rwightman / pytorch-image-models

TOP 1 ACCURACY TOP 5 ACCURACY
MODEL CODE PAPER
ε-REPR
CODE PAPER
ε-REPR
PAPER
GLOBAL RANK
Adversarial Inception V3
77.6% -- 93.7% -- #444
DLA-102
78.0% -- 94.0% -- #424
DLA-169
78.7% -- 94.3% -- #357
DLA-34
74.6% -- 92.1% -- #578
DLA-46-C
64.9% -- 86.3% -- #727
DLA-60
77.0% -- 93.3% -- #503
DLA-X-102
78.5% -- 94.2% -- #378
DLA-X-102 64
79.5% -- 94.6% -- #280
DLA-X-46-C
66.0% -- 87.0% -- #704
DLA-X-60
78.2% -- 94.0% -- #404
DLA-X-60-C
67.9% -- 88.4% -- #685
DPN-107
(224x224)
80.2% -- 94.9% -- #241
DPN-107
(320x320, Mean-Max Pooling)
81.8% -- 95.9% -- #136
DPN-131
(224x224)
79.8% 80.1% 94.7% 94.9% #271
DPN-131
(320x320, Mean-Max Pooling)
81.4% 81.5% 95.8% 95.8% #144
DPN-68
(224x224)
76.3% 76.4% 93.0% 93.1% #526
DPN-68
(320x320, Mean-Max Pooling)
78.5% 78.5% 94.4% 94.5% #336
DPN-68b
(224x224)
77.5% -- 93.8% -- #461
DPN-68b
(320x320, Mean-Max Pooling)
79.4% -- 95.0% -- #222
DPN-92
(224x224)
80.0% 79.3%
94.8% 94.6% #250
DPN-92
(320x320, Mean-Max Pooling)
81.3% 81.0%
95.7% 95.5% #156
DPN-98
(224x224)
79.6% 80.0% 94.6% 94.8% #269
DPN-98
(320x320, Mean-Max Pooling)
81.2% 81.3% 95.7% 95.6% #159
ECA-ResNet-101d
82.2% -- 96.1% -- #120
ECA-ResNet-50d
80.6% -- 95.3% -- #189
ECA-ResNet-Light
80.5% -- 95.3% -- #199
EfficientNet-B0
77.7% 76.3%
93.5% 93.2%
#473
EfficientNet-B0
(AdvProp)
77.1% -- 93.3% -- #486
EfficientNet-B0
(AutoAugment)
76.8% -- 93.2% -- #504
EfficientNet-B0
(NoisyStudent)
78.7% -- 94.4% -- #368
EfficientNet-B1
78.7% 78.8% 94.2% 94.4% #389
EfficientNet-B1
(AdvProp)
79.3% -- 94.3% -- #301
EfficientNet-B1
(AutoAugment)
78.8% -- 94.2% -- #346
EfficientNet-B1
(NoisyStudent)
81.4% -- 95.7% -- #146
EfficientNet-B2
80.4% 79.8%
95.1% 94.9% #206
EfficientNet-B2
(288x288, 1.0 crop)
80.6% -- 95.3% -- #187
EfficientNet-B2
(AdvProp)
80.3% -- 95.0% -- #218
EfficientNet-B2
(AutoAugment)
80.1% -- 94.9% -- #236
EfficientNet-B2
(NoisyStudent)
82.4% -- 96.3% -- #115
EfficientNet-B3
81.5% 81.1%
95.7% 95.5% #146
EfficientNet-B3
(320x320, 1.0 crop)
81.9% -- 95.8% -- #139
EfficientNet-B3
(AdvProp)
81.8% -- 95.6% -- #162
EfficientNet-B3
(AutoAugment)
81.6% -- 95.7% -- #139
EfficientNet-B3
(NoisyStudent)
84.1% -- 96.9% -- #69
EfficientNet-B4
(AdvProp)
83.2% -- 96.4% -- #89
EfficientNet-B4
(AutoAugment)
83.0% -- 96.3% -- #97
EfficientNet-B4
(NoisyStudent)
85.2% -- 97.5% -- #33
EfficientNet-B5
(AdvProp)
84.3% -- 97.0% -- #61
EfficientNet-B5
(NoisyStudent)
86.1% -- 97.8% -- #17
EfficientNet-B5
(RandAugment)
83.8% -- 96.8% -- #87
EfficientNet-B6
(AdvProp)
84.8% -- 97.1% -- #60
EfficientNet-B6
(AutoAugment)
84.1% -- 96.9% -- #66
EfficientNet-B6
(NoisyStudent)
86.5% -- 97.9% -- #11
EfficientNet-B7
(AdvProp)
85.1% -- 97.3% -- #48
EfficientNet-B7
(NoisyStudent)
86.8% -- 98.1% -- #8
EfficientNet-B7
(RandAugment)
84.9% -- 97.2% -- #45
EfficientNet-B8
(AdvProp)
85.4% -- 97.3% -- #28
EfficientNet-B8
(RandAugment)
85.4% -- 97.4% -- #40
EfficientNet-CondConv-B0 4 experts
77.3% -- 93.3% -- #497
EfficientNet-CondConv-B0 8 experts
77.9% -- 93.7% -- #438
EfficientNet-CondConv-B1 8 experts
79.3% -- 94.4% -- #296
EfficientNet-EdgeTPU-L
80.4% -- 95.2% -- #206
EfficientNet-EdgeTPU-M
78.7% -- 94.3% -- #353
EfficientNet-EdgeTPU-S
78.1% -- 93.6% -- #463
EfficientNet-L2 475
(NoisyStudent)
88.2% -- 98.5% -- #5
EfficientNet-L2
(NoisyStudent)
88.4% -- 98.6% -- #3
EfficientNet-Lite0
74.8% -- 92.2% -- #571
EfficientNet-Lite1
76.6% -- 93.2% -- #516
EfficientNet-Lite2
77.5% -- 93.7% -- #442
EfficientNet-Lite3
79.8% -- 94.9% -- #256
EfficientNet-Lite4
81.5% -- 95.7% -- #144
Ensemble Adversarial Inception V3
80.0% -- 94.9% -- #244
FBNet-C
75.1% 74.9% 92.4% -- #559
HRNet-W18-C
76.8% -- 93.4% -- #480
HRNet-W18-C-Small-V1
72.3% -- 90.7% -- #629
HRNet-W18-C-Small-V2
75.1% -- 92.4% -- #558
HRNet-W30-C
78.2% -- 94.2% -- #410
HRNet-W32-C
78.4% -- 94.2% -- #386
HRNet-W40-C
78.9% -- 94.5% -- #309
HRNet-W44-C
78.9% -- 94.4% -- #339
HRNet-W48-C
79.3% -- 94.5% -- #291
HRNet-W64-C
79.5% -- 94.7% -- #276
Inception ResNet V2
80.5% 80.1%
95.3% 95.1% #188
Inception V3
78.8% 78.8% 94.4% 94.4% #333
Inception V4
