Model eXplorer#

At MemryX, we do not maintain a curated model zoo which limits customers choice. Instead, we recommend customers choose/train their own model(s) and use MemryX automated tools to generate executable DFP files (.dfp = “dataflow program”).

Our automated tools do not modify original source models (e.g. no pruning, no distillation, etc.) and do not require any retraining (or any dataset) to maintain high accuracy. Instead, our tools compile models as they were trained, resulting in dataflow programs that execute with high accuracy and high utilization of available hardware.

The list of models below was created using a model explorer that automatically aggregates, compiles, and tests models from various public online sources on MemryX hardware. Anyone can use these publicly available models, access links for detailed model source information, and either recreate or simply download the compiled DFP. Unless explicitly stated, none of these models were developed by or are owned by MemryX. This model list will evolve over time depending on customer feedback.

Of course, a customer can certainly choose to modify any given model(s) prior to using MemryX tools. For example, if a customer is willing to tradeoff accuracy for performance, one can choose to prune, quantize, and/or distill model(s) and then create an executable for measuring performance & accuracy.

Benchmark Details

  • SDK Version: 2.0

  • Compilation: Closed-loop method is used to create DFPs. See Closed Loop Compilation tutorial.

  • Host: Intel i7-9700T (1.5 GHz), 16 GB RAM

  • Metrics: FPS and latency reported for Default (14 TFLOPS) and Full (20 TFLOPS) modes. Benchmarks up to 40 TFLOPS will be added in future releases.

  • Latency 1: Frame-to-frame latency (used to compute FPS)

  • Latency 2: Full system latency (including host) from initial input to final output

Understanding Model Icons
Tutorial code

Models featured in step-by-step coding tutorials. See Tutorials.

Example app (video)

Used in a complete example application that processes video streams. Browse MemryX eXamples.

Example app (image)

Used in a complete example application for still-image workflows. Browse MemryX eXamples.

Example app (audio)

Used in a complete example application for audio/voice pipelines. Browse MemryX eXamples.

Needs Neural Compiler extension

Requires additional extensions to run properly. See Neural Compiler and Neural Compiler Extensions tutorial.

MXA optimized

Optimized/retrained by the MemryX team for better MXA performance while preserving accuracy.

Models (Below is a partial list of tested models)

Below is a partial list of AI models that MemryX has downloaded, compiled, and benchmarked from public sources. This is not a model zoo; the models remain unmodified (unless explicitly mentioned), and MemryX customers are not restricted to using these models. Customers are welcome to compile additional models as needed. For guidance, see the Neural Compiler and Tutorials pages.

Classification (ImageNet)
Classification (ImageNet)
Object Detection
Object Detection
Segmentation
Segmentation
Pose Estimation
Pose Estimation
Image Enhancement/Super Resolution
Image Enhancement/Super Resolution
Face/Head
Face/Head
Classification (Other)
Classification (Other)
ADAS/Driver Monitoring
ADAS/Driver Monitoring
Hand/Palm
Hand/Palm
Depth Estimation
Depth Estimation
Point Cloud
Point Cloud
Audio/Speech
Audio/Speech
Emotion Detection
Emotion Detection
Style Transfer/GANs
Style Transfer/GANs
Gesture Recognition
Gesture Recognition
Tracking
Tracking
Wireframe/keypoint Detection
Wireframe/keypoint Detection
Re-identification
Re-identification
Classification (ImageNet)

#

Name

Input Resolution

Params Count

F/W

FPS (14T)

FPS (20T)

Latency 1 (14T)

Latency 1 (20T)

Latency 2 (14T)

Latency 2 (20T)

Source

DFP

1

ConvNext-tiny

224×224×3

27.3 M

ONNX

376

529

2.7 ms

1.9 ms

18.3 ms

13.1 ms

HuggingFace

DFP

2

CS3-DarkNet

256×256×3

8.9 M

ONNX

1678

2019

0.6 ms

0.5 ms

2.5 ms

2.0 ms

Timm

DFP

3

CS3-SE-DarkNet

256×256×3

20.9 M

ONNX

110

156

9.1 ms

6.4 ms

31.5 ms

22.5 ms

Timm

DFP

4

CSP-DarkNet-50

256×256×3

26.3 M

ONNX

467

662

2.1 ms

1.5 ms

9.9 ms

7.2 ms

OpenMMLab

DFP

5

CSP-DarkNet-53

256×256×3

26.3 M

ONNX

468

663

2.1 ms

1.5 ms

9.9 ms

7.2 ms

Timm

DFP

6

CSP-ResNet-50

256×256×3

20.6 M

ONNX

868

1126

1.2 ms

0.9 ms

5.4 ms

4.1 ms

OpenMMLab

DFP

7

DarkNet-53

256×256×3

39.7 M

ONNX

82

117

12.2 ms

8.5 ms

27.5 ms

19.5 ms

Timm

DFP

8

DarkNet-AA53

256×256×3

34.3 M

ONNX

224

317

4.5 ms

3.2 ms

14.2 ms

10.2 ms

Timm

DFP

9

DenseNet121

224×224×3

7.8 M

ONNX

737

1034

1.4 ms

1.0 ms

10.6 ms

7.7 ms

ONNX Zoo

DFP

10

DenseNet121

224×224×3

7.7 M

Keras

711

1008

1.4 ms

1.0 ms

11.1 ms

8.0 ms

Keras.Applications

DFP

11

DenseNet169

224×224×3

13.6 M

Keras

521

737

1.9 ms

1.4 ms

19.0 ms

13.6 ms

Keras.Applications

DFP

12

DenseNet201

224×224×3

19.3 M

Keras

333

472

3.0 ms

2.1 ms

32.1 ms

22.8 ms

Keras.Applications

DFP

13

DLA34

224×224×3

15.0 M

ONNX

603

854

1.7 ms

1.2 ms

4.4 ms

3.2 ms

OpenVINO

DFP

14

EfficientNet-B0

224×224×3

5.0 M

ONNX

1013

1433

1.0 ms

0.7 ms

7.4 ms

5.5 ms

OpenVINO

DFP

15

EfficientNet-B1

240×240×3

7.4 M

ONNX

518

734

1.9 ms

1.4 ms

14.8 ms

10.7 ms

OpenMMLab

DFP

16

EfficientNet-EdgeTpu(L)

300×300×3

10.1 M

TFLite

165

234

6.1 ms

4.3 ms

14.5 ms

10.4 ms

Coral

DFP

17

EfficientNet-EdgeTpu(M)

240×240×3

6.5 M

TFLite

449

636

2.2 ms

1.6 ms

6.7 ms

4.9 ms

Coral

DFP

18

EfficientNet-EdgeTpu(S)

