Timm 라이브러리 모델명 정리

timm 라이브러리는 pre-trained 된 모델을 인스턴스해서 쓸 수 있다.

프리 트레이닝 하는 데이터셋의 양이 테라 수준이라 직접 하기는 좀... 그렇다.

 

페이지 공홈

https://timm.fast.ai/

깃허브 공홈

https://github.com/huggingface/pytorch-image-models

 

 

timm

 

깃헙

구글같은 경우는 모든 모델의 학습 조건, 정확도 등을 상세하게 적어놔준다.

그런데 timm 라이브러리의 주인인 hugging face 친구들은 너무 불친절하다. (진심 킹받음)

그래도 어쩌겠나... 써야지 ㅠㅠ

 

일단 설치

pip install timm

 

그리고 이걸 인스턴스 하는 방법

# 방법1
model = timm.models.vit_base_patch16_224(pretrained=True).to(device)

# 방법2
model = timm.create_model('vit_base_patch16_224', pretrained=True).to(device)

여기서 원하는 모델명(ex : vit_base_patch16_224)을 선택하고,

pretrained 여부(ex : pretrained=True)를 선택하면 된다.

 

뭐지 졸라 쉽잖아?

아니다.

저기 들어갈 모델명을................. 정리한 자료가 없다..............^^

 

킹받으니 직접 뽑을 수 있다.

print(timm.list_models(pretrained=True))

기본적인 규칙은 아래를 따른다.

 

(모델명_상세 하이퍼 파라미터_기법 혹은 데이터셋)

예시 : vit_base_patch16_224_in21k

 

전체 결과는 아래와 같다.

검색해서 쓰면 되겠다.

