Contents Menu Expand Light mode Dark mode Auto light/dark mode
Mammoth
Mammoth

Getting started:

  • First steps
  • Load and save checkpoints
  • Distributed training
  • Scripts
  • Parseval

Contents:

  • Models
    • Coda Prompt Utils
      • model
      • vit
    • Deprecated
      • joint
    • Dualprompt Utils
      • attention
      • model
      • prompt
      • vision_transformer
    • L2p Utils
      • l2p_model
      • prompt
      • vit_prompt
    • Slca Utils
      • Convs
        • cifar_resnet
        • linears
        • resnet
        • vits
      • inc_net
      • toolkit
    • Twf Utils
      • afd
      • utils
    • Utils
      • continual_model
      • lider_model
    • agem
    • agem_r
    • bic
    • ccic
    • coda_prompt
    • der
    • derpp
    • derpp_lider
    • dualprompt
    • er
    • er_ace
    • er_ace_lider
    • ewc_on
    • fdr
    • gdumb
    • gdumb_lider
    • gem
    • gss
    • hal
    • icarl
    • icarl_lider
    • joint_gcl
    • l2p
    • lucir
    • lwf
    • lwf_mc
    • mer
    • pnn
    • rpc
    • sgd
    • si
    • twf
    • xder
    • xder_ce
    • xder_rpc
  • Datasets
    • Deprecated
      • old_mnist_360
    • Imagenet R Utils
    • Transforms
      • denormalization
      • permutation
      • rotation
    • Utils
      • continual_dataset
      • gcl_dataset
      • validation
    • mnist_360
    • perm_mnist
    • rot_mnist
    • seq_cifar10
    • seq_cifar100
    • seq_cifar100_224
    • seq_cifar100_224_rs
    • seq_cub200
    • seq_imagenet_r
    • seq_mnist
    • seq_tinyimagenet
    • seq_tinyimagenet_r
  • Backbones
    • Utils
      • modules
    • EfficientNet
    • MNISTMLP
    • MNISTMLP_PNN
    • ResNet18
    • ResNet18_PNN
    • ResNet50
  • Utils
    • args
    • augmentations
    • batch_norm
    • best_args
    • buffer
    • checkpoints
    • conditional_bn
    • conf
    • distributed
    • gss_buffer
    • kornia_utils
    • loggers
    • magic
    • main
    • metrics
    • mixup
    • prompt_templates
    • ring_buffer
    • schedulers
    • simclrloss
    • status
    • training
    • triplet
Back to top

xder_rpc#

Classes

class models.xder_rpc.XDerRPC(backbone, loss, args, transform)[source]#

Bases: ContinualModel

COMPATIBILITY: List[str] = ['class-il', 'task-il']#
NAME: str = 'xder_rpc'#
end_task(dataset)[source]#
forward(x)[source]#
static get_parser()[source]#
Return type:

ArgumentParser

observe(inputs, labels, not_aug_inputs, epoch=None)[source]#
update_logits(old, new, gt, task_start, n_tasks=1)[source]#

Functions

models.xder_rpc.dsimplex(num_classes=10)[source]#
Next
Datasets
Previous
xder_ce
Copyright © 2024, Pietro Buzzega, Matteo Boschini, Lorenzo Bonicelli, Aniello Panariello, Davide Abati, Angelo Porrello, Simone Calderara
Made with Sphinx and @pradyunsg's Furo
On this page
  • xder_rpc
    • XDerRPC
      • XDerRPC.COMPATIBILITY
      • XDerRPC.NAME
      • XDerRPC.end_task()
      • XDerRPC.forward()
      • XDerRPC.get_parser()
      • XDerRPC.observe()
      • XDerRPC.update_logits()
    • dsimplex()