80.2% -- 95.0% -- #227
MixNet-L
78.8% 78.9% 94.0% 94.2% #408
MixNet-M
77.0% 77.0% 93.2% 93.3% #517
MixNet-S
75.6% 75.8% 92.6% 92.8% #538
MixNet-XL
80.5% -- 94.9% -- #233
MnasNet-A1
75.5% 75.2% 92.6% 92.5% #546
MnasNet-B1
74.7% -- 92.1% -- #577
MobileNet V3-Large 0.75
73.4% -- 91.4% -- #608
MobileNet V3-Large 1.0
75.8% 75.2%
92.6% -- #540
MobileNet V3-Large Minimal 1.0
72.2% -- 90.6% -- #632
MobileNet V3-Small 0.75
65.7% -- 86.1% -- #724
MobileNet V3-Small 1.0
67.9% -- 87.7% -- #694
MobileNet V3-Small Minimal 1.0
62.9% -- 84.2% -- #732
Modified Aligned Xception
79.6% 79.8% 94.7% 94.8% #262
NASNet-A Large
82.6% -- 96.0% -- #128
PNASNet-5
82.7% 82.9% 96.0% 96.2% #103
Res2Net-50 14x8s
78.2% -- 93.8% -- #414
Res2Net-50 26x4s
77.9% -- 93.9% -- #436
Res2Net-50 26x6s
78.6% -- 94.1% -- #395
Res2Net-50 26x8s
79.2% -- 94.4% -- #346
Res2Net-50 48x2s
77.5% -- 93.5% -- #470
Res2Net-DLA-60
78.5% 79.5% 94.2% -- #383
Res2NeXt-101 26x4s
79.2% -- 94.4% -- #311
Res2NeXt-50
78.2% -- 93.9% -- #424
Res2NeXt-DLA-60
78.4% -- 94.1% -- #387
ResNet-101
79.3% -- 94.5% -- #296
ResNet-101-C
79.5% -- 94.6% -- #292
ResNet-101-D
80.4% -- 95.0% -- #220
ResNet-101-S
80.3% -- 95.2% -- #208
ResNet-152
79.7% -- 94.7% -- #265
ResNet-152-C
79.9% -- 94.8% -- #247
ResNet-152-D
80.5% -- 95.2% -- #195
ResNet-152-S
81.0% -- 95.4% -- #173
ResNet-18
70.8% -- 89.1% -- #669
ResNet-18
73.3% -- 91.4% -- #610
ResNet-26
75.3% -- 92.6% -- #544
ResNet-26-D
76.7% -- 93.2% -- #515
ResNet-34
75.1% -- 92.3% -- #563
ResNet-50
79.0% -- 93.7% -- #446
ResNet-50
79.2% -- 96.0% -- #303
ResNet-50
(288x288 Mean-Max Pooling)
82.0% -- 95.6% -- #167
ResNet-50
(288x288 Mean-Max Pooling)
80.1% -- 95.2% -- #198
ResNet-50-C
78.0% -- 94.0% -- #428
ResNet-50-D
79.1% 77.2%
94.5% 93.5%
#306
ResNet-50-S
78.7% -- 94.2% -- #363
ResNet-Blur-50
79.3% -- 94.6% -- #299
ResNeXt-101 32x16d
81.8% -- 96.1% -- #120
ResNeXt-101 32x16d
84.2% -- 97.2% -- #56
ResNeXt-101 32x16d
(288x288 Mean-Max Pooling)
82.6% -- 96.6% -- #96
ResNeXt-101 32x16d
(288x288 Mean-Max Pooling)
85.0% -- 97.6% -- #42
ResNeXt-101 32x32d
85.1% 85.1% 97.4% 97.5% #37
ResNeXt-101 32x32d
(288x288 Mean-Max Pooling)
85.9% -- 97.8% -- #17
ResNeXt-101 32x48d
85.4% 85.4% 97.6% 97.6% #24
ResNeXt-101 32x48d
(288x288 Mean-Max Pooling)
86.1% -- 97.9% -- #15
ResNeXt-101 32x4d
80.9% -- 95.7% -- #176
ResNeXt-101 32x4d
80.3% -- 94.9% -- #214
ResNeXt-101 32x4d
(288x288 Mean-Max Pooling)
84.0% -- 97.2% -- #73
ResNeXt-101 32x8d
82.7% 82.2%
96.6% 96.4% #106
ResNeXt-101 32x8d
84.3% -- 96.0% -- #126
ResNeXt-101 32x8d
(288x288 Mean-Max Pooling)
82.5% -- 96.5% -- #113
ResNeXt-101 32x8d
(288x288 Mean-Max Pooling)
83.5% -- 97.1% -- #62
ResNeXt-101 64x4d
80.6% -- 95.0% -- #191
ResNeXt-50 32x4d
80.3% -- 95.4% -- #176
ResNeXt-50 32x4d
79.8% -- 94.4% -- #321
ResNeXt-50 32x4d
(288x288 Mean-Max Pooling)
81.3% -- 96.8% -- #81
ResNeXt-50-D 32x4d
79.7% -- 94.9% -- #267
SelecSLS-42_B
77.2% -- 93.4% -- #492
SelecSLS-60
78.0% -- 93.8% -- #434
SelecSLS-60_B
78.4% -- 94.2% -- #386
SENet-154
81.3% 82.7% 95.5% 96.2% #169
SENet-154
81.2% -- 95.4% -- #181
SE-ResNet-101
78.4% -- 94.3% -- #394
SE-ResNet-152
78.7% -- 94.4% -- #337
SE-ResNet-18
71.8% -- 90.3% -- #641
SE-ResNet-34
74.8% -- 92.1% -- #578
SE-ResNet-50
77.6% -- 93.8% -- #448
SE-ResNeXt-101 32x4d
80.9% -- 95.3% -- #179
SE-ResNeXt-101 32x4d
80.2% -- 95.0% -- #216
SE-ResNeXt-101 64x4d
80.9% -- 95.3% -- #190
SE-ResNeXt-26 32x4d
77.1% -- 93.3% -- #501
SE-ResNeXt-26-D 32x4d
77.6% -- 93.6% -- #460
SE-ResNeXt-26-T 32x4d
78.0% -- 93.7% -- #451
SE-ResNeXt-26-TN 32x4d
78.0% -- 93.7% -- #430
SE-ResNeXt-50 32x4d
79.9% -- 94.8% -- #248
SE-ResNeXt-50 32x4d
79.1% -- 94.4% -- #317
Single-Path NAS
74.1% 75.0% 91.8% 92.2% #591
SKNet-50
80.2% -- 94.6% -- #231
SK-ResNet-18
73.0% -- 91.2% -- #618
SK-ResNet-34
76.9% -- 93.3% -- #500
Xception
79.0% 79.0% 94.4% 94.5% #328
See Full Build Details +get badge code
[![SotaBench](https://img.shields.io/endpoint.svg?url=https://sotabench.com/api/v0/badge/gh/beandkay/pytorch-image-models)](https://sotabench.com/user/tinyswish/repos/beandkay/pytorch-image-models)

