-
facebook/convnext-base-224
Image Classification • Updated • 4.52k • • 9 -
tanganke/convnext-base-224_sun397_sgd_batch-size-64_lr-0.01_steps-4000
Image Classification • 88M • Updated • 47 -
tanganke/convnext-base-224_stanford-cars_sgd_batch-size-64_lr-0.01_steps-4000
Image Classification • 87.8M • Updated • 41 -
tanganke/convnext-base-224_resisc45_sgd_batch-size-64_lr-0.01_steps-4000
Image Classification • 87.6M • Updated • 37
Anke Tang
tanganke
AI & ML interests
None yet
Recent Activity
published
a model
4 days ago
fusion-bench/resnet-checkpoints
Organizations
Eight image classification tasks are widely used for multi-task model merging. https://tanganke.github.io/fusion_bench/modelpool/clip_vit/
if you find these models helpful, consider citing [our paper](https://arxiv.org/abs/2406.03280)
if you find these models helpful, consider citing [our paper](https://arxiv.org/abs/2406.03280)
image classification datasets that are used in my research.
if you find these models helpful, consider citing [our paper](https://arxiv.org/abs/2406.03280)
-
tanganke/clip-vit-base-patch32_sun397
Feature Extraction • 87.5M • Updated • 2.16k -
tanganke/clip-vit-base-patch32_stanford-cars
Feature Extraction • 87.5M • Updated • 2.14k • • 2 -
tanganke/clip-vit-base-patch32_resisc45
Feature Extraction • 87.5M • Updated • 2.09k -
tanganke/clip-vit-base-patch32_eurosat
Feature Extraction • 87.5M • Updated • 2.22k
base_model = CLIPVisionModel.from_pretrained('openai/clip-vit-base-patch16')
model = PeftModel.from_pretrained(base_model, peft_model_id)
if you find these models helpful, consider citing [our paper](https://arxiv.org/abs/2406.03280)
-
tanganke/clip-vit-large-patch14_sun397
Feature Extraction • 0.3B • Updated • 448 -
tanganke/clip-vit-large-patch14_stanford-cars
Feature Extraction • 0.3B • Updated • 495 -
tanganke/clip-vit-large-patch14_resisc45
Feature Extraction • 0.3B • Updated • 463 -
tanganke/clip-vit-large-patch14_eurosat
Feature Extraction • 0.3B • Updated • 483
if you find these models helpful, consider citing [our paper](https://arxiv.org/abs/2406.03280)
if you find these models helpful, consider citing [our paper](https://arxiv.org/abs/2406.03280)
-
facebook/convnext-base-224
Image Classification • Updated • 4.52k • • 9 -
tanganke/convnext-base-224_sun397_sgd_batch-size-64_lr-0.01_steps-4000
Image Classification • 88M • Updated • 47 -
tanganke/convnext-base-224_stanford-cars_sgd_batch-size-64_lr-0.01_steps-4000
Image Classification • 87.8M • Updated • 41 -
tanganke/convnext-base-224_resisc45_sgd_batch-size-64_lr-0.01_steps-4000
Image Classification • 87.6M • Updated • 37
image classification datasets that are used in my research.
Eight image classification tasks are widely used for multi-task model merging. https://tanganke.github.io/fusion_bench/modelpool/clip_vit/
if you find these models helpful, consider citing [our paper](https://arxiv.org/abs/2406.03280)
-
tanganke/clip-vit-base-patch32_sun397
Feature Extraction • 87.5M • Updated • 2.16k -
tanganke/clip-vit-base-patch32_stanford-cars
Feature Extraction • 87.5M • Updated • 2.14k • • 2 -
tanganke/clip-vit-base-patch32_resisc45
Feature Extraction • 87.5M • Updated • 2.09k -
tanganke/clip-vit-base-patch32_eurosat
Feature Extraction • 87.5M • Updated • 2.22k
base_model = CLIPVisionModel.from_pretrained('openai/clip-vit-base-patch16')
model = PeftModel.from_pretrained(base_model, peft_model_id)
if you find these models helpful, consider citing [our paper](https://arxiv.org/abs/2406.03280)
-
tanganke/clip-vit-large-patch14_sun397
Feature Extraction • 0.3B • Updated • 448 -
tanganke/clip-vit-large-patch14_stanford-cars
Feature Extraction • 0.3B • Updated • 495 -
tanganke/clip-vit-large-patch14_resisc45
Feature Extraction • 0.3B • Updated • 463 -
tanganke/clip-vit-large-patch14_eurosat
Feature Extraction • 0.3B • Updated • 483
if you find these models helpful, consider citing [our paper](https://arxiv.org/abs/2406.03280)
if you find these models helpful, consider citing [our paper](https://arxiv.org/abs/2406.03280)
if you find these models helpful, consider citing [our paper](https://arxiv.org/abs/2406.03280)
if you find these models helpful, consider citing [our paper](https://arxiv.org/abs/2406.03280)