Mathilde Bindslev / ML-mini-project 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

EON Tuner

Nvidia Jetson Nano

100 ms

4194304 kB

16777216 kB

Filters

Status

DSP type

Model type

View

Data set

Variant

Sort

General

F1-score

Precision

Recall

83%
mfe-conv1d-f59
PERFORMANCE
LATENCY
4 ms of 100 ms
RAM
29 kB of 4194304 kB
ROM
576 kB of 16777216 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

MFE

0.02 | 0.01 | 32

ACCURACY (OVERALL)
CLASSIFICATION

0.005 | 100 | 83%

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

11/25/2024, 9:41:19 PM

79%
mfe-conv2d-f2d
PERFORMANCE
LATENCY
3 ms of 100 ms
RAM
62 kB of 4194304 kB
ROM
52 kB of 16777216 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

MFE

0.05 | 0.025 | 32

ACCURACY (OVERALL)
CLASSIFICATION

0.005 | 100 | 79%

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

11/25/2024, 9:36:41 PM

78%
mfe-conv1d-49e
PERFORMANCE
LATENCY
7 ms of 100 ms
RAM
45 kB of 4194304 kB
ROM
576 kB of 16777216 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

MFE

0.02 | 0.01 | 32

ACCURACY (OVERALL)
CLASSIFICATION

0.005 | 100 | 78%

Type Filters Kernel Rate
conv1d 32 3 -
conv1d 64 3 -
conv1d 128 3 -
conv1d 256 3 -
dropout - - 0.25

11/25/2024, 9:41:06 PM

70%
mfe-conv2d-54b
PERFORMANCE
LATENCY
3 ms of 100 ms
RAM
52 kB of 4194304 kB
ROM
412 kB of 16777216 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

MFE

0.05 | 0.05 | 32

ACCURACY (OVERALL)
CLASSIFICATION

0.005 | 100 | 70%

Type Filters Kernel Rate
conv2d 16 3 -
conv2d 32 3 -
conv2d 64 3 -
conv2d 128 3 -
dropout - - 0.5

11/25/2024, 9:35:17 PM

66%
mfe-conv2d-b96
PERFORMANCE
LATENCY
3 ms of 100 ms
RAM
52 kB of 4194304 kB
ROM
129 kB of 16777216 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

MFE

0.05 | 0.05 | 32

ACCURACY (OVERALL)
CLASSIFICATION

0.005 | 100 | 66%

Type Filters Kernel Rate
conv2d 16 3 -
conv2d 32 3 -
conv2d 64 3 -
dropout - - 0.25

11/25/2024, 9:39:40 PM

64%
mfe-conv1d-4a0
PERFORMANCE
LATENCY
2 ms of 100 ms
RAM
19 kB of 4194304 kB
ROM
65 kB of 16777216 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

MFE

0.032 | 0.032 | 32

ACCURACY (OVERALL)
CLASSIFICATION

0.005 | 100 | 64%

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

11/25/2024, 9:33:51 PM

64%
mfe-conv2d-238
PERFORMANCE
LATENCY
2 ms of 100 ms
RAM
35 kB of 4194304 kB
ROM
40 kB of 16777216 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

MFE

0.05 | 0.05 | 32

ACCURACY (OVERALL)
CLASSIFICATION

0.005 | 100 | 64%

Type Filters Kernel Rate
conv2d 8 3 -
conv2d 16 3 -
dropout - - 0.25

11/25/2024, 9:28:31 PM

62%
mfe-conv1d-361
PERFORMANCE
LATENCY
4 ms of 100 ms
RAM
44 kB of 4194304 kB
ROM
42 kB of 16777216 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

MFE

0.02 | 0.01 | 32

ACCURACY (OVERALL)
CLASSIFICATION

0.005 | 100 | 62%

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

11/25/2024, 9:38:51 PM

50%
mfe-conv1d-b56
PERFORMANCE
LATENCY
3 ms of 100 ms
RAM
25 kB of 4194304 kB
ROM
31 kB of 16777216 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

MFE

0.02 | 0.02 | 32

ACCURACY (OVERALL)
CLASSIFICATION

0.005 | 100 | 50%

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

11/25/2024, 9:37:20 PM

47%
mfcc-conv2d-bc8
PERFORMANCE
LATENCY
1 ms of 100 ms
RAM
53 kB of 4194304 kB
ROM
127 kB of 16777216 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

MFCC

0.02 | 0.01 | 32

ACCURACY (OVERALL)
CLASSIFICATION

0.005 | 100 | 47%

Type Filters Kernel Rate
conv2d 8 3 -
conv2d 16 3 -
conv2d 32 3 -
conv2d 64 3 -
dropout - - 0.25

11/25/2024, 9:36:31 PM

41%
mfcc-conv2d-84e
PERFORMANCE
LATENCY
12 ms of 100 ms
RAM
79 kB of 4194304 kB
ROM
127 kB of 16777216 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

MFCC

0.02 | 0.01 | 40

ACCURACY (OVERALL)
CLASSIFICATION

0.005 | 100 | 41%

Type Filters Kernel Rate
Data augmentation
conv2d 8 3 -
conv2d 16 3 -
conv2d 32 3 -
conv2d 64 3 -
dropout - - 0.25

11/25/2024, 9:35:00 PM

41%
mfe-conv1d-fb6
PERFORMANCE
LATENCY
3 ms of 100 ms
RAM
23 kB of 4194304 kB
ROM
164 kB of 16777216 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

MFE

0.05 | 0.025 | 32

ACCURACY (OVERALL)
CLASSIFICATION

0.005 | 100 | 41%

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

11/25/2024, 9:25:13 PM

38%
mfcc-conv2d-1d2
PERFORMANCE
LATENCY
1 ms of 100 ms
RAM
28 kB of 4194304 kB
ROM
123 kB of 16777216 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

MFCC

0.02 | 0.02 | 32

ACCURACY (OVERALL)
CLASSIFICATION

0.005 | 100 | 38%

Type Filters Kernel Rate
Data augmentation
conv2d 8 3 -
conv2d 16 3 -
conv2d 32 3 -
conv2d 64 3 -
dropout - - 0.25

11/25/2024, 9:43:10 PM

36%
mfe-conv2d-165
PERFORMANCE
LATENCY
4 ms of 100 ms
RAM
75 kB of 4194304 kB
ROM
128 kB of 16777216 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

MFE

0.02 | 0.02 | 32

ACCURACY (OVERALL)
CLASSIFICATION

0.005 | 100 | 36%

Type Filters Kernel Rate
Data augmentation
conv2d 8 3 -
conv2d 16 3 -
conv2d 32 3 -
conv2d 64 3 -
dropout - - 0.25

11/25/2024, 9:35:43 PM

34%
mfcc-conv1d-cff
PERFORMANCE
LATENCY
9 ms of 100 ms
RAM
51 kB of 4194304 kB
ROM
569 kB of 16777216 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

MFCC

0.02 | 0.01 | 32

ACCURACY (OVERALL)
CLASSIFICATION

0.005 | 100 | 34%

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

11/25/2024, 9:31:23 PM