Comments (12)
BTW, I am software engineer at LG Electronics US.
from dg-net.
Hi @bhooshan-supe-gmail
Yes. Since the original dataset do not provide the validation set, we split the validation set from the training set.
from dg-net.
@layumi
I am sorry to be nit picky but you have not split the data-set, but you have some part of training data-set duplicated as validation data-set.
On the other hand, I have made sure that in my data-set training and validation data-set are completely disjoint sets. And the side effect of that is my training and validation curves are not converging.
Please refer following image.
So I am wondering is this OK? Is this training reliable?
from dg-net.
-
Please check this line https://github.com/NVlabs/DG-Net/blob/master/prepare-market.py#L111
There are no-overlapping images between the training and validation set.
If you usetrain-all
, there will be the overlapping images. -
I do not know how you split the dataset. Actually, there are two ways to split the dataset.
-
One easy way is as shown in above. We select the first image of every class in the training set as the validation set. We evaluate the performance in a
Classification
style. -
Another way is in
Retrieval
style. Given 751 classes in the Market-1501 dataset, we split the first 651 classes as training set and leave out the 100 classes as validation set. We could use the images of 100 classes as query and gallery to evaluate the retrieval performance. However, since 100 classes have not beenseen
by the model, the model could not classify the images of the 100 classes.
from dg-net.
Hi @layumi
To be honest I am quite new to computer-vision and machine learning.
Thanks a lot for your guidance!
from dg-net.
Hi @layumi ,
We have our own but very small data-set (about 21 person-ids but about 1500 images).
And I am fine tuning on your model using our data-set.
Basically we are looking into how we can re-identify person from almost top-view (from a very steep angle) instead of side and/or front view.
from dg-net.
@bhooshan-supe-gmail
You may start from my tutorial, which is more straight forward https://github.com/layumi/Person_reID_baseline_pytorch/tree/master/tutorial
And recently I release a dataset and code for satellite-view, drone-view, ground-view geo-localization.
You are welcomed to check out it. https://github.com/layumi/University1652-Baseline
from dg-net.
Another way is in Retrieval style. Given 751 classes in the Market-1501 dataset, we split the first 651 classes as training set and leave out the 100 classes as validation set. We could use the images of 100 classes as query and gallery to evaluate the retrieval performance. However, since 100 classes have not been seen by the model, the model could not classify the images of the 100 classes.
How would you go about adding this retrieval style evaluation? does it make sense here to add retrieval style evaluation in addition to classification evaluation which makes the model to classify images to person/object ids?
from dg-net.
Hi @nikky4D
Sorry. What is 00 classes? Could you provide more descriptions?
from dg-net.
Sorry, I quoted it incorrectly, please see edited comment above
from dg-net.
Hi @nikky4D
-
Validation (Classification Setting)
I write it with the training code. You do not need to modify the split. -
Validation (Retrieval Setting)
If you want to evaluate on 651 / 100 split (751 ID in total), you need to modified the prepare data to split it.
Since the id is random, I simply use the first 651 ID as train and late 100 ID as val.
For validation on retrieval, you need to use the test.py to test the validation like the test setting.
(The validation result during the training is not correct. )
from dg-net.
Thank you. Then for the teacher training, is it better to use the retrieval split or classification setting for a more robust dg-net setup or does the dataset setup not matter in the final model?
from dg-net.
Related Issues (20)
- Train fp16 interrupt HOT 3
- Change the data set to train HOT 3
- doubt about a loss in the ‘gen_update’ HOT 2
- DG-Net_Trainer类的forward函数的一个疑问 HOT 1
- 如何采用训练好的模型去生成图片 HOT 1
- How to test accuracy. HOT 1
- in trainer.py /gen_update(), i cannot understand "encoder is tuned, input is fixed" and "encoder is fixed, input is tuned" HOT 1
- Doubt about dis_opt and gen_opt HOT 2
- How to use DG-Net for vehicle reid? HOT 2
- test_folder HOT 1
- Out of memory error while training the model HOT 1
- when I run train.py, print there error message. Can you help to solve the issue? Thank you ! HOT 1
- 关于inception score HOT 1
- 关于FID计算 HOT 4
- IndexError:Dimension out of range(excepted to be in range of [-1,0],but got 1) HOT 4
- how does two different networks extract appearance and clothing separately?
- appearance code and structure code HOT 1
- online feeding and identity supervision HOT 3
- test_2label报错 yaml.load()缺少 loader HOT 2
- why detach the gradient of appearance codes? HOT 4
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 dg-net.