Model zoo performances

This page lets you discover all of Akida model zoo machine learning models with their respective performances.

Note

The download links provided point towards standard Tensorflow Keras models that must be converted to Akida model using cnn2snn.convert.

image_icon_ref Image domain

Classification

Architecture

Resolution

Dataset

Quantization

Top-1 accuracy

Example

#Params

Size (KB)

NPs

Download

AkidaNet 0.25

160

ImageNet

8/4/4

42.58%

an_ex

480K

392.3

23

an_160_25_dl

AkidaNet 0.5

160

ImageNet

8/4/4

57.80%

an_ex

1.4M

1099.4

30

an_160_50_dl

AkidaNet

160

ImageNet

8/4/4

66.94%

an_ex

4.4M

4090.2

81

an_160_dl

AkidaNet 0.25

224

ImageNet

8/4/4

46.71%

an_ex

480K

398.1

25

an_224_25_dl

AkidaNet 0.5

224

ImageNet

8/4/4

61.30%

an_ex

1.4M

1214.4

38

an_224_50_dl

AkidaNet

224

ImageNet

8/4/4

69.65%

an_ex

4.4M

6322.6

129

an_224_dl

AkidaNet 0.5 edge

160

ImageNet

8/4/4

51.66%

ane_ex

4.0M

2017.1

38

ane_160_dl

AkidaNet 0.5 edge

224

ImageNet

8/4/4

54.03%

ane_ex

4.0M

2130.1

46

ane_224_dl

AkidaNet 0.5

160

Cats vs dogs

8/4/4

96.60%

868K

698.4

24

an_cvd_dl

AkidaNet 0.25

224

Imagenette

8/4/4

91.54%

227K

203.9

22

an_ite_25_dl

AkidaNet 0.5

224

Imagenette

8/4/4

95.67%

873K

815.5

32

an_ite_50_dl

AkidaNet

224

Imagenette

8/4/4

97.58%

3.4M

5544.2

116

an_ite_dl

AkidaNet 0.5

224

SIIM-ISIC Melanoma Classification

8/4/4

98.31% - AUROC 0.7969

868K

811.4

32

an_mel_del

AkidaNet 0.5

224

ODIR-5K Ocular disease recognition

8/4/4

92.42% - AUROC 0.9847

870K

811.4

32

an_odir_dl

AkidaNet 0.5

224

Retinal OCT ocular disease recognition

8/4/4

81.10% - AUROC 0.9662

870K

811.4

32

an_oct_dl

AkidaNet 0.5

224

PlantVillage

8/4/4

97.92%

an_pv_ex

1.1M

1018.8

33

an_pv_dl

AkidaNet 0.5

224

CIFAR10

8/4/4

92.89%

896K

829.3

33

an_c10_dl

AkidaNet 0.25

96

Visual Wake Words

8/4/4

82.75%

288K

227.7

17

vww_dl

MobileNetV1 0.25

160

ImageNet

8/4/4

40.86%

467K

365.4

23

mb_160_25_dl

MobileNetV1 0.5

160

ImageNet

8/4/4

55.94%

1.3M

1017.1

30

mb_160_50_dl

MobileNetV1

160

ImageNet

8/4/4

66.40%

4.2M

3554.5

78

mb_160_dl

MobileNetV1 0.25

224

ImageNet

8/4/4

45.12%

467K

366.9

25

mb_224_25_dl

MobileNetV1 0.5

224

ImageNet

8/4/4

59.76%

1.3M

1075.4

38

mb_224_50_dl

MobileNetV1

224

ImageNet

8/4/4

69.53%

4.2M

5251.8

123

mb_224_dl

MobileNetV1 0.5 edge

160

ImageNet

8/4/4

49.69%

3.9M

1935.1

38

mbe_160_dl

MobileNetV1 0.5 edge

224

ImageNet

8/4/4

51.83%

3.9M

1993.4

46

mbe_224_dl

VGG11

224

ImageNet

8/4/4

52.22%

47.1M

34825.2

21

vgg11_dl

GXNOR

28

MNIST

2/2/1

99.20%

gx_ex

1.6M

412.6

3

gx_dl

Object detection

Architecture

Resolution

Dataset

Quantization

mAP

Example

#Params

Size (KB)

NPs

Download

YOLOv2

224

PASCAL-VOC 2007 - person and car classes

8/4/4

38.85%

yl_voc_ex

3.6M

3061.0

71

yl_voc_dl

YOLOv2

224

WIDER FACE

8/4/4

73.81%

3.5M

3052.7

71

yl_wf_dl

Regression

Architecture

Resolution

Dataset

Quantization

MAE

Example

#Params

Size (KB)

NPs

Download

VGG-like

32

UTKFace (age estimation)

8/2/2

6.1791

reg_ex

458K

139.8

6

reg_dl

Face recognition

Architecture

Resolution

Dataset

Quantization

Accuracy

#Params

Size (KB)

NPs

Download

AkidaNet 0.5

112x96

CASIA Webface face identification

8/4/4

70.18%

2.3M

1929.8

21

fid_dl

AkidaNet 0.5 edge

112x96

CASIA Webface face identification

8/4/4

71.13%

23.6M

6979.6

35

fide_dl

AkidaNet 0.5

112x96

LFW face verification

8/4/4

97.25%

933K

691.2

20

fver_dl

audio_icon_ref Audio domain

Keyword spotting

Architecture

Dataset

Quantization

Top-1 accuracy

Example

#Params

Size (KB)

NPs

Download

DS-CNN

Google speech command

8/4/4

91.34%

kws_ex

22.7K

22.8

5

kws_dl

time_icon_ref Time domain

Fault detection

Architecture

Dataset

Quantization

Accuracy

#Params

Size (KB)

NPs

Download

Convtiny

CWRU Electric Motor Ball Bearing Fault Diagnosis

8/2/4

99.3%

59K

25.3

3

cwru_dl

Classification

Architecture

Resolution

Dataset

Quantization

Accuracy

#Params

Size (KB)

NPs

Download

AkidaNet 0.5

224

Physionet2017 ECG classification

8/4/4

73.50% - AUROC 0.7940

1.1M

1008.4

36

ecg_dl

pointcloud_icon_ref Point cloud

Classification

Architecture

Dataset

Quantization

Accuracy

Input scaling

#Params

Size (KB)

NPs

Download

PointNet++

ModelNet40 3D Point Cloud

8/4/4

84.76%

(127, 127)

602K

528.5

17

p++_dl