Why use PReLU in DenseBlock?

ai-med / quickNAT_pytorch

PyTorch Implementation of QuickNAT and Bayesian QuickNAT, a fast brain MRI segmentation framework with segmentation Quality control using structure-wise uncertainty

MIT License

101 stars 36 forks source link

Why use PReLU in DenseBlock? #15

Closed zhuczhuc closed 4 years ago

zhuczhuc commented 5 years ago

In matlab code, only relu is used, but in pytorch version, why the dense block use PReLU? Thanks

abhi4ssj commented 4 years ago

The performance slightly increased by using PReLU instead of ReLU. This is upto the user what to use.