224×224×3

3.9 M

TFLite

487

690

2.1 ms

1.4 ms

4.3 ms

3.2 ms

Coral

DFP

19

EfficientNet-lite0

224×224×3

4.4 M

TFLite

1939

2303

0.5 ms

0.4 ms

2.1 ms

1.6 ms

Kaggle

DFP

20

EfficientNet-lite1

240×240×3

5.1 M

TFLite

1942

2305

0.5 ms

0.4 ms

2.4 ms

1.9 ms

Kaggle

DFP

21

EfficientNet-lite2

260×260×3

5.8 M

TFLite

1538

1781

0.7 ms

0.6 ms

3.4 ms

2.7 ms

Kaggle

DFP

22

EfficientNet-lite3

280×280×3

7.8 M

TFLite

1218

1724

0.8 ms

0.6 ms

4.4 ms

3.2 ms

Kaggle

DFP

23

EfficientNet-lite4

300×300×3

12.4 M

TFLite

750

1062

1.3 ms

0.9 ms

9.0 ms

6.5 ms

Kaggle

DFP

24

EfficientNet-lite4

224×224×3

12.4 M

ONNX

1403

1984

0.7 ms

0.5 ms

6.1 ms

4.5 ms

ONNX Zoo

DFP

25

EfficientNet-v2-B0

224×224×3

6.8 M

ONNX

1100

1558

0.9 ms

0.6 ms

6.6 ms

4.9 ms

OpenMMLab

DFP

26

EfficientNet-v2-B0

224×224×3

6.9 M

Keras

1102

1559

0.9 ms

0.6 ms

6.0 ms

4.4 ms

Keras.Applications

DFP

27

EfficientNet-v2-B1

240×240×3

7.7 M

ONNX

1015

1438

1.0 ms

0.7 ms

10.1 ms

7.3 ms

OpenMMLab

DFP

28

EfficientNet-v2-B1

240×240×3

7.8 M

Keras

1018

1442

1.0 ms

0.7 ms

8.7 ms

6.3 ms

Keras.Applications

DFP

29

EfficientNet-v2-B2

260×260×3

9.6 M

ONNX

761

1077

1.3 ms

0.9 ms

14.7 ms

10.6 ms

OpenMMLab

DFP

30

EfficientNet-v2-B2

260×260×3

9.7 M

Keras

762

1080

1.3 ms

0.9 ms

13.5 ms

9.6 ms

Keras.Applications

DFP

31

EfficientNet-v2-B3

300×300×3

13.8 M

Keras

524

742

1.9 ms

1.3 ms

25.4 ms

18.1 ms

Keras.Applications

DFP

32

FastViT

256×256×3

3.8 M

ONNX

1124

1590

0.9 ms

0.6 ms

3.9 ms

2.9 ms

Timm

DFP

33

FBNet-v3

224×224×3

8.2 M

ONNX

1782

2259

0.6 ms

0.4 ms

7.8 ms

5.7 ms

Timm

DFP

34

FBNetC

224×224×3

5.3 M

ONNX

1941

2311

0.5 ms

0.4 ms

2.1 ms

1.7 ms

Timm

DFP

35

GerNet-large

256×256×3

29.6 M

ONNX

488

691

2.0 ms

1.4 ms

9.4 ms

6.8 ms

Timm

DFP

36

GhostNet

224×224×3

4.9 M

ONNX

1624

2245

0.6 ms

0.4 ms

3.7 ms

2.8 ms

Timm

DFP

37

GhostNet-v2

224×224×3

5.8 M

ONNX

1033

1462

1.0 ms

0.7 ms

6.2 ms

4.6 ms

Timm

DFP

38

GoogleNet

224×224×3

6.7 M

ONNX

518

734

1.9 ms

1.4 ms

3.8 ms

2.9 ms

ONNX Zoo

DFP

39

HardCoRe-NAS

224×224×3

4.9 M

ONNX

1939

2310

0.5 ms

0.4 ms

2.7 ms

2.1 ms

Timm

DFP

40

HBONet0.25

224×224×3

1.8 M

ONNX

1955

2319

0.5 ms

0.4 ms

1.4 ms

1.2 ms

OpenVINO

DFP

41

HBONet1.0

224×224×3

4.3 M

ONNX

1113

1178

0.9 ms

0.8 ms

3.2 ms

2.6 ms

OpenVINO

DFP

42

HGNet-tiny

224×224×3

14.0 M

ONNX

372

527

2.7 ms

1.9 ms

9.8 ms

7.1 ms

Timm

DFP

43

HGNet-v2

224×224×3

37.7 M

ONNX

96

136

10.4 ms

7.4 ms

41.2 ms

29.2 ms

Timm

DFP

44

Inception

224×224×3

6.7 M

ONNX

537

760

1.9 ms

1.3 ms

3.7 ms

2.8 ms

ONNX Zoo

DFP

45

Inception

224×224×3

6.3 M

TFLite

751

1064

1.3 ms

0.9 ms

2.8 ms

2.1 ms

Coral

DFP

46

Inception-ResNet-v2

299×299×3

28.9 M

TensorFlow

168

238

6.0 ms

4.2 ms

36.6 ms

26.0 ms

OpenVINO

DFP

47

Inception-v2

224×224×3

10.7 M

ONNX

751

1063

1.3 ms

0.9 ms

3.6 ms

2.7 ms

ONNX Zoo

DFP

48

Inception-v3

299×299×3

22.7 M

TFLite

317

449

3.2 ms

2.2 ms

10.2 ms

7.4 ms

Kaggle

DFP

49

Inception-v3

346×346×3

22.7 M

TFLite

275

390

3.6 ms

2.6 ms

12.1 ms

8.7 ms

AI Benchmark

DFP

50

Inception-v3

299×299×3

22.7 M

TensorFlow

317

449

3.2 ms

2.2 ms

10.2 ms

7.4 ms

OpenVINO

DFP

51

Inception-v3

299×299×3

22.7 M

ONNX

317

449

3.2 ms

2.2 ms

10.1 ms

7.3 ms

OpenMMLab

DFP

52

Inception-v3

224×224×3

10.7 M

TFLite

750

1062

1.3 ms

0.9 ms

3.7 ms

2.8 ms

Coral

DFP

53

Inception-v3

299×299×3

22.7 M

Keras

317

449

3.2 ms

2.2 ms

10.1 ms

7.3 ms

Keras.Applications

DFP

54

LCNet-0.5

224×224×3

1.8 M

ONNX

1956

2324

0.5 ms

0.4 ms

1.2 ms

1.0 ms

Timm

DFP

55

MobileNet

128×128×3

4.0 M

TFLite

6829

7915

0.1 ms

0.1 ms

1.0 ms

0.8 ms

Kaggle

DFP

56

MobileNet

224×224×3

4.0 M

TFLite

1955

2321

0.5 ms

0.4 ms

1.5 ms

1.2 ms

Kaggle

DFP

57

MobileNet

192×192×3

4.0 M

TFLite

3587

4223

0.3 ms

0.2 ms

1.3 ms

1.1 ms

Kaggle

DFP

58

MobileNet

224×224×3

4.0 M

ONNX

1947

2315

0.5 ms

0.4 ms

1.6 ms

1.3 ms

OpenCV

DFP

59

MobileNet

160×160×3

4.0 M

TFLite

4277

4877

0.2 ms

0.2 ms

1.1 ms

0.9 ms

Kaggle

DFP

60

MobileNet

224×224×3

4.1 M

Keras

1957

2313

0.5 ms

0.4 ms

1.7 ms

1.3 ms

Keras.Applications

DFP

61

MobileNet-EdgeTPU-v2-extra-small

224×224×3

4.2 M

TFLite

1946

2316

0.5 ms

0.4 ms

1.9 ms

1.5 ms

Kaggle

DFP

62

MobileNet-EdgeTPU-v2-m4

224×224×3

8.0 M

ONNX

564

799

1.8 ms

1.3 ms

4.2 ms

3.1 ms

Timm

DFP

63

MobileNet-v1

224×224×3

4.1 M

TensorFlow

1951

2319

0.5 ms

0.4 ms

1.7 ms

1.4 ms

OpenVINO

DFP

64

MobileNet-v2

224×224×3

3.3 M

ONNX

1959

2319

0.5 ms

0.4 ms

1.5 ms

1.2 ms

ONNX Zoo

DFP

65

MobileNet-v2

224×224×3

3.4 M

TFLite

1952

2316

0.5 ms

0.4 ms

1.5 ms

1.3 ms

Coral

DFP

66

MobileNet-v2

224×224×3

3.4 M

Keras

1947

2312

0.5 ms

0.4 ms

1.6 ms

1.3 ms

Keras.Applications

DFP

67

MobileNet-v2-0.5

224×224×3

1.9 M

ONNX

1952

2308

0.5 ms

0.4 ms

1.2 ms

1.0 ms

Timm

DFP

68

MobileNet-v3

512×512×3

5.2 M

TFLite

453

578

2.2 ms

1.7 ms

9.8 ms

7.4 ms

AI Benchmark

DFP

69

MobileNet-v3

224×224×3

3.9 M

TFLite

1941

2312

0.5 ms

0.4 ms

1.9 ms

1.5 ms

Coral

DFP

70

MobileNet-v4

224×224×3

4.0 M

ONNX

1943

2320

0.5 ms

0.4 ms

1.6 ms

1.3 ms

Timm

DFP

71

MobileNet-v4-conv-small

224×224×3

3.6 M

ONNX

1957

2324

0.5 ms

0.4 ms

1.3 ms

1.1 ms

Timm

DFP

72

MobileOne

224×224×3

7.4 M

ONNX

1949

2311

0.5 ms

0.4 ms

2.4 ms

1.9 ms

GitHub/PINTO

DFP

73

Mobileone-s4

224×224×3

14.3 M

ONNX

818

1159

1.2 ms

0.9 ms

11.2 ms

8.1 ms

Timm

DFP

74

NasNet(Mobile)

224×224×3

4.2 M

TFLite

1953

2313

0.5 ms

0.4 ms

2.0 ms

1.5 ms

Kaggle

DFP

75

NasNet(Mobile)

160×160×3

4.2 M

TFLite

4258

4841

0.2 ms

0.2 ms

1.6 ms

1.2 ms

Kaggle

DFP

76

NasNet(Mobile)

192×192×3

4.2 M

TFLite

3577

4214

0.3 ms

0.2 ms

1.7 ms

1.4 ms

Kaggle

DFP

77

NasNet(Mobile)

224×224×3

4.2 M

ONNX

1958

2307

0.5 ms

0.4 ms

1.9 ms

1.5 ms

Timm

DFP

78

NasNet(Mobile)

128×128×3

4.2 M

TFLite

4730

6683

0.2 ms

0.1 ms

1.4 ms

1.1 ms

Kaggle

DFP

79

NasNet(Mobile)-1.3

224×224×3

5.9 M

TFLite

1941

2314

0.5 ms

0.4 ms

2.3 ms

1.8 ms

Kaggle

DFP

80

NasNet(Mobile)-small

224×224×3

1.9 M

ONNX

1949

2304

0.5 ms

0.4 ms

2.0 ms

1.6 ms

Timm

DFP

81

PP-LCNet-v2

224×224×3

6.3 M

TensorFlow

1948

2316

0.5 ms

0.4 ms

2.3 ms

1.8 ms

GitHub/PINTO

DFP

82

PpResNet-50

224×224×3

24.4 M

ONNX

741

1050

1.3 ms

1.0 ms

6.0 ms

4.5 ms

OpenCV

DFP

83

RegNetX002

224×224×3

2.6 M

ONNX

1948

2317

0.5 ms

0.4 ms

2.2 ms

1.7 ms

Timm

DFP

84

RegNetX002

224×224×3

2.6 M

Keras

1941

2310

0.5 ms

0.4 ms

1.9 ms

1.5 ms

Keras.Applications

DFP

85

RegNetX004

224×224×3

5.0 M

Keras

1862

2275

0.5 ms

0.4 ms

3.4 ms

2.5 ms

Keras.Applications

DFP

86

RegNetX006

224×224×3

5.9 M

Keras

1199

1696

0.8 ms

0.6 ms

3.9 ms

2.9 ms

Keras.Applications

DFP

87

RegNetX008

224×224×3

7.0 M

Keras

1003

1420

1.0 ms

0.7 ms

4.8 ms

3.5 ms

Keras.Applications

DFP

88

RegNetX016

224×224×3

8.8 M

Keras

289

410

3.5 ms

2.4 ms

12.3 ms

8.8 ms

Keras.Applications

DFP

89

RegNetY002

224×224×3

3.0 M

ONNX

1919

2281

0.5 ms

0.4 ms

5.0 ms

3.8 ms

Timm

DFP

90

RegNetY002

224×224×3

3.0 M

Keras

1930

2297

0.5 ms

0.4 ms

3.9 ms

2.9 ms

Keras.Applications

DFP

91

RegNetY004

224×224×3

4.2 M

Keras

773

1094

1.3 ms

0.9 ms

10.2 ms

7.4 ms

Keras.Applications

DFP

92

RegNetY006

224×224×3

5.8 M

Keras

1118

1583

0.9 ms

0.6 ms

9.5 ms

6.8 ms

Keras.Applications

DFP

93

RegNetY008

224×224×3

6.0 M

Keras

1286

1772

0.8 ms

0.6 ms

7.9 ms

5.7 ms

Keras.Applications

DFP

94

RegNetY016

224×224×3

10.7 M

Keras

220

311

4.5 ms

3.2 ms

57.3 ms

40.7 ms

Keras.Applications

DFP

95

RepGhostNet-0.5

224×224×3

2.2 M

ONNX

1947

2303

0.5 ms

0.4 ms

2.0 ms

1.7 ms

Timm

DFP

96

RepVGG-A0

224×224×3

7.9 M

ONNX

1839

2315

0.5 ms

0.4 ms

2.1 ms

1.6 ms

OpenMMLab

DFP

97

RepVGG-A1

224×224×3

12.2 M

ONNX

1946

2315

0.5 ms

0.4 ms

2.2 ms

1.7 ms

OpenMMLab

DFP

98

RepVGG-A2

224×224×3

24.3 M

ONNX

742

1050

1.3 ms

1.0 ms

4.9 ms

3.6 ms

OpenMMLab

DFP

99

RepVGG-B0

224×224×3

13.7 M

ONNX

1078

1527

0.9 ms

0.7 ms

3.2 ms

2.4 ms

OpenMMLab

DFP

100

RepViT

224×224×3

5.2 M

ONNX

1920

2283

0.5 ms

0.4 ms

5.0 ms

3.7 ms

Timm

DFP

101

Res2NeXt50

224×224×3

23.5 M

ONNX

333

473

3.0 ms

2.1 ms

14.1 ms

10.1 ms

Timm

DFP

102

ResNet32-TS

256×256×3

17.1 M

ONNX

852

1206

1.2 ms

0.8 ms

3.8 ms

2.8 ms

Timm

DFP

103

ResNet33-TS

256×256×3

18.7 M

ONNX

804

1139

1.2 ms

0.9 ms

3.8 ms

2.9 ms

Timm

DFP

104

ResNet-18

224×224×3

11.1 M

ONNX

1836

2237

0.5 ms

0.4 ms

1.8 ms

1.4 ms

OpenVINO

DFP

105

ResNet-18-v2

224×224×3

11.2 M

ONNX

1836

2240

0.5 ms

0.4 ms

1.9 ms

1.4 ms

ONNX Zoo

DFP

106

ResNet-34

224×224×3

20.8 M

ONNX

898

1271

1.1 ms

0.8 ms

4.6 ms

3.4 ms

OpenMMLab

DFP

107

ResNet-34-v2

224×224×3

20.8 M

ONNX

967

1369

1.0 ms

0.7 ms

4.4 ms

3.3 ms

ONNX Zoo

DFP

108

ResNet-50

224×224×3

24.3 M

TFLite

811

1148

1.2 ms

0.9 ms

4.9 ms

3.7 ms

Coral

DFP

109

ResNet-50

224×224×3

24.4 M

ONNX

825

1168

1.2 ms

0.9 ms

6.2 ms

4.6 ms

ONNX Zoo

DFP

110

ResNet-50

224×224×3

24.4 M

Keras

811

1148

1.2 ms

0.9 ms

5.2 ms

3.8 ms

Keras.Applications

DFP

111

ResNet-50

224×224×3

24.4 M

Keras

811

1148

1.2 ms

0.9 ms

5.2 ms

3.8 ms

Keras.Applications

DFP

112

ResNet-50-v2

224×224×3

24.4 M

ONNX

691

979

1.4 ms

1.0 ms

6.6 ms

4.8 ms

ONNX Zoo

DFP

113

ResNet-50-v2

224×224×3

24.4 M

Keras

820

1161

1.2 ms

0.9 ms

5.7 ms

4.2 ms

Keras.Applications

DFP

114

ResNet-B-26

224×224×3

15.2 M

ONNX

1210

1476

0.8 ms

0.7 ms

2.3 ms

1.9 ms

Timm

DFP

115

ResNet-B-50 (Blur)

