lingtengqiu / Deeperlab-pytorch

Segmentation realize Deeperlab only segmentation part
138 stars 27 forks source link

SeparableConvBnRelu instead of ConvBnRelu #5

Open XiaLiPKU opened 5 years ago

XiaLiPKU commented 5 years ago

https://github.com/lingtengqiu/Deeperlab-pytorch/blob/df58590f7f28e61956c62b676c3fc7006ed46174/model/deeperlab.py#L118

As written in the paper, Similar to the encoder, the decoder uses two large kernel (7 x 7) depthwise convolutions to further increase the receptive field. There should be SeparableConvBnRelu instead of ConvBnRelu.

XiaLiPKU commented 5 years ago

And the kernel size here should be 7 instead of 3

lingtengqiu commented 5 years ago

because my GPU(8G), so in here I use 3*3,U can modify it by yourself