Comments (4)
Hello @hongduc2307,
11 recall positions are calculated on validation set here.
Because sampling precisions every 4 intervals as follows, so "11" is hard-coded here.
Lines 238 to 241 in a0e8af7
For evaluation, we keep consistent with mmdet3d, as implemented in the following lines.
from pointpillars.
@zhulf0804 Thank you for quick reply.
Yes I see your point here, but when I print len(score_thresholds)
it is not always 41 so the loop size is not 11.
I see the score_thresholds
could be taken from the following mmdet3d function. The third argument num_sample_pts=41
may not ensure that len(score_thresholds)
is 41.
from pointpillars.
Yes, you are right.
P-R curve draws (precision, recall) point at the specific scores. However, the recall can't be 100% even if given a very small score. Just like the following figure, the highest recall is slightly higher than 0.8. So it's not always 41 or 11.
from pointpillars.
@zhulf0804 Yes you're alright.
Now it's clear that the hard-code "11" should be changed depending on len(score_thresholds)
so the result AP will change a bit.
Thank you so much for kind answers. This repo is a really great work.
from pointpillars.
Related Issues (20)
- how to train with multi gpus!!!
- Potential mistake in anchors2bboxes function HOT 2
- Bad inference result on sample after overfitting on same sample HOT 15
- ModuleNotFoundError: No module named 'ops.voxel_op' HOT 2
- AttributeError: 'NoneType' object has no attribute 'shape' HOT 2
- Question about mAP calculation HOT 2
- Training and Validation Loss HOT 2
- How to run without CUDA
- Can you explain what changes you have made to make it better than the original one?
- Test on waymo data set HOT 1
- Can someone explain what this step is about?
- 膜拜大佬,非常好奇您的复现增加了什么方法 HOT 1
- Quick Shape explaination HOT 1
- shape mismatch of the forward function of the Loss class
- Question about Kitti transforms
- Questions about changing validation set evaluation to test set evaluation
- 哪里能得到每一轮训练日志文件?
- Pseudo image visualization
- AttributeError: 'NoneType' object has no attribute 'convert_from_pinhole_camera_parameters' HOT 2
- accuracy of test is very low HOT 1
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 pointpillars.