Comments (3)
Hi @liqi17thu, I find the two adaptations you mentioned in 3.(1) very interesting to think about.
- Using softmax instead of sigmoid as activation for prediction
I understand this as you still want to encourage the network to predict only 1 class(with high likelihood), rather than in typical multi-label classification setting where the prediction for each class is treated as independent variables. Is that correct? - Normalising the labels
I assume you're doing standard normalisation rather than softmax, so this won't change the BCE loss for the classes with label 0, but will change the BCE loss of the 2 classes with label 1 from NLL(red curve below) to(blue curve below), this would mean that the averaged loss is lowest when the network predicts probability 0.5 for both classes with label 1, but relatively high when it predicts probability 1 for one of the 2 correct classes. This seems opposite to the motivation of 1, so I'd love to hear more about your thoughts on the design of this loss, thanks!
from hdmapnet.
- Thanks for pointing out this! We have fixed this on the main branch.
- Your modification looks great! Is this only a visualization change or did you also modify the labels? Also, feel free to create a pull request for this modification.
- (1) We use BCE loss and one adaptation is that we also "softmax" the label, that is if there are two 1s, then we will normalize them to 0.5. But I guess it would be fine to directly use sigmoid as the activation function.
(2) This configuration is used throughout the whole paper. For the second question, a larger perception range should result in worse numerical results because it could be harder for sensors to perceive roads at a long distance. As for the resolution, I think a larger resolution would result in heavier computation costs. Also the solution should not be too small because a road divider won't have a width, say 0.3m.
from hdmapnet.
How you visualize generated label?
from hdmapnet.
Related Issues (20)
- lost intrins in IPM transformation HOT 2
- vis_segmentation_label.py AttributeError: 'Tensor' object has no attribute 'astype' HOT 2
- Is there anyway to get the World Coordinates from predicted BEV?
- XIO: fatal IO error 0 (Success) on X server "localhost:10.0"
- Is there any wrong with eval_iou()? HOT 6
- 'instance_seg' and 'direction_pred' both use 'self.up1_embedded.' is it intended?
- Are the HDMaPNet results from the validation set or the nuscene test set?
- The vectorized visualization results are very bad, but the training accuracy is close to the accuracy proposed in the paper。 HOT 3
- problem while evaluating
- How to predict new Data set HOT 2
- result visualization HOT 2
- trouble installing torch==1.10.2+cu113 torchaudio==0.10.2+cu113 torchvision==0.11.3+cu113 HOT 1
- question about cameras extrinsics, is the plane generated from z_pitch_yaw better ?
- what dose the **sort_points_by_dist** function do
- vis_label.py not working HOT 2
- whether the trained weights has been released? HOT 1
- How to reproduce mAP?
- 关于测试地图分割结果的问题 HOT 1
- Not able to install requirement.txt HOT 4
- Pytorch version does not exist
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 hdmapnet.