Iterative Filter Pruning for Concatenation-based CNN Architectures
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911869491478528 |
|---|---|
| author | Pavlitska, Svetlana Bagge, Oliver Peccia, Federico Mammadov, Toghrul Zöllner, J. Marius |
| author_facet | Pavlitska, Svetlana Bagge, Oliver Peccia, Federico Mammadov, Toghrul Zöllner, J. Marius |
| contents | Model compression and hardware acceleration are essential for the resource-efficient deployment of deep neural networks. Modern object detectors have highly interconnected convolutional layers with concatenations. In this work, we study how pruning can be applied to such architectures, exemplary for YOLOv7. We propose a method to handle concatenation layers, based on the connectivity graph of convolutional layers. By automating iterative sensitivity analysis, pruning, and subsequent model fine-tuning, we can significantly reduce model size both in terms of the number of parameters and FLOPs, while keeping comparable model accuracy. Finally, we deploy pruned models to FPGA and NVIDIA Jetson Xavier AGX. Pruned models demonstrate a 2x speedup for the convolutional layers in comparison to the unpruned counterparts and reach real-time capability with 14 FPS on FPGA. Our code is available at https://github.com/fzi-forschungszentrum-informatik/iterative-yolo-pruning. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_03715 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Iterative Filter Pruning for Concatenation-based CNN Architectures Pavlitska, Svetlana Bagge, Oliver Peccia, Federico Mammadov, Toghrul Zöllner, J. Marius Computer Vision and Pattern Recognition Model compression and hardware acceleration are essential for the resource-efficient deployment of deep neural networks. Modern object detectors have highly interconnected convolutional layers with concatenations. In this work, we study how pruning can be applied to such architectures, exemplary for YOLOv7. We propose a method to handle concatenation layers, based on the connectivity graph of convolutional layers. By automating iterative sensitivity analysis, pruning, and subsequent model fine-tuning, we can significantly reduce model size both in terms of the number of parameters and FLOPs, while keeping comparable model accuracy. Finally, we deploy pruned models to FPGA and NVIDIA Jetson Xavier AGX. Pruned models demonstrate a 2x speedup for the convolutional layers in comparison to the unpruned counterparts and reach real-time capability with 14 FPS on FPGA. Our code is available at https://github.com/fzi-forschungszentrum-informatik/iterative-yolo-pruning. |
| title | Iterative Filter Pruning for Concatenation-based CNN Architectures |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2405.03715 |