PAGCP

PAGCP copied to clipboard

Code for NYUv2 Dataset

1

Hello, I see from your paper that you used PAGCP on the NYUv2 dataset, but in the code here you only have implementation for VOC and COCO, is it possible...

VojiWest

修改网络模型后如何修改相应文件

2

就是我将Conv换成了GhostConv之后 还有C3换成了C3Ghost 那我该如何修改文件 来完成减枝呢 一直出错误

Anoue

报错

2

作者你好，我这边有点疑问想请问一下，在使用您的代码的时候，我在电脑上调通并且已经跑完了，但是第二天醒来再继续跑的时候就发生了报错。想请问一下这是怎么回事，我也并没有动过任何地方。 raceback (most recent call last): File "C:/YOLO/PAGCP-main/compress.py", line 612, in main(opt) File "C:/YOLO/PAGCP-main/compress.py", line 576, in main opt.save_dir = str(increment_path(Path(opt.project) / opt.name, exist_ok=opt.exist_ok)) File "C:\YOLO\PAGCP-main\utils\general.py", line 804, in increment_path...

huangjunc

yolov8 pruning

5

Hi, will you consider coming out with yolov8 pruning as a follow-up?

Zzzxi

Selecting the channels

1

Is it possible to use this algorithm to find the most inappropriate channels for our task without deleting them?! (We can select the less suitable channels without deleting them.) Thank...

SarinaAhmadi

Pruning based on self built datasets

1

Hello, may I ask if it is possible to add a pruning method on a self built dataset? Currently, the dataset can only select ['VOC ',' COCO ']

rememberBr

Γ？

1

作者，您好。在框图中有FLOPs

l3355768368

剪枝后推理速度

2

作者您好，我使用您的框架进行剪枝，参数量、计算量都砍了一半左右，但是剪枝后模型推理时间变化不大，请问这正常吗？

Lz000613

关于剪枝前模型每层基于FLOPs重排问题

6

博主你好，我计算出每层卷积的FLOPs后，发现不论是按照升序还是降序，都与实际剪枝顺序不符合，这是什么问题呢

fengfasheng

如何重複剪枝

3

剪枝過一次的模型，想再剪枝一次壓縮參數量，目前是將剪枝過後的模型先載入，再載入權重，但會遇到以下問題，想請問這作法是否是對的? RuntimeError: Given groups=1, expected weight to be at least 1 at dimension 0, but got weight of size [0, 2, 1, 1] instead

YuuuHsiang