Edge Impulse Experts / Muse_separately_recorded_events 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

Motion events

MacBook Pro 16" 2020 (Intel Core i9 2.4GHz)

30 ms

4096 kB

4096 kB

Filters

Status

DSP type

Network type

View

Data set

Precision

Sort

General

F1-score

Precision

Recall

63%
raw-dense-e18
Show logs
PERFORMANCE
LATENCY
1 ms of 30 ms
RAM
7 kB of 4194304 kB
ROM
67 kB of 536870912 kB
DSP NN Unused
INPUT

30 ms | 30 ms

RAW

Parameter Value
scale-axes 1
implementationVersion 1

ACCURACY
CLASSIFICATION (KERAS)

0.0000105 | 999

Type Filters Kernel Rate
dense 33 - -
dense 25 - -

10/6/2022, 4:39:55 PM

63%
raw-dense-ebc
Show logs
PERFORMANCE
LATENCY
1 ms of 30 ms
RAM
7 kB of 4194304 kB
ROM
59 kB of 536870912 kB
DSP NN Unused
INPUT

30 ms | 30 ms

RAW

Parameter Value
scale-axes 1
implementationVersion 1

ACCURACY
CLASSIFICATION (KERAS)

0.0005 | 30

Type Filters Kernel Rate
dense 20 - -
dense 10 - -
dropout - - 0.5

10/6/2022, 5:02:15 PM

38%
raw-conv1d-42e
Show logs
PERFORMANCE
LATENCY
31 ms of 30 ms
Exceeds target by 1 ms
RAM
47 kB of 4194304 kB
ROM
94 kB of 536870912 kB
DSP NN Unused
INPUT

30 ms | 30 ms

RAW

Parameter Value
scale-axes 1
implementationVersion 1

ACCURACY
CLASSIFICATION (KERAS)

0.0005 | 30

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

10/6/2022, 4:42:10 PM

38%
raw-dense-405
Show logs
PERFORMANCE
LATENCY
1 ms of 30 ms
RAM
7 kB of 4194304 kB
ROM
71 kB of 536870912 kB
DSP NN Unused
INPUT

30 ms | 30 ms

RAW

Parameter Value
scale-axes 1
implementationVersion 1

ACCURACY
CLASSIFICATION (KERAS)

0.0005 | 30

Type Filters Kernel Rate
dense 40 - -
dense 20 - -
dropout - - 0.25

10/6/2022, 4:46:13 PM

38%
raw-conv1d-643
Show logs
PERFORMANCE
LATENCY
33 ms of 30 ms
Exceeds target by 3 ms
RAM
30 kB of 4194304 kB
ROM
82 kB of 536870912 kB
DSP NN Unused
INPUT

30 ms | 30 ms

RAW

Parameter Value
scale-axes 1
implementationVersion 1

ACCURACY
CLASSIFICATION (KERAS)

0.0005 | 30

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

10/6/2022, 4:57:46 PM

38%
raw-conv2d-305
Show logs
PERFORMANCE
LATENCY
53 ms of 30 ms
Exceeds target by 23 ms
RAM
25 kB of 4194304 kB
ROM
97 kB of 536870912 kB
DSP NN Unused
INPUT

30 ms | 30 ms

RAW

Parameter Value
scale-axes 1
implementationVersion 1

ACCURACY
CLASSIFICATION (KERAS)

0.0005 | 30

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

10/6/2022, 5:00:53 PM

38%
raw-dense-42e
Show logs
PERFORMANCE
LATENCY
1 ms of 30 ms
RAM
7 kB of 4194304 kB
ROM
59 kB of 536870912 kB
DSP NN Unused
INPUT

30 ms | 30 ms

RAW

Parameter Value
scale-axes 1
implementationVersion 1

ACCURACY
CLASSIFICATION (KERAS)

