Implement of Zero-Shot CLIP Classifier #1737
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change | ||||
|---|---|---|---|---|---|---|
| @@ -0,0 +1,67 @@ | ||||||
| _base_ = '../_base_/default_runtime.py' | ||||||
|
|
||||||
| # data settings | ||||||
| data_preprocessor = dict( | ||||||
| type='MultiModalDataPreprocessor', | ||||||
| mean=[0.48145466 * 255, 0.4578275 * 255, 0.40821073 * 255], | ||||||
| std=[0.26862954 * 255, 0.26130258 * 255, 0.27577711 * 255], | ||||||
| to_rgb=False, | ||||||
| ) | ||||||
|
|
||||||
| test_pipeline = [ | ||||||
| dict(type='Resize', scale=(224, 224), interpolation='bicubic'), | ||||||
| dict( | ||||||
| type='PackInputs', | ||||||
| algorithm_keys=['text'], | ||||||
| meta_keys=['image_id', 'scale_factor'], | ||||||
| ), | ||||||
| ] | ||||||
|
|
||||||
| train_dataloader = None | ||||||
| test_dataloader = dict( | ||||||
| batch_size=32, | ||||||
| num_workers=8, | ||||||
| dataset=dict( | ||||||
| type='CIFAR100', | ||||||
| data_root='/public/DATA/qbw/img_cls_dataset/cifar100', | ||||||
|
There was a problem hiding this comment.
Suggested change
we use this format path instead of your real path in the released code, please also check other configs |
||||||
| split='test', | ||||||
| pipeline=test_pipeline), | ||||||
| sampler=dict(type='DefaultSampler', shuffle=False), | ||||||
| ) | ||||||
| test_evaluator = dict(type='Accuracy', topk=(1, 5)) | ||||||
|
|
||||||
| # schedule settings | ||||||
| train_cfg = None | ||||||
| val_cfg = None | ||||||
| test_cfg = dict() | ||||||
|
|
||||||
| # model settings | ||||||
| model = dict( | ||||||
| type='CLIP_zs', | ||||||
| vision_backbone=dict( | ||||||
| type='CLIPVisionTransformer', | ||||||
| input_resolution=224, | ||||||
| patch_size=16, | ||||||
| width=768, | ||||||
| layers=12, | ||||||
| heads=12, | ||||||
| output_dim=512, | ||||||
| ), | ||||||
| text_backbone=dict( | ||||||
| type='CLIPTransformer', | ||||||
| width=512, | ||||||
| layers=12, | ||||||
| heads=8, | ||||||
| attn_mask=True, | ||||||
| ), | ||||||
| tokenizer=dict( | ||||||
| type='AutoTokenizer', | ||||||
| name_or_path='openai/clip-vit-base-patch16', | ||||||
| use_fast=False), | ||||||
| vocab_size=49408, | ||||||
| transformer_width=512, | ||||||
| proj_dim=512, | ||||||
| text_prototype='cifar100', | ||||||
| text_prompt='openai_cifar100', | ||||||
| context_length=77, | ||||||
| ) | ||||||
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,69 @@ | ||
| _base_ = '../_base_/default_runtime.py' | ||
|
|
||
| # data settings | ||
| data_preprocessor = dict( | ||
| type='MultiModalDataPreprocessor', | ||
| mean=[0.48145466 * 255, 0.4578275 * 255, 0.40821073 * 255], | ||
| std=[0.26862954 * 255, 0.26130258 * 255, 0.27577711 * 255], | ||
| to_rgb=True, | ||
| ) | ||
|
|
||
| test_pipeline = [ | ||
| dict(type='LoadImageFromFile'), | ||
| dict(type='Resize', scale=(224, 224), interpolation='bicubic'), | ||
| dict( | ||
| type='PackInputs', | ||
| algorithm_keys=['text'], | ||
| meta_keys=['image_id', 'scale_factor'], | ||
| ), | ||
| ] | ||
|
|
||
| train_dataloader = None | ||
| test_dataloader = dict( | ||
| batch_size=32, | ||
| num_workers=8, | ||
| dataset=dict( | ||
| type='ImageNet', | ||
| data_root= | ||
| '/public/DATA/qbw/img_cls_dataset/in1k/imagenet-1k-huggingface/data/', | ||
| split='val', | ||
| pipeline=test_pipeline), | ||
| sampler=dict(type='DefaultSampler', shuffle=False), | ||
| ) | ||
| test_evaluator = dict(type='Accuracy', topk=(1, 5)) | ||
|
|
||
| # schedule settings | ||
| train_cfg = None | ||
| val_cfg = None | ||
| test_cfg = dict() | ||
|
|
||
| # model settings | ||
| model = dict( | ||
| type='CLIP_zs', | ||
| vision_backbone=dict( | ||
| type='CLIPVisionTransformer', | ||
| input_resolution=224, | ||
| patch_size=16, | ||
| width=768, | ||
| layers=12, | ||
| heads=12, | ||
| output_dim=512, | ||
| ), | ||
| text_backbone=dict( | ||
| type='CLIPTransformer', | ||
| width=512, | ||
| layers=12, | ||
| heads=8, | ||
| attn_mask=True, | ||
| ), | ||
| tokenizer=dict( | ||
| type='AutoTokenizer', | ||
| name_or_path='openai/clip-vit-base-patch16', | ||
| use_fast=False), | ||
| vocab_size=49408, | ||
| transformer_width=512, | ||
