With the recent advancement in the field of deep learning building deeper convolutional neural networks has become a trend for solving visualization problems. Though it gives accurate results the CNNs require computation of billions of FLOPS. To overcome this issue we introduce a computation efficient CNN architecture named ShuffleNet which is designed especially for mobile devices, drones and robots. It gives the best accuracy in the very limited computational budget.

This article demonstrates how we can implement a deep learning model with ShuffleNet architecture to classify images of CIFAR-10 dataset. Here, we define a Convolutional Neural Network (CNN) model using Torch to train this model. We will test the model to check the reduction in computational cost and obtain accuracy.

Architecture of ShuffleNet

This architecture uses pointwise group convolutions and channel shuffling to reduce the computational cost. In the first case, information is blocked as outputs from a certain group only relate to inputs within the group. To solve this issue we use channel shuffling operation as illustrated in the second case of the above figure. Information is passed on to different groups in the group convolution layer.

#developers corner #computer vision #deep learning #image classification #shufflenet