Comments (20)
Great, thanks. Didn't think that it would make such a difference. We will look in to it and possibly add it.
from pytracking.
Are the results that you mention (0.678 and 0.657) from a single run of the tracker, or an average over multiple runs? Due to the stochastic nature of the tracker, the results of the tracker can very slightly over different runs. Hence in the paper, we report an average over 5 runs.
from pytracking.
Are the results that you mention (0.678 and 0.657) from a single run of the tracker, or an average over multiple runs? Due to the stochastic nature of the tracker, the results of the tracker can very slightly over different runs. Hence in the paper, we report an average over 5 runs.
Sure, I run 5 times, and average the results.
from pytracking.
Ok. I will recheck the models we have trained and the train settings and get back to you.
from pytracking.
Ok. I will recheck the models we have trained and the train settings and get back to you.
Thank you for your attention! I find that the max frame interval in source code is 50, whereas in paper is 100. I have not validate where this difference will influence the performance. In addition, I ran in pytorch0.4.1, centos7, python3.7, and TITAN X(pascal).
from pytracking.
Ok. I will recheck the models we have trained and the train settings and get back to you.
I have not validate where -> I have not validated whether. Sorry for clerical error.
from pytracking.
The released models were trained using max gap 50 as well. We have updated this on arxiv (https://arxiv.org/pdf/1811.07628.pdf).
from pytracking.
The released models were trained using max gap 50 as well. We have updated this on arxiv (https://arxiv.org/pdf/1811.07628.pdf).
In addition, as you paper said " We use image flipping and color jittering for data augmentation." But it seems that only ToGrayscale and ToTensorAndJitter augmentation methods are employed during training.
from pytracking.
Yes, the image flipping and color jittering are indeed missing from the release code. We hope to integrate them soon. The released models were however also trained without them. So they should not be the reason for the performance gap.
from pytracking.
Yes, the image flipping and color jittering are indeed missing from the release code. We hope to integrate them soon. The released models were however also trained without them. So they should not be the reason for the performance gap.
The color jittering may not missing. It seems that ToTensorAndJitter includes the color jittering. Thus, only flipping is missing.
from pytracking.
Its true, only flipping is missing. Regarding the OTB results, in the ATOM paper we calculate AUC for all methods with 100 threshold values, to get a more accurate estimate. In the default setting of using 20 threshold, ATOM has 0.669.
from pytracking.
Its true, only flipping is missing. Regarding the OTB results, in the ATOM paper we calculate AUC for all methods with 100 threshold values, to get a more accurate estimate. In the default setting of using 20 threshold, ATOM has 0.669.
It doesn't seem to be a question of evaluation method. I train the model using the released code, then testing the OTB2015 results (denoted by R1). Then, I test the OTB2015 results (denoted by R2) of the released model. Both R1 and R2 are calculated AUC with 100 threshold values, and their means are 0.657 and 0.678, respectively.
from pytracking.
Its true, only flipping is missing. Regarding the OTB results, in the ATOM paper we calculate AUC for all methods with 100 threshold values, to get a more accurate estimate. In the default setting of using 20 threshold, ATOM has 0.669.
When flipping is missed, the final train loss is about 0.04, and when flipping is employed, the final train loss is about 0.09. Are these consistent with your training?
from pytracking.
If you do flipping, you must also remember to flip the bounding box annotations.
from pytracking.
If you do flipping, you must also remember to flip the bounding box annotations.
Sure, I do this.
from pytracking.
I don't know if the closed issue's new comment anthor could receive the notice or not. I have some doubt at #8 (comment) after read the ATOM's track logic.
Expecting answers, best regards!
from pytracking.
@dongfangduoshou123 We get notifications of your posts, even if the issue is closed. So you do not have to post here.
from pytracking.
If you do flipping, you must also remember to flip the bounding box annotations.
Now, after adding flip, I get the tracking performance which is the same as the released model, that is 0.676 AUC on OTB2015.
from pytracking.
Thank you for your excellent work and sharing!
I trained the atom using the source code, and all configurations and employed training sets are same as those in the source code. Then, use the last epoch to test on OTB2015. However, compared the released model whose AUC on OTB2015 is 0.678, I only get 0.657 AUC with the model trained by myself.
Did you write training code yourself?
from pytracking.
@ @noUmbrella can you tell me how to add filp? thank you for you work
from pytracking.
Related Issues (20)
- Error building extension '_prroi_pooling' HOT 9
- How to get box confidence score? HOT 4
- Train on custom dataset HOT 1
- Save video results HOT 1
- Training E.T.Track
- Initialization of tracker in a different code.
- Model of TaMOs HOT 2
- about avist HOT 1
- how to deal with No module named 'prroi_pool' HOT 2
- How to use my training model(.pth.tar file) to track with custom datasets ? HOT 1
- Can tomp process multiple images at once as batches? HOT 2
- Error building extension '_prroi_pooling' HOT 3
- Tamos has many bugs HOT 1
- Update installation for windows
- No matching checkpoint file found HOT 1
- Support for LMDB Dataset HOT 1
- TensorRT Conversion of KeepTrack HOT 2
- RTS Tracker Prediction Score HOT 1
- Documentation? HOT 1
- About TaoBurst.json 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 pytracking.