osmr / imgclsmob

TOP 1 ACCURACY TOP 5 ACCURACY
SPEED
MODEL CODE PAPER
ε-REPR
CODE PAPER
ε-REPR
PAPER
GLOBAL RANK
108-MENet-8x1
(g=3)
56.1% -- 79.2% -- #467
1.0-SqNxt-23
57.5% -- 80.9% -- #465
1.0-SqNxt-23v5
59.2% -- 82.2% -- #457
128-MENet-8x1
(g=4)
57.6% -- 80.4% -- #463
1.5-SqNxt-23
65.1% -- 86.5% -- #436
1.5-SqNxt-23v5
66.2% -- 87.0% -- #419
160-MENet-8x1
(g=8)
56.2% -- 79.2% -- #467
2.0-SqNxt-23
69.4% -- 89.0% -- #393
2.0-SqNxt-23v5
70.4% -- 89.3% -- #378
228-MENet-12x1
(g=3)
65.9% -- 86.8% -- #427
256-MENet-12x1
(g=4)
67.3% -- 87.5% -- #413
348-MENet-12x1
(g=3)
71.8% -- 90.4% -- #360
352-MENet-12x1
(g=8)
68.4% -- 88.0% -- #407
456-MENet-24x1
(g=3)
74.7% -- 92.0% -- #312
AlexNet
59.0% -- 81.8% -- 417.5 #458
AlexNet-b
58.4% -- 81.0% -- 418.1 #460
BAM-ResNet-50
76.9% -- 93.4% -- #258
BN-Inception
74.6% -- 92.3% -- 426.1 #307
BN-VGG-11
71.0% -- 90.4% -- 420.9 #375
BN-VGG-11b
70.4% -- 90.0% -- 415.6 #377
BN-VGG-13
72.2% -- 90.9% -- 406.0 #352
BN-VGG-13b
71.6% -- 90.4% -- 394.5 #364
BN-VGG-16
74.3% -- 92.2% -- 400.7 #326
BN-VGG-16b
72.8% -- 91.3% -- 394.4 #345
BN-VGG-19
75.9% -- 92.9% -- 395.8 #287
BN-VGG-19b
73.9% -- 91.6% -- 385.3 #334
CBAM-ResNet-50
77.6% -- 93.9% -- #214
CondenseNet-74
(C=G=4)
73.8% -- 91.7% -- #335
CondenseNet-74
(C=G=8)
71.1% -- 89.9% -- #376
DarkNet-53
78.3% -- 94.4% -- #203
DARTS
73.3% -- 91.3% -- #346
DenseNet-121
76.5% 76.4% 93.0% 93.3% #276
DenseNet-161
78.1% -- 93.9% -- 386.0 #214
DenseNet-169
77.6% 77.9% 93.7% 94.1% #232
DenseNet-201
78.2% 78.5% 93.9% 94.5% 392.4 #220
DiracNetV2-18
68.5% -- 88.3% -- #403
DiracNetV2-34
71.2% -- 90.1% -- #374
DLA-102
78.0% -- 94.0% -- #213
DLA-169
78.7% -- 94.3% -- #175
DLA-34
74.6% -- 92.1% -- #318
DLA-46-C
65.7% -- 86.8% -- #433
DLA-60
77.0% -- 93.3% -- #269
DLA-X-102
78.5% -- 94.2% -- #178
DLA-X2-102
79.5% -- 94.6% -- #129
DLA-X-46-C
66.7% -- 87.3% -- #416
DLA-X-60
78.2% -- 94.0% -- #206
DLA-X-60-C
69.0% -- 89.1% -- #397
DPN-131
79.5% -- 94.5% -- #136
DPN-68
76.8% -- 93.2% -- #272
DPN-98
79.2% -- 94.5% -- #143
DRN-C-26
75.1% -- 92.5% -- #299
DRN-C-42
77.1% -- 93.4% -- #257
DRN-C-58
78.3% -- 94.0% -- #209
DRN-D-105
79.4% -- 94.5% -- #131
DRN-D-22
74.2% -- 91.8% -- #328
DRN-D-38
76.2% -- 93.1% -- #282
DRN-D-54
78.8% -- 94.1% -- #169
EfficientNet-B0
75.2% 76.3% 92.5% 93.2% #298
EfficientNet-B0b
76.1% -- 93.0% -- #283
EfficientNet-B1
77.0% 78.8% 93.6% 94.4% #260
EfficientNet-B1b
78.4% -- 94.1% -- #195
EfficientNet-B2b
79.7% -- 94.7% -- 368.5 #118
EfficientNet-B3b
81.4% -- 95.6% -- 328.4 #74
EfficientNet-B4b
82.8% -- 96.2% -- 221.8 #44
EfficientNet-B5b
83.6% -- 96.7% -- 115.4 #40
EfficientNet-B6b
84.1% -- 96.9% -- 68.4 #30
EfficientNet-B7b
84.3% -- 96.9% -- 39.5 #29
