Holger Navarro / Advanced_gesture_typing_solution_Build2gether_2.0 Public
Target: Raspberry Pi RP2040 (Cortex-M0+ 133MHz) Clone this project
Experiments EON Tuner
The EON Tuner helps you quickly run hyper-parameter sweeps that explore different pre-processing + model architectures optimized for your defined objectives. Clone this project to use the EON Tuner.

Target

V2

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

64%
spectr-dense-ad7
PERFORMANCE
LATENCY
151 ms of 100 ms
Exceeds target by 51 ms
RAM
5 kB of 264 kB
ROM
16 kB of 2048 kB
DSP NN Unused
TIME-SERIES INPUT

4000 ms |
4000 ms |
Enabled

SPECTRAL-ANALYSIS

16

ACCURACY (KERAS)
CLASSIFICATION

0.0005 | 30 | 64%

Type Filters Kernel Rate
dense 40 - -
dense 20 - -
dropout - - 0.25

8/26/2024, 11:08:22 PM

53%
spectr-dense-b7f
PERFORMANCE
LATENCY
151 ms of 100 ms
Exceeds target by 51 ms
RAM
5 kB of 264 kB
ROM
16 kB of 2048 kB
DSP NN Unused
TIME-SERIES INPUT

4000 ms |
4000 ms |
Enabled

SPECTRAL-ANALYSIS

16

ACCURACY (KERAS)
CLASSIFICATION

0.0005 | 30 | 53%

Type Filters Kernel Rate
dense 40 - -
dense 20 - -
dropout - - 0.5

8/26/2024, 11:03:29 PM

47%
spectr-dense-4df
PERFORMANCE
LATENCY
43 ms of 100 ms
RAM
11 kB of 264 kB
ROM
18 kB of 2048 kB
DSP NN Unused
TIME-SERIES INPUT

4000 ms |
4000 ms |
Enabled

SPECTRAL-ANALYSIS

16

ACCURACY (KERAS)
CLASSIFICATION

0.0005 | 30 | 47%

Type Filters Kernel Rate
dense 40 - -
dense 20 - -
dropout - - 0.25

8/26/2024, 11:03:31 PM

46%
spectr-dense-60f
PERFORMANCE
LATENCY
43 ms of 100 ms
RAM
11 kB of 264 kB
ROM
18 kB of 2048 kB
DSP NN Unused
TIME-SERIES INPUT

4000 ms |
4000 ms |
Enabled

SPECTRAL-ANALYSIS

16

ACCURACY (KERAS)
CLASSIFICATION

0.0005 | 30 | 46%

Type Filters Kernel Rate
dense 40 - -
dense 20 - -
dropout - - 0.25

8/26/2024, 11:00:33 PM

40%
spectr-dense-f77
PERFORMANCE
LATENCY
43 ms of 100 ms
RAM
11 kB of 264 kB
ROM
18 kB of 2048 kB
DSP NN Unused
TIME-SERIES INPUT

4000 ms |
4000 ms |
Enabled

SPECTRAL-ANALYSIS

16

ACCURACY (KERAS)
CLASSIFICATION

0.0005 | 30 | 40%

Type Filters Kernel Rate
dense 40 - -
dense 20 - -
dense 10 - -
dropout - - 0.25

8/26/2024, 11:05:26 PM

38%
spectr-dense-1ef
PERFORMANCE
LATENCY
34 ms of 100 ms
RAM
11 kB of 264 kB
ROM
17 kB of 2048 kB
DSP NN Unused
TIME-SERIES INPUT

4000 ms |
4000 ms |
Enabled

SPECTRAL-ANALYSIS

16

ACCURACY (KERAS)
CLASSIFICATION

0.0005 | 30 | 38%

Type Filters Kernel Rate
dense 40 - -
dense 20 - -
dense 10 - -
dropout - - 0.25

8/26/2024, 11:00:50 PM

36%
spectr-dense-652
PERFORMANCE
LATENCY
43 ms of 100 ms
RAM
5 kB of 264 kB
ROM
17 kB of 2048 kB
DSP NN Unused
TIME-SERIES INPUT

4000 ms |
4000 ms |
Enabled

SPECTRAL-ANALYSIS

64

ACCURACY (KERAS)
CLASSIFICATION

0.0005 | 30 | 36%

Type Filters Kernel Rate
dense 40 - -
dense 20 - -
dropout - - 0.25

8/26/2024, 11:05:52 PM

34%
spectr-dense-a41
PERFORMANCE
LATENCY
43 ms of 100 ms
RAM
11 kB of 264 kB
ROM
16 kB of 2048 kB
DSP NN Unused
TIME-SERIES INPUT