How the Repository is Evaluated

The full sotabench.py file - source
import torch
from torchbench.image_classification import ImageNet
from timm import create_model
from timm.data import resolve_data_config, create_transform
from timm.models import TestTimePoolHead
import os

NUM_GPU = 1
BATCH_SIZE = 256 * NUM_GPU


def _entry(model_name, paper_model_name, paper_arxiv_id, batch_size=BATCH_SIZE,
           ttp=False, args=dict(), model_desc=None):
    return dict(
        model=model_name,
        model_description=model_desc,
        paper_model_name=paper_model_name,
        paper_arxiv_id=paper_arxiv_id,
        batch_size=batch_size,
        ttp=ttp,
        args=args)

# NOTE For any original PyTorch models, I'll remove from this list when you add to sotabench to
# avoid overlap and confusion. Please contact me.
model_list = [
    ## Weights ported by myself from other frameworks or trained myself in PyTorch
    _entry('adv_inception_v3', 'Adversarial Inception V3', '1611.01236',
           model_desc='Ported from official Tensorflow weights'),
    _entry('ens_adv_inception_resnet_v2', 'Ensemble Adversarial Inception V3', '1705.07204',
           model_desc='Ported from official Tensorflow weights'),
    _entry('dpn68', 'DPN-68 (224x224)', '1707.01629'),
    _entry('dpn68b', 'DPN-68b (224x224)', '1707.01629'),
    _entry('dpn92', 'DPN-92 (224x224)', '1707.01629'),
    _entry('dpn98', 'DPN-98 (224x224)', '1707.01629'),
    _entry('dpn107', 'DPN-107 (224x224)', '1707.01629'),
    _entry('dpn131', 'DPN-131 (224x224)', '1707.01629'),
    _entry('dpn68', 'DPN-68 (320x320, Mean-Max Pooling)', '1707.01629', ttp=True, args=dict(img_size=320)),
    _entry('dpn68b', 'DPN-68b (320x320, Mean-Max Pooling)', '1707.01629', ttp=True, args=dict(img_size=320)),
    _entry('dpn92', 'DPN-92 (320x320, Mean-Max Pooling)', '1707.01629',
           ttp=True, args=dict(img_size=320), batch_size=BATCH_SIZE//2),
    _entry('dpn98', 'DPN-98 (320x320, Mean-Max Pooling)', '1707.01629',
           ttp=True, args=dict(img_size=320), batch_size=BATCH_SIZE//2),
    _entry('dpn107', 'DPN-107 (320x320, Mean-Max Pooling)', '1707.01629',
           ttp=True, args=dict(img_size=320), batch_size=BATCH_SIZE//4),
    _entry('dpn131', 'DPN-131 (320x320, Mean-Max Pooling)', '1707.01629',
           ttp=True, args=dict(img_size=320), batch_size=BATCH_SIZE//4),
    _entry('efficientnet_b0', 'EfficientNet-B0', '1905.11946'),
    _entry('efficientnet_b1', 'EfficientNet-B1', '1905.11946'),
    _entry('efficientnet_b2', 'EfficientNet-B2', '1905.11946',
           model_desc='Trained from scratch in PyTorch w/ RandAugment'),
    _entry('efficientnet_b2a', 'EfficientNet-B2 (288x288, 1.0 crop)', '1905.11946',
           model_desc='Trained from scratch in PyTorch w/ RandAugment'),
    _entry('efficientnet_b3', 'EfficientNet-B3', '1905.11946',
           model_desc='Trained from scratch in PyTorch w/ RandAugment'),
    _entry('efficientnet_b3a', 'EfficientNet-B3 (320x320, 1.0 crop)', '1905.11946',
           model_desc='Trained from scratch in PyTorch w/ RandAugment'),
    _entry('efficientnet_es', 'EfficientNet-EdgeTPU-S', '1905.11946',
           model_desc='Trained from scratch in PyTorch w/ RandAugment'),

