frgfm / torch-scan

Seamless analysis of your PyTorch models (RAM usage, FLOPs, MACs, receptive field, etc.)

https://frgfm.github.io/torch-scan/latest

Apache License 2.0

208 stars 22 forks source link

feat: Added support of dilation in receptive field computation #28

Closed frgfm closed 3 years ago

frgfm commented 3 years ago

This PR addresses the issue raised in #27 by taking dilation into account for receptive field computation.

codecov[bot] commented 3 years ago

Codecov Report

Merging #28 into master will increase coverage by 0.05%. The diff coverage is 100.00%.

@@            Coverage Diff             @@
##           master      #28      +/-   ##
==========================================
+ Coverage   89.46%   89.52%   +0.05%     
==========================================
  Files           9        9              
  Lines         560      563       +3     
==========================================
+ Hits          501      504       +3     
  Misses         59       59

Impacted Files	Coverage Δ
torchscan/modules/receptive.py	`100.00% <100.00%> (ø)`