Comments (1)
可能有两个原因,一是模型刚开始训练的时候初始深度较小,投影时全部被 mask 掉而没有投到参考图片上;二是 loss_distortion 的权重过大,可能要根据其他参数调整。可以尝试增大采样的最小距离,降低 loss_distortion 的权重。
from occnerf.
Related Issues (20)
- Some problems of nusc-depth training code HOT 2
- How to train with v1.0-mini dataset? HOT 2
- How long does it typically take to train the OccNeRF model with semantic supervision? HOT 2
- Question about photometric loss. HOT 2
- Generalizability HOT 1
- How's the zero-shot ability? HOT 2
- Why do you mask the feat here?
- Why do you flip the xyz here? HOT 3
- How long does it take to train the full model? (8 a100) HOT 1
- depth training problems HOT 1
- depth trainning problems HOT 3
- Lack of memory on the GPU during training HOT 3
- Contact Author HOT 1
- Training code for SemanticKITTI HOT 1
- torch and CUDA version
- why cumsum the prob to render depth?
- Question about the use of auxiliary_frame in Depth and Semantic task
- Train Cost
- Model complexity and inference speed (fps)
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 occnerf.