RandBox icon indicating copy to clipboard operation
RandBox copied to clipboard

[ICCV 2023] PyTorch implementation of RandBox

Results 9 RandBox issues
Sort by recently updated
recently updated
newest added

请问t2和t2_ft的区别是什么

Hello author, I conducted experiments according to your file configuration (completely consistent settings) and found that the experimental results are different from the paper results. Task t1: **AOSE** is about...

I have downloaded the Coco and VOC datasets. How can I divide these datasets into t1, t2, t2_ft..........

Hello. First of all, thank you for your work and for sharing it! I am implementing the evaluation process of OWOD (defined in ```PascalVOCDetectionEvaluator.evaluate```). I have encountered several problems to...

How do you use your own images or videos for inference detection? Is there a script?

How long does it take for a 512 × 512 graph to be output in real time? Can it be converted to TRT?

Thank author for your great work. I am wondering how to draw Figure 2 in the paper as shown blow: ![image](https://github.com/scuwyh2000/RandBox/assets/39270545/e9307f49-1014-423c-b7b3-fb18c3430977) I have the following questions about the implementation of...

Namaste, This is regarding function [loss_nc_labels](https://github.com/scuwyh2000/RandBox/blob/b623402632265dee0ce48ba909eb329cccbfcc4a/randbox/loss.py#L156) Whatever computed till [line 183](https://github.com/scuwyh2000/RandBox/blob/b623402632265dee0ce48ba909eb329cccbfcc4a/randbox/loss.py#L183) is not used for further computation at all. Then in [line 186](https://github.com/scuwyh2000/RandBox/blob/b623402632265dee0ce48ba909eb329cccbfcc4a/randbox/loss.py#L186) the variable `target_classes_onehot` is defined as follows:...

Namaste, Thank you very much for the code. In the following [line](https://github.com/scuwyh2000/RandBox/blob/9b1f7d8e855d2fe9e512e8ac929d3a5f38ede652/randbox/detector.py#L327) diffused boxes are created. I have two questions: 1. The lines previous to this creates many variables which...