| proj_dim=512, | ||
| text_prototype='imagenet', | ||
| text_prompt='openai_imagenet_sub', # openai_imagenet, openai_imagenet_sub | ||
| context_length=77, | ||
| ) |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,67 @@ | ||
| _base_ = '../_base_/default_runtime.py' | ||
|
|
||
| # data settings | ||
| data_preprocessor = dict( | ||
| type='MultiModalDataPreprocessor', | ||
| mean=[0.48145466 * 255, 0.4578275 * 255, 0.40821073 * 255], | ||
| std=[0.26862954 * 255, 0.26130258 * 255, 0.27577711 * 255], | ||
| to_rgb=False, | ||
| ) | ||
|
|
||
| test_pipeline = [ | ||
| dict(type='Resize', scale=(224, 224), interpolation='bicubic'), | ||
| dict( | ||
| type='PackInputs', | ||
| algorithm_keys=['text'], | ||
| meta_keys=['image_id', 'scale_factor'], | ||
| ), | ||
| ] | ||
|
|
||
| train_dataloader = None | ||
| test_dataloader = dict( | ||
| batch_size=32, | ||
| num_workers=8, | ||
| dataset=dict( | ||
| type='CIFAR100', | ||
| data_root='/public/DATA/qbw/img_cls_dataset/cifar100', | ||
| split='test', | ||
| pipeline=test_pipeline), | ||
| sampler=dict(type='DefaultSampler', shuffle=False), | ||
| ) | ||
| test_evaluator = dict(type='Accuracy', topk=(1, 5)) | ||
|
|
||
| # schedule settings | ||
| train_cfg = None | ||
| val_cfg = None | ||
| test_cfg = dict() | ||
|
|
||
| # model settings | ||
| model = dict( | ||
| type='CLIP_zs', | ||
| vision_backbone=dict( | ||
| type='CLIPVisionTransformer', | ||
| input_resolution=224, | ||
| patch_size=14, | ||
| width=1024, | ||
| layers=24, | ||
| heads=16, | ||
| output_dim=768, | ||
| ), | ||
| text_backbone=dict( | ||
| type='CLIPTransformer', | ||
| width=768, | ||
| layers=12, | ||
| heads=12, | ||
| attn_mask=True, | ||
| ), | ||
| tokenizer=dict( | ||
| type='AutoTokenizer', | ||
| name_or_path='openai/clip-vit-large-patch14', | ||
| use_fast=False), | ||
| vocab_size=49408, | ||
| transformer_width=768, | ||
| proj_dim=768, | ||
| text_prototype='cifar100', | ||
| text_prompt='openai_cifar100', | ||
| context_length=77, | ||
| ) |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,69 @@ | ||
| _base_ = '../_base_/default_runtime.py' | ||
|
|
||
| # data settings | ||
| data_preprocessor = dict( | ||
| type='MultiModalDataPreprocessor', | ||
| mean=[0.48145466 * 255, 0.4578275 * 255, 0.40821073 * 255], | ||
| std=[0.26862954 * 255, 0.26130258 * 255, 0.27577711 * 255], | ||
| to_rgb=True, | ||
| ) | ||
|
|
||
| test_pipeline = [ | ||
| dict(type='LoadImageFromFile'), | ||
| dict(type='Resize', scale=(224, 224), interpolation='bicubic'), | ||
| dict( | ||
| type='PackInputs', | ||
| algorithm_keys=['text'], | ||
| meta_keys=['image_id', 'scale_factor'], | ||
| ), | ||
| ] | ||
|
|
||
| train_dataloader = None | ||
| test_dataloader = dict( | ||
| batch_size=32, | ||
| num_workers=8, | ||
| dataset=dict( | ||
| type='ImageNet', | ||
| data_root= | ||
| '/public/DATA/qbw/img_cls_dataset/in1k/imagenet-1k-huggingface/data/', | ||
| split='val', | ||
| pipeline=test_pipeline), | ||
| sampler=dict(type='DefaultSampler', shuffle=False), | ||
| ) | ||
| test_evaluator = dict(type='Accuracy', topk=(1, 5)) | ||
|
|
||
| # schedule settings | ||
| train_cfg = None | ||
| val_cfg = None | ||
| test_cfg = dict() | ||
|
|
||
| # model settings | ||
| model = dict( | ||
| type='CLIP_zs', | ||
| vision_backbone=dict( | ||
| type='CLIPVisionTransformer', | ||
| input_resolution=224, | ||
| patch_size=14, | ||
| width=1024, | ||
| layers=24, | ||
| heads=16, | ||
| output_dim=768, | ||
| ), | ||
| text_backbone=dict( | ||
| type='CLIPTransformer', | ||
| width=768, | ||
| layers=12, | ||
| heads=12, | ||
| attn_mask=True, | ||
| ), | ||
| tokenizer=dict( | ||
| type='AutoTokenizer', | ||
| name_or_path='openai/clip-vit-large-patch14', | ||
| use_fast=False), | ||
| vocab_size=49408, | ||
| transformer_width=768, | ||
| proj_dim=768, | ||
| text_prototype='imagenet', | ||
| text_prompt='openai_imagenet_sub', # openai_imagenet, openai_imagenet_sub | ||
| context_length=77, | ||
| ) |
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
move all these 4 configs to
configs/clip/folder, and rename them to format likeclip_vit-base-p16_zeroshot-cls_cifar100.py, just aschinese_clip