224×224×3

24.4 M

ONNX

530

752

1.9 ms

1.3 ms

7.7 ms

5.6 ms

Timm

DFP

116

ResNet-Q-51

256×256×3

34.0 M

ONNX

138

196

7.2 ms

5.1 ms

15.9 ms

11.4 ms

Timm

DFP

117

ResNet-v1-d50

224×224×3

24.4 M

ONNX

720

1019

1.4 ms

1.0 ms

5.5 ms

4.0 ms

OpenMMLab

DFP

118

ResNeXt

256×256×3

9.8 M

ONNX

904

976

1.1 ms

1.0 ms

3.0 ms

2.4 ms

Timm

DFP

119

ReXNet

224×224×3

4.6 M

ONNX

1923

2283

0.5 ms

0.4 ms

4.6 ms

3.4 ms

Timm

DFP

120

ReXNetr-200

224×224×3

15.7 M

ONNX

774

1097

1.3 ms

0.9 ms

11.0 ms

7.9 ms

Timm

DFP

121

SelecSLS60

224×224×3

29.2 M

ONNX

322

457

3.1 ms

2.2 ms

7.5 ms

5.5 ms

Timm

DFP

122

SeNasNet(Mobile)

224×224×3

3.7 M

ONNX

1942

2300

0.5 ms

0.4 ms

3.0 ms

2.3 ms

Timm

DFP

123

SeNasNet(Mobile)-0.75

224×224×3

2.8 M

ONNX

1945

2315

0.5 ms

0.4 ms

2.5 ms

1.9 ms

Timm

DFP

124

SeResNet33-TS

256×256×3

18.8 M

ONNX

304

391

3.3 ms

2.6 ms

17.3 ms

12.9 ms

Timm

DFP

125

ShuffleNet

224×224×3

1.4 M

ONNX

1949

2313

0.5 ms

0.4 ms

2.0 ms

1.6 ms

ONNX Zoo

DFP

126

ShuffleNet-v2

224×224×3

2.2 M

ONNX

1954

2317

0.5 ms

0.4 ms

1.7 ms

1.4 ms

ONNX Zoo

DFP

127

SPNasNet

224×224×3

4.2 M

ONNX

1938

2317

0.5 ms

0.4 ms

2.1 ms

1.6 ms

Timm

DFP

128

SqueezeNet

224×224×3

1.2 M

TFLite

1035

1466

1.0 ms

0.7 ms

1.9 ms

1.5 ms

Kaggle

DFP

129

SqueezeNet

224×224×3

1.2 M

ONNX

1957

2309

0.5 ms

0.4 ms

1.3 ms

1.1 ms

ONNX Zoo

DFP

130

SqueezeNet1.1

224×224×3

1.2 M

ONNX

1949

2322

0.5 ms

0.4 ms

1.3 ms

1.1 ms

ONNX Zoo

DFP

131

TinyNet-A

192×192×3

5.9 M

ONNX

1339

1895

0.7 ms

0.5 ms

7.2 ms

5.3 ms

Timm

DFP

132

VoVNet-v2

224×224×3

6.2 M

ONNX

1118

1235

0.9 ms

0.8 ms

3.8 ms

3.3 ms

Timm

DFP

133

Xception

299×299×3

25.7 M

ONNX

258

365

3.9 ms

2.7 ms

16.0 ms

11.5 ms

Timm

DFP

134

Xception

299×299×3

21.8 M

Keras

300

425

3.3 ms

2.4 ms

13.0 ms

9.4 ms

Keras.Applications

DFP

135

YOLO-v8-large-CLS

224×224×3

35.7 M

TFLite

258

366

3.9 ms

2.7 ms

13.4 ms

9.6 ms

Ultralytics

DFP

136

YOLO-v8-medium-CLS

224×224×3

16.3 M

TFLite

1018

1441

1.0 ms

0.7 ms

4.4 ms

3.3 ms

Ultralytics

DFP

137

YOLO-v8-nano-CLS

224×224×3

2.6 M

TFLite

1944

2322

0.5 ms

0.4 ms

1.4 ms

1.1 ms

Ultralytics

DFP

138

YOLO-v8-small-CLS

224×224×3

6.1 M

TFLite

1944

2312

0.5 ms

0.4 ms

1.8 ms

1.4 ms

Ultralytics

DFP

139

YOLO-v11-large-CLS

224×224×3

13.4 M

ONNX

477

676

2.1 ms

1.5 ms

9.4 ms

6.8 ms

Ultralytics

DFP

140

YOLO-v11-medium-CLS

224×224×3

11.1 M

ONNX

661

936

1.5 ms

1.1 ms

4.4 ms

3.3 ms

Ultralytics

DFP

141

YOLO-v11-nano-CLS

224×224×3

2.7 M

ONNX

1945

2317

0.5 ms

0.4 ms

1.8 ms

1.4 ms

Ultralytics

DFP

142

YOLO-v11-small-CLS

224×224×3

6.4 M

ONNX

1944

2311

0.5 ms

0.4 ms

2.5 ms

2.0 ms

Ultralytics

DFP

143

YOLO-v11-x-CLS

224×224×3

28.2 M

ONNX

229

324

4.4 ms

3.1 ms

19.3 ms

13.8 ms

Ultralytics

DFP
Object Detection

#

Name

Input Resolution

Params Count

F/W

FPS (14T)

FPS (20T)

Latency 1 (14T)

Latency 1 (20T)

Latency 2 (14T)

Latency 2 (20T)

Source

DFP

144

CenterNet(DLA)

