Torch-Pruning

Torch-Pruning copied to clipboard

Error in pruner.step() aufter update to 1.1.9

1

Hi, I updated from 1.0.0 to 1.1.9 today and now I get the following error when running pruner.step(): ``` pruner.step() File "/home/mle/prune_data_collection/pruning_benchmark_tool/.venv/lib/python3.8/site-packages/torch_pruning/pruner/algorithms/metapruner.py", line 159, in step for group in self.prune_global():...

martin-91x

[Warning] Unknown operation None encountered, which will be handled as an element-wise op

1

when i prune, i get warning: > site-packages/torch_pruning/dependency.py:738: UserWarning: [Warning] Unknown operation None encountered, which will be handled as an element-wise op > str(grad_fn)) So my parameters don't reduce (Before...

hoangdung3498

Varying max_sparsity from 0.1 to 0.9 for ALL Six pruners

4

I have been trying to change the ch_sparsity for all the six pruners Random, L1, lamp, Slim, GroupNorm and Group_sl. and then trying to compare the results that how much...

tajwar12

剪枝后训练，有没有边剪枝边训练

5

在benchmarks中，main.py和main_imagenet.py都是剪枝后训练 有没有边剪枝边训练的代码？

eeric

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...

minhhotboy9x

Hello, I am trying to apply filter pruning to NAFNet. I'm trying to pruning [this](https://github.com/megvii-research/NAFNet/blob/main/basicsr/models/archs/NAFNet_arch.py) architecture I used this code to prune the model. ```python if __name__ == '__main__': img_channel...

bnomq

使用 Torch-Pruning对backbone Resnet50_v2的人脸landmark-68点检测模型进行剪枝，可以剪枝，但是使用剪枝后的模型预测会出现报错 剪枝log Network_resnet50( (model): ResNet( (conv1): Conv2d(1, 32, kernel_size=(7, 7), stride=(2, 2), padding=(3, 3), bias=False) (bn1): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (relu): ReLU(inplace=True) (maxpool): MaxPool2d(kernel_size=3, stride=2, padding=1, dilation=1,...

qiulongquan

MultiheadAttentionPruner implementation does "random pruning" in inner dimensions of MHA

1

Hi, thanks for contributing a great library! I've been doing a close-up study of the `MultiheadAttentionPruner` implementation, and I have some concerns. The pruning of output channel in out_proj makes...

LukasHedegaard

RT

LuShouPeng

What is 'N' in "Iˆ = N · I / P{TopN(I )}"

1

Hello I'm a beginner. I would like to know the meaning of "N" used in the mathematical formula in the attached photo.

miki0902