search

Megvii-BaseDetection / GFSD

This project provides an implementation for "Generalized Few-Shot Object Detection without Forgetting" (CVPR2021) on PyTorch.
Apache License 2.0
46 stars 4 forks source link

Demo #5

Closed 2006pmach closed 3 years ago

2006pmach commented 3 years ago

Hi, is there an easy way to predict the boxes for a given input image? Something like this? Would be very helpful to actually look at the predictions beside computing the metrics... I also checked CVPODS for such a script but it seems to be missing there as well. Thx.

zb1439 commented 3 years ago

You can refer to https://github.com/Megvii-BaseDetection/cvpods/blob/master/tools/visualize_json_results.py which visualize the saved json file. Also, you can write your own code with fresh input images and visualize them using the APIs provided in cvpods, this python file also provides a good example.