Some knowledge about DepthWiseConv

As we all know, people invent DepthWiseConv for more efficient computation cost without accuracy loss.

DepthwiseConv coupled with PointWiseConv could be equal to normal convlution.

DepthWiseConv means that we assign a single kernel to each feature channel. PointWiseConv is a normal convolution kernel with kernel size 1 and stride 1.

DepthWiseConv aims to extract the spatial feature of a feature map, while PointWiseConv aims to extracte the correlation of different feature maps.

What’s the implementation of GRU cell in tensorflow?

We can use a chart to demonstrate the GRU cell implementation in Tensorflow, and let’s take a two cells GRU for example:

The evolution of the Activation Style in Residual Blocks

The Activation Style is different between different residual structures.

The relationship with Densenet

Since I use shufflent_V2 on the task of Face Antispoofing for quit a time, I found that shufflenet_V2　is efficient yet also could provide high accuracy.