adv_inception_v3
bat_resnext26ts
beit_base_patch16_224
beit_base_patch16_224_in22k
beit_base_patch16_384
beit_large_patch16_224
beit_large_patch16_224_in22k
beit_large_patch16_384
beit_large_patch16_512
beitv2_base_patch16_224
beitv2_base_patch16_224_in22k
beitv2_large_patch16_224
beitv2_large_patch16_224_in22k
botnet26t_256
cait_m36_384
cait_m48_448
cait_s24_224
cait_s24_384
cait_s36_384
cait_xs24_384
cait_xxs24_224
cait_xxs24_384
cait_xxs36_224
cait_xxs36_384
coat_lite_mini
coat_lite_small
coat_lite_tiny
coat_mini
coat_tiny
coatnet_0_rw_224
coatnet_1_rw_224
coatnet_bn_0_rw_224
coatnet_nano_rw_224
coatnet_rmlp_1_rw_224
coatnet_rmlp_2_rw_224
coatnet_rmlp_nano_rw_224
coatnext_nano_rw_224
convit_base
convit_small
convit_tiny
convmixer_768_32
convmixer_1024_20_ks9_p14
convmixer_1536_20
convnext_atto
convnext_atto_ols
convnext_base
convnext_base_384_in22ft1k
convnext_base_in22ft1k
convnext_base_in22k
convnext_femto
convnext_femto_ols
convnext_large
convnext_large_384_in22ft1k
convnext_large_in22ft1k
convnext_large_in22k
convnext_nano
convnext_nano_ols
convnext_pico
convnext_pico_ols
convnext_small
convnext_small_384_in22ft1k
convnext_small_in22ft1k
convnext_small_in22k
convnext_tiny
convnext_tiny_384_in22ft1k
convnext_tiny_hnf
convnext_tiny_in22ft1k
convnext_tiny_in22k
convnext_xlarge_384_in22ft1k
convnext_xlarge_in22ft1k
convnext_xlarge_in22k
crossvit_9_240
crossvit_9_dagger_240
crossvit_15_240
crossvit_15_dagger_240
crossvit_15_dagger_408
crossvit_18_240
crossvit_18_dagger_240
crossvit_18_dagger_408
crossvit_base_240
crossvit_small_240
crossvit_tiny_240
cs3darknet_focus_l
cs3darknet_focus_m
cs3darknet_l
cs3darknet_m
cs3darknet_x
cs3edgenet_x
cs3se_edgenet_x
cs3sedarknet_l
cs3sedarknet_x
cspdarknet53
cspresnet50
cspresnext50
darknet53
darknetaa53
deit3_base_patch16_224
deit3_base_patch16_224_in21ft1k
deit3_base_patch16_384
deit3_base_patch16_384_in21ft1k
deit3_huge_patch14_224
deit3_huge_patch14_224_in21ft1k
deit3_large_patch16_224
deit3_large_patch16_224_in21ft1k
deit3_large_patch16_384
deit3_large_patch16_384_in21ft1k
deit3_medium_patch16_224
deit3_medium_patch16_224_in21ft1k
deit3_small_patch16_224
deit3_small_patch16_224_in21ft1k
deit3_small_patch16_384
deit3_small_patch16_384_in21ft1k
deit_base_distilled_patch16_224
deit_base_distilled_patch16_384
deit_base_patch16_224
deit_base_patch16_384
deit_small_distilled_patch16_224
deit_small_patch16_224
deit_tiny_distilled_patch16_224
deit_tiny_patch16_224
densenet121
densenet161
densenet169
densenet201
densenetblur121d
dla34
dla46_c
dla46x_c
dla60
dla60_res2net
dla60_res2next
dla60x
dla60x_c
dla102
dla102x
dla102x2
dla169
dm_nfnet_f0
dm_nfnet_f1
dm_nfnet_f2
dm_nfnet_f3
dm_nfnet_f4
dm_nfnet_f5
dm_nfnet_f6
dpn68
dpn68b
dpn92
dpn98
dpn107
dpn131
eca_botnext26ts_256
eca_halonext26ts
eca_nfnet_l0
eca_nfnet_l1
eca_nfnet_l2
