Skip to main content

Table 4 The performance of different network on CIFAR-10

From: An multi-scale learning network with depthwise separable convolutions

Method Iterations, 5000; batch_size, 128
Acc(%) Number of training parameters
GoogLeNet 76.5 6640
AlexNet 75.7 2016
MobileNet 65.6 251
Our method 1 72.4 529
Our method 2 71.1 529