Shadowgraph
TrendingBuzzTop stargazers
Chrome extension
Sign in

MVRL/satmaepp_ViT-L_pretrain_fmow_rgb

Model

Model: SatMAE++ (https://arxiv.org/abs/2403.05419)

1

5 commits

1 linked in READMEs

updated Oct 27, 2024

See the code

README

Model: SatMAE++ (https://arxiv.org/abs/2403.05419)

Variant: ViT-L_pretrain_fmow_rgb

Example Usage:

from huggingface_hub import hf_hub_download
import torch

hf_hub_download("MVRL/satmaepp_ViT-L_pretrain_fmow_rgb", "model.py", local_dir=".")

from model import MaskedAutoencoderViT

model = MaskedAutoencoderViT.from_pretrained("MVRL/satmaepp_ViT-L_pretrain_fmow_rgb")

print(model.forward_encoder(torch.randn(1, 3, 224, 224), mask_ratio=0.0)[0].shape)
endpoints_compatible
pytorch
transformers

Similar repos

mubashir04/checkpoint_ViT-L_pretrain_fmow_rgb

Model

Description

1

MVRL/scalemae-vitlarge-800

Model

Model: ScaleMAE (https://arxiv.org/abs/2212.14532)

0

facebook/vit-mae-base

Model

Vision Transformer (base-sized model) pre-trained with MAE

43

facebook/vit-mae-huge

Model

Vision Transformer (huge-sized model) pre-trained with MAE

8

facebook/vit-mae-large

Model

Vision Transformer (large-sized model) pre-trained with MAE

13

mubashir04/checkpoint_ViT-L_pretrain_fmow_sentinel

Model

Description

0

zhu-xlab/FGMAE

Feature guided masked Autoencoder for self-supervised learning in remote sensing

31

mubashir04/checkpoint_ViT-L_finetune_fmow_rgb

Model

Description

1

Linked in READMEs

GISWLH/earth-embedding

A unified Python interface to Earth embeddings: image encoders, location encoders, and precomputed…

1

README badge

MVRL/satmaepp_ViT-L_pretrain_fmow_rgb

Model

Model: SatMAE++ (https://arxiv.org/abs/2403.05419)

1

5 commits

1 linked in READMEs

updated Oct 27, 2024

See the code

README

Model: SatMAE++ (https://arxiv.org/abs/2403.05419)

Variant: ViT-L_pretrain_fmow_rgb

Example Usage:

from huggingface_hub import hf_hub_download
import torch

hf_hub_download("MVRL/satmaepp_ViT-L_pretrain_fmow_rgb", "model.py", local_dir=".")

from model import MaskedAutoencoderViT

model = MaskedAutoencoderViT.from_pretrained("MVRL/satmaepp_ViT-L_pretrain_fmow_rgb")

print(model.forward_encoder(torch.randn(1, 3, 224, 224), mask_ratio=0.0)[0].shape)
endpoints_compatible
pytorch
transformers

Similar repos

mubashir04/checkpoint_ViT-L_pretrain_fmow_rgb

Model

Description

1

MVRL/scalemae-vitlarge-800

Model

Model: ScaleMAE (https://arxiv.org/abs/2212.14532)

0

facebook/vit-mae-base

Model

Vision Transformer (base-sized model) pre-trained with MAE

43

facebook/vit-mae-huge

Model

Vision Transformer (huge-sized model) pre-trained with MAE

8

facebook/vit-mae-large

Model

Vision Transformer (large-sized model) pre-trained with MAE

13

mubashir04/checkpoint_ViT-L_pretrain_fmow_sentinel

Model

Description

0

zhu-xlab/FGMAE

Feature guided masked Autoencoder for self-supervised learning in remote sensing

31

mubashir04/checkpoint_ViT-L_finetune_fmow_rgb

Model

Description

1

Linked in READMEs

GISWLH/earth-embedding

A unified Python interface to Earth embeddings: image encoders, location encoders, and precomputed…

1

README badge