Nguyễn Quốc Nhật Minh

I see in `yolov8_pruning.py` prune YOLOv8 that it always has to initialize a pruner and delete it repeatedly. When I try modifying this file, I initialize the pruner outside the...

Hi, I saw in the paper that to match student feature map size to teacher counterpart, we must use a conv2d to upscale student's feature map. However, I was confused...

About Adaptive Layer

2

I have some questions about adaptive layers when training KD. 1. When you combined your KD method with other intermediate feature map KD methods, you had to use adaptive layers...

Some questions about gcblock

1

When I read the `mmdet/distillation/losses/fgd.py`, there is something I can't understand. 1. In the init function of the `FeatureLoss`, at the end of that function, after all the initialization, why...

Hi, I'm trying to experiment with some criteria for yolov8 pruning with Taylor criteria. However, when I set the global pruning is True, the pruner doesn't prune. It only works...

Hi @VainF , I'm playing around with sparse training of `GroupNormPruner` for Yolov8. I read your instruction and it said I have to call `pruner.update_regularizer()` to initialize regularizer. However, I...

Implementation of "Structural Knowledge Distillation for Object Detection"

2

I read this paper [Structural Knowledge Distillation for Object Detection](https://arxiv.org/abs/2211.13133v1) and implemented KD with yolov8 but the result was very bad. I think that the problem was the way I...

Smaller pruned model yolov8s doesn't faster than original yolov8s on Tensor RT Jetson Nano

7

## Description I have 2 model yolov8s and pruned model yolov8s with smaller size. For the second model, I pruned its channel using structural pruning method of [Torch pruning](https://github.com/VainF/Torch-Pruning). After...

Inquiry about Layer Performance of FP16

4

## Description Hi, I'm newer to TensorRT and I'm trying to understand the layer performance. I read the doc [Optimizing for Tensor Cores](https://docs.nvidia.com/deeplearning/tensorrt/developer-guide/index.html#optimize-tensor-cores) and see that with the FP16 precision,...

TaskAlignedAssigner: difference between target_labels and target_gt_idx?

1

### Search before asking - [X] I have searched the Ultralytics YOLO [issues](https://github.com/ultralytics/ultralytics/issues) and [discussions](https://github.com/ultralytics/ultralytics/discussions) and found no similar questions. ### Question Hi, I'm trying to calculate varifocal loss for...