Migrations
/
pytorch-image-models
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Switch BEiT to HF hub weights

Browse Source
pull/1593/head
Ross Wightman 2 years ago
parent d1bfa9a000
commit 8ece53e194
2 changed files with 28 additions and 12 deletions
Show Stats Download Patch File Download Diff File

36
timm/models/beit.py
Unescape View File

@ -355,64 +355,76 @@ def _cfg(url='', **kwargs):
default_cfgs = generate_default_cfgs({ default_cfgs = generate_default_cfgs({
'beit_base_patch16_224.in22k_ft_in22k_in1k': _cfg( 'beit_base_patch16_224.in22k_ft_in22k_in1k': _cfg(
url='https://conversationhub.blob.core.windows.net/beit-share-public/beit/beit_base_patch16_224_pt22k_ft22kto1k.pth'), url='https://conversationhub.blob.core.windows.net/beit-share-public/beit/beit_base_patch16_224_pt22k_ft22kto1k.pth',
hf_hub_id='timm/'),
'beit_base_patch16_384.in22k_ft_in22k_in1k': _cfg( 'beit_base_patch16_384.in22k_ft_in22k_in1k': _cfg(
url='https://conversationhub.blob.core.windows.net/beit-share-public/beit/beit_base_patch16_384_pt22k_ft22kto1k.pth', url='https://conversationhub.blob.core.windows.net/beit-share-public/beit/beit_base_patch16_384_pt22k_ft22kto1k.pth',
hf_hub_id='timm/',
input_size=(3, 384, 384), crop_pct=1.0, input_size=(3, 384, 384), crop_pct=1.0,
), ),
'beit_base_patch16_224.in22k_ft_in22k': _cfg( 'beit_base_patch16_224.in22k_ft_in22k': _cfg(
url='https://conversationhub.blob.core.windows.net/beit-share-public/beit/beit_base_patch16_224_pt22k_ft22k.pth', url='https://conversationhub.blob.core.windows.net/beit-share-public/beit/beit_base_patch16_224_pt22k_ft22k.pth',
hf_hub_id='timm/',
num_classes=21841, num_classes=21841,
), ),
'beit_large_patch16_224.in22k_ft_in22k_in1k': _cfg( 'beit_large_patch16_224.in22k_ft_in22k_in1k': _cfg(
url='https://conversationhub.blob.core.windows.net/beit-share-public/beit/beit_large_patch16_224_pt22k_ft22kto1k.pth'), url='https://conversationhub.blob.core.windows.net/beit-share-public/beit/beit_large_patch16_224_pt22k_ft22kto1k.pth',
hf_hub_id='timm/'),
'beit_large_patch16_384.in22k_ft_in22k_in1k': _cfg( 'beit_large_patch16_384.in22k_ft_in22k_in1k': _cfg(
url='https://conversationhub.blob.core.windows.net/beit-share-public/beit/beit_large_patch16_384_pt22k_ft22kto1k.pth', url='https://conversationhub.blob.core.windows.net/beit-share-public/beit/beit_large_patch16_384_pt22k_ft22kto1k.pth',
hf_hub_id='timm/',
input_size=(3, 384, 384), crop_pct=1.0, input_size=(3, 384, 384), crop_pct=1.0,
), ),
'beit_large_patch16_512.in22k_ft_in22k_in1k': _cfg( 'beit_large_patch16_512.in22k_ft_in22k_in1k': _cfg(
url='https://conversationhub.blob.core.windows.net/beit-share-public/beit/beit_large_patch16_512_pt22k_ft22kto1k.pth', url='https://conversationhub.blob.core.windows.net/beit-share-public/beit/beit_large_patch16_512_pt22k_ft22kto1k.pth',
hf_hub_id='timm/',
input_size=(3, 512, 512), crop_pct=1.0, input_size=(3, 512, 512), crop_pct=1.0,
), ),
'beit_large_patch16_224.in22k_ft_in22k': _cfg( 'beit_large_patch16_224.in22k_ft_in22k': _cfg(
url='https://conversationhub.blob.core.windows.net/beit-share-public/beit/beit_large_patch16_224_pt22k_ft22k.pth', url='https://conversationhub.blob.core.windows.net/beit-share-public/beit/beit_large_patch16_224_pt22k_ft22k.pth',
hf_hub_id='timm/',
num_classes=21841, num_classes=21841,
), ),
'beitv2_base_patch16_224.in1k_ft_in22k_in1k': _cfg( 'beitv2_base_patch16_224.in1k_ft_in22k_in1k': _cfg(
url='https://conversationhub.blob.core.windows.net/beit-share-public/beitv2/beitv2_base_patch16_224_pt1k_ft21kto1k.pth', url='https://conversationhub.blob.core.windows.net/beit-share-public/beitv2/beitv2_base_patch16_224_pt1k_ft21kto1k.pth',
