Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

How to organize data sets? #1

Open
Kiritooo opened this issue Mar 13, 2018 · 8 comments
Open

How to organize data sets? #1

Kiritooo opened this issue Mar 13, 2018 · 8 comments

Comments

@Kiritooo
Copy link

hello, I'm new of the CV, I want to use your code to understand how to use dataset for pose estimation, but I don't know how to deal with data sets and name, I will not submit results to match only for learning, can you give a README thank you!

@Lmy0217
Copy link
Owner

Lmy0217 commented Mar 14, 2018

@Kiritooo We add README and will gradually improve it. If you want to know the approach of deal with data sets, please read datasets.py carefully.

@wuhaotju
Copy link

兄弟,线上能到多少?

@shiontao
Copy link

I find that the Accuracy is very low, what about you?

@shiontao
Copy link

Train Epoch: 16 [7680/9056 (85%)] Loss: 1.734629 Train Epoch: 16 [8320/9056 (92%)] Loss: 1.775722 Train Epoch: 16 [8960/9056 (99%)] Loss: 1.782988 Test set: Average loss: 2.9240, Accuracy: 369/2264 (16%) Train Epoch: 17 [0/9056 (0%)] Loss: 1.722289 Train Epoch: 17 [640/9056 (7%)] Loss: 1.780630 Train Epoch: 17 [1280/9056 (14%)] Loss: 1.787481 Train Epoch: 17 [1920/9056 (21%)] Loss: 1.722810 Train Epoch: 17 [2560/9056 (28%)] Loss: 1.876558
Is that normal?

@augusyan
Copy link

@rmfckaka I think it may be caused by overfitting, try image enhancement algorithm to enlarge your datasets. And the train loss increased , I guess u may take a smaller lr to train the model.

@wuhaotju
Copy link

@rmfckaka 我没有尝试

@aigeek
Copy link

aigeek commented Apr 20, 2018

分数百分之几?

@wzjiang
Copy link

wzjiang commented May 15, 2018

我的准确率也不高,没参加比赛,想试一下这个任务,有加群交流的吗(102611529)

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

7 participants