search

he-y / soft-filter-pruning

Soft Filter Pruning for Accelerating Deep Convolutional Neural Networks
https://arxiv.org/abs/1808.06866
374 stars 74 forks source link

How to preserve non-zero filters??? #5

Closed yuanze-lin closed 5 years ago

yuanze-lin commented 5 years ago

Thanks for your wonderful work, but I'm wondering how can I preserve finally compact model.

he-y commented 5 years ago

Please refer to the issue, which is similar to your proposed question.

yuanze-lin commented 5 years ago

Then have you test the compressed model under object detection algorithms(such as SSD, faster R-CNN etc) ???

he-y commented 5 years ago

No, we focus on the classification problem in this paper.

yyx1107 commented 4 years ago

Then have you test the compressed model under object detection algorithms(such as SSD, faster R-CNN etc) ???

Hi, have you try this?

he-y commented 4 years ago

@yyx1107 No. We focus on the image classification task.