Factorized Convolutional Neural Networks: at least 3 times off from old convolutional layer!!

apache / mxnet

Lightweight, Portable, Flexible Distributed/Mobile Deep Learning with Dynamic, Mutation-aware Dataflow Dep Scheduler; for Python, R, Julia, Scala, Go, Javascript and more

https://mxnet.apache.org

Apache License 2.0

20.77k stars 6.79k forks source link

Factorized Convolutional Neural Networks: at least 3 times off from old convolutional layer!! #3047

Closed starimpact closed 7 years ago

starimpact commented 8 years ago

http://arxiv.org/abs/1608.04337. Can you implemented it with mxnet? I heard it has been done with tensorflow. @tqchen @piiswrong

winstywang commented 8 years ago

Your contribution is welcomed :)

austingg commented 8 years ago

It's tf.nn.separable_conv2d() in TensorFLow

phunterlau commented 7 years ago

This issue is closed due to lack of activity in the last 90 days. Feel free to reopen if this is still an active issue. Thanks!