    _entry('gluon_inception_v3', 'Inception V3', '1512.00567', model_desc='Ported from GluonCV Model Zoo'),
    _entry('gluon_resnet18_v1b', 'ResNet-18', '1812.01187', model_desc='Ported from GluonCV Model Zoo'),
    _entry('gluon_resnet34_v1b', 'ResNet-34', '1812.01187', model_desc='Ported from GluonCV Model Zoo'),
    _entry('gluon_resnet50_v1b', 'ResNet-50', '1812.01187', model_desc='Ported from GluonCV Model Zoo'),
    _entry('gluon_resnet50_v1c', 'ResNet-50-C', '1812.01187', model_desc='Ported from GluonCV Model Zoo'),
    _entry('gluon_resnet50_v1d', 'ResNet-50-D', '1812.01187', model_desc='Ported from GluonCV Model Zoo'),
    _entry('gluon_resnet50_v1s', 'ResNet-50-S', '1812.01187', model_desc='Ported from GluonCV Model Zoo'),
    _entry('gluon_resnet101_v1b', 'ResNet-101', '1812.01187', model_desc='Ported from GluonCV Model Zoo'),
    _entry('gluon_resnet101_v1c', 'ResNet-101-C', '1812.01187', model_desc='Ported from GluonCV Model Zoo'),
    _entry('gluon_resnet101_v1d', 'ResNet-101-D', '1812.01187', model_desc='Ported from GluonCV Model Zoo'),
    _entry('gluon_resnet101_v1s', 'ResNet-101-S', '1812.01187', model_desc='Ported from GluonCV Model Zoo'),
    _entry('gluon_resnet152_v1b', 'ResNet-152', '1812.01187', model_desc='Ported from GluonCV Model Zoo'),
    _entry('gluon_resnet152_v1c', 'ResNet-152-C', '1812.01187', model_desc='Ported from GluonCV Model Zoo'),
    _entry('gluon_resnet152_v1d', 'ResNet-152-D', '1812.01187', model_desc='Ported from GluonCV Model Zoo'),
    _entry('gluon_resnet152_v1s', 'ResNet-152-S', '1812.01187', model_desc='Ported from GluonCV Model Zoo'),
    _entry('gluon_resnext50_32x4d', 'ResNeXt-50 32x4d', '1812.01187', model_desc='Ported from GluonCV Model Zoo'),
    _entry('gluon_resnext101_32x4d', 'ResNeXt-101 32x4d', '1812.01187', model_desc='Ported from GluonCV Model Zoo'),
    _entry('gluon_resnext101_64x4d', 'ResNeXt-101 64x4d', '1812.01187', model_desc='Ported from GluonCV Model Zoo'),
    _entry('gluon_senet154', 'SENet-154', '1812.01187', model_desc='Ported from GluonCV Model Zoo'),
    _entry('gluon_seresnext50_32x4d', 'SE-ResNeXt-50 32x4d', '1812.01187', model_desc='Ported from GluonCV Model Zoo'),
    _entry('gluon_seresnext101_32x4d', 'SE-ResNeXt-101 32x4d', '1812.01187', model_desc='Ported from GluonCV Model Zoo'),
    _entry('gluon_seresnext101_64x4d', 'SE-ResNeXt-101 64x4d', '1812.01187', model_desc='Ported from GluonCV Model Zoo'),
    _entry('gluon_xception65', 'Modified Aligned Xception', '1802.02611', batch_size=BATCH_SIZE//2,
           model_desc='Ported from GluonCV Model Zoo'),

    _entry('mixnet_xl', 'MixNet-XL', '1907.09595', model_desc="My own scaling beyond paper's MixNet Large"),
    _entry('mixnet_l', 'MixNet-L', '1907.09595'),
    _entry('mixnet_m', 'MixNet-M', '1907.09595'),
    _entry('mixnet_s', 'MixNet-S', '1907.09595'),

    _entry('fbnetc_100', 'FBNet-C', '1812.03443',
           model_desc='Trained in PyTorch with RMSProp, exponential LR decay'),
    _entry('mnasnet_100', 'MnasNet-B1', '1807.11626'),
    _entry('semnasnet_100', 'MnasNet-A1', '1807.11626'),
    _entry('spnasnet_100', 'Single-Path NAS', '1904.02877',
           model_desc='Trained in PyTorch with SGD, cosine LR decay'),
    _entry('mobilenetv3_large_100', 'MobileNet V3-Large 1.0', '1905.02244',
           model_desc='Trained in PyTorch with RMSProp, exponential LR decay, and hyper-params matching '
                      'paper as closely as possible.'),

    _entry('resnet18', 'ResNet-18', '1812.01187'),
    _entry('resnet26', 'ResNet-26', '1812.01187', model_desc='Block cfg of ResNet-34 w/ Bottleneck'),
    _entry('resnet26d', 'ResNet-26-D', '1812.01187',
           model_desc='Block cfg of ResNet-34 w/ Bottleneck, deep stem, and avg-pool in downsample layers.'),
    _entry('resnet34', 'ResNet-34', '1812.01187'),
    _entry('resnet50', 'ResNet-50', '1812.01187', model_desc='Trained with AugMix + JSD loss'),
    _entry('resnet50', 'ResNet-50 (288x288 Mean-Max Pooling)', '1812.01187',
           ttp=True, args=dict(img_size=288),
           model_desc='Trained with AugMix + JSD loss'),
    _entry('resnext50_32x4d', 'ResNeXt-50 32x4d', '1812.01187'),
    _entry('resnext50d_32x4d', 'ResNeXt-50-D 32x4d', '1812.01187',
           model_desc="'D' variant (3x3 deep stem w/ avg-pool downscale). Trained with "
                      "SGD w/ cosine LR decay, random-erasing (gaussian per-pixel noise) and label-smoothing"),

    _entry('seresnet18', 'SE-ResNet-18', '1709.01507'),
    _entry('seresnet34', 'SE-ResNet-34', '1709.01507'),
    _entry('seresnext26_32x4d', 'SE-ResNeXt-26 32x4d', '1709.01507',
           model_desc='Block cfg of SE-ResNeXt-34 w/ Bottleneck'),
    _entry('seresnext26d_32x4d', 'SE-ResNeXt-26-D 32x4d', '1812.01187',
           model_desc='Block cfg of SE-ResNeXt-34 w/ Bottleneck, deep stem, and avg-pool in downsample layers.'),
    _entry('seresnext26t_32x4d', 'SE-ResNeXt-26-T 32x4d', '1812.01187',
           model_desc='Block cfg of SE-ResNeXt-34 w/ Bottleneck, deep tiered stem, and avg-pool in downsample layers.'),
    _entry('seresnext26tn_32x4d', 'SE-ResNeXt-26-TN 32x4d', '1812.01187',
           model_desc='Block cfg of SE-ResNeXt-34 w/ Bottleneck, deep tiered narrow stem, and avg-pool in downsample layers.'),