ESPNetv2 x0.5
57.7% -- 79.8% -- #463
ESPNetv2 x1.0
66.1% -- 86.5% -- #422
ESPNetv2 x1.25
67.9% -- 87.8% -- #408
ESPNetv2 x1.5
69.2% -- 88.7% -- #396
ESPNetv2 x2.0
72.1% -- 90.4% -- #360
FBNet-Cb
75.1% -- 92.4% -- 407.7 #304
FD-MobileNet x0.25
44.1% -- 69.0% -- #476
FD-MobileNet x0.5
56.9% -- 79.8% -- #465
FD-MobileNet x0.75
61.6% -- 83.6% -- #444
FD-MobileNet x1.0
65.8% -- 86.6% -- #430
HarDNet-39DS
72.1% -- 90.4% -- 406.9 #359
HarDNet-68
76.5% -- 93.0% -- 403.0 #277
HarDNet-68DS
74.3% -- 91.9% -- 408.0 #325
HarDNet-85
78.0% -- 93.9% -- 392.2 #217
HRNetV2-W18
76.8% -- 93.4% -- 382.9 #253
HRNetV2-W30
78.2% -- 94.2% -- 377.8 #181
HRNetV2-W32
78.4% -- 94.2% -- 374.2 #187
HRNetV2-W40
78.9% -- 94.5% -- 354.0 #162
HRNetV2-W44
78.9% -- 94.4% -- 333.8 #164
HRNetV2-W48
79.3% -- 94.5% -- 315.6 #135
HRNetV2-W64
79.5% -- 94.7% -- 265.0 #125
HRNet-W18 Small V1
72.3% -- 90.7% -- 399.5 #354
HRNet-W18 Small V2
75.1% -- 92.4% -- 393.6 #301
IBN(b)-ResNet-50
76.4% -- 93.1% -- #279
IBN-DenseNet-121
75.5% -- 92.8% -- #292
IBN-DenseNet-169
76.8% -- 93.5% -- #273
IBN-ResNet-101
78.7% -- 94.4% -- #173
IBN-ResNet-50
77.2% -- 93.6% -- #242
IBN-ResNeXt-101
(32x4d)
79.1% -- 94.6% -- #145
IGCV3 x0.25
46.3% -- 71.3% -- #475
IGCV3 x0.5
60.2% -- 82.7% -- #450
IGCV3 x0.75
68.9% -- 88.6% -- #399
IGCV3 x1.0
72.1% -- 90.8% -- #353
InceptionResNetV2
80.1% -- 95.1% -- #107
InceptionV3
78.9% -- 94.4% -- #166
InceptionV4
79.4% -- 94.7% -- #122
i-RevNet-301
74.0% -- 91.6% -- #332
MixNet-L
78.9% 78.9% 94.2% 94.2% 400.3 #165
MixNet-M
77.1% 77.0% 93.4% 93.3% 404.0 #258
MixNet-S
76.0% 75.8% 92.8% 92.8% 413.1 #284
MnasNet-A1
75.3% 75.2% 92.6% 92.5% 413.1 #295
MnasNet-B1
74.6% -- 92.2% -- 415.4 #317
MobileNetV2b x0.25
51.4% -- 74.7% -- 402.4 #474
MobileNetV2b x0.5
64.0% -- 85.0% -- 406.1 #440
MobileNetV2b x0.75
68.9% -- 88.2% -- 390.5 #404
MobileNetV2b x1.0
71.5% -- 90.2% -- 403.0 #371
MobileNetV2 x0.25
51.7% -- 75.5% -- #473
MobileNetV2 x0.5
64.0% -- 85.1% -- #441
MobileNetV2 x0.75
69.8% -- 89.2% -- #384
MobileNetV2 x1.0
73.0% -- 91.1% -- #348
MobileNetV3 L/224/1.0
75.1% -- 92.2% -- #301
MobileNet x0.25
53.7% -- 77.5% -- #471
MobileNet x0.5
65.8% -- 86.5% -- #428
MobileNet x0.75
69.9% -- 89.2% -- #382
MobileNet x1.0
73.4% -- 91.0% -- #350
74.3% -- 91.8% -- #324
81.9% -- 95.8% -- #58
PeleeNet
68.2% -- 88.5% -- #400
PNASNet-5-Large
82.1% -- 95.7% -- #54
PolyNet
80.9% 81.3% 95.5% 95.8% #80
PrepResNet-10
64.9% -- 85.8% -- #438
PreResNet-101
78.3% -- 94.1% -- #202
PreResNet-101b
79.0% -- 94.4% -- #148
PreResNet-12
66.1% -- 86.5% -- #429
PreResNet-14
67.4% -- 87.6% -- #413
PreResNet-152
79.1% -- 94.5% -- #146
PreResNet-152b
79.9% -- 94.8% -- #113
PreResNet-16
