Yi Xuan / Recyclable Waste Classification - Version 1 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

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

spectr-conv1d-0c0
PERFORMANCE
LATENCY
103 ms of 100 ms
Exceeds target by 3 ms
RAM
22 kB of 256 kB
ROM
46 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

SPECTROGRAM

0.025 | 0.025 | -32

ACCURACY (KERAS)
CLASSIFICATION

0.005 | 100 | 0%

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

4/9/2024, 2:41:35 PM

92%
mfe-conv1d-da2
PERFORMANCE
LATENCY
189 ms of 100 ms
Exceeds target by 89 ms
RAM
17 kB of 256 kB
ROM
43 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

MFE

0.02 | 0.02 | 32

ACCURACY (KERAS)
CLASSIFICATION

0.005 | 100 | 92%

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

4/9/2024, 2:47:09 PM

81%
mfe-conv1d-c59
PERFORMANCE
LATENCY
204 ms of 100 ms
Exceeds target by 104 ms
RAM
20 kB of 256 kB
ROM
70 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

MFE

0.02 | 0.02 | 32

ACCURACY (KERAS)
CLASSIFICATION

0.005 | 100 | 81%

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

4/9/2024, 2:43:30 PM

73%
mfe-conv1d-045
PERFORMANCE
LATENCY
208 ms of 100 ms
Exceeds target by 108 ms
RAM
19 kB of 256 kB
ROM
35 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

MFE

0.032 | 0.016 | 32

ACCURACY (KERAS)
CLASSIFICATION

0.005 | 100 | 73%

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

4/9/2024, 2:57:50 PM

72%
mfcc-conv1d-11d
PERFORMANCE
LATENCY
253 ms of 100 ms
Exceeds target by 153 ms
RAM
17 kB of 256 kB
ROM
34 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

MFCC

0.05 | 0.025 | 32

ACCURACY (KERAS)
CLASSIFICATION

0.005 | 100 | 72%

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

4/9/2024, 2:55:58 PM

71%
mfe-conv1d-35a
PERFORMANCE
LATENCY
328 ms of 100 ms
Exceeds target by 228 ms
RAM
26 kB of 256 kB
ROM
33 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

MFE

0.02 | 0.01 | 32

ACCURACY (KERAS)
CLASSIFICATION

0.005 | 100 | 71%

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

4/9/2024, 3:03:12 PM

71%
mfcc-conv1d-889
PERFORMANCE
LATENCY
527 ms of 100 ms
Exceeds target by 427 ms
RAM
27 kB of 256 kB
ROM
69 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

MFCC

0.032 | 0.016 | 40

ACCURACY (KERAS)
CLASSIFICATION

0.005 | 100 | 71%

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

4/9/2024, 2:51:14 PM

67%
mfe-conv1d-3d4
PERFORMANCE
LATENCY
105 ms of 100 ms
Exceeds target by 5 ms
RAM
14 kB of 256 kB
ROM
35 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

MFE

0.032 | 0.032 | 32

ACCURACY (KERAS)
CLASSIFICATION

0.005 | 100 | 67%

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

4/9/2024, 2:53:54 PM

65%
mfcc-conv2d-f8b
PERFORMANCE
LATENCY
208 ms of 100 ms
Exceeds target by 108 ms
RAM
18 kB of 256 kB
ROM
37 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

MFCC

0.05 | 0.05 | 40

ACCURACY (KERAS)
CLASSIFICATION

0.005 | 100 | 65%

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

4/9/2024, 2:54:38 PM

62%
mfe-conv1d-ad6
PERFORMANCE
LATENCY
114 ms of 100 ms
Exceeds target by 14 ms
RAM
16 kB of 256 kB
ROM
70 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

MFE

0.05 | 0.05 | 32

ACCURACY (KERAS)
CLASSIFICATION

0.005 | 100 | 62%

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

4/9/2024, 2:40:19 PM

62%
mfcc-conv2d-a48
PERFORMANCE
LATENCY
448 ms of 100 ms
Exceeds target by 348 ms
RAM
24 kB of 256 kB
ROM
38 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

MFCC

0.02 | 0.02 | 40

ACCURACY (KERAS)
CLASSIFICATION

0.005 | 100 | 62%

Type Filters Kernel Rate
Data augmentation
conv2d 8 3 -
conv2d 16 3 -
conv2d 32 3 -
dropout - - 0.25

4/9/2024, 2:58:15 PM

59%
mfcc-conv1d-481
PERFORMANCE
LATENCY
169 ms of 100 ms
Exceeds target by 69 ms
RAM
15 kB of 256 kB
ROM
40 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

MFCC

0.05 | 0.05 | 40

ACCURACY (KERAS)
CLASSIFICATION

0.005 | 100 | 59%

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

4/9/2024, 2:42:28 PM

58%
mfe-conv1d-c42
PERFORMANCE
LATENCY
233 ms of 100 ms
Exceeds target by 133 ms
RAM
24 kB of 256 kB
ROM
172 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

MFE

0.05 | 0.025 | 32

ACCURACY (KERAS)
CLASSIFICATION

0.005 | 100 | 58%

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

4/9/2024, 2:45:17 PM

57%
mfcc-conv1d-b33
PERFORMANCE
LATENCY
374 ms of 100 ms
Exceeds target by 274 ms
RAM
21 kB of 256 kB
ROM
35 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

MFCC

0.032 | 0.016 | 32

ACCURACY (KERAS)
CLASSIFICATION

0.005 | 100 | 57%

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

4/9/2024, 2:53:04 PM

57%
mfe-conv1d-7f9
PERFORMANCE
LATENCY
151 ms of 100 ms
Exceeds target by 51 ms
RAM
16 kB of 256 kB
ROM
35 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

MFE

0.05 | 0.025 | 32

ACCURACY (KERAS)
CLASSIFICATION

0.005 | 100 | 57%

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

4/9/2024, 2:40:52 PM

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