Edge Impulse Experts / new-pico-voice Public
Target: Raspberry Pi RP2040 (Cortex-M0+ 133MHz) 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

Raspberry Pi RP2040 (Cortex-M0+ 133MHz)

100 ms

264 kB

2048 kB

Filters

Status

DSP type

Model type

View

Data set

Variant

Sort

General

F1-score

Precision

Recall

87%
mfe-conv1d-8bc
Show logs
PERFORMANCE
LATENCY
434 ms of 100 ms
Exceeds target by 334 ms
RAM
23 kB of 264 kB
ROM
38 kB of 2048 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

MFE

0.05 | 0.025 | 40

ACCURACY (KERAS)
CLASSIFICATION (KERAS)

0.005 | 100 | 87%

Type Filters Kernel Rate
Data augmentation
conv1d 8 3 -
conv1d 16 3 -
conv1d 32 3 -
dropout - - 0.25

7/20/2022, 3:38:03 PM

83%
mfe-conv1d-d6a
Show logs
PERFORMANCE
LATENCY
347 ms of 100 ms
Exceeds target by 247 ms
RAM
22 kB of 264 kB
ROM
73 kB of 2048 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

MFE

0.05 | 0.05 | 40

ACCURACY (KERAS)
CLASSIFICATION (KERAS)

0.005 | 100 | 83%

Type Filters Kernel Rate
Data augmentation
conv1d 16 3 -
conv1d 32 3 -
conv1d 64 3 -
conv1d 128 3 -
dropout - - 0.5

7/20/2022, 4:02:19 PM

81%
mfe-conv1d-c1a
Show logs
PERFORMANCE
LATENCY
309 ms of 100 ms
Exceeds target by 209 ms
RAM
22 kB of 264 kB
ROM
46 kB of 2048 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

MFE

0.032 | 0.032 | 40

ACCURACY (KERAS)
CLASSIFICATION (KERAS)

0.005 | 100 | 81%

Type Filters Kernel Rate
conv1d 16 3 -
conv1d 32 3 -
conv1d 64 3 -
dropout - - 0.25

7/20/2022, 3:56:29 PM

72%
mfe-conv1d-e87
Show logs
PERFORMANCE
LATENCY
427 ms of 100 ms
Exceeds target by 327 ms
RAM
23 kB of 264 kB
ROM
38 kB of 2048 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

MFE

0.05 | 0.025 | 40

ACCURACY (KERAS)
CLASSIFICATION (KERAS)

0.005 | 100 | 72%

Type Filters Kernel Rate
Data augmentation
conv1d 8 3 -
conv1d 16 3 -
conv1d 32 3 -
dropout - - 0.25

7/20/2022, 3:48:32 PM

67%
mfcc-conv1d-570
Show logs
PERFORMANCE
LATENCY
756 ms of 100 ms
Exceeds target by 656 ms
RAM
22 kB of 264 kB
ROM
45 kB of 2048 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 | 67%

Type Filters Kernel Rate
Data augmentation
conv1d 8 3 -
conv1d 16 3 -
conv1d 32 3 -
conv1d 64 3 -
dropout - - 0.5

7/20/2022, 3:58:31 PM

67%
mfe-conv1d-c08
Show logs
PERFORMANCE
LATENCY
416 ms of 100 ms
Exceeds target by 316 ms
RAM
22 kB of 264 kB
ROM
35 kB of 2048 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

MFE

0.05 | 0.025 | 40

ACCURACY (KERAS)
CLASSIFICATION (KERAS)

0.005 | 100 | 67%

Type Filters Kernel Rate
conv1d 8 3 -
conv1d 16 3 -
dropout - - 0.25

7/20/2022, 4:05:47 PM

62%
mfe-conv1d-204
Show logs
PERFORMANCE
LATENCY
393 ms of 100 ms
Exceeds target by 293 ms
RAM
23 kB of 264 kB
ROM
46 kB of 2048 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

MFE

0.032 | 0.032 | 40

ACCURACY (KERAS)
CLASSIFICATION (KERAS)

0.005 | 100 | 62%

Type Filters Kernel Rate
conv1d 8 3 -
conv1d 16 3 -
conv1d 32 3 -
conv1d 64 3 -
dropout - - 0.25

