Structured Binary Neural Networks for Image Recognition

    Cited by: 2|Bibtex|Views14|Links

    Abstract:

    We propose methods to train convolutional neural networks (CNNs) with both binarized weights and activations, leading to quantized models that are specifically friendly to mobile devices with limited power capacity and computation resources. Previous works on quantizing CNNs often seek to approximate the floating-point information using...More

    Code:

    Data:

    Your rating :
    0

     

    Tags
    Comments