    _entry('skresnet18', 'SK-ResNet-18', '1903.06586'),
    _entry('skresnet34', 'SK-ResNet-34', '1903.06586'),
    _entry('skresnext50_32x4d', 'SKNet-50', '1903.06586'),

    _entry('ecaresnetlight', 'ECA-ResNet-Light', '1910.03151',
           model_desc='A tweaked ResNet50d with ECA attn.'),
    _entry('ecaresnet50d', 'ECA-ResNet-50d', '1910.03151',
           model_desc='A ResNet50d with ECA attn'),
    _entry('ecaresnet101d', 'ECA-ResNet-101d', '1910.03151',
           model_desc='A ResNet101d with ECA attn'),

    _entry('resnetblur50', 'ResNet-Blur-50', '1904.11486'),

    _entry('tf_efficientnet_b0', 'EfficientNet-B0 (AutoAugment)', '1905.11946',
           model_desc='Ported from official Google AI Tensorflow weights'),
    _entry('tf_efficientnet_b1', 'EfficientNet-B1 (AutoAugment)', '1905.11946',
           model_desc='Ported from official Google AI Tensorflow weights'),
    _entry('tf_efficientnet_b2', 'EfficientNet-B2 (AutoAugment)', '1905.11946',
           model_desc='Ported from official Google AI Tensorflow weights'),
    _entry('tf_efficientnet_b3', 'EfficientNet-B3 (AutoAugment)', '1905.11946', batch_size=BATCH_SIZE//2,
           model_desc='Ported from official Google AI Tensorflow weights'),
    _entry('tf_efficientnet_b4', 'EfficientNet-B4 (AutoAugment)', '1905.11946', batch_size=BATCH_SIZE//2,
           model_desc='Ported from official Google AI Tensorflow weights'),
    _entry('tf_efficientnet_b5', 'EfficientNet-B5 (RandAugment)', '1905.11946', batch_size=BATCH_SIZE//4,
           model_desc='Ported from official Google AI Tensorflow weights'),
    _entry('tf_efficientnet_b6', 'EfficientNet-B6 (AutoAugment)', '1905.11946', batch_size=BATCH_SIZE//8,
           model_desc='Ported from official Google AI Tensorflow weights'),
    _entry('tf_efficientnet_b7', 'EfficientNet-B7 (RandAugment)', '1905.11946', batch_size=BATCH_SIZE//8,
           model_desc='Ported from official Google AI Tensorflow weights'),
    _entry('tf_efficientnet_b8', 'EfficientNet-B8 (RandAugment)', '1905.11946', batch_size=BATCH_SIZE // 8,
           model_desc='Ported from official Google AI Tensorflow weights'),

    _entry('tf_efficientnet_b0_ap', 'EfficientNet-B0 (AdvProp)', '1911.09665',
           model_desc='Ported from official Google AI Tensorflow weights'),
    _entry('tf_efficientnet_b1_ap', 'EfficientNet-B1 (AdvProp)', '1911.09665',
           model_desc='Ported from official Google AI Tensorflow weights'),
    _entry('tf_efficientnet_b2_ap', 'EfficientNet-B2 (AdvProp)', '1911.09665',
           model_desc='Ported from official Google AI Tensorflow weights'),
    _entry('tf_efficientnet_b3_ap', 'EfficientNet-B3 (AdvProp)', '1911.09665', batch_size=BATCH_SIZE // 2,
           model_desc='Ported from official Google AI Tensorflow weights'),
    _entry('tf_efficientnet_b4_ap', 'EfficientNet-B4 (AdvProp)', '1911.09665', batch_size=BATCH_SIZE // 2,
           model_desc='Ported from official Google AI Tensorflow weights'),
    _entry('tf_efficientnet_b5_ap', 'EfficientNet-B5 (AdvProp)', '1911.09665', batch_size=BATCH_SIZE // 4,
           model_desc='Ported from official Google AI Tensorflow weights'),
    _entry('tf_efficientnet_b6_ap', 'EfficientNet-B6 (AdvProp)', '1911.09665', batch_size=BATCH_SIZE // 8,
           model_desc='Ported from official Google AI Tensorflow weights'),
    _entry('tf_efficientnet_b7_ap', 'EfficientNet-B7 (AdvProp)', '1911.09665', batch_size=BATCH_SIZE // 8,
           model_desc='Ported from official Google AI Tensorflow weights'),
    _entry('tf_efficientnet_b8_ap', 'EfficientNet-B8 (AdvProp)', '1911.09665', batch_size=BATCH_SIZE // 8,
           model_desc='Ported from official Google AI Tensorflow weights'),

    _entry('tf_efficientnet_b0_ns', 'EfficientNet-B0 (NoisyStudent)', '1911.04252',
           model_desc='Ported from official Google AI Tensorflow weights'),
    _entry('tf_efficientnet_b1_ns', 'EfficientNet-B1 (NoisyStudent)', '1911.04252',
           model_desc='Ported from official Google AI Tensorflow weights'),
    _entry('tf_efficientnet_b2_ns', 'EfficientNet-B2 (NoisyStudent)', '1911.04252',
           model_desc='Ported from official Google AI Tensorflow weights'),
    _entry('tf_efficientnet_b3_ns', 'EfficientNet-B3 (NoisyStudent)', '1911.04252', batch_size=BATCH_SIZE // 2,
           model_desc='Ported from official Google AI Tensorflow weights'),
    _entry('tf_efficientnet_b4_ns', 'EfficientNet-B4 (NoisyStudent)', '1911.04252', batch_size=BATCH_SIZE // 2,
           model_desc='Ported from official Google AI Tensorflow weights'),
    _entry('tf_efficientnet_b5_ns', 'EfficientNet-B5 (NoisyStudent)', '1911.04252', batch_size=BATCH_SIZE // 4,
           model_desc='Ported from official Google AI Tensorflow weights'),
    _entry('tf_efficientnet_b6_ns', 'EfficientNet-B6 (NoisyStudent)', '1911.04252', batch_size=BATCH_SIZE // 8,
           model_desc='Ported from official Google AI Tensorflow weights'),
    _entry('tf_efficientnet_b7_ns', 'EfficientNet-B7 (NoisyStudent)', '1911.04252', batch_size=BATCH_SIZE // 8,
           model_desc='Ported from official Google AI Tensorflow weights'),
    _entry('tf_efficientnet_l2_ns_475', 'EfficientNet-L2 475 (NoisyStudent)', '1911.04252', batch_size=BATCH_SIZE // 16,
           model_desc='Ported from official Google AI Tensorflow weights'),
    _entry('tf_efficientnet_l2_ns', 'EfficientNet-L2 (NoisyStudent)', '1911.04252', batch_size=BATCH_SIZE // 64,
           model_desc='Ported from official Google AI Tensorflow weights'),