69.5% -- 88.9% -- #391
PreResNet-18
71.6% -- 90.3% -- #366
PreResNet-18 x0.25
59.9% -- 81.9% -- 426.0 #454
PreResNet-18 x0.5
66.0% -- 86.6% -- 433.1 #423
PreResNet-18 x0.75
69.8% -- 88.9% -- 429.0 #385
PreResNet-200b
78.7% -- 94.1% -- #198
PreResNet-26
73.7% -- 91.5% -- #337
PreResNet-269b
79.1% -- 94.2% -- #147
PreResNet-34
75.1% -- 92.3% -- #308
PreResNet-50
77.6% -- 93.5% -- #236
PreResNet-50b
77.5% -- 93.4% -- #242
PreResNet=BC-14b
68.7% -- 88.2% -- 427.5 #406
PreResNet-BC-26b
74.5% -- 92.0% -- #322
PreResNet-BC-38b
77.1% -- 93.4% -- #255
ProxylessNAS CPU
75.3% -- 92.4% -- #297
ProxylessNAS GPU
75.2% -- 92.6% -- #296
ProxylessNAS Mob-14
76.7% -- 93.4% -- #263
ProxylessNAS Mobile
74.6% -- 92.2% -- #318
PyramidNet-101
(a=360)
78.0% -- 93.8% -- #225
ResNet-10
65.3% -- 85.6% -- #439
ResNet-101
78.1% 78.2% 93.8% 94.0% #226
ResNet-101b
79.4% -- 94.7% -- #124
ResNet-12
66.4% -- 86.7% -- #417
ResNet-14
67.5% -- 87.5% -- #411
ResNet-152
79.0% 78.6%
94.5% 94.3% #141
ResNet-152b
80.1% -- 95.0% -- #100
ResNet-16
69.5% -- 88.8% -- #391
ResNet-18
71.5% 72.1% 90.2% -- 412.9 #372
ResNet-18 x0.25
60.4% -- 82.2% -- 438.7 #452
ResNet-18 x0.5
66.2% -- 86.7% -- 438.2 #421
ResNet-18 x0.75
69.6% -- 88.9% -- 435.0 #388
ResNet-26
73.7% -- 91.5% -- #336
ResNet-34
75.2% -- 92.2% -- #300
ResNet-50
77.7% 77.1%
93.7% 93.3%
#234
ResNet-50b
77.6% -- 93.6% -- #238
ResNet-BC-14b
69.3% -- 88.5% -- 428.6 #395
ResNet-BC-26b
74.9% -- 92.0% -- #319
ResNet-BC-38b
76.3% -- 93.0% -- #280
ResNeXt-101
(32x4d)
80.0% -- 94.8% -- #117
ResNeXt-101
(64x4d)
80.4% -- 94.9% -- #93
ResNeXt-14
(16x4d)
68.1% -- 87.5% -- #412
ResNeXt-14
(32x2d)
67.4% -- 87.2% -- #412
ResNeXt-14
(32x4d)
69.7% -- 88.5% -- #398
ResNeXt-26
(32x2d)
73.4% -- 91.1% -- #340
ResNeXt-26
(32x4d)
75.9% -- 92.5% -- #297
ResNeXt-50
(32x4d)
79.2% -- 94.4% -- #155
SelecSLS-42b
77.1% -- 93.4% -- 405.9 #259
SelecSLS-60
77.9% -- 93.9% -- 414.8 #219
SelecSLS-60b
78.4% -- 94.2% -- 409.4 #192
SENet-154
81.4% 82.7% 95.4% 96.2% #80
SENet-16
74.4% -- 91.8% -- #327
SENet-28
78.1% -- 94.0% -- #207
SE-PreResNet-10
66.0% -- 86.6% -- #425
SE-PreResNet-18
71.9% -- 90.4% -- #361
SE-PreResNet-BC-26b
76.8% -- 93.4% -- #268
SE-PreResNet-BC-38b
78.4% -- 94.2% -- #198
SE-ResNet-10
66.1% -- 86.3% -- #434
SE-ResNet-101
78.1% -- 94.1% -- #212
SE-ResNet-152
78.5% -- 94.2% -- #176
SE-ResNet-18
71.8% -- 90.4% -- #361
SE-ResNet-26
74.3% -- 91.8% -- #329
SE-ResNet-50
78.8% -- 94.2% -- 369.0 #170
SE-ResNet-50b
79.2% -- 94.6% -- #131
SE-ResNet-BC-26b
76.4% -- 93.0% -- #282
SE-ResNet-BC-38b
78.4% -- 94.1% -- #196
SE-ResNeXt-101
(32x4d)
80.8% -- 95.2% -- 369.8 #83
SE-ResNeXt-101
(64x4d)
80.7% -- 95.2% -- 263.6 #89
SE-ResNeXt-50
(32x4d)
