DIODE icon indicating copy to clipboard operation
DIODE copied to clipboard

Official PyTorch implementation of Data-free Knowledge Distillation for Object Detection, WACV 2021.

Results 11 DIODE issues
Sort by recently updated
recently updated
newest added

Great works! But I wonder whether this method can be used for a two-stage object detector, e.g., Faster RCNN or not?

Hi @akshaychawla. Thanks for the code. I tried to generate images of KITTI dataset with yolov3 model but got bad results. I used my own yolov3 pretrained model / cfg...

Hi @akshaychawla, could you please give me access to the GCS data? Thanks a lot.

@akshaychawla Hi, I recently try to reproduce your work, and face one error and didnt figure it out yet. I just downloaded the tiled pseudo data as the training data,...

Hi @akshaychawla, can you give me access to the GCS data? Thanks so much.

As the comments in [LINE_looped_runner_yolo.sh](https://github.com/NVlabs/DIODE/blob/yolo/scripts/LINE_looped_runner_yolo.sh) show, the authors use 28 gpus to generate a dataset in 48 hours. Can you provide the detailed running time of a) generate 160x160 images,...

I just download the pretrained model 'yolo-tiny.pt' and 'yolov3-spp-ultralytics.pt' and try to run the script. However, I met the loading error 'RuntimeError: storage has wrong size: expected 0 got 32768'...

Good day, Thank you for the nice job and for making it open-source ~ I have some doubts about these two losses. Could you please explain why you have taken...

Due to the size of the google cloud storage bucket, it became prohibitively expensive to continue hosting the data on GCS. If you need access to the cloud storage bucket...

Hi @akshaychawla could you please give me access to the data of DIODE? The permission of the download link was denied. Thanks a lot!