7/20/2022, 4:07:30 PM

59%
mfcc-conv1d-275
Show logs
PERFORMANCE
LATENCY
764 ms of 100 ms
Exceeds target by 664 ms
RAM
22 kB of 264 kB
ROM
45 kB of 2048 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 | 59%

Type Filters Kernel Rate
Data augmentation
conv1d 8 3 -
conv1d 16 3 -
conv1d 32 3 -
conv1d 64 3 -
dropout - - 0.25

7/20/2022, 3:39:38 PM

58%
mfcc-conv1d-f4e
Show logs
PERFORMANCE
LATENCY
815 ms of 100 ms
Exceeds target by 715 ms
RAM
22 kB of 264 kB
ROM
45 kB of 2048 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

MFCC

0.032 | 0.032 | 40

ACCURACY (KERAS)
CLASSIFICATION (KERAS)

0.005 | 100 | 58%

Type Filters Kernel Rate
Data augmentation
conv1d 8 3 -
conv1d 16 3 -
conv1d 32 3 -
conv1d 64 3 -
dropout - - 0.5

7/20/2022, 3:39:01 PM

58%
mfcc-conv1d-883
Show logs
PERFORMANCE
LATENCY
815 ms of 100 ms
Exceeds target by 715 ms
RAM
22 kB of 264 kB
ROM
45 kB of 2048 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

MFCC

0.032 | 0.032 | 40

ACCURACY (KERAS)
CLASSIFICATION (KERAS)

0.005 | 100 | 58%

Type Filters Kernel Rate
Data augmentation
conv1d 8 3 -
conv1d 16 3 -
conv1d 32 3 -
conv1d 64 3 -
dropout - - 0.5

7/20/2022, 3:39:49 PM

58%
mfcc-conv2d-e42
Show logs
PERFORMANCE
LATENCY
428 ms of 100 ms
Exceeds target by 328 ms
RAM
20 kB of 264 kB
ROM
60 kB of 2048 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

MFCC

0.05 | 0.05 | 32

ACCURACY (KERAS)
CLASSIFICATION (KERAS)

0.005 | 100 | 58%

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

7/20/2022, 3:50:24 PM

53%
mfcc-conv2d-a2e
Show logs
PERFORMANCE
LATENCY
440 ms of 100 ms
Exceeds target by 340 ms
RAM
18 kB of 264 kB
ROM
40 kB of 2048 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

MFCC

0.05 | 0.05 | 32

ACCURACY (KERAS)
CLASSIFICATION (KERAS)

0.005 | 100 | 53%

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

7/20/2022, 3:38:52 PM

53%
mfcc-conv1d-bba
Show logs
PERFORMANCE
LATENCY
1012 ms of 100 ms
Exceeds target by 912 ms
RAM
24 kB of 264 kB
ROM
45 kB of 2048 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

MFCC

0.05 | 0.025 | 40

ACCURACY (KERAS)
CLASSIFICATION (KERAS)

0.005 | 100 | 53%

Type Filters Kernel Rate
conv1d 16 3 -
conv1d 32 3 -
conv1d 64 3 -
dropout - - 0.25

7/20/2022, 3:41:47 PM

53%
mfcc-conv1d-feb
Show logs
PERFORMANCE
LATENCY
599 ms of 100 ms
Exceeds target by 499 ms
RAM
21 kB of 264 kB
ROM
45 kB of 2048 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 | 53%

Type Filters Kernel Rate
Data augmentation
conv1d 8 3 -
conv1d 16 3 -
conv1d 32 3 -
conv1d 64 3 -
dropout - - 0.25

7/20/2022, 3:43:56 PM

51%
mfe-conv1d-014
Show logs
PERFORMANCE
LATENCY
416 ms of 100 ms
Exceeds target by 316 ms
RAM
22 kB of 264 kB
ROM
35 kB of 2048 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

MFE

0.05 | 0.025 | 40

ACCURACY (KERAS)
CLASSIFICATION (KERAS)

0.005 | 100 | 51%

Type Filters Kernel Rate
Data augmentation
conv1d 8 3 -
conv1d 16 3 -
dropout - - 0.25

7/20/2022, 3:52:30 PM

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