Skip to content
This repository has been archived by the owner on Dec 8, 2024. It is now read-only.

Can anyone train coco from scratch? #144

Open
ckqsars opened this issue Apr 24, 2020 · 1 comment
Open

Can anyone train coco from scratch? #144

ckqsars opened this issue Apr 24, 2020 · 1 comment

Comments

@ckqsars
Copy link

ckqsars commented Apr 24, 2020

I have train the d0 on coco 2 weeks, whatever I change the learning rate, or other parameters, the val cl loss is around 1.0 but the map is 0

Classification loss: 1.15289. Regression loss: 0.11328. Total loss: 1.26617

Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.000
Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.000
Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.000
Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.000
Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.000
Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.000
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.000
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.000
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.001
Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.000
Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.001
Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.003

@luckyxianxian
Copy link

I also have this problem. Have you solved it? Ask for help.

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

No branches or pull requests

2 participants