79.7% -- 94.8% -- 389.8 #116
ShuffleNetV2b x0.5
59.7% -- 81.8% -- #456
ShuffleNetV2b x1.0
69.4% -- 88.8% -- #394
ShuffleNetV2b x1.5
72.7% -- 90.9% -- #350
ShuffleNetV2b x2.0
74.4% -- 91.7% -- #333
ShuffleNetV2 x0.5
59.0% -- 81.4% -- #459
ShuffleNetV2 x1.0
68.6% -- 88.4% -- #403
ShuffleNetV2 x1.5
72.5% -- 90.6% -- #358
ShuffleNetV2 x2.0
74.1% -- 91.6% -- #331
ShuffleNet x0.25
(g=1)
37.6% -- 62.7% -- #478
ShuffleNet x0.25
(g=3)
38.3% -- 63.5% -- #477
ShuffleNet x0.5
(g=1)
53.4% -- 77.4% -- #472
ShuffleNet x0.5
(g=3)
55.8% -- 79.2% -- #470
ShuffleNet x0.75
(g=1)
60.4% -- 82.9% -- #448
ShuffleNet x0.75
(g=3)
61.8% -- 83.5% -- #445
ShuffleNet x1.0
(g=1)
65.1% -- 86.1% -- #437
ShuffleNet x1.0
(g=2)
65.8% -- 86.4% -- #433
ShuffleNet x1.0
(g=3)
65.6% -- 86.5% -- #430
ShuffleNet x1.0
(g=4)
65.8% -- 86.6% -- #429
ShuffleNet x1.0
(g=8)
65.9% -- 86.6% -- #426
SPNASNet
74.1% -- 91.8% -- 412.2 #326
SqueezeNet v1.0
60.7% -- 82.3% -- #446
SqueezeNet v1.1
60.7% -- 82.3% -- #450
SqueezeResNet v1.0
60.2% -- 81.9% -- #451
SqueezeResNet v1.1
59.9% -- 81.8% -- #455
VGG-11
70.1% 70.4% 89.6% 89.6% 411.2 #381
VGG-13
71.2% 71.3% 90.2% 90.1% 406.1 #373
VGG-16
73.0% 74.4% 91.3% 91.9% 396.4 #348
VGG-19
74.3% 74.5% 92.1% 92.0% 338.8 #327
VoVNet-39
76.8% -- 93.4% -- 410.3 #269
VoVNet-57
77.7% -- 93.7% -- 402.2 #231
WRN-50-2
77.5% -- 93.6% -- #241
Xception
79.0% 79.0% 94.5% 94.5% #156
ZFNet
60.2% 64.0% 82.7% 85.3% 428.2 #447
ZFNet-b
63.6% -- 85.1% -- 426.3 #440
See Full Build Details +get badge code
[![SotaBench](https://img.shields.io/endpoint.svg?url=https://sotabench.com/api/v0/badge/gh/osmr/imgclsmob)](https://sotabench.com/user/osemery/repos/osmr/imgclsmob)

How the Repository is Evaluated

The full sotabench.py file - source
from torchbench.image_classification import ImageNet
from pytorch.pytorchcv.models.model_store import _model_sha1
from pytorch.pytorchcv.model_provider import get_model as ptcv_get_model
import torchvision.transforms as transforms
import torch
import math
from sys import version_info
# import os


for model_name, model_metainfo in (_model_sha1.items() if version_info[0] >= 3 else _model_sha1.iteritems()):
    net = ptcv_get_model(model_name, pretrained=True)
    error, checksum, repo_release_tag, caption, paper, ds, img_size, scale, batch, rem = model_metainfo
    if (ds != "in1k") or (img_size == 0) or ((len(rem) > 0) and (rem[-1] == "*")):
        continue
    paper_model_name = caption
    paper_arxiv_id = paper
    input_image_size = img_size
    resize_inv_factor = scale
    batch_size = batch
    model_description = "pytorch" + (rem if rem == "" else ", " + rem)
    assert (not hasattr(net, "in_size")) or (input_image_size == net.in_size[0])
