Open NoLookDefense opened 2 years ago
Hi, @NoLookDefense Thanks for your interest. Our experiments on object detection is conducted base on another Github repo (https://github.com/lzx1413/PytorchSSD). Please also refer to issue https://github.com/changlin31/DS-Net/issues/4
Thank you. I noticed that the code is recently updated two years ago. Is it just an SSD implementation, without your algorithms like slimmable NN and gating implementation?
Yes, we currently don't have plans to release the detailed code for object detection. Sorry for any inconvenience.
@changlin31
Do we need to use the pretrained weight trained from slimmer algorithm if we want to train object detection?
@changlin31
Do we need to use the pretrained weight trained from slimmer algorithm if we want to train object detection?
Hi @twmht
We used the dynamic slimmable pretrained weight for our object detection results in the paper. But I expect performing slimmable training on object detection task with a normally pretrained network is also possible. (We are getting good results with the second training approach on action recognition tasks)
@changlin31
What is your second training approach? Did you mention in the paper?
@twmht
By second approach, I mean: first, directly load a normal ImageNet pre-trained model (e.g. pytorch ResNet checkpoint) and then, perform supernet training and gate training on the downstream tasks.
I did not mention this in the paper. This is a work we are currently working on.
@changlin31
did you also use in-place distilling with object detection? Which loss did you use for the classification branch?
Hello. Thanks for your work. I noticed that you also conducted some experiments in object detection. I wonder whether or when you will release the code