ResNet with bottleneck 3x3 Convolutions substituted by 3x3 Grouped Convolutions.
Image source: Squeeze-and-Excitation Networks
Image shows the architecture of SE block and where is it placed in ResNet bottleneck block.
This model was trained using script available on NGC and in GitHub repo.
The following datasets were used to train this model:
Performance numbers for this model are available in NGC.