512×512×3

17.1 M

ONNX

109

154

9.2 ms

6.5 ms

22.5 ms

16.7 ms

OpenVINO

DFP

145

CenterNet-MobileNet-v2

320×320×3

2.3 M

TensorFlow

838

939

1.2 ms

1.1 ms

4.4 ms

3.7 ms

TF Object Detection Zoo

DFP

146

CenterNet-MobileNet-v2-kpts

320×320×3

2.3 M

ONNX

762

806

1.3 ms

1.2 ms

4.4 ms

3.8 ms

TF Object Detection Zoo

DFP

147

CenterNet-ResNet-fpn

512×512×3

24.2 M

TensorFlow

66

94

15.2 ms

10.6 ms

28.3 ms

20.9 ms

TF Object Detection Zoo

DFP

148

DAMO-YOLO-medium

640×640×3

26.9 M

ONNX

35

50

28.6 ms

20.0 ms

49.3 ms

34.9 ms

DaMoYolo

DFP

149

DAMO-YOLO-Nl

416×416×3

5.4 M

ONNX

312

442

3.2 ms

2.3 ms

10.0 ms

7.3 ms

DaMoYolo

DFP

150

DAMO-YOLO-Ns

416×416×3

1.3 M

ONNX

611

865

1.6 ms

1.2 ms

4.8 ms

3.8 ms

DaMoYolo

DFP

151

DAMO-YOLO-small

640×640×3

15.5 M

ONNX

150

212

6.7 ms

4.7 ms

19.5 ms

14.1 ms

DaMoYolo

DFP

152

DAMO-YOLO-tiny

640×640×3

8.1 M

ONNX

386

386

2.6 ms

2.6 ms

10.4 ms

10.4 ms

DaMoYolo

DFP

153

DbNet-ResNet-18

736×1344×3

11.6 M

ONNX

16

23

62.5 ms

43.5 ms

75.3 ms

53.8 ms

OpenMMLab

DFP

154

DroNet

608×608×3

67.4 K

TFLite

365

445

2.7 ms

2.2 ms

3.7 ms

3.2 ms

GitHub/PINTO

DFP

155

EfficientDet-Lite1

384×384×3

4.2 M

TFLite

216

221

4.6 ms

4.5 ms

18.1 ms

15.2 ms

Coral

DFP

156

License-plate-Detection-LPD-YuNet

240×320×3

1008.7 K

ONNX

725

913

1.4 ms

1.1 ms

2.4 ms

2.1 ms

OpenCV

DFP

157

MediaPipe-object-Detection-3d-camera

224×224×3

2.4 M

TFLite

1940

2312

0.5 ms

0.4 ms

2.0 ms

1.6 ms

MediaPipe

DFP

158

MediaPipe-object-Detection-3d-chair

224×224×3

2.4 M

TFLite

1931

2307

0.5 ms

0.4 ms

2.0 ms

1.6 ms

MediaPipe

DFP

159

MediaPipe-object-Detection-3d-chair-1stag…

640×480×3

1.4 M

TFLite

413

503

2.4 ms

2.0 ms

5.4 ms

4.3 ms

MediaPipe

DFP

160

MediaPipe-object-Detection-3d-cup

224×224×3

2.4 M

TFLite

1939

2305

0.5 ms

0.4 ms

2.0 ms

1.6 ms

MediaPipe

DFP

161

MediaPipe-object-Detection-3d-sneakers

224×224×3

2.4 M

TFLite

1937

2286

0.5 ms

0.4 ms

2.0 ms

1.6 ms

MediaPipe

DFP

162

Mobile-object-labeler

224×224×3

3.5 M

TFLite

1951

2328

0.5 ms

0.4 ms

1.5 ms

1.2 ms

Kaggle

DFP

163

Mobile-object-localizer

192×192×3

1.7 M

TFLite

3588

4201

0.3 ms

0.2 ms

1.3 ms

1.1 ms

GitHub/PINTO

DFP

164

MobileNet-YOLO-v4-syg

416×416×3

10.0 M

TensorFlow

766

957

1.3 ms

1.0 ms

8.2 ms

6.1 ms

OpenVINO

DFP

165

NanoDet

416×416×3

919.8 K

ONNX

787

948

1.3 ms

1.1 ms

4.0 ms

3.4 ms

OpenCV

DFP

166

NanoDet+ (ShuffleNet)-v2-1.5x

416×416×3

2.3 M

ONNX

616

766

1.6 ms

1.3 ms

6.3 ms

5.1 ms

OpenVINO

DFP

167

NanoDetwithShuffleNet-v2-1.5x

416×416×3

2.0 M

ONNX

639

891

1.6 ms

1.1 ms

5.0 ms

4.0 ms

OpenVINO

DFP

168

Person-Detection

512×512×3

1.7 M

TFLite

476

581

2.1 ms

1.7 ms

3.8 ms

3.2 ms

GitHub/PINTO

DFP

169

Person-vehicle-bike-Detection-crossroad-0…

1024×1024×3

1.1 M

TFLite

117

155

8.5 ms

6.5 ms

14.0 ms

10.9 ms

GitHub/PINTO

DFP

170

Person-vehicle-bike-Detection-crossroad-1…

512×512×3

2.8 M

TFLite

476

578

2.1 ms

1.7 ms

4.5 ms

3.6 ms

GitHub/PINTO

DFP

171

PP-YOLOE-Plus

640×640×3

7.6 M

ONNX

73

103

13.7 ms

9.7 ms

31.6 ms

23.2 ms

GitHub/PINTO

DFP

172

RtmDet-small

640×640×3

9.6 M

ONNX

56

79

17.9 ms

12.7 ms

39.4 ms

28.2 ms

OpenMMLab

DFP

173

RtmDet-tiny

640×640×3

5.3 M

ONNX

128

182

7.8 ms

5.5 ms

17.2 ms

12.9 ms

OpenMMLab

DFP

174

RtmDet-tiny-fast

640×640×3

5.3 M

ONNX

126

179

7.9 ms

5.6 ms

17.3 ms

13.0 ms

OpenMMLab

DFP

175

SpaghettiNet-EdgeTPU

320×320×3

3.3 M

TFLite

1187

1420

0.8 ms

0.7 ms

3.5 ms

2.9 ms

GitHub/PINTO

DFP

176

SSD300

300×300×3

32.7 M

ONNX

52

74

19.2 ms

13.5 ms

28.5 ms

20.4 ms

OpenMMLab

DFP

177

SSD512

512×512×3

34.4 M

ONNX

20

29

50.0 ms

34.5 ms

64.5 ms

46.2 ms

OpenMMLab

DFP

178

SSD-FPNMobileNet

640×640×3

29.5 M

TFLite

41

58

24.4 ms

17.2 ms

44.3 ms

33.5 ms

Coral

DFP

179

SSD-MobileNet

300×300×3

6.5 M

TFLite

1199

1443

0.8 ms

0.7 ms

2.1 ms

1.9 ms

Coral

DFP

180

SSD-MobileNet-v2

300×300×3

5.8 M

TFLite

1195

1441

0.8 ms

0.7 ms

2.3 ms

1.9 ms

Coral

DFP

181

SSD-MobileNet-v2 (MNAS-FPN)

320×320×3

2.4 M

TFLite

305

311

3.3 ms

3.2 ms

8.8 ms

8.0 ms

GitHub/PINTO

DFP

182

SSDlite-MobileNet-v2

320×320×3

4.0 M

ONNX

1195

1424

0.8 ms

0.7 ms

2.6 ms

2.1 ms

OpenMMLab

DFP

183

SSDlite-MobileNet-v2

300×300×3

4.3 M

TensorFlow

1195

1430

0.8 ms

0.7 ms

2.5 ms

2.0 ms

GitHub/PINTO

DFP

184

SSDLiteMobileDet

320×320×3

3.9 M

TFLite

1197

1416

0.8 ms

0.7 ms

3.3 ms

2.6 ms

Coral

DFP

185

SSSD-ResNet34

1200×1200×3

19.0 M

ONNX

21

30

47.6 ms

33.3 ms

63.6 ms

46.4 ms

OpenVINO

DFP

186

Text-Detection-db

480×640×3

11.6 M

TensorFlow

59

83

16.9 ms

12.0 ms

22.8 ms

17.2 ms

GitHub/PINTO

DFP

187

Vehicle-license-plate-detection

300×300×3

619.4 K

TFLite

1203

1450

0.8 ms

0.7 ms

1.6 ms

1.4 ms

GitHub/PINTO

DFP

188

Vehicle-license-plate-detection

256×256×3

561.2 K

TensorFlow

1684

2016

0.6 ms

0.5 ms

2.5 ms

2.0 ms

OpenVINO

DFP

189

YOLO-NAS-small

640×640×3

12.3 M

ONNX

106

150

9.4 ms

6.7 ms

20.9 ms

15.5 ms

Ultralytics

DFP

190

YOLO-tiny

416×416×3

15.1 M

TensorFlow

492

697

2.0 ms

1.4 ms

4.1 ms

3.1 ms

GitHub/RedisAI

DFP

191

YOLO-v2-tiny

416×416×3

15.1 M

TFLite

593

840

1.7 ms

1.2 ms

3.4 ms

2.6 ms

OpenVINO

DFP

192

YOLO-v3-lite

256×256×3

6.4 M

ONNX

1666

2001

0.6 ms

0.5 ms

2.9 ms

2.2 ms

GitHub/PINTO

DFP

193

YOLO-v3-MobileNet-v2

320×320×3

3.2 M

ONNX

713

1009

1.4 ms

1.0 ms

4.8 ms

4.0 ms

OpenMMLab

DFP

194

YOLO-v3-MobileNet-v2

416×416×3

3.2 M

ONNX

545

614

1.8 ms

1.6 ms

6.4 ms

5.5 ms

OpenMMLab

DFP

195

YOLO-v4-tiny

416×416×3

5.8 M

TFLite

608

675

1.6 ms

1.5 ms

3.7 ms

3.2 ms

AI Benchmark

DFP

196

YOLO-v5-medium-v6.1-fast

640×640×3

20.2 M

ONNX

106

150

9.4 ms

6.7 ms

20.2 ms

15.5 ms

OpenMMLab

DFP

197

YOLO-v5-medium-v6.1-fastb64-VOC

512×512×3

20.0 M

ONNX

186

256

5.4 ms

3.9 ms

15.5 ms

11.2 ms

OpenMMLab

DFP

198

YOLO-v5-mu

640×640×3

23.9 M

ONNX

96

137

10.4 ms

7.3 ms

26.6 ms

19.0 ms

Ultralytics

DFP

199

YOLO-v5-n6u

1280×1280×3

4.1 M

ONNX

81

96

12.3 ms

10.4 ms

30.6 ms

27.2 ms

Ultralytics

DFP

200

YOLO-v5-nano-p6-v6.2-fast

1280×1280×3

3.1 M

ONNX

65

66

15.4 ms

15.2 ms

38.9 ms

37.0 ms

OpenMMLab

DFP

201

YOLO-v5-nano-v6.1-fast

640×640×3

1.8 M

ONNX

271

271

3.7 ms

3.7 ms

10.0 ms

10.0 ms

OpenMMLab

DFP

202

YOLO-v5-nano-v6.1-fastb64-VOC

512×512×3

1.7 M

ONNX

475

571

2.1 ms

1.8 ms

4.4 ms

3.8 ms

OpenMMLab

DFP

203

YOLO-v5-nu

640×640×3

2.5 M

ONNX

327

388

3.1 ms

2.6 ms

7.8 ms

7.2 ms

Ultralytics

DFP

204

YOLO-v5-s6u

1280×1280×3

14.6 M

ONNX

42

59

23.8 ms

16.9 ms

47.8 ms

37.2 ms

Ultralytics

DFP

205

YOLO-v5-small-p6-v6.2-fast

1280×1280×3

12.0 M

ONNX

46

66

21.7 ms

15.2 ms

50.3 ms

42.5 ms

OpenMMLab

DFP

206

YOLO-v5-small-v6.1-fast

640×640×3

6.9 M

ONNX

269

269

3.7 ms

3.7 ms

11.1 ms

11.1 ms

OpenMMLab

DFP

207

YOLO-v5-small-v6.1-fastb64-VOC

512×512×3

6.7 M

ONNX

474

572

2.1 ms

1.7 ms

5.5 ms

4.5 ms

OpenMMLab

DFP

208

YOLO-v5-su

640×640×3

8.7 M

ONNX

265

376

3.8 ms

2.7 ms

10.8 ms

8.6 ms

Ultralytics

DFP

209

YOLO-v6-medium-fast

640×640×3

32.7 M

ONNX

56

80

17.9 ms

12.5 ms

46.1 ms

32.8 ms

OpenMMLab

DFP

210

YOLO-v6-nano-fast

640×640×3

4.1 M

ONNX

327

392

3.1 ms

2.6 ms

7.2 ms

6.2 ms

OpenMMLab

DFP

211

YOLO-v6-small-fast

640×640×3

16.4 M

ONNX

143

202

7.0 ms

5.0 ms

16.7 ms

12.1 ms

OpenMMLab

DFP

212

YOLO-v6-tiny-fast

640×640×3

9.2 M

ONNX

228

323

4.4 ms

3.1 ms

10.8 ms

8.2 ms

OpenMMLab

DFP

213

YOLO-v7

256×640×3

35.2 M

ONNX

57

81

17.5 ms

12.3 ms

54.2 ms

38.6 ms

GitHub/PINTO

DFP

214

YOLO-v7-13M (MXA-Optimized)

640×640×3

12.4 M

ONNX

85

121

11.8 ms

8.3 ms

29.6 ms

23.6 ms

GitHub/Official YOLOv7

DFP

215

YOLO-v7-22M (MXA-Optimized)

640×640×3

20.4 M

ONNX

59

84

16.9 ms

11.9 ms

41.8 ms

31.7 ms

GitHub/Official YOLOv7

DFP

216

YOLO-v7-27M (MXA-Optimized)

640×640×3

25.5 M

ONNX

48

68

20.8 ms

14.7 ms

51.0 ms

38.1 ms

GitHub/Official YOLOv7

DFP

217

YOLO-v7-large-fast

640×640×3

35.2 M

ONNX

22

31

45.5 ms

32.3 ms

102.0 ms

72.3 ms

OpenMMLab

DFP

218

YOLO-v7-tiny

320×320×3

5.9 M

ONNX

1162

1166

0.9 ms

0.9 ms

3.7 ms

3.2 ms

GitHub/Official YOLOv7

DFP

219

YOLO-v7-tiny

640×640×3

5.9 M

ONNX

269

270

3.7 ms

3.7 ms

10.4 ms

9.8 ms

GitHub/Official YOLOv7

DFP

220

YOLO-v7-tiny

480×640×3

5.9 M

ONNX

380

385

2.6 ms

2.6 ms

8.7 ms

7.8 ms

GitHub/PINTO

DFP

221

YOLO-v7-tiny

416×416×3

5.9 M

ONNX

652

675

1.5 ms

1.5 ms

5.4 ms

4.7 ms

GitHub/Official YOLOv7

DFP

222

YOLO-v8-medium

640×640×3

24.7 M

ONNX

45

64

22.2 ms

15.6 ms

38.3 ms

27.5 ms

Ultralytics

DFP

223

YOLO-v8-nano

640×640×3

3.0 M

ONNX

327

388

3.1 ms

2.6 ms

8.2 ms

7.4 ms

Ultralytics

DFP

224

YOLO-v8-nano-Oriented-Bounding-Boxes

1024×1024×3

2.9 M

ONNX

128

151

7.8 ms

6.6 ms

16.0 ms

14.2 ms

Ultralytics

DFP

225

YOLO-v8-small

640×640×3

10.6 M

ONNX

186

263

5.4 ms

3.8 ms

11.6 ms

9.3 ms

Ultralytics

DFP

226

YOLO-v8-small-Oriented-Bounding-Boxes

1024×1024×3

10.9 M

ONNX

77

107

13.0 ms

9.3 ms

21.1 ms

16.9 ms

Ultralytics

DFP

227

YOLO-v9-medium

640×640×3

19.1 M

ONNX

40

56

25.0 ms

17.9 ms

61.9 ms

44.1 ms

Ultralytics

DFP

228

YOLO-v9-small

640×640×3

6.9 M

ONNX

109

151

9.2 ms

6.6 ms

32.6 ms

23.4 ms

Ultralytics

DFP

229

YOLO-v9-tiny

640×640×3

2.0 M

ONNX

261

369

3.8 ms

2.7 ms

16.6 ms

12.3 ms

Ultralytics

DFP

230

YOLO-v10-medium

320×320×3

14.6 M

ONNX

166

233

6.0 ms

4.3 ms

18.1 ms

13.0 ms

Ultralytics

DFP

231

YOLO-v10-medium

480×480×3

14.6 M

ONNX

43

60

23.3 ms

16.7 ms

38.7 ms

27.6 ms

Ultralytics

DFP

232

YOLO-v10-nano

320×320×3

2.2 M

ONNX

685

954

1.5 ms

1.0 ms

4.8 ms

3.9 ms

Ultralytics

DFP

233

YOLO-v10-nano

480×480×3

2.2 M

ONNX

121

171

8.3 ms

5.8 ms

13.6 ms

10.5 ms

Ultralytics

DFP

234

YOLO-v10-small

480×480×3

6.9 M

ONNX

106

150

9.4 ms

6.7 ms

16.7 ms

12.6 ms

Ultralytics

DFP

235

YOLO-v10-small

320×320×3

6.9 M

ONNX

319

439

3.1 ms

2.3 ms

8.2 ms

6.1 ms

Ultralytics

DFP

236

YOLO-v11-medium

320×320×3

19.2 M

ONNX

200

283

5.0 ms

3.5 ms

20.2 ms

14.4 ms

Ultralytics

DFP

237

YOLO-v11-nano (MXA-Optimized)