    _entry('tf_efficientnet_cc_b0_4e', 'EfficientNet-CondConv-B0 4 experts', '1904.04971',
           model_desc='Ported from official Google AI Tensorflow weights'),
    _entry('tf_efficientnet_cc_b0_8e', 'EfficientNet-CondConv-B0 8 experts', '1904.04971',
           model_desc='Ported from official Google AI Tensorflow weights'),
    _entry('tf_efficientnet_cc_b1_8e', 'EfficientNet-CondConv-B1 8 experts', '1904.04971',
           model_desc='Ported from official Google AI Tensorflow weights'),

    _entry('tf_efficientnet_es', 'EfficientNet-EdgeTPU-S', '1905.11946',
           model_desc='Ported from official Google AI Tensorflow weights'),
    _entry('tf_efficientnet_em', 'EfficientNet-EdgeTPU-M', '1905.11946',
           model_desc='Ported from official Google AI Tensorflow weights'),
    _entry('tf_efficientnet_el', 'EfficientNet-EdgeTPU-L', '1905.11946', batch_size=BATCH_SIZE//2,
           model_desc='Ported from official Google AI Tensorflow weights'),

    _entry('tf_efficientnet_lite0', 'EfficientNet-Lite0', '1905.11946',
           model_desc='Ported from official Google AI Tensorflow weights'),
    _entry('tf_efficientnet_lite1', 'EfficientNet-Lite1', '1905.11946',
           model_desc='Ported from official Google AI Tensorflow weights'),
    _entry('tf_efficientnet_lite2', 'EfficientNet-Lite2', '1905.11946',
           model_desc='Ported from official Google AI Tensorflow weights'),
    _entry('tf_efficientnet_lite3', 'EfficientNet-Lite3', '1905.11946', batch_size=BATCH_SIZE // 2,
           model_desc='Ported from official Google AI Tensorflow weights'),
    _entry('tf_efficientnet_lite4', 'EfficientNet-Lite4', '1905.11946', batch_size=BATCH_SIZE // 2,
           model_desc='Ported from official Google AI Tensorflow weights'),

    _entry('tf_inception_v3', 'Inception V3', '1512.00567', model_desc='Ported from official Tensorflow weights'),
    _entry('tf_mixnet_l', 'MixNet-L', '1907.09595', model_desc='Ported from official Google AI Tensorflow weights'),
    _entry('tf_mixnet_m', 'MixNet-M', '1907.09595', model_desc='Ported from official Google AI Tensorflow weights'),
    _entry('tf_mixnet_s', 'MixNet-S', '1907.09595', model_desc='Ported from official Google AI Tensorflow weights'),
    _entry('tf_mobilenetv3_large_100', 'MobileNet V3-Large 1.0', '1905.02244',
           model_desc='Ported from official Google AI Tensorflow weights'),
    _entry('tf_mobilenetv3_large_075', 'MobileNet V3-Large 0.75', '1905.02244',
           model_desc='Ported from official Google AI Tensorflow weights'),
    _entry('tf_mobilenetv3_large_minimal_100', 'MobileNet V3-Large Minimal 1.0', '1905.02244',
           model_desc='Ported from official Google AI Tensorflow weights'),
    _entry('tf_mobilenetv3_small_100', 'MobileNet V3-Small 1.0', '1905.02244',
           model_desc='Ported from official Google AI Tensorflow weights'),
    _entry('tf_mobilenetv3_small_075', 'MobileNet V3-Small 0.75', '1905.02244',
           model_desc='Ported from official Google AI Tensorflow weights'),
    _entry('tf_mobilenetv3_small_minimal_100', 'MobileNet V3-Small Minimal 1.0', '1905.02244',
           model_desc='Ported from official Google AI Tensorflow weights'),

    ## Cadene ported weights (to remove if Cadene adds sotabench)
    _entry('inception_resnet_v2', 'Inception ResNet V2', '1602.07261'),
    _entry('inception_v4', 'Inception V4', '1602.07261'),
    _entry('nasnetalarge', 'NASNet-A Large', '1707.07012', batch_size=BATCH_SIZE // 4),
    _entry('pnasnet5large', 'PNASNet-5', '1712.00559', batch_size=BATCH_SIZE // 4),
    _entry('seresnet50', 'SE-ResNet-50', '1709.01507'),
    _entry('seresnet101', 'SE-ResNet-101', '1709.01507'),
    _entry('seresnet152', 'SE-ResNet-152', '1709.01507'),
    _entry('seresnext50_32x4d', 'SE-ResNeXt-50 32x4d', '1709.01507'),
    _entry('seresnext101_32x4d', 'SE-ResNeXt-101 32x4d', '1709.01507'),
    _entry('senet154', 'SENet-154', '1709.01507'),
    _entry('xception', 'Xception', '1610.02357',  batch_size=BATCH_SIZE//2),

    ## Torchvision weights
    # _entry('densenet121'),
    # _entry('densenet161'),
    # _entry('densenet169'),
    # _entry('densenet201'),
    # _entry('inception_v3', paper_model_name='Inception V3', ),
    # _entry('tv_resnet34', , ),
    # _entry('tv_resnet50', , ),
    # _entry('resnet101', , ),
    # _entry('resnet152', , ),
    # _entry('tv_resnext50_32x4d', , ),
    # _entry('resnext101_32x8d', ),
    # _entry('wide_resnet50_2' , ),
    # _entry('wide_resnet101_2', , ),

