Mathias / woodpeckerDetector Public
Clone this project

EON Tuner

The EON Tuner helps you find the most optimal architecture for your embedded machine-learning application. Clone this project to use the EON Tuner.

Target

No name set

Audible events

Nordic nRF5340 DK (Cortex-M33 128MHz)

200 ms

512 kB

1024 kB

Filters

Status

DSP type

Network type

View

Data set

Precision

Sort

General

F1-score

Precision

Recall

100%
spectr-conv1d-2e5
Show logs
PERFORMANCE
LATENCY
152 ms of 200 ms
RAM
16 kB of 512 kB
ROM
85 kB of 1024 kB
DSP NN Unused
INPUT

4000 ms | 4000 ms

SPECTROGRAM

0.05 | 0.05 | -72

ACCURACY
NEURAL NETWORK (KERAS)

0.005 | 100

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

7/30/2021, 8:50:09 AM

100%
spectr-conv1d-b70
Show logs
PERFORMANCE
LATENCY
82 ms of 200 ms
RAM
30 kB of 512 kB
ROM
65 kB of 1024 kB
DSP NN Unused
INPUT

2000 ms | 500 ms

SPECTROGRAM

0.025 | 0.025 | -72

ACCURACY
NEURAL NETWORK (KERAS)

0.005 | 100

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

7/30/2021, 8:52:26 AM

100%
spectr-conv1d-585
Show logs
PERFORMANCE
LATENCY
152 ms of 200 ms
RAM
16 kB of 512 kB
ROM
85 kB of 1024 kB
DSP NN Unused
INPUT

2000 ms | 2000 ms

SPECTROGRAM

0.05 | 0.025 | -52

ACCURACY
NEURAL NETWORK (KERAS)

0.005 | 100

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

7/30/2021, 8:53:02 AM

100%
spectr-conv1d-977
Show logs
PERFORMANCE
LATENCY
100 ms of 200 ms
RAM
14 kB of 512 kB
ROM
39 kB of 1024 kB
DSP NN Unused
INPUT

4000 ms | 2000 ms

SPECTROGRAM

0.05 | 0.05 | -52

ACCURACY
NEURAL NETWORK (KERAS)

0.005 | 100

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

7/30/2021, 8:56:20 AM

100%
spectr-conv1d-4a2
Show logs
PERFORMANCE
LATENCY
102 ms of 200 ms
RAM
24 kB of 512 kB
ROM
75 kB of 1024 kB
DSP NN Unused
INPUT

4000 ms | 4000 ms

SPECTROGRAM

0.05 | 0.025 | -52

ACCURACY
NEURAL NETWORK (KERAS)

0.005 | 100

Type Filters Kernel Rate
conv1d 8 3 -
conv1d 16 3 -
dropout - - 0.25
dense 64 - -
dropout - - 0.25

7/30/2021, 8:58:32 AM

100%
spectr-conv1d-1a8
Show logs
PERFORMANCE
LATENCY
110 ms of 200 ms
RAM
35 kB of 512 kB
ROM
75 kB of 1024 kB
DSP NN Unused
INPUT

2000 ms | 500 ms

SPECTROGRAM

0.025 | 0.0125 | -52

ACCURACY
NEURAL NETWORK (KERAS)

0.005 | 100

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

7/30/2021, 9:08:14 AM

100%
mfe-conv1d-8bf
Show logs
PERFORMANCE
LATENCY
48 ms of 200 ms
RAM
25 kB of 512 kB
ROM
35 kB of 1024 kB
DSP NN Unused
INPUT

2000 ms | 2000 ms

MFE

0.032 | 0.032 | 40

ACCURACY
NEURAL NETWORK (KERAS)

0.005 | 100

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

7/30/2021, 9:09:51 AM

100%
spectr-conv1d-5c7
Show logs
PERFORMANCE
LATENCY
230 ms of 200 ms
Exceeds target by 30 ms
RAM
20 kB of 512 kB
ROM
44 kB of 1024 kB
DSP NN Unused
INPUT

2000 ms | 2000 ms

SPECTROGRAM

0.025 | 0.025 | -52

ACCURACY
NEURAL NETWORK (KERAS)

0.005 | 100

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

7/30/2021, 9:11:09 AM

99%
spectr-conv2d-48f
Show logs
PERFORMANCE
LATENCY
128 ms of 200 ms
RAM
21 kB of 512 kB
ROM
101 kB of 1024 kB
DSP NN Unused
INPUT

1000 ms | 500 ms

SPECTROGRAM

0.075 | 0.075 | -72

ACCURACY
NEURAL NETWORK (KERAS)

0.005 | 100

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

7/30/2021, 8:54:58 AM

99%
spectr-conv1d-2a6
Show logs
PERFORMANCE
LATENCY
62 ms of 200 ms
RAM
38 kB of 512 kB
ROM
57 kB of 1024 kB
DSP NN Unused
INPUT

1000 ms | 250 ms

SPECTROGRAM

0.025 | 0.0125 | -32

ACCURACY
NEURAL NETWORK (KERAS)

0.005 | 100

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

7/30/2021, 9:14:02 AM

99%
spectr-conv1d-a26
Show logs
PERFORMANCE
LATENCY
74 ms of 200 ms
RAM
39 kB of 512 kB
ROM
45 kB of 1024 kB
DSP NN Unused
INPUT

1000 ms | 500 ms

SPECTROGRAM

0.025 | 0.0125 | -52

ACCURACY
NEURAL NETWORK (KERAS)

0.005 | 100

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

7/30/2021, 9:03:43 AM

99%
spectr-conv1d-1a8
Show logs
PERFORMANCE
LATENCY
94 ms of 200 ms
RAM
18 kB of 512 kB
ROM
58 kB of 1024 kB
DSP NN Unused
INPUT

4000 ms | 4000 ms

SPECTROGRAM

0.075 | 0.075 | -32

ACCURACY
NEURAL NETWORK (KERAS)

0.005 | 100

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

7/30/2021, 9:07:47 AM

99%
mfe-conv1d-c24
Show logs
PERFORMANCE
LATENCY
24 ms of 200 ms
RAM
28 kB of 512 kB
ROM
34 kB of 1024 kB
DSP NN Unused
INPUT

1000 ms | 1000 ms

MFE

0.032 | 0.016 | 40

ACCURACY
NEURAL NETWORK (KERAS)

0.005 | 100

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

7/30/2021, 8:54:02 AM

99%
spectr-conv2d-9d3
Show logs
PERFORMANCE
LATENCY
216 ms of 200 ms
Exceeds target by 16 ms
RAM
21 kB of 512 kB
ROM
75 kB of 1024 kB
DSP NN Unused
INPUT

1000 ms | 500 ms

SPECTROGRAM

0.075 | 0.075 | -52

ACCURACY
NEURAL NETWORK (KERAS)

0.005 | 100

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

7/30/2021, 9:08:15 AM

98%
spectr-conv1d-0e6
Show logs
PERFORMANCE
LATENCY
230 ms of 200 ms
Exceeds target by 30 ms
RAM
32 kB of 512 kB
ROM
113 kB of 1024 kB
DSP NN Unused
INPUT

2000 ms | 1000 ms

SPECTROGRAM

0.05 | 0.025 | -32

ACCURACY
NEURAL NETWORK (KERAS)

0.005 | 100

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

7/30/2021, 8:51:49 AM

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