640×640×3

3.9 M

ONNX

326

384

3.1 ms

2.6 ms

9.2 ms

7.9 ms

Ultralytics

DFP

238

YOLO-v11-nano (MXA-Optimized)

480×480×3

3.9 M

ONNX

557

660

1.8 ms

1.5 ms

5.9 ms

5.2 ms

Ultralytics

DFP

239

YOLO-v11-nano (MXA-Optimized)

800×800×3

3.9 M

ONNX

212

246

4.7 ms

4.1 ms

13.0 ms

11.5 ms

Ultralytics

DFP

240

YOLO-v11-nano

480×480×3

2.5 M

ONNX

122

173

8.2 ms

5.8 ms

13.8 ms

10.8 ms

Ultralytics

DFP

241

YOLO-v11-nano

320×320×3

2.5 M

ONNX

775

1087

1.3 ms

0.9 ms

4.8 ms

4.0 ms

Ultralytics

DFP

242

YOLO-v11-small (MXA-Optimized)

640×640×3

14.1 M

ONNX

99

140

10.1 ms

7.1 ms

22.9 ms

16.5 ms

Ultralytics

DFP

243

YOLO-v11-small (MXA-Optimized)

480×480×3

14.1 M

ONNX

220

312

4.5 ms

3.2 ms

15.6 ms

11.2 ms

Ultralytics

DFP

244

YOLO-v11-small

480×480×3

9.0 M

ONNX

102

144

9.8 ms

6.9 ms

17.9 ms

13.1 ms

Ultralytics

DFP

245

YOLO-v11-small

320×320×3

9.0 M

ONNX

315

448

3.2 ms

2.2 ms

8.6 ms

6.4 ms

Ultralytics

DFP

246

YOLOX-medium

640×640×3

24.1 M

ONNX

65

92

15.4 ms

10.9 ms

36.3 ms

25.9 ms

GitHub/YOLOX

DFP

247

YOLOX-medium-ti-lite

416×416×3

24.1 M

ONNX

158

224

6.3 ms

4.5 ms

19.5 ms

14.0 ms

GitHub/YOLOX

DFP

248

YOLOX-medium-ti-lite

640×640×3

24.1 M

ONNX

70

100

14.3 ms

10.0 ms

35.5 ms

25.4 ms

GitHub/YOLOX

DFP

249

YOLOX-nano

416×416×3

883.3 K

ONNX

809

836

1.2 ms

1.2 ms

3.6 ms

3.4 ms

GitHub/YOLOX

DFP

250

YOLOX-nano-ti-lite

416×416×3

2.1 M

ONNX

787

951

1.3 ms

1.1 ms

3.6 ms

3.1 ms

GitHub/YOLOX

DFP

251

YOLOX-small

640×640×3

8.5 M

ONNX

262

371

3.8 ms

2.7 ms

10.0 ms

8.0 ms

OpenMMLab

DFP

252

YOLOX-small-ti-lite

416×416×3

8.5 M

ONNX

510

722

2.0 ms

1.4 ms

5.4 ms

4.4 ms

GitHub/YOLOX

DFP

253

YOLOX-small-ti-lite

640×640×3

8.5 M

ONNX

235

321

4.3 ms

3.1 ms

10.0 ms

8.3 ms

GitHub/YOLOX

DFP

254

YOLOX-tiny

416×416×3

4.8 M

ONNX

644

835

1.6 ms

1.2 ms

4.8 ms

4.1 ms

OpenVINO

DFP

255

YOLOX-tiny-ti-lite

416×416×3

4.8 M

ONNX

786

951

1.3 ms

1.1 ms

4.6 ms

3.8 ms

GitHub/YOLOX

DFP
Segmentation

#

Name

Input Resolution

Params Count

F/W

FPS (14T)

FPS (20T)

Latency 1 (14T)

Latency 1 (20T)

Latency 2 (14T)

Latency 2 (20T)

Source

DFP

256

Autoseg-EdgeTPU-small

512×512×3

2.4 M

TFLite

46

66

21.7 ms

15.2 ms

39.9 ms

28.5 ms

Kaggle

DFP

257

BiseNet (ResNet-18)

512×512×3

12.7 M

ONNX

155

220

6.5 ms

4.5 ms

14.7 ms

11.3 ms

OpenMMLab

DFP

258

BiseNet (ResNet-18) - CityScapes

512×512×3

12.7 M

ONNX

144

204

6.9 ms

4.9 ms

15.2 ms

11.2 ms

OpenMMLab

DFP

259

BiseNetv2 (FCN) - CityScapes

512×512×3

3.2 M

ONNX

123

174

8.1 ms

5.7 ms

15.0 ms

11.0 ms

OpenMMLab

DFP

260

Deeplab-EdgeTPU-extra-small

512×512×3

3.1 M

TFLite

410

580

2.4 ms

1.7 ms

5.9 ms

4.7 ms

Kaggle

DFP

261

Deeplab-EdgeTPU-small

512×512×3

4.5 M

TFLite

320

453

3.1 ms

2.2 ms

6.9 ms

5.2 ms

Kaggle

DFP

262

Deeplab-v3

257×257×3

672.2 K

TFLite

1408

1991

0.7 ms

0.5 ms

2.7 ms

2.1 ms

Kaggle

DFP

263

DeepLab-v3 (MobileNet-v2)

513×513×3

672.2 K

TFLite

476

580

2.1 ms

1.7 ms

4.3 ms

3.5 ms

Coral

DFP

264

Deeplab-v3-plus

1024×1024×3

2.1 M

TFLite

27

31

37.0 ms

32.3 ms

49.1 ms

42.8 ms

AI Benchmark

DFP

265

EdgeTPU-DeepLab-slim

513×513×3

2.0 M

TFLite

475

578

2.1 ms

1.7 ms

6.1 ms

4.9 ms

Coral

DFP

266

Edgetpu-segmentation-EdgeTPU

512×512×3

2.2 M

TFLite

46

66

21.7 ms

15.2 ms

36.3 ms

26.0 ms

GitHub/PINTO

DFP

267

Edgetpu-segmentation-EdgeTPU

16×320×16

49.5 K

TFLite

2217

2218

0.5 ms

0.5 ms

1.3 ms

1.3 ms

GitHub/PINTO

DFP

268

ErfNet

208×976×3

2.0 M

ONNX

151

214

6.6 ms

4.7 ms

23.6 ms

17.0 ms

OpenVINO

DFP

269

ERFNet

256×512×3

2.0 M

ONNX

222

224

4.5 ms

4.5 ms

18.2 ms

14.8 ms

GitHub/PINTO

DFP

270

Fast-scnnk-CityScapes

512×512×3

1.3 M

ONNX

476

578

2.1 ms

1.7 ms

4.6 ms

3.8 ms

OpenMMLab

DFP

271

FastSAM-small

640×640×3

11.2 M

ONNX

79

113

12.7 ms

8.8 ms

20.8 ms

15.8 ms

Ultralytics

DFP

272

FPN (ResNet-50) - ADE20K

512×512×3

27.2 M

ONNX

18

26

55.6 ms

38.5 ms

73.0 ms

52.9 ms

OpenMMLab

DFP

273

HRNet

256×192×3

27.2 M

ONNX

115

164

8.7 ms

6.1 ms

45.8 ms

32.6 ms

GitHub/PINTO

DFP

274

Human-segmentation

192×192×3

1.5 M

TFLite

627

866

1.6 ms

1.2 ms

3.3 ms

2.5 ms

GitHub/PINTO

DFP

275

MagicTouch

512×512×4

2.9 M

TFLite

244

345

4.1 ms

2.9 ms

10.7 ms

8.4 ms

GitHub/PINTO

DFP

276

MediaPipe-selfie-segmentation

256×256×3

103.8 K

TFLite

691

934

1.4 ms

1.1 ms

4.1 ms

3.4 ms

MediaPipe

DFP

277

MediaPipe-selfie-segmentation-landscape

144×256×3

103.9 K

TFLite

1414

2000

0.7 ms

0.5 ms

2.7 ms

2.2 ms

MediaPipe

DFP

278

PaNet-ResNet-18-ffm

640×640×3

11.7 M

ONNX

27

38

37.0 ms

26.3 ms

58.3 ms

41.5 ms

OpenMMLab

DFP

279

Selfie-Segmentation

256×256×3

103.9 K

TFLite

766

1071

1.3 ms

0.9 ms

4.6 ms

3.5 ms

GitHub/PINTO

DFP

280

Selfie-segmenter-landscape

144×256×3

103.9 K

TFLite

1412

1998

0.7 ms

0.5 ms

2.7 ms

2.2 ms

GitHub/TorinMB

DFP

281

STDC1-CityScapes

512×512×3

7.9 M

ONNX

159

226

6.3 ms

4.4 ms

12.2 ms

9.2 ms

OpenMMLab

DFP

282

STDC2-CityScapes

512×512×3

11.7 M

ONNX

157

223

6.4 ms

4.5 ms

17.1 ms

12.4 ms

OpenMMLab

DFP

283

U-NetMobileNet-v2

256×256×3

6.2 M

TFLite

50

71

20.0 ms

14.1 ms

23.0 ms

16.8 ms

Coral

DFP

284

U-NetMobileNet-v2

128×128×3

6.2 M

TFLite

202

286

5.0 ms

3.5 ms

6.6 ms

4.9 ms

Coral

DFP

285

UNet

1024×1024×3

1.9 M

TFLite

27

32

37.0 ms

31.2 ms

42.1 ms

35.6 ms

AI Benchmark

DFP

286

UNet

256×256×1

29.6 M

ONNX

31

44

32.3 ms

22.7 ms

35.4 ms

25.3 ms

Zetane Viewer

DFP

287

YOLO-v8-medium-seg

640×640×3

26.0 M

ONNX

27

38

37.0 ms

26.3 ms

60.0 ms

42.6 ms

Ultralytics

DFP

288

YOLO-v8-nano-seg

640×640×3

3.2 M

ONNX

207

212

4.8 ms

4.7 ms

12.2 ms

11.3 ms

Ultralytics

DFP
Pose Estimation

#

Name

Input Resolution

Params Count

F/W

FPS (14T)

