Cumhur Erkut / Mubarik-project-1 Public
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

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

100%
spectr-conv1d-ca3
PERFORMANCE
LATENCY
505 ms of 100 ms
Exceeds target by 405 ms
RAM
112 kB of 256 kB
ROM
36 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

10000 ms |
10000 ms |
Enabled

SPECTROGRAM

0.075 | 0.0375 | -32

ACCURACY (KERAS)
CLASSIFICATION

0.005 | 100 | 100%

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

3/26/2024, 7:48:52 AM

77%
spectr-conv1d-032
PERFORMANCE
LATENCY
259 ms of 100 ms
Exceeds target by 159 ms
RAM
61 kB of 256 kB
ROM
37 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

10000 ms |
10000 ms |
Enabled

SPECTROGRAM

0.075 | 0.075 | -52

ACCURACY (KERAS)
CLASSIFICATION

0.005 | 100 | 77%

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

3/26/2024, 7:47:50 AM

77%
spectr-conv1d-34b
PERFORMANCE
LATENCY
616 ms of 100 ms
Exceeds target by 516 ms
RAM
113 kB of 256 kB
ROM
50 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

10000 ms |
10000 ms |
Enabled

SPECTROGRAM

0.075 | 0.0375 | -32

ACCURACY (KERAS)
CLASSIFICATION

0.005 | 100 | 77%

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

3/26/2024, 7:45:30 AM

77%
spectr-conv1d-e3b
PERFORMANCE
LATENCY
518 ms of 100 ms
Exceeds target by 418 ms
RAM
113 kB of 256 kB
ROM
38 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

10000 ms |
10000 ms |
Enabled

SPECTROGRAM

0.075 | 0.0375 | -32

ACCURACY (KERAS)
CLASSIFICATION

0.005 | 100 | 77%

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

3/26/2024, 7:48:08 AM

69%
spectr-conv1d-f14
PERFORMANCE
LATENCY
444 ms of 100 ms
Exceeds target by 344 ms
RAM
86 kB of 256 kB
ROM
48 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

10000 ms |
10000 ms |
Enabled

SPECTROGRAM

0.05 | 0.05 | -32

ACCURACY (KERAS)
CLASSIFICATION

0.005 | 100 | 69%

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

3/26/2024, 7:44:12 AM

69%
spectr-conv1d-907
PERFORMANCE
LATENCY
517 ms of 100 ms
Exceeds target by 417 ms
RAM
88 kB of 256 kB
ROM
75 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

10000 ms |
10000 ms |
Enabled

SPECTROGRAM

0.05 | 0.05 | -32

ACCURACY (KERAS)
CLASSIFICATION

0.005 | 100 | 69%

Type Filters Kernel Rate
Data augmentation
conv1d 16 3 -
conv1d 32 3 -
conv1d 64 3 -
conv1d 128 3 -
dropout - - 0.25

3/26/2024, 7:48:02 AM

62%
spectr-conv1d-440
PERFORMANCE
LATENCY
738 ms of 100 ms
Exceeds target by 638 ms
RAM
162 kB of 256 kB
ROM
40 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

10000 ms |
10000 ms |
Enabled

SPECTROGRAM

0.05 | 0.025 | -72

ACCURACY (KERAS)
CLASSIFICATION

0.005 | 100 | 62%

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

3/26/2024, 7:41:59 AM

62%
spectr-conv1d-a77
PERFORMANCE
LATENCY
279 ms of 100 ms
Exceeds target by 179 ms
RAM
63 kB of 256 kB
ROM
44 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

10000 ms |
10000 ms |
Enabled

SPECTROGRAM

0.075 | 0.075 | -32

ACCURACY (KERAS)
CLASSIFICATION

0.005 | 100 | 62%

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

3/26/2024, 7:46:45 AM

62%
spectr-conv1d-c11
PERFORMANCE
LATENCY
285 ms of 100 ms
Exceeds target by 185 ms
RAM
61 kB of 256 kB
ROM
39 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

10000 ms |
10000 ms |
Enabled

SPECTROGRAM

0.075 | 0.075 | -32

ACCURACY (KERAS)
CLASSIFICATION

0.005 | 100 | 62%

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

3/26/2024, 7:50:15 AM

46%
spectr-conv1d-4c1
PERFORMANCE
LATENCY
615 ms of 100 ms
Exceeds target by 515 ms
RAM
113 kB of 256 kB
ROM
50 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

10000 ms |
10000 ms |
Enabled

SPECTROGRAM

0.075 | 0.0375 | -52

ACCURACY (KERAS)
CLASSIFICATION

0.005 | 100 | 46%

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

3/26/2024, 7:43:04 AM

38%
spectr-conv1d-0a6
PERFORMANCE
LATENCY
366 ms of 100 ms
Exceeds target by 266 ms
RAM
61 kB of 256 kB
ROM
50 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

10000 ms |
10000 ms |
Enabled

SPECTROGRAM

0.075 | 0.075 | -72

ACCURACY (KERAS)
CLASSIFICATION

0.005 | 100 | 38%

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

3/26/2024, 7:49:06 AM

31%
spectr-conv1d-de5
PERFORMANCE
LATENCY
361 ms of 100 ms
Exceeds target by 261 ms
RAM
64 kB of 256 kB
ROM
74 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

10000 ms |
10000 ms |
Enabled

SPECTROGRAM

0.075 | 0.075 | -32

ACCURACY (KERAS)
CLASSIFICATION

0.005 | 100 | 31%

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

3/26/2024, 7:39:02 AM

31%
spectr-conv1d-2ea
PERFORMANCE
LATENCY
262 ms of 100 ms
Exceeds target by 162 ms
RAM
61 kB of 256 kB
ROM
37 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

10000 ms |
10000 ms |
Enabled

SPECTROGRAM

0.075 | 0.075 | -72

ACCURACY (KERAS)
CLASSIFICATION

0.005 | 100 | 31%

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

3/26/2024, 7:40:30 AM

31%
spectr-conv1d-799
PERFORMANCE
LATENCY
769 ms of 100 ms
Exceeds target by 669 ms
RAM
164 kB of 256 kB
ROM
47 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

10000 ms |
10000 ms |
Enabled

SPECTROGRAM

0.05 | 0.025 | -52

ACCURACY (KERAS)
CLASSIFICATION

0.005 | 100 | 31%

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

3/26/2024, 7:40:44 AM

31%
spectr-conv1d-882
PERFORMANCE
LATENCY
285 ms of 100 ms
Exceeds target by 185 ms
RAM
61 kB of 256 kB
ROM
39 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

10000 ms |
10000 ms |
Enabled

SPECTROGRAM

0.075 | 0.075 | -32

ACCURACY (KERAS)
CLASSIFICATION

0.005 | 100 | 31%

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

3/26/2024, 7:42:41 AM