eca_resnet33ts
eca_resnext26ts
ecaresnet26t
ecaresnet50d
ecaresnet50d_pruned
ecaresnet50t
ecaresnet101d
ecaresnet101d_pruned
ecaresnet269d
ecaresnetlight
edgenext_base
edgenext_small
edgenext_small_rw
edgenext_x_small
edgenext_xx_small
efficientformer_l1
efficientformer_l3
efficientformer_l7
efficientnet_b0
efficientnet_b1
efficientnet_b1_pruned
efficientnet_b2
efficientnet_b2_pruned
efficientnet_b3
efficientnet_b3_pruned
efficientnet_b4
efficientnet_el
efficientnet_el_pruned
efficientnet_em
efficientnet_es
efficientnet_es_pruned
efficientnet_lite0
efficientnetv2_rw_m
efficientnetv2_rw_s
efficientnetv2_rw_t
ens_adv_inception_resnet_v2
ese_vovnet19b_dw
ese_vovnet39b
fbnetc_100
fbnetv3_b
fbnetv3_d
fbnetv3_g
gc_efficientnetv2_rw_t
gcresnet33ts
gcresnet50t
gcresnext26ts
gcresnext50ts
gcvit_base
gcvit_small
gcvit_tiny
gcvit_xtiny
gcvit_xxtiny
gernet_l
gernet_m
gernet_s
ghostnet_100
gluon_inception_v3
gluon_resnet18_v1b
gluon_resnet34_v1b
gluon_resnet50_v1b
gluon_resnet50_v1c
gluon_resnet50_v1d
gluon_resnet50_v1s
gluon_resnet101_v1b
gluon_resnet101_v1c
gluon_resnet101_v1d
gluon_resnet101_v1s
gluon_resnet152_v1b
gluon_resnet152_v1c
gluon_resnet152_v1d
gluon_resnet152_v1s
gluon_resnext50_32x4d
gluon_resnext101_32x4d
gluon_resnext101_64x4d
gluon_senet154
gluon_seresnext50_32x4d
gluon_seresnext101_32x4d
gluon_seresnext101_64x4d
gluon_xception65
gmixer_24_224
gmlp_s16_224
halo2botnet50ts_256
halonet26t
halonet50ts
haloregnetz_b
hardcorenas_a
hardcorenas_b
hardcorenas_c
hardcorenas_d
hardcorenas_e
hardcorenas_f
hrnet_w18
hrnet_w18_small
hrnet_w18_small_v2
hrnet_w30
hrnet_w32
hrnet_w40
hrnet_w44
hrnet_w48
hrnet_w64
ig_resnext101_32x8d
ig_resnext101_32x16d
ig_resnext101_32x32d
ig_resnext101_32x48d
inception_resnet_v2
inception_v3
inception_v4
jx_nest_base
jx_nest_small
jx_nest_tiny
lambda_resnet26rpt_256
lambda_resnet26t
lambda_resnet50ts
lamhalobotnet50ts_256
lcnet_050
lcnet_075
lcnet_100
legacy_senet154
legacy_seresnet18
legacy_seresnet34
legacy_seresnet50
legacy_seresnet101
legacy_seresnet152
legacy_seresnext26_32x4d
legacy_seresnext50_32x4d
legacy_seresnext101_32x4d
levit_128
levit_128s
levit_192
levit_256
levit_384
maxvit_nano_rw_256
maxvit_rmlp_nano_rw_256
maxvit_rmlp_pico_rw_256
maxvit_rmlp_small_rw_224
maxvit_rmlp_tiny_rw_256
maxvit_tiny_rw_224
maxxvit_rmlp_nano_rw_256
maxxvit_rmlp_small_rw_256
mixer_b16_224
mixer_b16_224_in21k
mixer_b16_224_miil
mixer_b16_224_miil_in21k
mixer_l16_224
mixer_l16_224_in21k
mixnet_l
mixnet_m
mixnet_s
mixnet_xl
mnasnet_100
mnasnet_small
mobilenetv2_050
mobilenetv2_100
mobilenetv2_110d
mobilenetv2_120d
mobilenetv2_140
mobilenetv3_large_100
mobilenetv3_large_100_miil
mobilenetv3_large_100_miil_in21k
mobilenetv3_rw
mobilenetv3_small_050
mobilenetv3_small_075
mobilenetv3_small_100
mobilevit_s
mobilevit_xs
mobilevit_xxs
mobilevitv2_050
mobilevitv2_075