FPS (20T)

Latency 1 (14T)

Latency 1 (20T)

Latency 2 (14T)

Latency 2 (20T)

Source

DFP

289

BodyPix (MobileNet)

480×640×3

1.2 M

TFLite

414

495

2.4 ms

2.0 ms

4.4 ms

3.8 ms

Coral

DFP

290

BodyPix (MobileNet)

512×512×3

1.2 M

TFLite

476

573

2.1 ms

1.7 ms

4.0 ms

3.4 ms

Coral

DFP

291

BodyPix (MobileNet)

768×1024×3

1.2 M

TFLite

170

203

5.9 ms

4.9 ms

9.7 ms

8.2 ms

Coral

DFP

292

BodyPix (MobileNet)

576×768×3

1.2 M

TFLite

297

356

3.4 ms

2.8 ms

5.9 ms

5.2 ms

Coral

DFP

293

BodyPix (MobileNet)

720×1280×3

1.2 M

TFLite

146

176

6.8 ms

5.7 ms

11.3 ms

9.7 ms

Coral

DFP

294

BodyPix (MobileNet)

352×480×3

1.2 M

TFLite

806

971

1.2 ms

1.0 ms

3.0 ms

2.5 ms

Coral

DFP

295

BodyPix (ResNet-50)

496×768×3

22.7 M

TFLite

152

215

6.6 ms

4.7 ms

17.8 ms

13.0 ms

Coral

DFP

296

BodyPix (ResNet-50)

624×864×3

22.7 M

TFLite

112

159

8.9 ms

6.3 ms

20.6 ms

15.0 ms

Coral

DFP

297

BodyPix (ResNet-50)

288×416×3

22.7 M

TFLite

247

348

4.0 ms

2.9 ms

12.2 ms

8.9 ms

Coral

DFP

298

BodyPix (ResNet-50)

480×640×3

22.7 M

TFLite

99

139

10.1 ms

7.2 ms

23.5 ms

17.4 ms

Coral

DFP

299

BodyPix (ResNet-50)

672×928×3

22.7 M

TFLite

53

75

18.9 ms

13.3 ms

35.1 ms

25.5 ms

Coral

DFP

300

Handpose-estimation-mediapipe

224×224×3

988.0 K

ONNX

1953

2306

0.5 ms

0.4 ms

1.4 ms

1.1 ms

OpenCV

DFP

301

Handpose-estimation-mediapipe8

224×224×3

904.1 K

ONNX

1476

2089

0.7 ms

0.5 ms

3.0 ms

2.3 ms

OpenCV

DFP

302

HHP-Net

1×5×1, 1×5×1, 1×5×1

91.8 K

TFLite

12355

12376

0.1 ms

0.1 ms

0.2 ms

0.2 ms

GitHub/PINTO

DFP

303

Human-pose-estimation-3d-0001

256×448×3

4.8 M

ONNX

460

652

2.2 ms

1.5 ms

8.9 ms

6.5 ms

OpenVINO

DFP

304

MediaPipe-pose-landk

256×256×3

3.0 M

TFLite

739

877

1.4 ms

1.1 ms

4.3 ms

3.6 ms

MediaPipe

DFP

305

MediaPipe-pose-landk-heavy

256×256×3

13.1 M

TFLite

103

145

9.7 ms

6.9 ms

14.6 ms

10.6 ms

MediaPipe

DFP

306

MediaPipe-pose-landk-lite

256×256×3

1.3 M

TFLite

716

903

1.4 ms

1.1 ms

3.7 ms

3.1 ms

MediaPipe

DFP

307

MoveNet.SinglePose.Lightning

192×192×3

2.2 M

TFLite

2587

2672

0.4 ms

0.4 ms

2.2 ms

1.9 ms

Coral

DFP

308

MoveNet.SinglePose.Thunder

256×256×3

5.9 M

TFLite

1376

1462

0.7 ms

0.7 ms

3.8 ms

3.4 ms

Coral

DFP

309

Pose-estimation-mediapipe

258×258×3

1.3 M

ONNX

567

775

1.8 ms

1.3 ms

4.2 ms

3.3 ms

OpenCV

DFP

310

PoseC3D

48×64×64×17

2.0 M

ONNX

29

41

34.5 ms

24.4 ms

42.2 ms

30.6 ms

GitHub/PINTO

DFP

311

PoseC3D

48×56×56×17

2.9 M

ONNX

33

47

30.3 ms

21.3 ms

36.8 ms

26.5 ms

GitHub/PINTO

DFP

312

PoseNet (MobileNet)

353×481×3

1.2 M

TFLite

804

968

1.2 ms

1.0 ms

2.7 ms

2.3 ms

Coral

DFP

313

PoseNet (MobileNet)

481×641×3

1.2 M

TFLite

414

502

2.4 ms

2.0 ms

4.4 ms

3.7 ms

Coral

DFP

314

PoseNet (MobileNet)

721×1281×3

1.2 M

TFLite

146

176

6.8 ms

5.7 ms

10.8 ms

9.2 ms

Coral

DFP

315

PoseNet (ResNet-50)

288×416×3

22.6 M

TFLite

257

365

3.9 ms

2.7 ms

12.2 ms

8.8 ms

Coral

DFP

316

PoseNet (ResNet-50)

496×768×3

22.6 M

TFLite

152

216

6.6 ms

4.6 ms

16.6 ms

12.2 ms

Coral

DFP

317

PoseNet (ResNet-50)

736×960×3

22.6 M

TFLite

82

117

12.2 ms

8.5 ms

25.0 ms

18.2 ms

Coral

DFP

318

PoseNet (ResNet-50)

624×864×3

22.6 M

TFLite

112

158

8.9 ms

6.3 ms

20.4 ms

14.9 ms

Coral

DFP

319

PoseNet (ResNet-50)

480×640×3

22.6 M

TFLite

116

165

8.6 ms

6.1 ms

20.3 ms

14.8 ms

Coral

DFP

320

PoseNet (ResNet-50)

672×928×3

22.6 M

TFLite

53

75

18.9 ms

13.3 ms

35.4 ms

25.6 ms

Coral

DFP

321

RtmDet-nano-person

320×320×3

962.8 K

ONNX

1197

1442

0.8 ms

0.7 ms

3.1 ms

2.5 ms

OpenMMLab

DFP

322

Simcc-MobileNet-v2-wo-onv

256×192×3

2.2 M

ONNX

1945

2312

0.5 ms

0.4 ms

1.6 ms

1.4 ms

OpenMMLab

DFP

323

YOLO-v8-medium-pose

640×640×3

25.2 M

ONNX

43

61

23.3 ms

16.4 ms

38.8 ms

27.8 ms

Ultralytics

DFP

324

YOLO-v8-nano-pose

640×640×3

3.1 M

ONNX

327

389

3.1 ms

2.6 ms

8.0 ms

7.1 ms

Ultralytics

DFP

325

YOLO-v8-small-pose

640×640×3

11.1 M

ONNX

228

323

4.4 ms

3.1 ms

11.4 ms

9.0 ms

Ultralytics

DFP
Image Enhancement/Super Resolution

#

Name

Input Resolution

Params Count

F/W

FPS (14T)

FPS (20T)

Latency 1 (14T)

Latency 1 (20T)

Latency 2 (14T)

Latency 2 (20T)

