Skip to content

Latest commit

History

11 Commits

Folders and files

NameName
Last commit message
Last commit date

Repository files navigation

CondConv-tensorflow

Conditional convolution (Dynamic convolution) in tensorflow2.2.0. This depository implements the method described in the paper:

CondConv: Conditionally Parameterized Convolutions for Efficient Inference
Brandon Yang, Gabriel Bender, Quoc V.Le, Jiquan Ngiam
Source PDF

Meanwhile, the softmax with a large temperature for kernel attention introduced by Dynamic Convolution: Attention Over Convolution Kernels is adopted.

Another similar paper: DyNet: Dynamic Convolution for Accelerating Convolutional Neural Networks.

Start

You can start according to the default arguments by python main.py. Or specify the arguments:

pythonmain.py--archcond_cifar_resnet--num_layers56--num_experts3--datasetcifar10--num_classes10

About

Conditional convolution (Dynamic convolution) in tensorflow2

Topics

Resources

Stars

22 stars

Watchers

1 watching

Forks

Releases

Packages

Contributors

Languages