Comments (1)
At first we used resnet34, and then we also tested Resnest50. As LM dataset is relatively easy, we found that the results of resnet34 were also acceptable, so we reported Resnest34. The uploaded config file uses 50. you can change to 34 yourself
from so-pose.
Related Issues (19)
- Since we need ground truth 2D-3D matching and self-occlusion results, we provide generation methods in .gdrn_selfocc_modeling/tools. Please refer to generate_*.py. HOT 3
- question about backbone in experiment configs for LM dataset HOT 6
- question about implementation of 2D cross layer consistency HOT 8
- Some questions about generate_pbr_P_fast.py
- Some error questions about generate_P_fast.py HOT 4
- 缺失lib.egl_renderer HOT 3
- 缺少lib.egl_renderer
- LINEMOD results HOT 2
- 生成xyz_crop时碰到的一些问题 HOT 2
- Models link not working HOT 1
- 没有egl_renderer HOT 7
- 请问在训练过程中,cpu无法跑满怎么办。 HOT 2
- 关于configs/gdrn_selfocc/lm参数设置 HOT 1
- 对于real+syn实验的疑问 HOT 1
- How to evaluate the trained model on YCBV? HOT 1
- 配置文件中`TRAIN2=("lmo_pbr_train")`是否必要 HOT 2
- How can I inference the results? HOT 2
- 请问在可视化结果时可以提供一下你们的lib.egl_renderer吗,感谢。 HOT 3
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 so-pose.