Source

DFP

326

AOD-Net

720×1280×3

1.7 K

TFLite

17

24

58.8 ms

41.7 ms

61.5 ms

44.2 ms

GitHub/PINTO

DFP

327

AOD-Net

480×640×3

1.7 K

TFLite

51

73

19.6 ms

13.7 ms

20.9 ms

15.2 ms

GitHub/PINTO

DFP

328

Colorization-v2

256×256×1

30.7 M

ONNX

31

44

32.3 ms

22.7 ms

52.0 ms

37.4 ms

OpenVINO

DFP

329

DPED

384×512×48

414.7 K

TFLite

40

45

25.0 ms

22.2 ms

46.6 ms

44.4 ms

AI Benchmark

DFP

330

ESRGAN

128×128×3

1.2 M

TFLite

61

86

16.4 ms

11.6 ms

24.0 ms

17.2 ms

AI Benchmark

DFP

331

Fast-SRGAN

512×512×3

154.9 K

TFLite

3

5

333.3 ms

200.0 ms

265.7 ms

189.3 ms

GitHub/PINTO

DFP

332

Fast-SRGAN

128×128×3

154.9 K

TFLite

61

87

16.4 ms

11.5 ms

17.5 ms

12.6 ms

GitHub/PINTO

DFP

333

IMDN

480×640×3

873.0 K

TFLite

8

12

125.0 ms

83.3 ms

141.5 ms

106.4 ms

GitHub/PINTO

DFP

334

IMDN

360×640×3

873.0 K

TFLite

11

16

90.9 ms

62.5 ms

108.8 ms

81.7 ms

GitHub/PINTO

DFP

335

IMDN

1024×1024×3

149.1 K

TFLite

39

41

25.6 ms

24.4 ms

29.2 ms

27.8 ms

AI Benchmark

DFP

336

MBLLEN

480×640×3

439.6 K

TFLite

10

15

100.0 ms

66.7 ms

99.4 ms

70.6 ms

GitHub/PINTO

DFP

337

MBLLEN

720×1280×3

439.6 K

TFLite

3

5

333.3 ms

200.0 ms

290.7 ms

206.3 ms

GitHub/PINTO

DFP

338

Noise2Noise

256×256×3

1.2 M

TFLite

60

86

16.7 ms

11.6 ms

21.0 ms

15.1 ms

GitHub/PINTO

DFP

339

PMN

416×416×4

7.4 M

ONNX

43

61

23.3 ms

16.4 ms

26.9 ms

19.3 ms

GitHub/PINTO

DFP

340

Real-Time-Super-Resolution

240×320×3

1.3 M

TFLite

6

9

166.7 ms

111.1 ms

166.5 ms

118.2 ms

GitHub/PINTO

DFP

341

RFDN

96×96×3

423.3 K

ONNX

12

17

83.3 ms

58.8 ms

79.9 ms

56.7 ms

GitHub/PINTO

DFP

342

RFDN

160×160×3

423.3 K

ONNX

22

31

45.5 ms

32.3 ms

77.0 ms

55.0 ms

GitHub/PINTO

DFP

343

SCI

288×800×3

0.2 K

ONNX

426

556

2.3 ms

1.8 ms

3.6 ms

3.0 ms

GitHub/PINTO

DFP

344

SCL-LLE

240×320×3

77.6 K

TFLite

104

147

9.6 ms

6.8 ms

13.2 ms

10.3 ms

GitHub/PINTO

DFP

345

SCL-LLE

180×320×3

77.6 K

TFLite

138

195

7.2 ms

5.1 ms

10.1 ms

7.8 ms

GitHub/PINTO

DFP

346

SG-Low-Light-Image-Enhancement

24×54×3

10.3 K

ONNX

6650

6963

0.2 ms

0.1 ms

0.4 ms

0.4 ms

GitHub/PINTO

DFP

347

SRCNN-di-v2-k

896×896×3

19.6 K

ONNX

7

10

142.9 ms

100.0 ms

138.2 ms

98.4 ms

OpenMMLab

DFP

348

SRGAN

256×256×3

1.4 M

TFLite

7

11

142.9 ms

90.9 ms

135.8 ms

96.5 ms

AI Benchmark

DFP

349

Super-Resolution

224×224×1

58.3 K

ONNX

160

226

6.2 ms

4.4 ms

6.9 ms

5.0 ms

ONNX Zoo

DFP

350

TBEFN

180×320×3

475.0 K

TFLite

195

205

5.1 ms

4.9 ms

6.7 ms

6.2 ms

GitHub/PINTO

DFP

351

TBEFN

240×320×3

475.0 K

TFLite

146

154

6.8 ms

6.5 ms

8.5 ms

7.9 ms

GitHub/PINTO

DFP

352

VSR

540×960×3

18.6 K

TFLite

22

22

45.5 ms

45.5 ms

71.5 ms

67.7 ms

AI Benchmark

DFP

353

XLSR

360×640×3

21.5 K

TFLite

69

98

14.5 ms

10.2 ms

24.7 ms

20.4 ms

AI Benchmark

DFP

354

Y-Net

480×640×3

190.9 K

TFLite

32

39

31.2 ms

25.6 ms

32.7 ms

26.6 ms

GitHub/PINTO

DFP

355

Y-Net

240×320×3

190.9 K

TFLite

130

160

7.7 ms

6.2 ms

8.7 ms

7.2 ms

GitHub/PINTO

DFP

356

Zero-DCE

360×640×3

77.6 K

TFLite

40

42

25.0 ms

23.8 ms

34.1 ms

32.9 ms

GitHub/PINTO

DFP

357

Zero-DCE

240×320×3

77.6 K

TFLite

120

126

8.3 ms

7.9 ms

11.9 ms

11.4 ms

GitHub/PINTO

DFP

358

Zero-DCE-improved

360×512×3

23.0 K

ONNX

86

123

11.6 ms

8.1 ms

19.0 ms

15.6 ms

GitHub/PINTO

DFP
Face/Head

#

Name

Input Resolution

Params Count

F/W

FPS (14T)

FPS (20T)

Latency 1 (14T)

Latency 1 (20T)

Latency 2 (14T)

Latency 2 (20T)

Source

DFP

359

ACR-Loss

224×224×3

2.3 M

TFLite

1946

2319

0.5 ms

0.4 ms

1.5 ms

1.2 ms

GitHub/PINTO

DFP

360

BlazeFace

128×128×3

99.0 K

TensorFlow

6840

7902

0.1 ms

0.1 ms

0.5 ms

0.5 ms

GitHub/PINTO

DFP

361

BlazeFace-short-range

128×128×3

99.1 K

TFLite

6843

7894

0.1 ms

0.1 ms

0.5 ms

0.5 ms

GitHub/TorinMB

DFP

362

Face-Detection-0100

256×256×3

1.7 M

TFLite

1689

2020

0.6 ms

0.5 ms

1.6 ms

1.4 ms

GitHub/PINTO

DFP

363

Face-Detection-adas-0001

384×672×3

1.0 M

TFLite

532

648

1.9 ms

1.5 ms

3.5 ms

3.0 ms

GitHub/PINTO

DFP

364

Face-Detection-YuNet

640×640×3

51.9 K

ONNX

328

398

3.0 ms

2.5 ms

4.7 ms

4.1 ms

OpenCV

DFP

365

Face-landk

160×160×3

611.3 K

ONNX

4272

4906

0.2 ms

0.2 ms

0.7 ms

0.6 ms

GitHub/PINTO

DFP

366

Face-Mask-Detection

300×300×3

2.5 M

TFLite

839

1188

1.2 ms

0.8 ms

2.8 ms

2.3 ms

GitHub/PINTO

DFP

367

Face-recognition-sface

112×112×3

9.2 M

ONNX

2580

3651

0.4 ms

0.3 ms

1.4 ms

1.1 ms

OpenCV

DFP

368

FaceBoxes

1024×1024×3

982.3 K

ONNX

128

156

7.8 ms

6.4 ms

10.5 ms

9.0 ms

OpenVINO

DFP

369

FaceMesh

192×192×3

590.5 K

TFLite

3602

4224

0.3 ms

0.2 ms

0.8 ms

0.7 ms

GitHub/PINTO

DFP

370

Head-Pose-Estimation

320×320×3

798.8 K

ONNX

1198

1441

0.8 ms

0.7 ms

2.4 ms

2.0 ms

GitHub/YinguoBing

DFP

371

MediaPipe-face-Detection-range

192×192×3

502.1 K

TFLite

3584

4180

0.3 ms

0.2 ms

1.5 ms

1.2 ms

MediaPipe

DFP

372

MediaPipe-face-Detection-short-range

128×128×3

99.1 K

TFLite

6841

7891

0.1 ms

0.1 ms

0.5 ms

0.5 ms

MediaPipe

DFP

373

MediaPipe-iris-landk

64×64×3

636.0 K

TFLite

10648

10648

0.1 ms

0.1 ms

0.6 ms

0.6 ms

MediaPipe

DFP

374

RetinaFacewithResNet-50

640×640×3

26.0 M

ONNX

45

63

22.2 ms

15.9 ms

34.4 ms

24.8 ms

OpenVINO

DFP

375

SFace

112×112×3

9.2 M

TFLite

2579

3652

0.4 ms

0.3 ms

1.4 ms

1.1 ms

GitHub/PINTO

DFP

376

SSD-MobileNet-v2 (Face)

320×320×3

5.1 M

TFLite

1198

1438

0.8 ms

0.7 ms

2.6 ms

2.1 ms

Coral

DFP

377

SynergyNet

120×120×3

2.2 M

ONNX

4945

6989

0.2 ms

0.1 ms

1.0 ms

0.8 ms

GitHub/PINTO

DFP

378

UltraLightweightFaceDetectionRFB320

240×320×3

274.5 K

ONNX

1693

2019

0.6 ms

0.5 ms

1.4 ms

1.2 ms

OpenVINO

DFP

379

Version-RFB

240×320×3

274.5 K

ONNX

1692

2015

0.6 ms

0.5 ms

1.4 ms

1.2 ms

ONNX Zoo

DFP

380

WHENet

224×224×3

4.1 M

TFLite

970

1373

1.0 ms

0.7 ms

6.4 ms

4.8 ms

GitHub/PINTO

DFP

381

YOLO-v5-Face

256×320×3

1.6 M

TensorFlow

1640

1989

0.6 ms

0.5 ms

2.8 ms

2.2 ms

GitHub/PINTO

DFP

382

YuNet

120×160×3

81.1 K

TensorFlow

5957

6875

0.2 ms

0.1 ms

0.5 ms

0.5 ms

GitHub/PINTO

DFP

383

YuNet-v2

640×640×3

51.9 K

TFLite

328

398

3.0 ms

2.5 ms

4.7 ms

4.0 ms

GitHub/PINTO

DFP
Classification (Other)

#

Name

Input Resolution

Params Count

F/W

FPS (14T)

FPS (20T)

Latency 1 (14T)

Latency 1 (20T)

Latency 2 (14T)

Latency 2 (20T)

Source

DFP

384

Aiy-vision-classifier-birds

224×224×3

3.3 M

TFLite

1785

2317

0.6 ms

0.4 ms

1.9 ms

1.5 ms

Kaggle

DFP

385

Aiy-vision-classifier-food

192×192×3

5.0 M

TFLite

3587

4217

0.3 ms

0.2 ms

1.3 ms

1.1 ms

Kaggle

DFP

386

Aiy-vision-classifier-insects

224×224×3

3.4 M

TFLite

1785

2313

0.6 ms

0.4 ms

2.0 ms

1.5 ms

Kaggle

DFP

387

Aiy-vision-classifier-plants

224×224×3

4.7 M

TFLite

1785

2320

0.6 ms

0.4 ms

2.0 ms

1.6 ms

Kaggle

DFP

388

Anti-spoof-mn3

128×128×3

2.9 M

TFLite

3882

5488

0.3 ms

0.2 ms

1.7 ms

1.3 ms

GitHub/PINTO

DFP

389

CropNet-classifier-cassava-disease

224×224×3

4.0 M

TFLite

1935

2298

0.5 ms

0.4 ms

3.0 ms

2.3 ms

Kaggle

DFP

390

Gender-googleNet

224×224×3

5.7 M

ONNX

518

734

1.9 ms

1.4 ms

3.8 ms

2.8 ms

ONNX Zoo

DFP

391

Malaria-Detector

125×125×3

6.7 M

Keras

6865

8117

0.1 ms

0.1 ms

0.5 ms

0.4 ms

xmartlabs

DFP

392

NSFW

224×224×3

5.6 M

TFLite

1835

2233

0.5 ms

0.4 ms

2.0 ms

1.6 ms

GitHub/PINTO

DFP

393

Ocr-japanese

512×512×1

23.1 M

TensorFlow

14

20

71.4 ms

50.0 ms

95.1 ms

67.4 ms

GitHub/PINTO

DFP

394

Person-Attributes-recog-crossroad-0230

160×80×3

717.7 K

TFLite

5822

8107

0.2 ms

0.1 ms

0.6 ms

0.5 ms

GitHub/PINTO

DFP

395

Vehicle-Attributes-recog-barrier-0039

72×72×3

611.5 K

TFLite

7130

8794

0.1 ms

0.1 ms

0.6 ms

0.5 ms

GitHub/PINTO

DFP

396

Vehicle-Attributes-recog-barrier-0042

72×72×3

10.7 M

TFLite

5907

8350

0.2 ms

0.1 ms

1.2 ms

1.0 ms

GitHub/PINTO

DFP
ADAS/Driver Monitoring

#

Name

Input Resolution

Params Count

F/W

FPS (14T)

FPS (20T)

Latency 1 (14T)

Latency 1 (20T)

Latency 2 (14T)

Latency 2 (20T)

Source

DFP

397

Driver-action-recognition-adas-0002-encod…

224×224×3

2.7 M

TFLite

1941

2306

0.5 ms

0.4 ms

1.7 ms

1.3 ms

GitHub/PINTO

DFP

398

Gaze-estimation-adas-0002

60×60×3, 60×60×3, 3

1.8 M

TFLite

272

272

3.7 ms

3.7 ms

4.3 ms

4.3 ms

GitHub/PINTO

DFP

399

Head-pose-estimation-adas-0001

60×60×3

1.8 M

TFLite

8387

11657

0.1 ms

0.1 ms

0.7 ms

0.6 ms

GitHub/PINTO

DFP

400

Open-closed-eye-0001

32×32×3

11.0 K

ONNX

19451

19451

0.1 ms

0.1 ms

0.2 ms

0.2 ms

OpenVINO

DFP

401

Pedestrian-and-vehicle-Detector-adas-0001

384×672×3

1.6 M

TFLite

532

643

1.9 ms

1.6 ms

4.0 ms

3.4 ms

GitHub/PINTO

DFP

402

Pedestrian-Detection-adas-0002

384×672×3

1.1 M

TFLite

532

646

1.9 ms

1.5 ms

3.7 ms

3.2 ms

GitHub/PINTO

DFP

403

Road-segmentation-adas-0001

512×896×3

180.0 K

TFLite

145

186

6.9 ms

5.4 ms

10.0 ms

7.7 ms

GitHub/PINTO

DFP

404

Vehicle-Detection-0200

256×256×3

1.7 M

TFLite

1691

2020

0.6 ms

0.5 ms

1.6 ms

1.4 ms

GitHub/PINTO

DFP

405

YOLOp320

320×320×3

7.6 M

ONNX

402

570

2.5 ms

1.8 ms

7.3 ms

5.4 ms

GitHub/YOLOP

DFP

406

YOLOp640

640×640×3

7.6 M

ONNX

134

189

7.5 ms

5.3 ms

19.0 ms

14.1 ms

GitHub/YOLOP

DFP
Hand/Palm

#

Name

Input Resolution

Params Count

F/W

FPS (14T)

