Open wassname opened 8 months ago
Perhaps consider replacing geometric_median_dataset with nn.BatchNorm1d(x, affine=False) layer It doe a similar thing with less parameters and complexity.
geometric_median_dataset
nn.BatchNorm1d(x, affine=False)
Perhaps consider replacing
geometric_median_dataset
withnn.BatchNorm1d(x, affine=False)
layer It doe a similar thing with less parameters and complexity.