-
大佬您好，谢谢你的开源，请问我用yolov5m完成稀疏训练过后，在用prune.py剪枝的过程中出现了以下报错，希望大佬解答一下在m，l模型剪枝的时候需要对prune.py做哪些修改，还是我这里是其他错误的原因，十分感谢感谢感谢
from n params module arguments
0 -1 1 5280 models.common.Focus [3, 48, 3]
1 -1 1 4…
-
### Search before asking
- [X] I have searched the Ultralytics YOLO [issues](https://github.com/ultralytics/ultralytics/issues) and [discussions](https://github.com/ultralytics/ultralytics/discussion…
-
I use yolov8 pruning code, to be more precisely the updated version for the new version of ultralytics: https://github.com/chbw818/yolov8-prune-using-torch-pruning-/tree/main
I am struggling with l…
-
## Issue description
Using torch.ao.quantization to do Post-training Static Quantization , didn't show error but it's not change the model layer to quantized layer(ex: nn.Conv2d is still Conv2d …
-
### 问题确认 Search before asking
- [X] 我已经查询[历史issue](https://github.com/PaddlePaddle/PaddleDetection/issues)，没有发现相似的bug。I have searched the [issues](https://github.com/PaddlePaddle/PaddleDetection/issu…
-
https://arxiv.org/abs/1907.11093
-
I just started using NNCF and I used NNCF to do filter pruning on Yolov5s. When I trained the model according to the steps in `Useage`, the model could be trained or saved using `torch. save`, but it …
-
您好
我按照readme 稀疏训练以后，使用prune.py时，出现了RuntimeError: Given groups=1, weight of size [115, 128, 1, 1], expected input[1, 111, 80, 80] to have 128 channels, but got 111 channels instead
去查了一下，好像是img读取的问…
-
I am running the notebook YOLO example of TLT Version 2 release in the tlt docker. I have successfully trained, pruned, and retrained the YOLO-restnet18. The results of FP32’s are fine but when I exec…
-
Hello,
I want to use the COCO train dataset for Fine-tuning after pruning yolov8n model. I tried to keep just train2017.cache in the dataset folder however, it always points to the validation subset…