Deepdrive docs
  • Deepdrive
  • vendor
    • openai
      • README
        • PPO2
        • A2C
    • tensorflow
      • Surgically extracted MobileNetV2 from tensorflow/models @ 84da970ee43c04fbd53a1db3c824ea32cec8936b
        • TensorFlow Research Models
          • slim
            • nets
              • README
          • Running the TensorFlow Official ResNet with TensorRT
  • Deepdrive
  • docs
    • tutorial
      • cloud
        • Cloud setup
      • uepy
        • UnrealEnginePython Tutorial
      • leaderboard
        • Submitting to the Deepdrive leaderboard
    • Miniconda
  • README
Powered by GitBook
On this page
  • MobileNetV2
  • Performance
  • Latency
  • MACs
  • Pretrained models
  • Imagenet Checkpoints
  • Example

Was this helpful?

  1. vendor
  2. tensorflow
  3. Surgically extracted MobileNetV2 from tensorflow/models @ 84da970ee43c04fbd53a1db3c824ea32cec8936b
  4. TensorFlow Research Models
  5. slim
  6. nets

README

PreviousnetsNextRunning the TensorFlow Official ResNet with TensorRT

Last updated 5 years ago

Was this helpful?

MobileNetV2

This folder contains building code for MobileNetV2, based on

Performance

Latency

This is the timing of vs MobileNetV2 using TF-Lite on the large core of Pixel 1 phone.

MACs

MACs, also sometimes known as MADDs - the number of multiply-accumulates needed to compute an inference on a single image is a common metric to measure the efficiency of the model.

Pretrained models

Imagenet Checkpoints

Classification Checkpoint

MACs (M)

Parameters (M)

Top 1 Accuracy

Top 5 Accuracy

Mobile CPU (ms) Pixel 1

582

6.06

75.0

92.5

138.0

509

5.34

74.4

92.1

123.0

300

3.47

71.8

91.0

73.8

221

3.47

70.7

90.1

55.1

154

3.47

68.8

89.0

40.2

99

3.47

65.3

86.9

27.6

56

3.47

60.3

83.2

17.6

209

2.61

69.8

89.6

55.8

153

2.61

68.7

88.9

41.6

107

2.61

66.4

87.3

30.4

69

2.61

63.2

85.3

21.9

39

2.61

58.8

81.6

14.2

97

1.95

65.4

86.4

28.7

71

1.95

63.9

85.4

21.1

50

1.95

61.0

83.2

14.9

32

1.95

57.7

80.8

9.9

18

1.95

51.2

75.8

6.4

59

1.66

60.3

82.9

19.7

43

1.66

58.2

81.2

14.6

30

1.66

55.7

79.1

10.5

20

1.66

50.8

75.0

6.9

11

1.66

45.5

70.4

4.5

Example

Below is the graph comparing V2 vs a few selected networks. The size of each blob represents the number of parameters. Note for there are no published size numbers. We estimate it to be comparable to MobileNetV2 numbers.

See this or open and run the network directly in .

ShuffleNet
ipython notebook
Colaboratory
mobilenet_v2_1.4_224
mobilenet_v2_1.3_224
mobilenet_v2_1.0_224
mobilenet_v2_1.0_192
mobilenet_v2_1.0_160
mobilenet_v2_1.0_128
mobilenet_v2_1.0_96
mobilenet_v2_0.75_224
mobilenet_v2_0.75_192
mobilenet_v2_0.75_160
mobilenet_v2_0.75_128
mobilenet_v2_0.75_96
mobilenet_v2_0.5_224
mobilenet_v2_0.5_192
mobilenet_v2_0.5_160
mobilenet_v2_0.5_128
mobilenet_v2_0.5_96
mobilenet_v2_0.35_224
mobilenet_v2_0.35_192
mobilenet_v2_0.35_160
mobilenet_v2_0.35_128
mobilenet_v2_0.35_96
MobileNetV2: Inverted Residuals and Linear Bottlenecks
MobileNetV1
mnet_v1_vs_v2_pixel1_latency.png
madds_top1_accuracy