AFallDay

What exactly does this method prune?

1

After reading the paper it never made sense that structured pruning was pruning what, parameters, weights? I think it's a bit abstract, please answer my questions, thanks!

How to iteratively prune in yolov5?

1

When I set the number of iterative pruning to 5, it only performs one pruning and then ends, how do I need to change the code to perform multiple iterative...

how can I prune destseg by using torching pruning tool? thanks

yolov5 pruning model does not detect images

14

Before Pruning: MACs=1.009904 G, #Params=0.007226 G After Pruning: MACs=0.379899 G, #Params=0.002635 G image 1/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000009.jpg: 480x640 (no detections), 101.8ms image 2/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000025.jpg: 448x640 (no detections), 82.9ms image 3/128 D:\Torch-Pruning-master\data\coco128\images\train2017\000000000030.jpg: 448x640...

Is there a better way to fine-tune yolov5s models after pruning

2

I've tried putting the pruning code into train.py, but its detection is only half as good as the original, is there a better way? thanks

 How do I fix the warning that appears on the second line, please

Is there a fine-tuning code for yolov5 after pruning? thanks @JonnyKong @VainF @eltociear @horseee @ghimiredhikura

ModuleNotFoundError: No module named 'ultralytics.yolo'

1

  How can I solve the problem? thanks

May I ask yolov5 how to port the method of calculating P, R, AP, MAP in val.py to adapt to detect.py, what code need to be packed?

3

### Search before asking - [X] I have searched the YOLOv5 [issues](https://github.com/ultralytics/yolov5/issues) and [discussions](https://github.com/ultralytics/yolov5/discussions) and found no similar questions. ### Question May I ask yolov5 how to port the method...

Why are the layers in ignored_layers still pruned?

5

Here is my code and the results of running it.   The layers printed out by ignored_layers are Detcet's layers, but it is still pruned. Here's the number of...