About the structure of the DDRNet

[zhuzhuzhu2]

Dera Yuanduo

Thanks very much for your perfect Network. I have a question about the structure of the DDRNet.

In your program code, the layer of the bottleneck block in the low-resolution branch was made with stride=2, I think after this bottleneck block, the output size will become 1/2. And in your paper, as the image below shows, in the conv5_1 of the low-resolution branch, one Residual basic block (stride=2) and one bottleneck block(stride=2) have been used. Why does the output size change from14x14 to 7x7 after two blocks whose stride is both equal to 2?

I would appreciate it if you would answer my question.

[ydhongHIT]

Dera Yuanduo

Thanks very much for your perfect Network. I have a question about the structure of the DDRNet.

In your program code, the layer of the bottleneck block in the low-resolution branch was made with stride=2, I think after this bottleneck block, the output size will become 1/2. And in your paper, as the image below shows, in the conv5_1 of the low-resolution branch, one Residual basic block (stride=2) and one bottleneck block(stride=2) have been used. Why does the output size change from14x14 to 7x7 after two blocks whose stride is both equal to 2?

I would appreciate it if you would answer my question.

Stride = 2 is for cityscapes. For imagenet, stride should be 1. The stride can be adjusted flexibly according to the image resolution.