🪐 Timm Encoders

Pytorch Image Models (a.k.a. timm) has a lot of pretrained models and interface which allows using these models as encoders in smp, however, not all models are supported

  • transformer models do not have features_only functionality implemented

  • some models do not have appropriate strides

Below is a table of suitable encoders (for DeepLabV3, DeepLabV3+, and PAN dilation support is needed also)

Total number of encoders: 467

Note

To use following encoders you have to add prefix tu-, e.g. tu-adv_inception_v3

Encoder name

Support dilation

adv_inception_v3

bat_resnext26ts

✅

botnet26t_256

✅

botnet50ts_256

✅

cspresnet50

✅

cspresnet50d

✅

cspresnet50w

✅

cspresnext50

✅

densenet121

densenet121d

densenet161

densenet169

densenet201

densenet264

densenet264d_iabn

densenetblur121d

dla102

dla102x

dla102x2

dla169

dla34

dla46_c

dla46x_c

dla60

dla60_res2net

dla60_res2next

dla60x

dla60x_c

dm_nfnet_f0

✅

dm_nfnet_f1

✅

dm_nfnet_f2

✅

dm_nfnet_f3

✅

dm_nfnet_f4

✅

dm_nfnet_f5

✅

dm_nfnet_f6

✅

dpn107

dpn131

dpn68

dpn68b

dpn92

dpn98

eca_botnext26ts_256

✅

eca_efficientnet_b0

✅

eca_halonext26ts

✅

eca_lambda_resnext26ts

✅

eca_nfnet_l0

✅

eca_nfnet_l1

✅

eca_nfnet_l2

✅

eca_nfnet_l3

✅

eca_swinnext26ts_256

✅

eca_vovnet39b

ecaresnet101d

✅

ecaresnet101d_pruned

✅

ecaresnet200d

✅

ecaresnet269d

✅

ecaresnet26t

✅

ecaresnet50d

✅

ecaresnet50d_pruned

✅

ecaresnet50t

✅

ecaresnetlight

✅

ecaresnext26t_32x4d

✅

ecaresnext50t_32x4d

✅

efficientnet_b0

✅

efficientnet_b1

✅

efficientnet_b1_pruned

✅

efficientnet_b2

✅

efficientnet_b2_pruned

✅

efficientnet_b2a

✅

efficientnet_b3

✅

efficientnet_b3_pruned

✅

efficientnet_b3a

✅

efficientnet_b4

✅

efficientnet_b5

✅

efficientnet_b6

✅

efficientnet_b7

✅

efficientnet_b8

✅

efficientnet_cc_b0_4e

✅

efficientnet_cc_b0_8e

✅

efficientnet_cc_b1_8e

✅

efficientnet_el

✅

efficientnet_el_pruned

✅

efficientnet_em

✅

efficientnet_es

✅

efficientnet_es_pruned

✅

efficientnet_l2

✅

efficientnet_lite0

✅

efficientnet_lite1

✅

efficientnet_lite2

✅

efficientnet_lite3

✅

efficientnet_lite4

✅

efficientnetv2_l

✅

efficientnetv2_m

✅

efficientnetv2_rw_m

✅

efficientnetv2_rw_s

✅

efficientnetv2_s

✅

ens_adv_inception_resnet_v2

ese_vovnet19b_dw

ese_vovnet19b_slim

ese_vovnet19b_slim_dw

ese_vovnet39b

ese_vovnet39b_evos

ese_vovnet57b

ese_vovnet99b

ese_vovnet99b_iabn

fbnetc_100

✅

fbnetv3_b

✅

fbnetv3_d

✅

fbnetv3_g

✅

gc_efficientnet_b0

✅

gcresnet50t

✅

gcresnext26ts

✅

geresnet50t

✅

gernet_l

✅

gernet_m

✅

gernet_s

✅

ghostnet_050

ghostnet_100

ghostnet_130

gluon_inception_v3

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_resnet18_v1b

✅

gluon_resnet34_v1b

✅

gluon_resnet50_v1b

✅

gluon_resnet50_v1c

✅

gluon_resnet50_v1d

✅

gluon_resnet50_v1s

✅

gluon_resnext101_32x4d

✅

gluon_resnext101_64x4d

✅

gluon_resnext50_32x4d

✅

gluon_senet154

✅

gluon_seresnext101_32x4d

✅

gluon_seresnext101_64x4d

✅

gluon_seresnext50_32x4d

✅

gluon_xception65

✅

halonet26t

✅

halonet50ts

✅

halonet_h1

✅

halonet_h1_c4c5

✅

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_32x16d

✅

ig_resnext101_32x32d

✅

ig_resnext101_32x48d

✅

ig_resnext101_32x8d

✅

inception_resnet_v2

inception_v3

inception_v4

lambda_resnet26t

✅

lambda_resnet50t

✅

legacy_senet154

legacy_seresnet101

legacy_seresnet152

legacy_seresnet18

legacy_seresnet34

legacy_seresnet50

legacy_seresnext101_32x4d

legacy_seresnext26_32x4d

legacy_seresnext50_32x4d

mixnet_l

✅

mixnet_m

✅

mixnet_s

✅

mixnet_xl

✅

mixnet_xxl

✅

mnasnet_050

✅

mnasnet_075

✅

mnasnet_100

