Edge Impulse Experts / Acute Lymphoblastic Leukaemia Classifier Public
Target: Arduino Nano 33 BLE Sense (Cortex-M4F 64MHz) Clone this project
Experiments EON Tuner
The EON Tuner helps you find the most optimal architecture for your embedded machine-learning application. Clone this project to use the EON Tuner.

Target

No name set

Arduino Nano 33 BLE Sense (Cortex-M4F 64MHz)

100 ms

256 kB

1024 kB

Filters

Status

DSP type

Model type

View

Data set

Variant

Sort

General

F1-score

Precision

Recall

89%
grayscale-mobilenetv1-653
Show logs
PERFORMANCE
LATENCY
216 ms of 100 ms
Exceeds target by 116 ms
RAM
58 kB of 256 kB
ROM
114 kB of 1024 kB
DSP NN Unused
IMAGE INPUT

96 |
96

IMAGE

Grayscale

ACCURACY (KERAS-TRANSFER-IMAGE)
TRANSFER LEARNING (IMAGES)

0.0005 | 20 | 89%

MobileNetV1 0.1
64 | 0.5

6/23/2023, 3:27:38 PM

83%
grayscale-mobilenetv1-9a7
Show logs
PERFORMANCE
LATENCY
262 ms of 100 ms
Exceeds target by 162 ms
RAM
58 kB of 256 kB
ROM
114 kB of 1024 kB
DSP NN Unused
IMAGE INPUT

96 |
96

IMAGE

Grayscale

ACCURACY (KERAS-TRANSFER-IMAGE)
TRANSFER LEARNING (IMAGES)

0.0005 | 20 | 83%

MobileNetV1 0.1
64 | 0.5 |

6/23/2023, 3:30:11 PM

81%
rgb-mobilenetv1-aa0
Show logs
PERFORMANCE
LATENCY
278 ms of 100 ms
Exceeds target by 178 ms
RAM
64 kB of 256 kB
ROM
108 kB of 1024 kB
DSP NN Unused
IMAGE INPUT

96 |
96

IMAGE

RGB

ACCURACY (KERAS-TRANSFER-IMAGE)
TRANSFER LEARNING (IMAGES)

0.0005 | 20 | 81%

MobileNetV1 0.1
16 | 0.1

6/23/2023, 3:28:26 PM

77%
rgb-mobilenetv1-149
Show logs
PERFORMANCE
LATENCY
288 ms of 100 ms
Exceeds target by 188 ms
RAM
64 kB of 256 kB
ROM
108 kB of 1024 kB
DSP NN Unused
IMAGE INPUT

96 |
96

IMAGE

RGB

ACCURACY (KERAS-TRANSFER-IMAGE)
TRANSFER LEARNING (IMAGES)

0.0005 | 20 | 77%

MobileNetV1 0.1
16 | 0.1 |

6/23/2023, 3:28:17 PM

73%
rgb-mobilenetv1-c7f
Show logs
PERFORMANCE
LATENCY
288 ms of 100 ms
Exceeds target by 188 ms
RAM
64 kB of 256 kB
ROM
108 kB of 1024 kB
DSP NN Unused
IMAGE INPUT

96 |
96

IMAGE

RGB

ACCURACY (KERAS-TRANSFER-IMAGE)
TRANSFER LEARNING (IMAGES)

0.0005 | 20 | 73%

MobileNetV1 0.1
16 | 0.1 |

6/23/2023, 3:32:18 PM

63%
rgb-conv2d-1d7
Show logs
PERFORMANCE
LATENCY
121 ms of 100 ms
Exceeds target by 21 ms
RAM
18 kB of 256 kB
ROM
33 kB of 1024 kB
DSP NN Unused
IMAGE INPUT

32 |
32

IMAGE

RGB

ACCURACY (KERAS)
CLASSIFICATION

0.0005 | 10 | 63%

Type Filters Kernel Rate
conv2d 8 3 -
conv2d 16 3 -
conv2d 32 3 -
dropout - - 0.25

6/23/2023, 3:21:52 PM

60%
grayscale-mobilenetv1-d7c
Show logs
PERFORMANCE
LATENCY
234 ms of 100 ms
Exceeds target by 134 ms
RAM
58 kB of 256 kB
ROM
108 kB of 1024 kB
DSP NN Unused
IMAGE INPUT

96 |
96

IMAGE

Grayscale

ACCURACY (KERAS-TRANSFER-IMAGE)
TRANSFER LEARNING (IMAGES)

0.0005 | 20 | 60%

MobileNetV1 0.1
16 | 0.5 |

6/23/2023, 3:27:55 PM

57%
rgb-conv2d-db1
Show logs
PERFORMANCE
LATENCY
105 ms of 100 ms
Exceeds target by 5 ms
RAM
18 kB of 256 kB
ROM
33 kB of 1024 kB
DSP NN Unused
IMAGE INPUT

32 |
32

IMAGE

RGB

ACCURACY (KERAS)
CLASSIFICATION

0.0005 | 10 | 57%

Type Filters Kernel Rate
conv2d 8 3 -
conv2d 16 3 -
conv2d 32 3 -
dropout - - 0.5

6/23/2023, 3:28:03 PM

55%
grayscale-conv2d-5cd
Show logs
PERFORMANCE
LATENCY
101 ms of 100 ms
Exceeds target by 1 ms
RAM
17 kB of 256 kB
ROM
33 kB of 1024 kB
DSP NN Unused
IMAGE INPUT

32 |
32

IMAGE

Grayscale

ACCURACY (KERAS)
CLASSIFICATION

0.0005 | 10 | 55%

Type Filters Kernel Rate
conv2d 8 3 -
conv2d 16 3 -
conv2d 32 3 -
dropout - - 0.25

6/23/2023, 3:21:46 PM

53%
rgb-conv2d-66b
Show logs
PERFORMANCE
LATENCY
86 ms of 100 ms
RAM
17 kB of 256 kB
ROM
29 kB of 1024 kB
DSP NN Unused
IMAGE INPUT

32 |
32

IMAGE

RGB

ACCURACY (KERAS)
CLASSIFICATION

0.0005 | 10 | 53%

Type Filters Kernel Rate
conv2d 8 3 -
conv2d 16 3 -
dropout - - 0.25

6/23/2023, 3:26:44 PM

Help & documentation Get help on the forum Send feedback Contact sales
Join us
Terms of Service Privacy policy