论文标题
E2GC：深神经网络中的节能小组卷积
E2GC: Energy-efficient Group Convolution in Deep Neural Networks
论文作者
论文摘要
选择组卷积（GCONV）的组（$ g $）数量以以计算和参数有效方式提高深神经网络（DNNS）的预测性能。但是，我们表明，幼稚的$ g $ GCONV选择会在计算复杂性和数据重用程度之间产生不平衡，从而导致DNNS的次优效率。我们设计了一个最佳的组尺寸模型，该模型可以在计算成本和数据移动成本之间保持平衡，从而优化了DNN的能源效率。根据该模型的见解，我们提出了一个“节能组卷积”（E2GC）模块，在该模块中，与GCONV的先前实现不同，组大小（$ g $）保持不变。此外，为了证明E2GC模块的功效，我们将此模块纳入了Mobilenet-V1和Resnext-50的设计中，并在两个GPU，P100和P4000上执行实验。我们表明，在可比的计算复杂性下，具有恒定组大小（E2GC）的DNN比具有固定数量的组（F $ G $ GC）的DNN更节能。例如，在P100 GPU上，当E2GC模块在两个DNN中替换F $ G $ GC模块时，Mobilenet-V1和Resnext-50的能源效率分别增加了10.8％和4.73％。此外，通过我们对Imagenet-1K和Food-101图像分类数据集进行广泛的实验，我们表明E2GC模块可以在DNN的概括能力和代表力之间进行权衡。因此，可以通过选择适当的$ g $来优化DNN的预测性能。代码和训练有素的模型可在https://github.com/iithcandle/e2gc-release上找到。
The number of groups ($g$) in group convolution (GConv) is selected to boost the predictive performance of deep neural networks (DNNs) in a compute and parameter efficient manner. However, we show that naive selection of $g$ in GConv creates an imbalance between the computational complexity and degree of data reuse, which leads to suboptimal energy efficiency in DNNs. We devise an optimum group size model, which enables a balance between computational cost and data movement cost, thus, optimize the energy-efficiency of DNNs. Based on the insights from this model, we propose an "energy-efficient group convolution" (E2GC) module where, unlike the previous implementations of GConv, the group size ($G$) remains constant. Further, to demonstrate the efficacy of the E2GC module, we incorporate this module in the design of MobileNet-V1 and ResNeXt-50 and perform experiments on two GPUs, P100 and P4000. We show that, at comparable computational complexity, DNNs with constant group size (E2GC) are more energy-efficient than DNNs with a fixed number of groups (F$g$GC). For example, on P100 GPU, the energy-efficiency of MobileNet-V1 and ResNeXt-50 is increased by 10.8% and 4.73% (respectively) when E2GC modules substitute the F$g$GC modules in both the DNNs. Furthermore, through our extensive experimentation with ImageNet-1K and Food-101 image classification datasets, we show that the E2GC module enables a trade-off between generalization ability and representational power of DNN. Thus, the predictive performance of DNNs can be optimized by selecting an appropriate $G$. The code and trained models are available at https://github.com/iithcandle/E2GC-release.
