The deployment of convolutional neural networks is often hindered by high
computational and storage requirements. Structured model pruning is a promising
approach to alleviate these requirements. Using the VGG-16 model as an example,
we measure the accuracy-efficiency trade-off for various structured model
pruning methods and datasets (CIFAR-10 and ImageNet) on Tensor Processing Units
(TPUs). To measure the actual performance of models, we develop a structured
model pruning library for TensorFlow2 to modify models in place (instead of
adding mask layers). We show that structured model pruning can significantly
improve model memory usage and speed on TPUs without losing accuracy,
especially for small datasets (e.g., CIFAR-10).

本研究使用 VGG-16 模型作为示例，测量了各种结构模型修剪方法和数据集（CIFAR-10 和 ImageNet）在 Tensor Processing Units（TPUs）上的准确性和效率之间的权衡，使用 TensorFlow2 开发了一个结构模型修剪库以在 TPUs 上显着提高模型内存使用和速度而不失准确性，这尤其适用于较小的数据集（如 CIFAR-10）。