RANPAC#

Arguments#

Options

--rp_sizeint

Help: size of the random projection layer (L in the paper)

Default: 10000

Classes#

class models.ranpac_utils.ranpac.RanPAC_Model(backbone, args)[source]#

Bases: object

eval()[source]#

optimise_ridge_parameter(Features, Y)[source]#

replace_fc(trainloader)[source]#

to(device)[source]#

train(*args)[source]#

property training#