Comments (1)
1/h may be very small, so the network cannot predict it well. Multiplying 1/h with 700 can make the training more stable. In my experiments, multiplying 1/h with 400, 500, 600, or 700 all work well.
from monodet.
Related Issues (16)
- TypeError: stat: path should be string, bytes, os.PathLike or integer, not NoneType
- different datasets have different images sizes
- what's the difference between box.hegiht and predicted height ?
- Evaluation output is not correct HOT 3
- RuntimeError: CUDA error: device-side assert triggered HOT 2
- Using model for video stream HOT 3
- How to get the average precision (AP) from custom dataset
- ImportError: cannot import name '_C' HOT 1
- evaluate problem
- when I train,why does loss gradually become negative,Thank you! HOT 2
- How to train on Waymo dataset ?
- Training on the Waymo dataset HOT 3
- MonoRCNN++: Where do I find the code? HOT 1
- How you are getting the BEV only using monocular cameras?
- Waymo dataset experiment reproducing
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 monodet.