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

老哥,我想问一下,这个代码的训练出来的模型,怎么样在官方版centernet使用? #1

Open
idantony opened this issue Dec 6, 2021 · 2 comments

Comments

@idantony
Copy link

idantony commented Dec 6, 2021

您好,我是一个初学者,正如题目所说,我在结合您这个代码和官方版https://github.com/xingyizhou/CenterNet 一起在看代码学习,我用您这个跑出来的模型,想试试在官方版里试试推论,但是参数和代码不知道怎么改,请多多指教!

@GNAYUOHZ
Copy link
Owner

GNAYUOHZ commented Apr 4, 2022

你好,网络不是完全一样的,不能通用的

@zubi00
Copy link

zubi00 commented Jun 23, 2022

I am using your code "[https://github.com/GNAYUOHZ/centernet-visdrone]" for object detection only to train in my own dataset. I changed the code where necessary but after training, I always encounter the same error as shown below. Hope you will consider my request.
evaluating object category 1/10...
evaluating object category 2/10...
evaluating object category 3/10...
evaluating object category 4/10...
Evaluation completed. The performance of the detector is presented as follows.
2022-06-23 08:32:56: AP [IoU=0.50:0.95 | maxDets=500] = 11.79%.
2022-06-23 08:32:56: AP [IoU=0.50 | maxDets=500] = 19.20%.
2022-06-23 08:32:56: AP [IoU=0.75 | maxDets=500] = 13.12%.
2022-06-23 08:32:56: AR [IoU=0.50:0.95 | maxDets= 1] = 3.39%.
2022-06-23 08:32:56: AR [IoU=0.50:0.95 | maxDets= 10] = 8.80%.
2022-06-23 08:32:56: AR [IoU=0.50:0.95 | maxDets=100] = 13.54%.
2022-06-23 08:32:56: AR [IoU=0.50:0.95 | maxDets=500] = 27.67%.
2022-06-23 08:32:56: Class Car AP = 10.82%
2022-06-23 08:32:56: Class Truck AP = 13.81%
2022-06-23 08:32:56: Class Stop-Sign AP = 19.76%
2022-06-23 08:32:56: Class Traffic-Light AP = 0.63%
Traceback (most recent call last):
File "C:\centernet-motive\test.py", line 130, in
test_visdrone()
File "C:\centernet-motive\test.py", line 112, in test_visdrone
f'Class {opt.dataset_info["class_name"][i]} AP = {ap:3.2f}%')
IndexError: list index out of range

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

3 participants