hf_hub_id='timm/',
mean=IMAGENET_DEFAULT_MEAN, std=IMAGENET_DEFAULT_STD mean=IMAGENET_DEFAULT_MEAN, std=IMAGENET_DEFAULT_STD
), ),
'beitv2_base_patch16_224.in1k_ft_in22k': _cfg( 'beitv2_base_patch16_224.in1k_ft_in22k': _cfg(
url='https://conversationhub.blob.core.windows.net/beit-share-public/beitv2/beitv2_base_patch16_224_pt1k_ft21k.pth', url='https://conversationhub.blob.core.windows.net/beit-share-public/beitv2/beitv2_base_patch16_224_pt1k_ft21k.pth',
num_classes=21841, hf_hub_id='timm/',
mean=IMAGENET_DEFAULT_MEAN, std=IMAGENET_DEFAULT_STD num_classes=21841, mean=IMAGENET_DEFAULT_MEAN, std=IMAGENET_DEFAULT_STD
), ),
'beitv2_large_patch16_224.in1k_ft_in22k_in1k': _cfg( 'beitv2_large_patch16_224.in1k_ft_in22k_in1k': _cfg(
url='https://conversationhub.blob.core.windows.net/beit-share-public/beitv2/beitv2_large_patch16_224_pt1k_ft21kto1k.pth', url='https://conversationhub.blob.core.windows.net/beit-share-public/beitv2/beitv2_large_patch16_224_pt1k_ft21kto1k.pth',
crop_pct=0.95, hf_hub_id='timm/',
mean=IMAGENET_DEFAULT_MEAN, std=IMAGENET_DEFAULT_STD crop_pct=0.95, mean=IMAGENET_DEFAULT_MEAN, std=IMAGENET_DEFAULT_STD
), ),
'beitv2_large_patch16_224.in1k_ft_in22k': _cfg( 'beitv2_large_patch16_224.in1k_ft_in22k': _cfg(
url='https://conversationhub.blob.core.windows.net/beit-share-public/beitv2/beitv2_large_patch16_224_pt1k_ft21k.pth', url='https://conversationhub.blob.core.windows.net/beit-share-public/beitv2/beitv2_large_patch16_224_pt1k_ft21k.pth',
num_classes=21841, hf_hub_id='timm/',
mean=IMAGENET_DEFAULT_MEAN, std=IMAGENET_DEFAULT_STD num_classes=21841, mean=IMAGENET_DEFAULT_MEAN, std=IMAGENET_DEFAULT_STD
), ),
'eva_giant_patch14_224.clip_ft_in1k': _cfg( 'eva_giant_patch14_224.clip_ft_in1k': _cfg(
hf_hub_id='BAAI/EVA', hf_hub_filename='eva_clip_vis_enc_sz224_ftcls_89p1.pt', # hf_hub_id='BAAI/EVA', hf_hub_filename='eva_clip_vis_enc_sz224_ftcls_89p1.pt',
hf_hub_id='timm/',
mean=OPENAI_CLIP_MEAN, std=OPENAI_CLIP_STD, crop_pct=1.0, mean=OPENAI_CLIP_MEAN, std=OPENAI_CLIP_STD, crop_pct=1.0,
), ),
'eva_giant_patch14_336.clip_ft_in1k': _cfg( 'eva_giant_patch14_336.clip_ft_in1k': _cfg(
hf_hub_id='BAAI/EVA', hf_hub_filename='eva_clip_vis_enc_sz336_ftcls_89p4.pt', # hf_hub_id='BAAI/EVA', hf_hub_filename='eva_clip_vis_enc_sz336_ftcls_89p4.pt',
hf_hub_id='timm/',
mean=OPENAI_CLIP_MEAN, std=OPENAI_CLIP_STD, mean=OPENAI_CLIP_MEAN, std=OPENAI_CLIP_STD,
input_size=(3, 336, 336), crop_pct=1.0, crop_mode='squash'), input_size=(3, 336, 336), crop_pct=1.0, crop_mode='squash'),
'eva_giant_patch14_336.m30m_ft_in22k_in1k': _cfg( 'eva_giant_patch14_336.m30m_ft_in22k_in1k': _cfg(
hf_hub_id='BAAI/EVA', hf_hub_filename='eva_21k_1k_336px_psz14_ema_89p6.pt', # hf_hub_id='BAAI/EVA', hf_hub_filename='eva_21k_1k_336px_psz14_ema_89p6.pt',
hf_hub_id='timm/',
mean=IMAGENET_DEFAULT_MEAN, std=IMAGENET_DEFAULT_STD, mean=IMAGENET_DEFAULT_MEAN, std=IMAGENET_DEFAULT_STD,
input_size=(3, 336, 336), crop_pct=1.0, crop_mode='squash'), input_size=(3, 336, 336), crop_pct=1.0, crop_mode='squash'),
'eva_giant_patch14_560.m30m_ft_in22k_in1k': _cfg( 'eva_giant_patch14_560.m30m_ft_in22k_in1k': _cfg(
hf_hub_id='BAAI/EVA', hf_hub_filename='eva_21k_1k_560px_psz14_ema_89p7.pt', # hf_hub_id='BAAI/EVA', hf_hub_filename='eva_21k_1k_560px_psz14_ema_89p7.pt',
hf_hub_id='timm/',
mean=IMAGENET_DEFAULT_MEAN, std=IMAGENET_DEFAULT_STD, mean=IMAGENET_DEFAULT_MEAN, std=IMAGENET_DEFAULT_STD,
input_size=(3, 560, 560), crop_pct=1.0, crop_mode='squash'), input_size=(3, 560, 560), crop_pct=1.0, crop_mode='squash'),
}) })