4000 ms |
4000 ms |
Enabled

SPECTRAL-ANALYSIS

16

ACCURACY (KERAS)
CLASSIFICATION

0.0005 | 30 | 34%

Type Filters Kernel Rate
dense 20 - -
dense 10 - -
dropout - - 0.25

8/26/2024, 11:06:12 PM

33%
spectr-dense-e04
PERFORMANCE
LATENCY
34 ms of 100 ms
RAM
11 kB of 264 kB
ROM
17 kB of 2048 kB
DSP NN Unused
TIME-SERIES INPUT

4000 ms |
4000 ms |
Enabled

SPECTRAL-ANALYSIS

16

ACCURACY (KERAS)
CLASSIFICATION

0.0005 | 30 | 33%

Type Filters Kernel Rate
dense 40 - -
dense 20 - -
dropout - - 0.5

8/26/2024, 11:03:09 PM

33%
spectr-dense-741
PERFORMANCE
LATENCY
43 ms of 100 ms
RAM
11 kB of 264 kB
ROM
18 kB of 2048 kB
DSP NN Unused
TIME-SERIES INPUT

4000 ms |
4000 ms |
Enabled

SPECTRAL-ANALYSIS

16

ACCURACY (KERAS)
CLASSIFICATION

0.0005 | 30 | 33%

Type Filters Kernel Rate
dense 40 - -
dense 20 - -
dropout - - 0.5

8/26/2024, 11:01:04 PM

32%
spectr-dense-e94
PERFORMANCE
LATENCY
151 ms of 100 ms
Exceeds target by 51 ms
RAM
5 kB of 264 kB
ROM
15 kB of 2048 kB
DSP NN Unused
TIME-SERIES INPUT

4000 ms |
4000 ms |
Enabled

SPECTRAL-ANALYSIS

16

ACCURACY (KERAS)
CLASSIFICATION

0.0005 | 30 | 32%

Type Filters Kernel Rate
dense 20 - -
dense 10 - -
dropout - - 0.5

8/26/2024, 11:05:50 PM

29%
spectr-dense-11f
PERFORMANCE
LATENCY
151 ms of 100 ms
Exceeds target by 51 ms
RAM
5 kB of 264 kB
ROM
17 kB of 2048 kB
DSP NN Unused
TIME-SERIES INPUT

4000 ms |
4000 ms |
Enabled

SPECTRAL-ANALYSIS

16

ACCURACY (KERAS)
CLASSIFICATION

0.0005 | 30 | 29%

Type Filters Kernel Rate
dense 40 - -
dense 20 - -
dense 10 - -
dropout - - 0.5

8/26/2024, 11:00:56 PM

29%
spectr-dense-c4c
PERFORMANCE
LATENCY
43 ms of 100 ms
RAM
5 kB of 264 kB
ROM
17 kB of 2048 kB
DSP NN Unused
TIME-SERIES INPUT

4000 ms |
4000 ms |
Enabled

SPECTRAL-ANALYSIS

64

ACCURACY (KERAS)
CLASSIFICATION

0.0005 | 30 | 29%

Type Filters Kernel Rate
dense 40 - -
dense 20 - -
dropout - - 0.5

8/26/2024, 11:08:05 PM

19%
spectr-dense-6aa
PERFORMANCE
LATENCY
43 ms of 100 ms
RAM
11 kB of 264 kB
ROM
16 kB of 2048 kB
DSP NN Unused
TIME-SERIES INPUT

4000 ms |
4000 ms |
Enabled

SPECTRAL-ANALYSIS

16

ACCURACY (KERAS)
CLASSIFICATION

0.0005 | 30 | 19%

Type Filters Kernel Rate
dense 20 - -
dense 10 - -
dropout - - 0.5

8/26/2024, 11:06:14 PM

18%
spectr-dense-49f
PERFORMANCE
LATENCY
43 ms of 100 ms
RAM
6 kB of 264 kB
ROM
18 kB of 2048 kB
DSP NN Unused
TIME-SERIES INPUT

4000 ms |
4000 ms |
Enabled

SPECTRAL-ANALYSIS

64

ACCURACY (KERAS)
CLASSIFICATION

0.0005 | 30 | 18%

Type Filters Kernel Rate
dense 40 - -
dense 20 - -
dense 10 - -
dropout - - 0.25

8/26/2024, 11:01:06 PM

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