LeapLabTHU/DAT

How to visualize the learned offsets?

zzwei1 opened this issue · 8 comments

Hi,nice work!
I'm confusing about visualizing the learned offsets as shown in Fig. 6?
Could you give some reference code?

What a nice work! I'm looking forward to the code of visualizations.Thank you!

The visualizations require a forward run of the object detection model on the MS-COCO validation dataset. Maybe I will release the visualization codes after the release of the object detection codes and the semantic segmentation codes.

Can we visualize the learned offsets with the classification task?

wewan commented

Would you mind also telling me how to visualize the Figure 5? Any code snippet?

The visualizations require a forward run of the object detection model on the MS-COCO validation dataset. Maybe I will release the visualization codes after the release of the object detection codes and the semantic segmentation codes.

Can you please release the snippet for this.

Hello @sharat29ag @wewan @cbq233333 @zzwei1,

I will release a notebook in next a few weeks in detection codebase to finish this.

Hello @hagianga21,

Ideally, it is feasible to visualize the offsets in classification tasks. However, the images are very small so the visual effects could not be as promising as expected.

Can we visualize the learned offsets with the Semantic Segmanatation task?