Skip to main content

Table 5 The performance of different network on SVHN

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

Method Iterations, 10000; batch_size, 128
Acc(%) Number of training parameters
GoogLeNet 92.3 6640
AlexNet 92.0 2016
MobileNet 90.8 251
Our method 1 91.6 529
Our method 2 91.3 529