Comments (7)
What I do understand, please correct me if I'm wrong.
You can take these values from here layers/functions/detection_gmm.py:
For example, in the demo.py file... When you test some image you can use the while loop to obtain the uncertainty for each bbox, something like this:
max_loc_al_uc = torch.max(detections[0][i][j][5:9]) # 4 values (four coordinates values)
max_loc_ep_uc = torch.max(detections[0][i][j][9:13]) # 4 values (four coordinates values)
cl_al_uc = torch.max(detections[0][i][j][13:14]) # 1 value
cl_ep_uc = torch.max(detections[0][i][j][14:15]) # 1 value
from al-mdn.
For the localization, the 4 values are the uncertainty about the center, height, and weight {x, y, w, h}. On pg. 4 of the paper in section 3.3 Scoring Function: "[...] For localization,
And in the function you cited, you want to take the labeled_set because they have high score values, labeling them and continue the active learning loop.
from al-mdn.
Thank you @BrenoAV very much for your answer indeed the same thing that I understood but I have a small concern concerning the four values for the random and epistimological localisation why it sends 4 values instead of a single value as the case of the classification. and for the function can we use it if we want to select a set of images to label ?
from al-mdn.
thank you once again @BrenoAV for your help and support now things seem understandable.
from al-mdn.
Hello @BrenoAV
As you can see this line, output contains scores, box coordinates, aleatoric & epistemic uncertainties of each task.
You can print out each uncertainty value using detections
variable, like scores and box coordinates.
To output normalized values, you need to know the mean and variance of each uncertainty distribution for the dataset.
For doing this, you can use this function.
from al-mdn.
It makes sense now for me, thank you very much @jwchoi384
from al-mdn.
hello please if you have a concrete example how to recover them for each image?
@jwchoi384 @BrenoAV
from al-mdn.
Related Issues (20)
- How to use GMM in Faster RCNN? HOT 1
- Why using reparameterizaiton-trick for classification loss computation HOT 1
- Issue in running HOT 1
- Stop training after first iteration
- Uncertainties for different classes / class imbalance problem HOT 3
- Same learning rate schedules for COCO active learning and supervised learning
- Training stop in the last iteration iter:119999
- How to train on custom dataset ? HOT 2
- Where is the released code of AL-SSL? HOT 1
- Could you expose the code that gmm be applied to Faster-RCNN?
- Autograde issue while evalution HOT 1
- diverges during training on my own dataset HOT 1
- I am having a problem with the loss function as I am using FLIR dataset, it only has 12 classes that it uses, and this is causing an issue with the loss function, I would like to learn more about it in the supplementary notes, but I can't seem to find the supplementary, where are they? HOT 1
- The question of the mixture weight π of GMM HOT 3
- Error in VOC Evaluation script HOT 1
- Question of AL selecting the best weight HOT 2
- Hello, the running result of demo. py is abnormal. All the scores are concentrated around 0.1, and none exceeds 0.5. Have you ever encountered such problems
- RuntimeError: Error(s) in loading state_dict for DataParallel: HOT 2
- About Eq.5 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 al-mdn.