ONNXPruner: ONNX-Based General Model Pruning Adapter

arXiv:2404.08016v1 Announce Type: new
Abstract: Recent advancements in model pruning have focused on developing new algorithms and improving upon benchmarks. However, the practical application of these algorithms across various models and platforms remains a significant challenge. To address this challenge, we propose ONNXPruner, a versatile pruning adapter designed for the ONNX format models. ONNXPruner streamlines the adaptation process across diverse deep learning frameworks and hardware platforms. A novel aspect of ONNXPruner is its use of node association trees, which automatically …

abstract adapter algorithms application arxiv benchmarks challenge cs.lg format general however improving onnx platforms practical pruning type