✅

mnasnet_140

✅

mnasnet_a1

✅

mnasnet_b1

✅

mnasnet_small

✅

mobilenetv2_100

✅

mobilenetv2_110d

✅

mobilenetv2_120d

✅

mobilenetv2_140

✅

mobilenetv3_large_075

✅

mobilenetv3_large_100

✅

mobilenetv3_large_100_miil

✅

mobilenetv3_large_100_miil_in21k

✅

mobilenetv3_rw

✅

mobilenetv3_small_075

✅

mobilenetv3_small_100

✅

nasnetalarge

nf_ecaresnet101

✅

nf_ecaresnet26

✅

nf_ecaresnet50

✅

nf_regnet_b0

✅

nf_regnet_b1

✅

nf_regnet_b2

✅

nf_regnet_b3

✅

nf_regnet_b4

✅

nf_regnet_b5

✅

nf_resnet101

✅

nf_resnet26

✅

nf_resnet50

✅

nf_seresnet101

✅

nf_seresnet26

✅

nf_seresnet50

✅

nfnet_f0

✅

nfnet_f0s

✅

nfnet_f1

✅

nfnet_f1s

✅

nfnet_f2

✅

nfnet_f2s

✅

nfnet_f3

✅

nfnet_f3s

✅

nfnet_f4

✅

nfnet_f4s

✅

nfnet_f5

✅

nfnet_f5s

✅

nfnet_f6

✅

nfnet_f6s

✅

nfnet_f7

✅

nfnet_f7s

✅

nfnet_l0

✅

pnasnet5large

rednet26t

✅

rednet50ts

✅

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

✅

repvgg_a2

✅

repvgg_b0

✅

repvgg_b1

✅

repvgg_b1g4

✅

repvgg_b2

✅

repvgg_b2g4

✅

repvgg_b3

✅

repvgg_b3g4

✅

res2net101_26w_4s

✅

res2net50_14w_8s

✅

res2net50_26w_4s

✅

res2net50_26w_6s

✅

res2net50_26w_8s

✅

res2net50_48w_2s

✅

res2next50

✅

resnest101e

✅

resnest14d

✅

resnest200e

✅

resnest269e

✅

resnest26d

✅

resnest50d

✅

resnest50d_1s4x24d

✅

resnest50d_4s2x40d

✅

resnet101

✅

resnet101d

✅

resnet152

✅

resnet152d

✅

resnet18

✅

resnet18d

✅

resnet200

✅

resnet200d

✅

resnet26

✅

resnet26d

✅

resnet26t

✅

resnet34

✅

resnet34d

✅

resnet50

✅

resnet50d

✅

resnet50t

✅

resnet51q

✅

resnet61q

✅

resnetblur18

✅

resnetblur50

✅

resnetrs101

✅

resnetrs152

✅

resnetrs200

✅

resnetrs270

✅

resnetrs350

✅

resnetrs420

✅

resnetrs50

✅

resnetv2_101

✅

resnetv2_101d

✅

resnetv2_101x1_bitm

✅

resnetv2_101x1_bitm_in21k

✅

resnetv2_101x3_bitm

✅

resnetv2_101x3_bitm_in21k

✅

resnetv2_152

✅

resnetv2_152d

✅

resnetv2_152x2_bit_teacher

✅

resnetv2_152x2_bit_teacher_384

✅

resnetv2_152x2_bitm

✅

resnetv2_152x2_bitm_in21k

✅

resnetv2_152x4_bitm

✅

resnetv2_152x4_bitm_in21k

✅

resnetv2_50

✅

resnetv2_50d

✅

resnetv2_50t

✅

resnetv2_50x1_bit_distilled

✅

resnetv2_50x1_bitm

✅

resnetv2_50x1_bitm_in21k

✅

resnetv2_50x3_bitm

✅

resnetv2_50x3_bitm_in21k

✅

resnext101_32x4d

✅

resnext101_32x8d

✅

resnext101_64x4d

✅

resnext50_32x4d

✅

resnext50d_32x4d

✅

rexnet_100

rexnet_130

rexnet_150

rexnet_200

rexnetr_100

rexnetr_130

rexnetr_150

rexnetr_200

selecsls42

selecsls42b

selecsls60

selecsls60b

selecsls84

semnasnet_050

✅

semnasnet_075

✅

semnasnet_100

✅

semnasnet_140

✅

senet154

✅

seresnet101

✅

seresnet152

✅

seresnet152d

✅

seresnet18

✅

seresnet200d

✅

seresnet269d

✅

seresnet34

✅

seresnet50

✅

seresnet50t

✅

seresnext101_32x4d

✅

seresnext101_32x8d

✅

seresnext26d_32x4d

✅

seresnext26t_32x4d

✅

seresnext26tn_32x4d

✅

seresnext50_32x4d

✅

skresnet18

✅

skresnet34

✅

skresnet50

✅

skresnet50d

✅

skresnext50_32x4d

✅

spnasnet_100

✅

ssl_resnet18

✅

ssl_resnet50

✅

ssl_resnext101_32x16d

✅

ssl_resnext101_32x4d

✅

ssl_resnext101_32x8d

✅

ssl_resnext50_32x4d

✅

swinnet26t_256

✅

swinnet50ts_256

✅

swsl_resnet18

✅

swsl_resnet50

✅

swsl_resnext101_32x16d

✅

swsl_resnext101_32x4d

✅

swsl_resnext101_32x8d

✅

swsl_resnext50_32x4d

✅

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_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

✅

tv_densenet121

tv_resnet101

✅

tv_resnet152

✅

tv_resnet34

✅

tv_resnet50

✅

tv_resnext50_32x4d

✅

vovnet39a

vovnet57a

wide_resnet101_2

✅

wide_resnet50_2

✅

xception

xception41

✅

xception65

✅

xception71

✅