    ImageNet.benchmark(
        model=net,
        model_description=model_description,
        paper_model_name=paper_model_name,
        paper_arxiv_id=paper_arxiv_id,
        input_transform=transforms.Compose([
            transforms.Resize(int(math.ceil(float(input_image_size) / resize_inv_factor))),
            transforms.CenterCrop(input_image_size),
            transforms.ToTensor(),
            transforms.Normalize(
                mean=[0.485, 0.456, 0.406],
                std=[0.229, 0.224, 0.225]),
        ]),
        batch_size=batch_size,
        num_gpu=1,
        # data_root=os.path.join("..", "imgclsmob_data", "imagenet")
    )
    torch.cuda.empty_cache()
STATUS
BUILD
COMMIT MESSAGE
RUN TIME
Update info about ICNet models
osmr   100370e  ·  13 hours ago
1h:01m:45s
Working on ICNet, 2
osmr   460dc07  ·  yesterday
0h:56m:39s
Working on ICNet
osmr   3544837  ·  yesterday
0h:58m:27s
Update info about SimplePose(Mobile) models
osmr   4c1ed04  ·  2 days ago
0h:49m:33s
Update info about SimplePose models
osmr   b130280  ·  2 days ago
unknown
Update info about AlphaPose models
osmr   9c98c51  ·  2 days ago
unknown
Update info about MobileNetV2b models
osmr   ed026eb  ·  2 days ago
1h:07m:27s
Working on COCO dataset, 7
osmr   553f777  ·  3 days ago
0h:54m:16s
Working on COCO dataset, 6
osmr   d137cd2  ·  5 days ago
0h:59m:00s
Working on COCO dataset, 5
osmr   2593c5c  ·  6 days ago
0h:57m:28s
Working on COCO dataset, 4
osmr   bb5532e  ·  Feb 14 2020
0h:55m:58s
Working on COCO dataset, 3
osmr   263934a  ·  Feb 14 2020
0h:54m:59s
Working on COCO dataset, 2
osmr   1fffda8  ·  Feb 13 2020
0h:56m:32s
Working on COCO dataset
osmr   b7be479  ·  Feb 11 2020
0h:56m:28s
Update info about ResNet(A) models
osmr   7509b95  ·  Feb 09 2020
0h:55m:23s
Work on ResNet-A
osmr   4867ad5  ·  Feb 08 2020
0h:53m:04s
Update PIP-package (pytorchcv: 0.0.57), fix #52
osmr   a092c00  ·  Feb 07 2020
0h:57m:51s
Fix TF2 seg model loading bug
osmr   a7bab29  ·  Feb 07 2020
0h:47m:47s
Fix PEP warning
osmr   40dc20f  ·  Feb 07 2020
0h:47m:52s
Update info about TF2 seg models for COCO
osmr   74f8ae0  ·  Feb 07 2020
unknown
Update info about TF2 models for ADE20K
osmr   25a4d50  ·  Feb 07 2020
0h:54m:59s
Update info about PSPNet/TF2 model for Cityscapes
osmr   2089cd9  ·  Feb 07 2020
0h:48m:28s
Update info about TF2 models for VOC2012
osmr   698ad3f  ·  Feb 07 2020
unknown
Update info about ResNet(D) models for TF2
osmr   c5c08cc  ·  Feb 07 2020
0h:56m:08s
Work on seg models for TF2
osmr   8fd3496  ·  Feb 06 2020
0h:54m:22s
Update info about CUB models for TF2
osmr   7707460  ·  Feb 06 2020
0h:54m:51s