mobilevitv2_100
mobilevitv2_125
mobilevitv2_150
mobilevitv2_150_384_in22ft1k
mobilevitv2_150_in22ft1k
mobilevitv2_175
mobilevitv2_175_384_in22ft1k
mobilevitv2_175_in22ft1k
mobilevitv2_200
mobilevitv2_200_384_in22ft1k
mobilevitv2_200_in22ft1k
mvitv2_base
mvitv2_large
mvitv2_small
mvitv2_tiny
nasnetalarge
nf_regnet_b1
nf_resnet50
nfnet_l0
pit_b_224
pit_b_distilled_224
pit_s_224
pit_s_distilled_224
pit_ti_224
pit_ti_distilled_224
pit_xs_224
pit_xs_distilled_224
pnasnet5large
poolformer_m36
poolformer_m48
poolformer_s12
poolformer_s24
poolformer_s36
pvt_v2_b0
pvt_v2_b1
pvt_v2_b2
pvt_v2_b2_li
pvt_v2_b3
pvt_v2_b4
pvt_v2_b5
regnetv_040
regnetv_064
regnetx_002
regnetx_004
regnetx_006
regnetx_008
regnetx_016
regnetx_032
regnetx_040
regnetx_064
regnetx_080
regnetx_120
regnetx_160
regnetx_320
regnety_002
regnety_004
regnety_006
regnety_008
regnety_016
regnety_032
regnety_040
regnety_064
regnety_080
regnety_120
regnety_160
regnety_320
regnetz_040
regnetz_040h
regnetz_b16
regnetz_c16
regnetz_c16_evos
regnetz_d8
regnetz_d8_evos
regnetz_d32
regnetz_e8
repvgg_a2
repvgg_b0
repvgg_b1
repvgg_b1g4
repvgg_b2
repvgg_b2g4
repvgg_b3
repvgg_b3g4
res2net50_14w_8s
res2net50_26w_4s
res2net50_26w_6s
res2net50_26w_8s
res2net50_48w_2s
res2net101_26w_4s
res2next50
resmlp_12_224
resmlp_12_224_dino
resmlp_12_distilled_224
resmlp_24_224
resmlp_24_224_dino
resmlp_24_distilled_224
resmlp_36_224
resmlp_36_distilled_224
resmlp_big_24_224
resmlp_big_24_224_in22ft1k
resmlp_big_24_distilled_224
resnest14d
resnest26d
resnest50d
resnest50d_1s4x24d
resnest50d_4s2x40d
resnest101e
resnest200e
resnest269e
resnet10t
resnet14t
resnet18
resnet18d
resnet26
resnet26d
resnet26t
resnet32ts
resnet33ts
resnet34
resnet34d
resnet50
resnet50_gn
resnet50d
resnet51q
resnet61q
resnet101
resnet101d
resnet152
resnet152d
resnet200d
resnetaa50
resnetblur50
resnetrs50
resnetrs101
resnetrs152
resnetrs200
resnetrs270
resnetrs350
resnetrs420
resnetv2_50
resnetv2_50d_evos
resnetv2_50d_gn
resnetv2_50x1_bit_distilled
resnetv2_50x1_bitm
resnetv2_50x1_bitm_in21k
resnetv2_50x3_bitm
resnetv2_50x3_bitm_in21k
resnetv2_101
resnetv2_101x1_bitm
resnetv2_101x1_bitm_in21k
resnetv2_101x3_bitm
resnetv2_101x3_bitm_in21k
resnetv2_152x2_bit_teacher
resnetv2_152x2_bit_teacher_384
resnetv2_152x2_bitm
resnetv2_152x2_bitm_in21k
resnetv2_152x4_bitm
resnetv2_152x4_bitm_in21k
resnext26ts
resnext50_32x4d
resnext50d_32x4d
resnext101_32x8d
resnext101_64x4d
rexnet_100
rexnet_130
rexnet_150
rexnet_200
sebotnet33ts_256
sehalonet33ts
selecsls42b
selecsls60
selecsls60b
semnasnet_075
semnasnet_100
sequencer2d_l
sequencer2d_m
sequencer2d_s
seresnet33ts
seresnet50
seresnet152d
seresnext26d_32x4d
seresnext26t_32x4d
seresnext26ts
seresnext50_32x4d
seresnext101_32x8d
seresnext101d_32x8d
seresnextaa101d_32x8d
skresnet18
skresnet34
skresnext50_32x4d
spnasnet_100
ssl_resnet18
