Layer-Wise Data-Free CNN Compression. (arXiv:2011.09058v3 [cs.CV] UPDATED)

We present a computationally efficient method for compressing a trained
neural network without using real data. We break the problem of data-free
network compression into independent layer-wise compressions. We show how to
efficiently generate layer-wise training data using only a pretrained network.
We use this data to perform independent layer-wise compressions on the
pretrained network. We also show how to precondition the network to improve the
accuracy of our layer-wise compression method. We present results for
layer-wise compression using quantization …

arxiv cnn compression cv data free