ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices | Synced
The ShuffleNet utilizes pointwise group convolution and channel shuffle to reduce computation cost while maintaining accuracy. It manages to obtain lower top-1 error than the MobileNet system on Im...
Source: Synced | AI Technology & Industry Review
The ShuffleNet utilizes pointwise group convolution and channel shuffle to reduce computation cost while maintaining accuracy. It manages to obtain lower top-1 error than the MobileNet system on ImageNet classification, and achieves ~13x actual speedup over AlexNet while maintaining comparable accuracy.