ssl_resnet50
ssl_resnext50_32x4d
ssl_resnext101_32x4d
ssl_resnext101_32x8d
ssl_resnext101_32x16d
swin_base_patch4_window7_224
swin_base_patch4_window7_224_in22k
swin_base_patch4_window12_384
swin_base_patch4_window12_384_in22k
swin_large_patch4_window7_224
swin_large_patch4_window7_224_in22k
swin_large_patch4_window12_384
swin_large_patch4_window12_384_in22k
swin_s3_base_224
swin_s3_small_224
swin_s3_tiny_224
swin_small_patch4_window7_224
swin_tiny_patch4_window7_224
swinv2_base_window8_256
swinv2_base_window12_192_22k
swinv2_base_window12to16_192to256_22kft1k
swinv2_base_window12to24_192to384_22kft1k
swinv2_base_window16_256
swinv2_cr_small_224
swinv2_cr_small_ns_224
swinv2_cr_tiny_ns_224
swinv2_large_window12_192_22k
swinv2_large_window12to16_192to256_22kft1k
swinv2_large_window12to24_192to384_22kft1k
swinv2_small_window8_256
swinv2_small_window16_256
swinv2_tiny_window8_256
swinv2_tiny_window16_256
swsl_resnet18
swsl_resnet50
swsl_resnext50_32x4d
swsl_resnext101_32x4d
swsl_resnext101_32x8d
swsl_resnext101_32x16d
tf_efficientnet_b0
tf_efficientnet_b0_ap
tf_efficientnet_b0_ns
tf_efficientnet_b1
tf_efficientnet_b1_ap
tf_efficientnet_b1_ns
tf_efficientnet_b2
tf_efficientnet_b2_ap
tf_efficientnet_b2_ns
tf_efficientnet_b3
tf_efficientnet_b3_ap
tf_efficientnet_b3_ns
tf_efficientnet_b4
tf_efficientnet_b4_ap
tf_efficientnet_b4_ns
tf_efficientnet_b5
tf_efficientnet_b5_ap
tf_efficientnet_b5_ns
tf_efficientnet_b6
tf_efficientnet_b6_ap
tf_efficientnet_b6_ns
tf_efficientnet_b7
tf_efficientnet_b7_ap
tf_efficientnet_b7_ns
tf_efficientnet_b8
tf_efficientnet_b8_ap
tf_efficientnet_cc_b0_4e
tf_efficientnet_cc_b0_8e
tf_efficientnet_cc_b1_8e
tf_efficientnet_el
tf_efficientnet_em
tf_efficientnet_es
tf_efficientnet_l2_ns
tf_efficientnet_l2_ns_475
tf_efficientnet_lite0
tf_efficientnet_lite1
tf_efficientnet_lite2
tf_efficientnet_lite3
tf_efficientnet_lite4
tf_efficientnetv2_b0
tf_efficientnetv2_b1
tf_efficientnetv2_b2
tf_efficientnetv2_b3
tf_efficientnetv2_l
tf_efficientnetv2_l_in21ft1k
tf_efficientnetv2_l_in21k
tf_efficientnetv2_m
tf_efficientnetv2_m_in21ft1k
tf_efficientnetv2_m_in21k
tf_efficientnetv2_s
tf_efficientnetv2_s_in21ft1k
tf_efficientnetv2_s_in21k
tf_efficientnetv2_xl_in21ft1k
tf_efficientnetv2_xl_in21k
tf_inception_v3
tf_mixnet_l
tf_mixnet_m
tf_mixnet_s
tf_mobilenetv3_large_075
tf_mobilenetv3_large_100
tf_mobilenetv3_large_minimal_100
tf_mobilenetv3_small_075
tf_mobilenetv3_small_100
tf_mobilenetv3_small_minimal_100
tinynet_a
tinynet_b
tinynet_c
tinynet_d
tinynet_e
tnt_s_patch16_224
tresnet_l
tresnet_l_448
tresnet_m
tresnet_m_448
tresnet_m_miil_in21k
tresnet_v2_l
tresnet_xl
tresnet_xl_448
tv_densenet121
tv_resnet34
tv_resnet50
tv_resnet101
tv_resnet152
tv_resnext50_32x4d
twins_pcpvt_base
twins_pcpvt_large
twins_pcpvt_small
twins_svt_base
twins_svt_large
twins_svt_small