Update info about DenseNet models for TF2/CF/SVHN
osmr   2bd40d6  ·  Feb 04 2020
0h:49m:55s
Update info about PyramidNet models for TF2/CF/SVHN
osmr   4466473  ·  Feb 04 2020
unknown
Update info about SE-PreResNet models for TF2/CF/SVHN
osmr   6cf816a  ·  Feb 04 2020
unknown
Update info about SE-ResNet models for TF2/CF/SVHN
osmr   933b94c  ·  Feb 04 2020
0h:58m:02s
Update info about SE-ResNet-50 model
osmr   f280183  ·  Feb 03 2020
0h:52m:28s
Update info about ResNeXt models for TF2/CF/SVHN
osmr   04287f4  ·  Feb 03 2020
0h:18m:49s
Update info about PreResNet models for TF2/CF/SVHN
osmr   9cd2847  ·  Feb 03 2020
0h:28m:03s
Fix a mistake in readme
osmr   ccf5094  ·  Feb 02 2020
0h:55m:35s
Fix links after testing
osmr   ec62412  ·  Feb 01 2020
0h:54m:02s
Update info about ResNet models for TF2/CF/SVHN
osmr   9f6ec71  ·  Feb 01 2020
0h:49m:44s
Update info about SINet model, 2
osmr   5613523  ·  Feb 01 2020
unknown
Refactoring SINet
osmr   f11f809  ·  Feb 01 2020
0h:57m:47s
Update Readme
osmr   9e21176  ·  Jan 30 2020
0h:57m:21s
Working on SINet, 3
osmr   491a274  ·  Jan 30 2020
unknown
Update info about SINet model
osmr   fd4fdec  ·  Jan 30 2020
unknown
Working on SINet, 2
osmr   651da9e  ·  Jan 30 2020
0h:59m:01s
Working on SINet
osmr   f913454  ·  Jan 29 2020
0h:54m:38s
Working on TF2 for SVHN
osmr   6a9718b  ·  Jan 28 2020
0h:56m:57s
Working on TF2 for CF10
osmr   1812673  ·  Jan 27 2020
0h:57m:02s
Update PIP-packages (gluoncv2: 0.0.55, pytorchcv: 0.0.55, chaine…
osmr   f928f6c  ·  Jan 17 2020
0h:48m:10s
Remove unused script
osmr   99370ed  ·  Jan 17 2020
unknown
Update info about HarDNet models
osmr   ea3df12  ·  Jan 17 2020
1h:05m:28s
Update PIP-packages (gluoncv2: 0.0.54, pytorchcv: 0.0.54, chaine…
osmr   ba82c6a  ·  Jan 16 2020
0h:48m:44s
Fix some mistakes in models
osmr   ea65d92  ·  Jan 16 2020
1h:07m:39s
Fix some mistakes in README
osmr   3a44d79  ·  Jan 15 2020
0h:04m:25s
Update info about EffiNet-Edge models
osmr   8b58548  ·  Jan 15 2020
0h:08m:55s
Update info about EffiNet-AP models
osmr   26debd8  ·  Jan 15 2020
0h:05m:20s
Update info about DenseNet-161 models
osmr   39b70a0  ·  Jan 15 2020
0h:08m:55s
Add EffiNet-Edge model
osmr   c90a031  ·  Jan 14 2020
0h:10m:23s
Update info about VoVNet models
osmr   1192791  ·  Jan 13 2020
0h:04m:19s
Add VoVNet model
osmr   3197ca9  ·  Jan 13 2020
0h:08m:42s
Update PIP-packages (tf2cv: 0.0.5)
osmr   2de308d  ·  Jan 12 2020
0h:08m:38s
Fix some PEP8 warnings, 4
osmr   59770a7  ·  Jan 12 2020
0h:03m:07s
Fix some PEP8 warnings, 3
osmr   0a75716  ·  Jan 12 2020
unknown
Fix some PEP8 warnings, 2
osmr   572fe63  ·  Jan 12 2020
0h:04m:49s
Fix some PEP8 warnings
osmr   6a474c6  ·  Jan 12 2020
