Edge Impulse Inc. / Keywords Detection - EON Tuner Search Space Public
Target: Cortex-M7 216MHz 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

Cortex-M7 216MHz

100 ms

340 kB

1024 kB

Filters

Status

DSP type

Model type

View

Data set

Variant

Sort

General

F1-score

Precision

Recall

92%
mfe-conv2d-b5c
Show logs
PERFORMANCE
LATENCY
220 ms of 100 ms
Exceeds target by 120 ms
RAM
43 kB of 340 kB
ROM
86 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

MFE

0.032 | 0.016 | 32

ACCURACY (KERAS)
CLASSIFICATION (KERAS)

0.005 | 100 | 92%

Type Filters Kernel Rate
conv2d 8 3 -
conv2d 16 3 -
conv2d 32 3 -
conv2d 64 3 -
dropout - - 0.5

9/27/2022, 6:15:49 PM

90%
mfcc-conv1d-ab2
Show logs
PERFORMANCE
LATENCY
312 ms of 100 ms
Exceeds target by 212 ms
RAM
34 kB of 340 kB
ROM
200 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

MFCC

0.02 | 0.02 | 32

ACCURACY (KERAS)
CLASSIFICATION (KERAS)

0.005 | 100 | 90%

Type Filters Kernel Rate
conv1d 32 3 -
conv1d 64 3 -
conv1d 128 3 -
conv1d 256 3 -
dropout - - 0.25

9/27/2022, 5:16:54 PM

88%
mfcc-conv2d-9cc
Show logs
PERFORMANCE
LATENCY
301 ms of 100 ms
Exceeds target by 201 ms
RAM
36 kB of 340 kB
ROM
69 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

MFCC

0.02 | 0.02 | 40

ACCURACY (KERAS)
CLASSIFICATION (KERAS)

0.005 | 100 | 88%

Type Filters Kernel Rate
Data augmentation
conv2d 16 3 -
conv2d 32 3 -
dropout - - 0.5

9/27/2022, 5:41:49 PM

88%
mfe-conv1d-8d7
Show logs
PERFORMANCE
LATENCY
126 ms of 100 ms
Exceeds target by 26 ms
RAM
35 kB of 340 kB
ROM
102 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

MFE

0.02 | 0.01 | 32

ACCURACY (KERAS)
CLASSIFICATION (KERAS)

0.005 | 100 | 88%

Type Filters Kernel Rate
Data augmentation
conv1d 32 3 -
conv1d 64 3 -
conv1d 128 3 -
dropout - - 0.5

9/27/2022, 5:33:42 PM

88%
mfcc-conv2d-cbb
Show logs
PERFORMANCE
LATENCY
103 ms of 100 ms
Exceeds target by 3 ms
RAM
28 kB of 340 kB
ROM
66 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

MFCC

0.02 | 0.02 | 32

ACCURACY (KERAS)
CLASSIFICATION (KERAS)

0.005 | 100 | 88%

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

9/27/2022, 5:39:23 PM

88%
mfe-conv1d-1a8
Show logs
PERFORMANCE
LATENCY
125 ms of 100 ms
Exceeds target by 25 ms
RAM
35 kB of 340 kB
ROM
102 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

MFE

0.02 | 0.01 | 32

ACCURACY (KERAS)
CLASSIFICATION (KERAS)

0.005 | 100 | 88%

Type Filters Kernel Rate
conv1d 32 3 -
conv1d 64 3 -
conv1d 128 3 -
dropout - - 0.5

9/27/2022, 5:17:14 PM

88%
mfe-conv2d-9b1
Show logs
PERFORMANCE
LATENCY
204 ms of 100 ms
Exceeds target by 104 ms
RAM
50 kB of 340 kB
ROM
76 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

MFE

0.02 | 0.02 | 32

ACCURACY (KERAS)
CLASSIFICATION (KERAS)

0.005 | 100 | 88%

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

9/27/2022, 6:18:02 PM

88%
mfe-mobilenetv1-725
Show logs
PERFORMANCE
LATENCY
154 ms of 100 ms
Exceeds target by 54 ms
RAM
71 kB of 340 kB
ROM
153 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
500 ms |
Enabled

