SqueezeNet Deep Compression + pytorch pruning

  1. How do I interface this pruning code with SqueezeNet Deep Compression (0.66MB) ?
    The pruning code currently uses version 1.1 of SqueezeNet which is 2.8MB
    The 0.66MB version is in caffe format, is there any easy way to make it pytorch-friendly ?

  2. Besides, do you guys know where or how to obtain the 0.47MB version of SqueezeNet ?
    In other words, how to make the weights bitwidth to be 6 instead of 8 ?
    I cannot find the modification spot in this SqueezeNet generation code.