    ## Facebook WSL weights
    _entry('ig_resnext101_32x8d', 'ResNeXt-101 32x8d', '1805.00932',
           model_desc='Weakly-Supervised pre-training on 1B Instagram hashtag dataset by Facebook Research'),
    _entry('ig_resnext101_32x16d', 'ResNeXt-101 32x16d', '1805.00932',
           model_desc='Weakly-Supervised pre-training on 1B Instagram hashtag dataset by Facebook Research'),
    _entry('ig_resnext101_32x32d', 'ResNeXt-101 32x32d', '1805.00932', batch_size=BATCH_SIZE // 2,
           model_desc='Weakly-Supervised pre-training on 1B Instagram hashtag dataset by Facebook Research'),
    _entry('ig_resnext101_32x48d', 'ResNeXt-101 32x48d', '1805.00932', batch_size=BATCH_SIZE // 4,
           model_desc='Weakly-Supervised pre-training on 1B Instagram hashtag dataset by Facebook Research'),

    _entry('ig_resnext101_32x8d', 'ResNeXt-101 32x8d (288x288 Mean-Max Pooling)', '1805.00932',
           ttp=True, args=dict(img_size=288),
           model_desc='Weakly-Supervised pre-training on 1B Instagram hashtag dataset by Facebook Research'),
    _entry('ig_resnext101_32x16d', 'ResNeXt-101 32x16d (288x288 Mean-Max Pooling)', '1805.00932',
           ttp=True, args=dict(img_size=288), batch_size=BATCH_SIZE // 2,
           model_desc='Weakly-Supervised pre-training on 1B Instagram hashtag dataset by Facebook Research'),
    _entry('ig_resnext101_32x32d', 'ResNeXt-101 32x32d (288x288 Mean-Max Pooling)', '1805.00932',
           ttp=True, args=dict(img_size=288), batch_size=BATCH_SIZE // 4,
           model_desc='Weakly-Supervised pre-training on 1B Instagram hashtag dataset by Facebook Research'),
    _entry('ig_resnext101_32x48d', 'ResNeXt-101 32x48d (288x288 Mean-Max Pooling)', '1805.00932',
           ttp=True, args=dict(img_size=288), batch_size=BATCH_SIZE // 8,
           model_desc='Weakly-Supervised pre-training on 1B Instagram hashtag dataset by Facebook Research'),

    ## Facebook SSL weights
    _entry('ssl_resnet18', 'ResNet-18', '1905.00546',
           model_desc='Semi-Supervised pre-training on YFCC100M dataset by Facebook Research'),
    _entry('ssl_resnet50', 'ResNet-50', '1905.00546',
           model_desc='Semi-Supervised pre-training on YFCC100M dataset by Facebook Research'),
    _entry('ssl_resnext50_32x4d', 'ResNeXt-50 32x4d', '1905.00546',
           model_desc='Semi-Supervised pre-training on YFCC100M dataset by Facebook Research'),
    _entry('ssl_resnext101_32x4d', 'ResNeXt-101 32x4d', '1905.00546',
           model_desc='Semi-Supervised pre-training on YFCC100M dataset by Facebook Research'),
    _entry('ssl_resnext101_32x8d', 'ResNeXt-101 32x8d', '1905.00546',
           model_desc='Semi-Supervised pre-training on YFCC100M dataset by Facebook Research'),
    _entry('ssl_resnext101_32x16d', 'ResNeXt-101 32x16d', '1905.00546',
           model_desc='Semi-Supervised pre-training on YFCC100M dataset by Facebook Research'),

    _entry('ssl_resnet50', 'ResNet-50 (288x288 Mean-Max Pooling)', '1905.00546',
           ttp=True, args=dict(img_size=288),
           model_desc='Semi-Supervised pre-training on YFCC100M dataset by Facebook Research'),
    _entry('ssl_resnext50_32x4d', 'ResNeXt-50 32x4d (288x288 Mean-Max Pooling)', '1905.00546',
           ttp=True, args=dict(img_size=288),
           model_desc='Semi-Supervised pre-training on YFCC100M dataset by Facebook Research'),
    _entry('ssl_resnext101_32x4d', 'ResNeXt-101 32x4d (288x288 Mean-Max Pooling)', '1905.00546',
           ttp=True, args=dict(img_size=288),
           model_desc='Semi-Supervised pre-training on YFCC100M dataset by Facebook Research'),
    _entry('ssl_resnext101_32x8d', 'ResNeXt-101 32x8d (288x288 Mean-Max Pooling)', '1905.00546',
           ttp=True, args=dict(img_size=288),
           model_desc='Semi-Supervised pre-training on YFCC100M dataset by Facebook Research'),
    _entry('ssl_resnext101_32x16d', 'ResNeXt-101 32x16d (288x288 Mean-Max Pooling)', '1905.00546',
           ttp=True, args=dict(img_size=288), batch_size=BATCH_SIZE // 2,
           model_desc='Semi-Supervised pre-training on YFCC100M dataset by Facebook Research'),

    ## Facebook SWSL weights
    _entry('swsl_resnet18', 'ResNet-18', '1905.00546',
           model_desc='Semi-Weakly-Supervised pre-training on 1 billion unlabelled dataset by Facebook Research'),
    _entry('swsl_resnet50', 'ResNet-50', '1905.00546',
           model_desc='Semi-Weakly-Supervised pre-training on 1 billion unlabelled dataset by Facebook Research'),
    _entry('swsl_resnext50_32x4d', 'ResNeXt-50 32x4d', '1905.00546',
           model_desc='Semi-Weakly-Supervised pre-training on 1 billion unlabelled dataset by Facebook Research'),
    _entry('swsl_resnext101_32x4d', 'ResNeXt-101 32x4d', '1905.00546',
           model_desc='Semi-Weakly-Supervised pre-training on 1 billion unlabelled dataset by Facebook Research'),
    _entry('swsl_resnext101_32x8d', 'ResNeXt-101 32x8d', '1905.00546',
           model_desc='Semi-Weakly-Supervised pre-training on 1 billion unlabelled dataset by Facebook Research'),
    _entry('swsl_resnext101_32x16d', 'ResNeXt-101 32x16d', '1905.00546',
           model_desc='Semi-Weakly-Supervised pre-training on 1 billion unlabelled dataset by Facebook Research'),