4
timm/models/vision_transformer.py
Unescape View File

@ -1052,18 +1052,22 @@ default_cfgs = generate_default_cfgs({
# EVA fine-tuned weights from MAE style MIM - EVA-CLIP target pretrain # EVA fine-tuned weights from MAE style MIM - EVA-CLIP target pretrain
# https://github.com/baaivision/EVA/blob/7ecf2c0a370d97967e86d047d7af9188f78d2df3/eva/README.md#eva-l-learning-better-mim-representations-from-eva-clip # https://github.com/baaivision/EVA/blob/7ecf2c0a370d97967e86d047d7af9188f78d2df3/eva/README.md#eva-l-learning-better-mim-representations-from-eva-clip
'eva_large_patch14_196.in22k_ft_in22k_in1k': _cfg( 'eva_large_patch14_196.in22k_ft_in22k_in1k': _cfg(
# hf_hub_id='BAAI/EVA', hf_hub_filename='eva_l_psz14_196px_21k_to_1k_ft_88p6.pt',
hf_hub_id='timm/', hf_hub_id='timm/',
mean=OPENAI_CLIP_MEAN, std=OPENAI_CLIP_STD, mean=OPENAI_CLIP_MEAN, std=OPENAI_CLIP_STD,
input_size=(3, 196, 196), crop_pct=1.0), input_size=(3, 196, 196), crop_pct=1.0),
'eva_large_patch14_336.in22k_ft_in22k_in1k': _cfg( 'eva_large_patch14_336.in22k_ft_in22k_in1k': _cfg(
# hf_hub_id='BAAI/EVA', hf_hub_filename='eva_l_psz14_336px_21k_to_1k_ft_89p2.pt',
hf_hub_id='timm/', hf_hub_id='timm/',
mean=OPENAI_CLIP_MEAN, std=OPENAI_CLIP_STD, mean=OPENAI_CLIP_MEAN, std=OPENAI_CLIP_STD,
input_size=(3, 336, 336), crop_pct=1.0, crop_mode='squash'), input_size=(3, 336, 336), crop_pct=1.0, crop_mode='squash'),
'eva_large_patch14_196.in22k_ft_in1k': _cfg( 'eva_large_patch14_196.in22k_ft_in1k': _cfg(
# hf_hub_id='BAAI/EVA', hf_hub_filename='eva_l_psz14_196px_1k_ft_88p0.pt',
hf_hub_id='timm/', hf_hub_id='timm/',
mean=OPENAI_CLIP_MEAN, std=OPENAI_CLIP_STD, mean=OPENAI_CLIP_MEAN, std=OPENAI_CLIP_STD,
input_size=(3, 196, 196), crop_pct=1.0), input_size=(3, 196, 196), crop_pct=1.0),
'eva_large_patch14_336.in22k_ft_in1k': _cfg( 'eva_large_patch14_336.in22k_ft_in1k': _cfg(
# hf_hub_id='BAAI/EVA', hf_hub_filename='eva_l_psz14_336px_1k_ft_88p65.pt',
hf_hub_id='timm/', hf_hub_id='timm/',
mean=OPENAI_CLIP_MEAN, std=OPENAI_CLIP_STD, mean=OPENAI_CLIP_MEAN, std=OPENAI_CLIP_STD,
input_size=(3, 336, 336), crop_pct=1.0, crop_mode='squash'), input_size=(3, 336, 336), crop_pct=1.0, crop_mode='squash'),

Write Preview
Loading…
Cancel
Save