0h:07m:46s
Update info about SelecSLS models
osmr   83d92dc  ·  Jan 12 2020
0h:08m:15s
Prepare some TF models for publishing, 3
osmr   c03fa67  ·  Jan 11 2020
0h:08m:35s
1) Add testing all models for PT & TF2; 2) Prepare some TF model…
osmr   3c35a25  ·  Jan 10 2020
0h:09m:16s
Experiments with sotabench, 3
osmr   f390668  ·  Jan 01 2020
0h:44m:50s
Experiments with sotabench, 2
osmr   2f36bc6  ·  Jan 01 2020
1h:00m:50s
Experiments with sotabench
osmr   06382bb  ·  Jan 01 2020
0h:07m:23s
Update README
osmr   e9c4ebd  ·  Dec 31 2019
0h:37m:10s
Ready to publish the fourth pack of the TF2-models
osmr   9926b32  ·  Dec 31 2019
unknown
1) Work on TF2-models, 2) Prepare some TF models for publishing,…
osmr   c427bf9  ·  Dec 31 2019
0h:43m:40s
Work on TF2-models
osmr   f32142b  ·  Dec 30 2019
0h:42m:22s
Work on DLA & DPN for TF2
osmr   d0b0560  ·  Dec 29 2019
0h:40m:53s
Work on FBNet for TF2
osmr   9eccd0b  ·  Dec 29 2019
0h:36m:11s
Update PIP-packages (tf2cv: 0.0.4)
osmr   103ba89  ·  Dec 29 2019
unknown
Work on IBN-nets for TF2
osmr   9ec8f93  ·  Dec 29 2019
0h:42m:02s
Update info about DRN models for TF2
osmr   0cc0c7f  ·  Dec 29 2019
0h:43m:16s
Add some nets to TF2, 5
osmr   9d8ff60  ·  Dec 28 2019
0h:40m:19s
Merge
osmr f28bf12    9761d05  ·  Dec 28 2019
0h:36m:53s
Add some nets to TF2, 4
osmr   c114b40  ·  Dec 28 2019
0h:42m:08s
Add some nets to TF2, 3
osmr   75c4fbc  ·  Dec 28 2019
0h:42m:07s
Update info about some TF2 models, 2
osmr   b9ee37c  ·  Dec 27 2019
0h:42m:07s
Add some nets to TF2, 2
osmr   08ad9cc  ·  Dec 26 2019
0h:42m:07s
Add some nets to TF2
osmr   2b976af  ·  Dec 25 2019
0h:42m:38s
Remove unused scripts
osmr   ec626d3  ·  Dec 23 2019
0h:36m:58s
Work on GhostNet
osmr   1f4ac77  ·  Dec 23 2019
0h:45m:01s
Some tests of GhostNet
osmr   e0b8404  ·  Dec 23 2019
0h:44m:40s
Fix some bugs in readmes
osmr   0688051  ·  Dec 14 2019
0h:44m:47s
Update PIP-packages (tf2cv: 0.0.3)
osmr   8959784  ·  Dec 13 2019
0h:37m:17s
Fix some bugs in TF2 models
osmr   5859d9c  ·  Dec 13 2019
0h:46m:11s
Update TF2 readme
osmr   667d01d  ·  Dec 13 2019
0h:37m:24s
Update PIP-packages (tf2cv: 0.0.2)
osmr   144e877  ·  Dec 13 2019
unknown
Fix a bug with TF2 models loading
osmr   564b131  ·  Dec 13 2019
0h:44m:03s
Update info for TF2 models
osmr   47e2956  ·  Dec 12 2019
0h:37m:22s
Update README for TF 2.0, 4
osmr   8be4bfc  ·  Dec 12 2019
0h:45m:29s
Update README for TF 2.0, 3
osmr   397c10a  ·  Dec 11 2019
0h:46m:50s
Update README for TF 2.0, 2
osmr   7ad99af  ·  Dec 10 2019
0h:39m:50s
Update README for TF 2.0
osmr   e8be354  ·  Dec 10 2019
unknown
Update PIP-packages (tf2cv: 0.0.1)
osmr   7c47c17  ·  Dec 10 2019
unknown
Work on TF2, 3
