Skip to content

Instantly share code, notes, and snippets.

@samson-wang
Last active March 3, 2024 12:15
Show Gist options
  • Save samson-wang/a6073c18f2adf16e0ab5fb95b53db3e6 to your computer and use it in GitHub Desktop.
Save samson-wang/a6073c18f2adf16e0ab5fb95b53db3e6 to your computer and use it in GitHub Desktop.
ResNet Receptive Field Size
layer resnet18 resnet34 resnet50 resnet101
conv1 7 7 7 7
maxpool 11 11 11 11
layer1 43 59 35 35
layer2 99 179 91 91
layer3 211 547 267 811
layer4 435 899 427 971

This is calculated on ResNet-V2 which does a stride 2 convolution on 3x3 kernel.

@kriskorrel-cw
Copy link

@kriskorrel-cw Stride 2 on Conv1x1 is referred to ResNet-v1. And Stride 2 on Conv3x3 is V2 which performs better than v1.

Actually, there are plenty of versions of resnet, i.e. https://arxiv.org/abs/1812.01187 FYI.

Ah I see. Yeah I was basing my calculations on the original version. I don't know what the RF is for other versions.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment