Open zhyj3038 opened 5 years ago
@zhyj3038 Of course it works. We use Darknet just for the convenience of comparison with the original YOLOv3. You can also implement all the procedure of SlimYOLOv3 in pytorch for your convenience.
normal training is not neccessary for sparsity training? if i just want to prune the network can i skip the normal training step?
I wonder why step 1 and step 4 involve darknet, the pytorch version yolov3 can not wrk out it ?