Ramasamy / ITU_W Public
Target: Arduino Nano 33 BLE Sense (Cortex-M4F 64MHz) 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

Poultry_voice

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

Run #1 - Poultry_voice (Jul 01 2024, 04:19:48, finished)
spectr-conv1d-0cd
PERFORMANCE
LATENCY
33 ms of 100 ms
RAM
23 kB of 256 kB
ROM
35 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

SPECTROGRAM

0.075 | 0.075 | -52

ACCURACY (KERAS)
CLASSIFICATION

0.005 | 100 | 0%

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

7/1/2024, 4:44:43 AM

45%
spectr-conv1d-0cf
PERFORMANCE
LATENCY
76 ms of 100 ms
RAM
28 kB of 256 kB
ROM
45 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

SPECTROGRAM

0.075 | 0.0375 | -52

ACCURACY (KERAS)
CLASSIFICATION

0.005 | 100 | 45%

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

7/1/2024, 4:44:13 AM

37%
spectr-conv1d-372
PERFORMANCE
LATENCY
33 ms of 100 ms
RAM
23 kB of 256 kB
ROM
35 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

SPECTROGRAM

0.075 | 0.075 | -72

ACCURACY (KERAS)
CLASSIFICATION

0.005 | 100 | 37%

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

7/1/2024, 4:40:05 AM

33%
spectr-conv1d-fbb
PERFORMANCE
LATENCY
66 ms of 100 ms
RAM
26 kB of 256 kB
ROM
71 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

SPECTROGRAM

0.075 | 0.075 | -72

ACCURACY (KERAS)
CLASSIFICATION

0.005 | 100 | 33%

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

7/1/2024, 4:44:40 AM

31%
spectr-conv1d-a9b
PERFORMANCE
LATENCY
185 ms of 100 ms
Exceeds target by 85 ms
RAM
40 kB of 256 kB
ROM
47 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

SPECTROGRAM

0.025 | 0.0125 | -72

ACCURACY (KERAS)
CLASSIFICATION

0.005 | 100 | 31%

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

7/1/2024, 4:44:02 AM

17%
spectr-conv1d-1d7
PERFORMANCE
LATENCY
47 ms of 100 ms
RAM
23 kB of 256 kB
ROM
36 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

SPECTROGRAM

0.075 | 0.075 | -32

ACCURACY (KERAS)
CLASSIFICATION

0.005 | 100 | 17%

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

7/1/2024, 4:41:15 AM

spectr-conv1d-a2d
PERFORMANCE
LATENCY
91 ms of 100 ms
RAM
30 kB of 256 kB
ROM
44 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

SPECTROGRAM

0.05 | 0.025 | -52

ACCURACY (KERAS)
CLASSIFICATION

0.005 | 100 | 0%

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

7/1/2024, 4:40:49 AM

48%
spectr-conv1d-148
PERFORMANCE
LATENCY
122 ms of 100 ms
Exceeds target by 22 ms
RAM
31 kB of 256 kB
ROM
73 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

SPECTROGRAM

0.05 | 0.025 | -52

ACCURACY (KERAS)
CLASSIFICATION

0.005 | 100 | 48%

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

7/1/2024, 4:30:44 AM

46%
spectr-conv1d-e0a
PERFORMANCE
LATENCY
65 ms of 100 ms
RAM
24 kB of 256 kB
ROM
72 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

SPECTROGRAM

0.05 | 0.05 | -32

ACCURACY (KERAS)
CLASSIFICATION

0.005 | 100 | 46%

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

7/1/2024, 4:37:37 AM

31%
spectr-conv1d-07a
PERFORMANCE
LATENCY
73 ms of 100 ms
RAM
31 kB of 256 kB
ROM
72 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

SPECTROGRAM

0.075 | 0.0375 | -52

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 - - 0.25

7/1/2024, 4:39:04 AM

0%
spectr-conv1d-c6c
PERFORMANCE
LATENCY
103 ms of 100 ms
Exceeds target by 3 ms
RAM
24 kB of 256 kB
ROM
37 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

SPECTROGRAM

0.025 | 0.025 | -52

ACCURACY (KERAS)
CLASSIFICATION

0.005 | 100 | 0%

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

7/1/2024, 4:39:48 AM

spectr-conv1d-a85
PERFORMANCE
LATENCY
171 ms of 100 ms
Exceeds target by 71 ms
RAM
39 kB of 256 kB
ROM
39 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

SPECTROGRAM

0.025 | 0.0125 | -72

ACCURACY (KERAS)
CLASSIFICATION

0.005 | 100 | 0%

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

7/1/2024, 4:37:40 AM

spectr-conv1d-42d
PERFORMANCE
LATENCY
77 ms of 100 ms
RAM
29 kB of 256 kB
ROM
44 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

SPECTROGRAM

0.075 | 0.0375 | -52

ACCURACY (KERAS)
CLASSIFICATION

0.005 | 100 | 0%

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

7/1/2024, 4:33:22 AM

40%
spectr-conv1d-2ad
PERFORMANCE
LATENCY
112 ms of 100 ms
Exceeds target by 12 ms
RAM
27 kB of 256 kB
ROM
73 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

SPECTROGRAM

0.025 | 0.025 | -52

ACCURACY (KERAS)
CLASSIFICATION

0.005 | 100 | 40%

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

7/1/2024, 4:34:21 AM

27%
spectr-conv1d-15b
PERFORMANCE
LATENCY
42 ms of 100 ms
RAM
26 kB of 256 kB
ROM
71 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

SPECTROGRAM

0.075 | 0.075 | -32

ACCURACY (KERAS)
CLASSIFICATION

0.005 | 100 | 27%

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

7/1/2024, 4:30:28 AM

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