vgg11
vgg11_bn
vgg13
vgg13_bn
vgg16
vgg16_bn
vgg19
vgg19_bn
visformer_small
vit_base_patch8_224
vit_base_patch8_224_dino
vit_base_patch8_224_in21k
vit_base_patch16_224
vit_base_patch16_224_dino
vit_base_patch16_224_in21k
vit_base_patch16_224_miil
vit_base_patch16_224_miil_in21k
vit_base_patch16_224_sam
vit_base_patch16_384
vit_base_patch16_rpn_224
vit_base_patch32_224
vit_base_patch32_224_clip_laion2b
vit_base_patch32_224_in21k
vit_base_patch32_224_sam
vit_base_patch32_384
vit_base_r50_s16_224_in21k
vit_base_r50_s16_384
vit_giant_patch14_224_clip_laion2b
vit_huge_patch14_224_clip_laion2b
vit_huge_patch14_224_in21k
vit_large_patch14_224_clip_laion2b
vit_large_patch16_224
vit_large_patch16_224_in21k
vit_large_patch16_384
vit_large_patch32_224_in21k
vit_large_patch32_384
vit_large_r50_s32_224
vit_large_r50_s32_224_in21k
vit_large_r50_s32_384
vit_relpos_base_patch16_224
vit_relpos_base_patch16_clsgap_224
vit_relpos_base_patch32_plus_rpn_256
vit_relpos_medium_patch16_224
vit_relpos_medium_patch16_cls_224
vit_relpos_medium_patch16_rpn_224
vit_relpos_small_patch16_224
vit_small_patch8_224_dino
vit_small_patch16_224
vit_small_patch16_224_dino
vit_small_patch16_224_in21k
vit_small_patch16_384
vit_small_patch32_224
vit_small_patch32_224_in21k
vit_small_patch32_384
vit_small_r26_s32_224
vit_small_r26_s32_224_in21k
vit_small_r26_s32_384
vit_srelpos_medium_patch16_224
vit_srelpos_small_patch16_224
vit_tiny_patch16_224
vit_tiny_patch16_224_in21k
vit_tiny_patch16_384
vit_tiny_r_s16_p8_224
vit_tiny_r_s16_p8_224_in21k
vit_tiny_r_s16_p8_384
volo_d1_224
volo_d1_384
volo_d2_224
volo_d2_384
volo_d3_224
volo_d3_448
volo_d4_224
volo_d4_448
volo_d5_224
volo_d5_448
volo_d5_512
wide_resnet50_2
wide_resnet101_2
xception
xception41
xception41p
xception65
xception65p
xception71
xcit_large_24_p8_224
xcit_large_24_p8_224_dist
xcit_large_24_p8_384_dist
xcit_large_24_p16_224
xcit_large_24_p16_224_dist
xcit_large_24_p16_384_dist
xcit_medium_24_p8_224
xcit_medium_24_p8_224_dist
xcit_medium_24_p8_384_dist
xcit_medium_24_p16_224
xcit_medium_24_p16_224_dist
xcit_medium_24_p16_384_dist
xcit_nano_12_p8_224
xcit_nano_12_p8_224_dist
xcit_nano_12_p8_384_dist
xcit_nano_12_p16_224
xcit_nano_12_p16_224_dist
xcit_nano_12_p16_384_dist
xcit_small_12_p8_224
xcit_small_12_p8_224_dist
xcit_small_12_p8_384_dist
xcit_small_12_p16_224
xcit_small_12_p16_224_dist
xcit_small_12_p16_384_dist
xcit_small_24_p8_224
xcit_small_24_p8_224_dist
xcit_small_24_p8_384_dist
xcit_small_24_p16_224
xcit_small_24_p16_224_dist
xcit_small_24_p16_384_dist
xcit_tiny_12_p8_224
xcit_tiny_12_p8_224_dist
xcit_tiny_12_p8_384_dist
xcit_tiny_12_p16_224
xcit_tiny_12_p16_224_dist
xcit_tiny_12_p16_384_dist
xcit_tiny_24_p8_224
xcit_tiny_24_p8_224_dist
xcit_tiny_24_p8_384_dist
xcit_tiny_24_p16_224
xcit_tiny_24_p16_224_dist
xcit_tiny_24_p16_384_dist

 

끝.