0.0005 | 30

Type Filters Kernel Rate
dense 20 - -
dense 10 - -
dropout - - 0.25

10/6/2022, 5:09:18 PM

38%
raw-conv1d-47f
Show logs
PERFORMANCE
LATENCY
30 ms of 30 ms
RAM
47 kB of 4194304 kB
ROM
94 kB of 536870912 kB
DSP NN Unused
INPUT

30 ms | 30 ms

RAW

Parameter Value
scale-axes 1
implementationVersion 1

ACCURACY
CLASSIFICATION (KERAS)

0.0005 | 30

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

10/6/2022, 5:12:55 PM

25%
raw-dense-8f8
Show logs
PERFORMANCE
LATENCY
1 ms of 30 ms
RAM
8 kB of 4194304 kB
ROM
59 kB of 536870912 kB
DSP NN Unused
INPUT

30 ms | 30 ms

RAW

Parameter Value
scale-axes 1
implementationVersion 1

ACCURACY
CLASSIFICATION (KERAS)

0.0005 | 30

Type Filters Kernel Rate
dense 20 - -
dense 10 - -
dense 5 - -
dropout - - 0.5

10/6/2022, 4:40:22 PM

25%
raw-conv2d-273
Show logs
PERFORMANCE
LATENCY
10 ms of 30 ms
RAM
15 kB of 4194304 kB
ROM
66 kB of 536870912 kB
DSP NN Unused
INPUT

30 ms | 30 ms

RAW

Parameter Value
scale-axes 1
implementationVersion 1

ACCURACY
CLASSIFICATION (KERAS)

0.0005 | 30

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

10/6/2022, 4:46:08 PM

25%
raw-conv1d-2fb
Show logs
PERFORMANCE
LATENCY
25 ms of 30 ms
RAM
28 kB of 4194304 kB
ROM
75 kB of 536870912 kB
DSP NN Unused
INPUT

30 ms | 30 ms

RAW

Parameter Value
scale-axes 1
implementationVersion 1

ACCURACY
CLASSIFICATION (KERAS)

0.0005 | 30

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

10/6/2022, 4:48:33 PM

25%
raw-dense-314
Show logs
PERFORMANCE
LATENCY
1 ms of 30 ms
RAM
8 kB of 4194304 kB
ROM
59 kB of 536870912 kB
DSP NN Unused
INPUT

30 ms | 30 ms

RAW

Parameter Value
scale-axes 1
implementationVersion 1

ACCURACY
CLASSIFICATION (KERAS)

0.0005 | 30

Type Filters Kernel Rate
dense 20 - -
dense 10 - -
dense 5 - -
dropout - - 0.25

10/6/2022, 4:48:33 PM

25%
raw-conv1d-854
Show logs
PERFORMANCE
LATENCY
2 ms of 30 ms
RAM
19 kB of 4194304 kB
ROM
69 kB of 536870912 kB
DSP NN Unused
INPUT

30 ms | 30 ms

RAW

Parameter Value
scale-axes 1
implementationVersion 1

ACCURACY
CLASSIFICATION (KERAS)

0.0005 | 30

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

10/6/2022, 4:50:42 PM

25%
raw-conv1d-d1f
Show logs
PERFORMANCE
LATENCY
26 ms of 30 ms
RAM
30 kB of 4194304 kB
ROM
82 kB of 536870912 kB
DSP NN Unused
INPUT

30 ms | 30 ms

RAW

Parameter Value
scale-axes 1
implementationVersion 1

ACCURACY
CLASSIFICATION (KERAS)

0.0005 | 30

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

10/6/2022, 4:53:52 PM

25%
raw-conv1d-e93
Show logs
PERFORMANCE
LATENCY
4 ms of 30 ms
RAM
19 kB of 4194304 kB
ROM
69 kB of 536870912 kB
DSP NN Unused
INPUT

30 ms | 30 ms

RAW

Parameter Value
scale-axes 1
implementationVersion 1

ACCURACY
CLASSIFICATION (KERAS)

0.0005 | 30

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

10/6/2022, 4:56:52 PM

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