FPS (20T)

Latency 1 (14T)

Latency 1 (20T)

Latency 2 (14T)

Latency 2 (20T)

Source

DFP

407

Hand-Detection-and-Tracking

256×256×3

1.3 M

TensorFlow

1034

1126

1.0 ms

0.9 ms

4.3 ms

3.4 ms

GitHub/PINTO

DFP

408

Hand-recrop

256×256×3

26.1 K

TFLite

1688

2023

0.6 ms

0.5 ms

1.0 ms

0.8 ms

GitHub/PINTO

DFP

409

MediaPipe-hand-landk

224×224×3

2.6 M

TFLite

1948

2310

0.5 ms

0.4 ms

1.9 ms

1.5 ms

MediaPipe

DFP

410

MediaPipe-hand-landk-lite

224×224×3

988.0 K

TFLite

1951

2323

0.5 ms

0.4 ms

1.4 ms

1.2 ms

MediaPipe

DFP

411

MediaPipe-hand-recrop

256×256×3

26.4 K

TFLite

1700

2023

0.6 ms

0.5 ms

1.0 ms

0.8 ms

MediaPipe

DFP

412

MediaPipe-palm-Detection

192×192×3

1.1 M

TFLite

907

1282

1.1 ms

0.8 ms

2.6 ms

2.0 ms

MediaPipe

DFP

413

MediaPipe-palm-Detection-lite

192×192×3

937.6 K

TFLite

1259

1736

0.8 ms

0.6 ms

2.2 ms

1.7 ms

MediaPipe

DFP

414

Palm-Detection-mediapipe

192×192×3

937.6 K

ONNX

1147

1552

0.9 ms

0.6 ms

2.3 ms

1.8 ms

OpenCV

DFP
Depth Estimation

#

Name

Input Resolution

Params Count

F/W

FPS (14T)

FPS (20T)

Latency 1 (14T)

Latency 1 (20T)

Latency 2 (14T)

Latency 2 (20T)

Source

DFP

415

Graft-PSMNet

256×120×160

1.2 M

ONNX

96

96

10.4 ms

10.4 ms

17.8 ms

17.8 ms

GitHub/PINTO

DFP

416

Graft-PSMNet

256×80×120

1.2 M

ONNX

193

193

5.2 ms

5.2 ms

9.6 ms

9.6 ms

GitHub/PINTO

DFP

417

HR-Depth

384×1280×3

10.7 M

ONNX

52

52

19.2 ms

19.2 ms

37.3 ms

37.1 ms

GitHub/PINTO

DFP

418

MiDaS

256×256×3

15.8 M

TFLite

216

305

4.6 ms

3.3 ms

14.4 ms

10.4 ms

Kaggle

DFP

419

PyDNet

192×320×3

1.9 M

TFLite

353

501

2.8 ms

2.0 ms

5.0 ms

3.8 ms

GitHub/PINTO

DFP

420

PyDNet2

384×1280×3

699.9 K

TFLite

44

62

22.7 ms

16.1 ms

28.5 ms

21.2 ms

GitHub/PINTO

DFP

421

PyDNet2

384×640×3

699.9 K

TFLite

88

125

11.4 ms

8.0 ms

14.7 ms

11.0 ms

GitHub/PINTO

DFP
Point Cloud

#

Name

Input Resolution

Params Count

F/W

FPS (14T)

FPS (20T)

Latency 1 (14T)

Latency 1 (20T)

Latency 2 (14T)

Latency 2 (20T)

Source

DFP

422

MMDet3d-CenterPoint

800×800×64

4.9 M

ONNX

11

11

90.9 ms

90.9 ms

124.2 ms

124.2 ms

GitHub/Tartisan

DFP

423

MMDet3d-CenterPoint

20×10

0.6 K

ONNX

37082

37740

0.0 ms

0.0 ms

0.2 ms

0.2 ms

GitHub/Tartisan

DFP

424

MMDet3d-PointPillars

468×468×64

4.6 M

ONNX

2

3

500.0 ms

333.3 ms

428.2 ms

315.7 ms

GitHub/Tartisan

DFP

425

MMDet3d-PointPillars

20×10

0.6 K

ONNX

36838

37740

0.0 ms

0.0 ms

0.2 ms

0.2 ms

GitHub/Tartisan

DFP

426

PointPillars (SECFPN) - KITTI 3D

496×432×64

4.6 M

ONNX

10

14

100.0 ms

71.4 ms

118.1 ms

90.1 ms

OpenMMLab

DFP

427

PointPillars (SECFPN-SBN) - NUS 3D

400×400×64

4.7 M

ONNX

13

18

76.9 ms

55.6 ms

108.7 ms

86.4 ms

OpenMMLab

DFP

428

SFA3D

608×608×3

12.1 M

TensorFlow

89

94

11.2 ms

10.6 ms

19.8 ms

17.1 ms

GitHub/PINTO

DFP
Audio/Speech

#

Name

Input Resolution

Params Count

F/W

FPS (14T)

FPS (20T)

Latency 1 (14T)

Latency 1 (20T)

Latency 2 (14T)

Latency 2 (20T)

Source

DFP

429

Audio-classification (YamNet)

96×64×1

3.6 M

TFLite

11587

11974

0.1 ms

0.1 ms

0.8 ms

0.7 ms

Kaggle

DFP

430

Audio-Denoising (UNet)

128×128×1

1.9 M

Keras

1736

2114

0.6 ms

0.5 ms

1.8 ms

1.3 ms

GitHub/vbelz

DFP

431

FRILL

96×64×1

9.6 M

TFLite

5466

7722

0.2 ms

0.1 ms

1.3 ms

1.0 ms

GitHub/PINTO

DFP

432

Light-SERNet

184×40×1

449.9 K

TFLite

3210

3374

0.3 ms

0.3 ms

0.7 ms

0.6 ms

GitHub/PINTO

DFP

433

Speech-enhancement

128×128×1

1.9 M

ONNX

967

1370

1.0 ms

0.7 ms

2.1 ms

1.6 ms

GitHub/PINTO

DFP

434

YAMNet

96×64×1

3.6 M

TFLite

11580

12028

0.1 ms

0.1 ms

0.8 ms

0.7 ms

GitHub/PINTO

DFP
Emotion Detection

#

Name

Input Resolution

Params Count

F/W

FPS (14T)

FPS (20T)

Latency 1 (14T)

Latency 1 (20T)

Latency 2 (14T)

Latency 2 (20T)

Source

DFP

435

Emotion-FERPlus

64×64×1

8.4 M

TFLite

965

1366

1.0 ms

0.7 ms

1.7 ms

1.3 ms

GitHub/PINTO

DFP

436

Emotion-ferplus

64×64×1

8.4 M

ONNX

991

1403

1.0 ms

0.7 ms

1.7 ms

1.3 ms

ONNX Zoo

DFP

437

Facial-expRession-recognition-MobilefaceN…

112×112×3

1.1 M

TFLite

5718

7626

0.2 ms

0.1 ms

0.9 ms

0.8 ms

GitHub/PINTO

DFP

438

Facial-expRession-recognition-MobilefaceN…

112×112×3

1.1 M

ONNX

5719

7623

0.2 ms

0.1 ms

0.9 ms

0.8 ms

OpenCV

DFP

439

Facial-expRession-recognition-MobilefaceN…

112×112×3

1.1 M

ONNX

978

1386

1.0 ms

0.7 ms

5.5 ms

3.9 ms

OpenCV

DFP
Style Transfer/GANs

#

Name

Input Resolution

Params Count

F/W

FPS (14T)

FPS (20T)

Latency 1 (14T)

Latency 1 (20T)

Latency 2 (14T)

Latency 2 (20T)

Source

DFP

440

Arbitrary-stylization

256×256×3

2.2 M

TFLite

1687

2020

0.6 ms

0.5 ms

1.7 ms

1.4 ms

GitHub/PINTO

DFP

441

Arbitrary-stylization-inception-v3

256×256×3

8.6 M

TFLite

566

801

1.8 ms

1.2 ms

4.8 ms

3.6 ms

Kaggle

DFP

442

Facial-cartoonizer

512×512×3

2.0 M

ONNX

61

87

16.4 ms

11.5 ms

19.7 ms

14.3 ms

GitHub/Facial Image Cartoonizaiton

DFP

443

MobileStyleGAN

512

2.0 M

ONNX

36696

37254

0.0 ms

0.0 ms

0.2 ms

0.2 ms

GitHub/PINTO

DFP
Gesture Recognition

#

Name

Input Resolution

Params Count

F/W

FPS (14T)

FPS (20T)

Latency 1 (14T)

Latency 1 (20T)

Latency 2 (14T)

Latency 2 (20T)

Source

DFP

444

American-sign-language

224×224×3

2.7 M

TFLite

1939

2313

0.5 ms

0.4 ms

1.5 ms

1.3 ms

Kaggle

DFP

445

FINNger

96×96×3

3.2 M

TensorFlow

378

536

2.6 ms

1.9 ms

3.8 ms

2.8 ms

GitHub/PINTO

DFP

446

Naruto-handsign-Detection

416×416×3

871.1 K

TFLite

809

845

1.2 ms

1.2 ms

3.3 ms

3.0 ms

GitHub/PINTO

DFP
Tracking

#

Name

Input Resolution

Params Count

F/W

FPS (14T)

FPS (20T)

Latency 1 (14T)

Latency 1 (20T)

Latency 2 (14T)

Latency 2 (20T)

Source

DFP

447

LiteTrack

127×127×3

1.2 M

TFLite

2447

3462

0.4 ms

0.3 ms

2.6 ms

2.0 ms

GitHub/PINTO

DFP

448

OpenCV-DaSiamRPN (Feature Extractor)

360×480×3

4.8 M

ONNX

93

132

10.8 ms

7.6 ms

12.6 ms

9.2 ms

OpenCV

DFP

449

OpenCV-DaSiamRPN (Kernel-R1)

256×24×24

11.3 M

ONNX

110

114

9.1 ms

8.8 ms

13.7 ms

13.2 ms

OpenCV

DFP
Wireframe/keypoint Detection

#

Name

Input Resolution

Params Count

F/W

FPS (14T)

FPS (20T)

Latency 1 (14T)

Latency 1 (20T)

Latency 2 (14T)

Latency 2 (20T)

Source

DFP

450

M-LSD

320×320×4

599.8 K

TFLite

804

1094

1.2 ms

0.9 ms

3.0 ms

2.4 ms

GitHub/PINTO

DFP

451

M-LSD

512×512×4

1.5 M

TFLite

31

44

32.3 ms

22.7 ms

37.4 ms

27.4 ms

GitHub/PINTO

DFP
Re-identification

#

Name

Input Resolution

Params Count

F/W

FPS (14T)

FPS (20T)

Latency 1 (14T)

Latency 1 (20T)

Latency 2 (14T)

Latency 2 (20T)

Source

DFP

452

Person-ReID-YouTube

256×128×3

25.5 M

ONNX

735

1041

1.4 ms

1.0 ms

4.1 ms

3.0 ms

OpenCV

DFP
Third-Party Licenses

Each of these models is shared under the original creator’s license. Please check the license at the source page.