    _entry('swsl_resnet50', 'ResNet-50 (288x288 Mean-Max Pooling)', '1905.00546',
           ttp=True, args=dict(img_size=288),
           model_desc='Semi-Weakly-Supervised pre-training on 1 billion unlabelled dataset by Facebook Research'),
    _entry('swsl_resnext50_32x4d', 'ResNeXt-50 32x4d (288x288 Mean-Max Pooling)', '1905.00546',
           ttp=True, args=dict(img_size=288),
           model_desc='Semi-Weakly-Supervised pre-training on 1 billion unlabelled dataset by Facebook Research'),
    _entry('swsl_resnext101_32x4d', 'ResNeXt-101 32x4d (288x288 Mean-Max Pooling)', '1905.00546',
           ttp=True, args=dict(img_size=288),
           model_desc='Semi-Weakly-Supervised pre-training on 1 billion unlabelled dataset by Facebook Research'),
    _entry('swsl_resnext101_32x8d', 'ResNeXt-101 32x8d (288x288 Mean-Max Pooling)', '1905.00546',
           ttp=True, args=dict(img_size=288),
           model_desc='Semi-Weakly-Supervised pre-training on 1 billion unlabelled dataset by Facebook Research'),
    _entry('swsl_resnext101_32x16d', 'ResNeXt-101 32x16d (288x288 Mean-Max Pooling)', '1905.00546',
           ttp=True, args=dict(img_size=288), batch_size=BATCH_SIZE // 2,
           model_desc='Semi-Weakly-Supervised pre-training on 1 billion unlabelled dataset by Facebook Research'),

    ## DLA official impl weights (to remove if sotabench added to source)
    _entry('dla34', 'DLA-34', '1707.06484'),
    _entry('dla46_c', 'DLA-46-C', '1707.06484'),
    _entry('dla46x_c', 'DLA-X-46-C', '1707.06484'),
    _entry('dla60x_c', 'DLA-X-60-C', '1707.06484'),
    _entry('dla60', 'DLA-60', '1707.06484'),
    _entry('dla60x', 'DLA-X-60', '1707.06484'),
    _entry('dla102', 'DLA-102', '1707.06484'),
    _entry('dla102x', 'DLA-X-102', '1707.06484'),
    _entry('dla102x2', 'DLA-X-102 64', '1707.06484'),
    _entry('dla169', 'DLA-169', '1707.06484'),

    ## Res2Net official impl weights (to remove if sotabench added to source)
    _entry('res2net50_26w_4s', 'Res2Net-50 26x4s', '1904.01169'),
    _entry('res2net50_14w_8s', 'Res2Net-50 14x8s', '1904.01169'),
    _entry('res2net50_26w_6s', 'Res2Net-50 26x6s', '1904.01169'),
    _entry('res2net50_26w_8s', 'Res2Net-50 26x8s', '1904.01169'),
    _entry('res2net50_48w_2s', 'Res2Net-50 48x2s', '1904.01169'),
    _entry('res2net101_26w_4s', 'Res2NeXt-101 26x4s', '1904.01169'),
    _entry('res2next50', 'Res2NeXt-50', '1904.01169'),
    _entry('dla60_res2net', 'Res2Net-DLA-60', '1904.01169'),
    _entry('dla60_res2next', 'Res2NeXt-DLA-60', '1904.01169'),

    ## HRNet official impl weights
    _entry('hrnet_w18_small', 'HRNet-W18-C-Small-V1', '1908.07919'),
    _entry('hrnet_w18_small_v2', 'HRNet-W18-C-Small-V2', '1908.07919'),
    _entry('hrnet_w18', 'HRNet-W18-C', '1908.07919'),
    _entry('hrnet_w30', 'HRNet-W30-C', '1908.07919'),
    _entry('hrnet_w32', 'HRNet-W32-C', '1908.07919'),
    _entry('hrnet_w40', 'HRNet-W40-C', '1908.07919'),
    _entry('hrnet_w44', 'HRNet-W44-C', '1908.07919'),
    _entry('hrnet_w48', 'HRNet-W48-C', '1908.07919'),
    _entry('hrnet_w64', 'HRNet-W64-C', '1908.07919'),


    ## SelecSLS official impl weights
    _entry('selecsls42b', 'SelecSLS-42_B', '1907.00837',
           model_desc='Originally from https://github.com/mehtadushy/SelecSLS-Pytorch'),
    _entry('selecsls60', 'SelecSLS-60', '1907.00837',
           model_desc='Originally from https://github.com/mehtadushy/SelecSLS-Pytorch'),
    _entry('selecsls60b', 'SelecSLS-60_B', '1907.00837',
           model_desc='Originally from https://github.com/mehtadushy/SelecSLS-Pytorch'),
]

for m in model_list:
    model_name = m['model']
    # create model from name
    model = create_model(model_name, pretrained=True)
    param_count = sum([m.numel() for m in model.parameters()])
    print('Model %s, %s created. Param count: %d' % (model_name, m['paper_model_name'], param_count))

    # get appropriate transform for model's default pretrained config
    data_config = resolve_data_config(m['args'], model=model, verbose=True)
    if m['ttp']:
        model = TestTimePoolHead(model, model.default_cfg['pool_size'])
        data_config['crop_pct'] = 1.0
    input_transform = create_transform(**data_config)

    # Run the benchmark
    ImageNet.benchmark(
        model=model,
        model_description=m.get('model_description', None),
        paper_model_name=m['paper_model_name'],
        paper_arxiv_id=m['paper_arxiv_id'],
        input_transform=input_transform,
        batch_size=m['batch_size'],
        num_gpu=NUM_GPU,
        data_root=os.environ.get('IMAGENET_DIR', './imagenet')
    )

    torch.cuda.empty_cache()


STATUS
BUILD
COMMIT MESSAGE
RUN TIME
Revert "add resnetcb50" This reverts commit a238109dfb17579cbe8…
beandkay   4513b18  ·  May 26 2020
0h:38m:05s
add resnetcb50
beandkay   a238109  ·  May 25 2020
0h:17m:37s
1h:44m:24s