osmr   05b4c50  ·  Dec 10 2019
0h:43m:55s
Work on TF2, 2
osmr   2980953  ·  Dec 09 2019
0h:42m:43s
Work on TF2
osmr   0c30e37  ·  Dec 08 2019
0h:28m:14s
Update PIP-packages (gluoncv2: 0.0.53, pytorchcv: 0.0.53, chaine…
osmr   72e817a  ·  Dec 05 2019
0h:45m:27s
Remove unused script
osmr   a26629a  ·  Dec 04 2019
0h:42m:11s
Update info about HRNet models
osmr   e93203e  ·  Dec 04 2019
1h:06m:06s
1) Working on HRNet, 2) Some experiments with TF2
osmr   93610a1  ·  Dec 03 2019
0h:42m:13s
Experiments with HRNet, 2
osmr   ff7423d  ·  Dec 03 2019
0h:41m:11s
Experiments with HRNet
osmr   71920cd  ·  Dec 01 2019
0h:43m:37s
Update info about VGG-19 model
osmr   8d635f0  ·  Nov 29 2019
0h:45m:31s
Working on TF2, 3
osmr   a2b859e  ·  Nov 26 2019
0h:41m:43s
Remove the previous version of MnasNet architecture
osmr   719fe9c  ·  Nov 24 2019
0h:41m:35s
Update PIP-packages (gluoncv2: 0.0.52, pytorchcv: 0.0.52, chaine…
osmr   df5b285  ·  Nov 24 2019
unknown
Update info about MnasNet models
osmr   1005d0d  ·  Nov 24 2019
0h:44m:38s
Working on MnasNet for TF1
osmr   b856755  (+4 commits )  ·  Nov 23 2019
0h:36m:54s
Update info about SE-ResNeXt-50/101 models
osmr   b6a154f  ·  Nov 20 2019
0h:50m:33s
Working on ResNeXt models
osmr   dbb02e9  ·  Nov 20 2019
0h:30m:34s
Working on TF2, 2
osmr   e73091e  ·  Nov 20 2019
0h:40m:51s
Working on TF2
osmr   b665d52  ·  Nov 18 2019
0h:41m:28s
Update PIP-packages (kerascv: 0.0.38)
osmr   f8e7fbb  ·  Nov 16 2019
0h:40m:29s
Fix a bug in EffNet for KE (fix #40)
osmr   92a0c62  ·  Nov 16 2019
0h:42m:43s
Prep for workin on MnasNet
osmr   fb220bf  ·  Nov 10 2019
0h:41m:15s
Update PIP-packages (gluoncv2: 0.0.51, pytorchcv: 0.0.51, chaine…
osmr   458c23b  ·  Nov 10 2019
0h:42m:28s
Cosmetic refactoring
osmr   abdece4  ·  Nov 10 2019
0h:41m:18s
Update info about SPNASNet model
osmr   2a0143a  ·  Nov 06 2019
0h:46m:53s
Update info about FBNet-Cb model
osmr   51d2d15  ·  Nov 06 2019
unknown
Update info about MixNet-L model
osmr   e40d1f7  ·  Nov 06 2019
0h:12m:35s
Experimenting with Sotabench, 6
osmr   ceb2e0f  ·  Nov 04 2019
1h:29m:18s
Experimenting with Sotabench, 5
osmr   b55ef4e  ·  Nov 04 2019
0h:23m:05s
Experimenting with Sotabench, 4
osmr 5cfd753    abb0a9e  ·  Nov 04 2019
1h:26m:57s
Experimenting with Sotabench, 2
osmr   6baac27  ·  Nov 02 2019
0h:42m:43s
Update info about MixNet-M model
osmr   cc191ac  ·  Nov 02 2019
6h:34m:35s
Experimenting with Sotabench
osmr   a7c8968  ·  Oct 29 2019
0h:52m:21s
0h:15m:25s
unknown
unknown
Update README
osmr   dcf351b  ·  Oct 29 2019
0h:04m:34s
Update info about MixNet-S model
osmr   6cc5e11  ·  Oct 29 2019
unknown
Add sotabench
osmr   d9e9877  ·  Oct 29 2019
unknown
unknown