DUALPROMPT#
Arguments#
Options
- --train_maskbool
Help: if using the class mask at training
Default:
True
- --pretrainedunknown
Help: Load pretrained model or not
Default:
True
- --dropfloat
Help: Dropout rate (default: 0.)
Default:
0.0
- --drop_pathfloat
Help: Drop path rate (default: 0.)
Default:
0.0
- --clip_gradfloat
Help: Clip gradient norm (default: None, no clipping)
Default:
1.0
- --use_g_promptbool
Help: if using G-Prompt
Default:
True
- --g_prompt_lengthint
Help: length of G-Prompt
Default:
5
- --g_prompt_layer_idxint
Help: the layer index of the G-Prompt
Default:
[0, 1]
- --use_prefix_tune_for_g_promptbool
Help: if using the prefix tune for G-Prompt
Default:
True
- --use_e_promptbool
Help: if using the E-Prompt
Default:
True
- --e_prompt_layer_idxint
Help: the layer index of the E-Prompt
Default:
[2, 3, 4]
- --use_prefix_tune_for_e_promptbool
Help: if using the prefix tune for E-Prompt
Default:
True
- --prompt_poolbool
Help: None
Default:
True
- --sizeint
Help: None
Default:
10
- --lengthint
Help: None
Default:
5
- --top_kint
Help: None
Default:
1
- --initializerstr
Help: None
Default:
uniform
- --prompt_keybool
Help: None
Default:
True
- --prompt_key_initstr
Help: None
Default:
uniform
- --use_prompt_maskbool
Help: None
Default:
True
- --mask_first_epochbool
Help: None
Default:
False
- --shared_prompt_poolbool
Help: None
Default:
True
- --shared_prompt_keybool
Help: None
Default:
False
- --batchwise_promptbool
Help: None
Default:
True
- --embedding_keystr
Help: None
Default:
cls
- --predefined_keystr
Help: None
- --pull_constraintunknown
Help: None
Default:
True
- --pull_constraint_coefffloat
Help: None
Default:
1.0
- --same_key_valuebool
Help: None
Default:
False
- --global_poolstr
Help: type of global pooling for final sequence
Default:
token
Choices:
token, avg
- --head_typestr
Help: input type of classification head
Default:
token
Choices:
token, gap, prompt, token+prompt
- --freezelist
Help: freeze part in backbone model
Default:
['blocks', 'patch_embed', 'cls_token', 'norm', 'pos_embed']
DualPrompt: Complementary Prompting for Rehearsal-free Continual Learning
Note
WARNING: DualPrompt USES A CUSTOM BACKBONE: vit_base_patch16_224. The backbone is a ViT-B/16 pretrained on Imagenet 21k and finetuned on ImageNet 1k.
Classes#
- class models.dualprompt.DualPrompt(backbone, loss, args, transform, dataset=None)[source]#
Bases:
ContinualModel
DualPrompt: Complementary Prompting for Rehearsal-free Continual Learning.