Leveraging Structured Pruning of Convolutional Neural Networks
arXiv:2206.06247 · doi:10.1109/SiPS55645.2022.9919253
Abstract
Structured pruning is a popular method to reduce the cost of convolutional neural networks, that are the state of the art in many computer vision tasks. However, depending on the architecture, pruning introduces dimensional discrepancies which prevent the actual reduction of pruned networks. To tackle this problem, we propose a method that is able to take any structured pruning mask and generate a network that does not encounter any of these problems and can be leveraged efficiently. We provide an accurate description of our solution and show results of gains, in energy consumption and inference time on embedded hardware, of pruned convolutional neural networks.
arXiv comment6 pages, 5 figures, submitted to SiPS 2022
References in corpus (8)
- Distilling the Knowledge in a Neural Network
- Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding
- BinaryConnect: Training Deep Neural Networks with binary weights during propagations
- Pruning Convolutional Neural Networks for Resource Efficient Inference
- High-Resolution Representations for Labeling Pixels and Regions
- Scalable Training of Artificial Neural Networks with Adaptive Sparse Connectivity inspired by Network Science
- Region Mutual Information Loss for Semantic Segmentation
- Rethinking Weight Decay For Efficient Neural Network Pruning