT 4
- What's the usage of the function "process_grasp_labels" in the "label_generation.py" file ? HOT 3
- knn install error
- 训练时knn遇到错误 HOT 1
- About angles HOT 3
- 部署到真机 HOT 3
- List of objects in seen ans unseen test set HOT 2
- what means of "assign views"? HOT 1
- The process has been kill HOT 1
- why the prediction of grasp_width is multiplied 1.2 when construct grasp pose? HOT 1
- 自定义workspace_mask HOT 4
- Inquiry Regarding Grasp Generation Discrepancy in Multi-View Reconstruction Point cloud HOT 3
- data convention of `camera_poses.npy` in graspnet-1billion dataset HOT 3
- run command_demo.sh error HOT 3
- 代码中 ToleranceNet 好像是 (128, 128, 12) ? HOT 1
- How to generate scene collision labels for custom datasets? HOT 1
- Increasing GPU memory during training time: Cuda out for memory error HOT 1
- graspness运行test得到的ap值为什么比文章中的高那么多
- test.py AP比论文中的高不少 HOT 2
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 graspnet-baseline.