MFE

0.02 | 0.01 | 40

ACCURACY (KERAS-TRANSFER-KWS)
TRANSFER LEARNING (KEYWORD SPOTTING)

0.01 | 30 | 88%

MobileNetV1 0.1
128 | 0.1

9/27/2022, 5:14:55 PM

88%
mfe-conv1d-f2e
Show logs
PERFORMANCE
LATENCY
229 ms of 100 ms
Exceeds target by 129 ms
RAM
31 kB of 340 kB
ROM
201 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

MFE

0.02 | 0.02 | 32

ACCURACY (KERAS)
CLASSIFICATION (KERAS)

0.005 | 100 | 88%

Type Filters Kernel Rate
Data augmentation
conv1d 32 3 -
conv1d 64 3 -
conv1d 128 3 -
conv1d 256 3 -
dropout - - 0.5

9/27/2022, 5:55:34 PM

87%
mfcc-conv1d-a94
Show logs
PERFORMANCE
LATENCY
190 ms of 100 ms
Exceeds target by 90 ms
RAM
34 kB of 340 kB
ROM
200 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

MFCC

0.02 | 0.02 | 32

ACCURACY (KERAS)
CLASSIFICATION (KERAS)

0.005 | 100 | 87%

Type Filters Kernel Rate
Data augmentation
conv1d 32 3 -
conv1d 64 3 -
conv1d 128 3 -
conv1d 256 3 -
dropout - - 0.5

9/27/2022, 5:30:46 PM

87%
mfe-conv1d-f83
Show logs
PERFORMANCE
LATENCY
107 ms of 100 ms
Exceeds target by 7 ms
RAM
33 kB of 340 kB
ROM
64 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

MFE

0.02 | 0.01 | 32

ACCURACY (KERAS)
CLASSIFICATION (KERAS)

0.005 | 100 | 87%

Type Filters Kernel Rate
conv1d 8 3 -
conv1d 16 3 -
conv1d 32 3 -
dropout - - 0.5

9/27/2022, 6:22:33 PM

87%
mfcc-conv2d-587
Show logs
PERFORMANCE
LATENCY
201 ms of 100 ms
Exceeds target by 101 ms
RAM
42 kB of 340 kB
ROM
87 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

MFCC

0.05 | 0.025 | 32

ACCURACY (KERAS)
CLASSIFICATION (KERAS)

0.005 | 100 | 87%

Type Filters Kernel Rate
conv2d 32 3 -
conv2d 64 3 -
dropout - - 0.5

9/27/2022, 6:34:45 PM

87%
mfe-conv1d-0ad
Show logs
PERFORMANCE
LATENCY
127 ms of 100 ms
Exceeds target by 27 ms
RAM
35 kB of 340 kB
ROM
102 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

MFE

0.02 | 0.01 | 32

ACCURACY (KERAS)
CLASSIFICATION (KERAS)

0.005 | 100 | 87%

Type Filters Kernel Rate
Data augmentation
conv1d 32 3 -
conv1d 64 3 -
conv1d 128 3 -
dropout - - 0.25

9/27/2022, 5:21:28 PM

87%
mfcc-conv1d-edd
Show logs
PERFORMANCE
LATENCY
251 ms of 100 ms
Exceeds target by 151 ms
RAM
36 kB of 340 kB
ROM
200 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

MFCC

0.02 | 0.02 | 40

ACCURACY (KERAS)
CLASSIFICATION (KERAS)

0.005 | 100 | 87%

Type Filters Kernel Rate
Data augmentation
conv1d 32 3 -
conv1d 64 3 -
conv1d 128 3 -
conv1d 256 3 -
dropout - - 0.5

9/27/2022, 5:23:14 PM

87%
mfcc-conv2d-d07
Show logs
PERFORMANCE
LATENCY
174 ms of 100 ms
Exceeds target by 74 ms
RAM
35 kB of 340 kB
ROM
85 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

MFCC

0.032 | 0.032 | 32

ACCURACY (KERAS)
CLASSIFICATION (KERAS)

0.005 | 100 | 87%

Type Filters Kernel Rate
conv2d 32 3 -
conv2d 64 3 -
dropout - - 0.25

9/27/2022, 6:25:48 PM

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