Comments (5)
Hi, @ahangchen .
You're right that we put one validation data and one training data as a pair when validation.
So the score of objective-2 is different from objective-1 when validation.
However, it does not effect the final result. So I haven't changed the code.
And another reason is that the validation data is limited. Therefore I decide use the training data as another element in the pair when validation.
from 2016_person_re-id.
I can't agree that this doesn't effect the final result(the comparison accuracy)... The comparison is the result of feature extraction of two images. One of this extraction with familiar data will lead to higher accuracy of comparison while extraction with unseen data may lead to uncertain result and get lower accuracy.
Limitation of the validation data is a problem, but I prefer to reuse some of the validation data rather than reuse training data.
from 2016_person_re-id.
@ahangchen First of all, thank you. It is considered to be a validation bug. But we think the implicit result that we used presently also reflects the code running correctly. Because the another part is validation data which is blind to the model. Furthermore, we do not really care validation classification since we test on a retrieval problem.
Second, I will consider it again and may fix it next week. I am writing the new version of this code. In the next version, I will also provide a more stable training method.
from 2016_person_re-id.
@ahangchen
Today I update the second version of this repo and consider your suggestion again. It is nice to have a more reasonable validation curve.
But if we fix this, we need to ensure there are two validation images from same ID. We need to add some extra code to ensure this. I still think we do not really care about validation. To keep code simple, I decide to keep this version of validation. Besides, I still think the ideal curve should be similar to the validation curve now, if we train the model in the right way. So it is fine to use the present version.
Anyway, your suggestion is nice! Thank you very much.
from 2016_person_re-id.
@layumi Got it. Thank you for your reply. 😄
from 2016_person_re-id.
Related Issues (20)
- undefined function or variable 'dagnn.Square' HOT 6
- run zzd_evaluation_res_faster.m and got NULL HOT 1
- About the share weights? HOT 2
- some issues about Oxford5k dataset and train order HOT 3
- Use 2016_person_re-ID train DukeMTMC HOT 5
- about the cuhk03 evaluation HOT 15
- download link for pre-trained models HOT 6
- Attempt to execute SCRIPT vl_nnconv as a function: HOT 1
- Implementation on Keras HOT 2
- Pytorch implementation of this paper HOT 4
- The variable "dagnn" or class "dagnn.DagNN.loadobj" is not defined. HOT 5
- Undefined function or variable 'net' HOT 5
- about training the cuhk03 dataset HOT 1
- there is an error when i am running the train_id_net_res_2stream HOT 4
- some problem about softmax output
- 可视化 HOT 2
- the ratio of classification loss and verification loss is 1/2 HOT 4
- the way of ResNet-50-Basel HOT 2
- how to get the result of single query and multi query HOT 3
- how to make the activation maps HOT 3
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 2016_person_re-id.