MJRoBot (Marcelo Rovai) / XIAO-ESP32S3-KWS Public
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

Arduino Nicla Vision (Cortex-M7 480MHz)

100 ms

1024 kB

2048 kB

Filters

Status

DSP type

Model type

View

Data set

Variant

Sort

General

F1-score

Precision

Recall

90%
mfe-conv1d-239
PERFORMANCE
LATENCY
15 ms of 100 ms
RAM
20 kB of 1024 kB
ROM
66 kB of 2048 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

MFE

0.05 | 0.025 | 32

ACCURACY (KERAS)
CLASSIFICATION

0.005 | 100 | 90%

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

5/22/2023, 7:14:09 PM

90%
mfe-conv1d-93d
PERFORMANCE
LATENCY
15 ms of 100 ms
RAM
20 kB of 1024 kB
ROM
66 kB of 2048 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

MFE

0.05 | 0.025 | 32

ACCURACY (KERAS)
CLASSIFICATION

0.005 | 100 | 90%

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

5/22/2023, 7:14:58 PM

90%
mfe-conv1d-954
PERFORMANCE
LATENCY
9 ms of 100 ms
RAM
13 kB of 1024 kB
ROM
30 kB of 2048 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

MFE

0.032 | 0.032 | 32

ACCURACY (KERAS)
CLASSIFICATION

0.005 | 100 | 90%

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

5/22/2023, 7:19:29 PM

90%
mfcc-conv1d-ac7
PERFORMANCE
LATENCY
15 ms of 100 ms
RAM
15 kB of 1024 kB
ROM
36 kB of 2048 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

MFCC

0.032 | 0.032 | 32

ACCURACY (KERAS)
CLASSIFICATION

0.005 | 100 | 90%

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

5/22/2023, 7:15:42 PM

90%
mfe-conv1d-232
PERFORMANCE
LATENCY
10 ms of 100 ms
RAM
15 kB of 1024 kB
ROM
38 kB of 2048 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

MFE

0.032 | 0.032 | 32

ACCURACY (KERAS)
CLASSIFICATION

0.005 | 100 | 90%

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

5/22/2023, 7:06:47 PM

89%
mfe-conv1d-b7e
PERFORMANCE
LATENCY
10 ms of 100 ms
RAM
15 kB of 1024 kB
ROM
38 kB of 2048 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

MFE

0.032 | 0.032 | 32

ACCURACY (KERAS)
CLASSIFICATION

0.005 | 100 | 89%

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

5/22/2023, 7:12:35 PM

89%
mfe-conv1d-5e3
PERFORMANCE
LATENCY
9 ms of 100 ms
RAM
15 kB of 1024 kB
ROM
38 kB of 2048 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

MFE

0.032 | 0.032 | 32

ACCURACY (KERAS)
CLASSIFICATION

0.005 | 100 | 89%

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

5/22/2023, 7:09:37 PM

89%
mfe-conv1d-b53
PERFORMANCE
LATENCY
9 ms of 100 ms
RAM
14 kB of 1024 kB
ROM
30 kB of 2048 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

MFE

0.032 | 0.032 | 32

ACCURACY (KERAS)
CLASSIFICATION

0.005 | 100 | 89%

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

5/22/2023, 6:53:26 PM

89%
mfe-conv2d-7f5
PERFORMANCE
LATENCY
9 ms of 100 ms
RAM
18 kB of 1024 kB
ROM
33 kB of 2048 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

MFE

0.05 | 0.05 | 32

ACCURACY (KERAS)
CLASSIFICATION

0.005 | 100 | 89%

Type Filters Kernel Rate
conv2d 8 3 -
conv2d 16 3 -
conv2d 32 3 -
dropout - - 0.5

5/22/2023, 7:19:03 PM

88%
mfe-conv1d-fe7
PERFORMANCE
LATENCY
12 ms of 100 ms
RAM
17 kB of 1024 kB
ROM
30 kB of 2048 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

MFE

0.05 | 0.025 | 32

ACCURACY (KERAS)
CLASSIFICATION

0.005 | 100 | 88%

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

5/22/2023, 7:04:51 PM

88%
mfe-conv1d-890
PERFORMANCE
LATENCY
9 ms of 100 ms
RAM
13 kB of 1024 kB
ROM
27 kB of 2048 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

MFE

0.032 | 0.032 | 32

ACCURACY (KERAS)
CLASSIFICATION

0.005 | 100 | 88%

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

5/22/2023, 7:10:13 PM

88%
mfe-conv1d-b79
PERFORMANCE
LATENCY
10 ms of 100 ms
RAM
14 kB of 1024 kB
ROM
38 kB of 2048 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

MFE

0.032 | 0.032 | 32

ACCURACY (KERAS)
CLASSIFICATION

0.005 | 100 | 88%

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

5/22/2023, 7:20:57 PM

88%
mfe-conv1d-f7b
PERFORMANCE
LATENCY
10 ms of 100 ms
RAM
14 kB of 1024 kB
ROM
38 kB of 2048 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

MFE

0.032 | 0.032 | 32

ACCURACY (KERAS)
CLASSIFICATION

0.005 | 100 | 88%

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

5/22/2023, 7:06:13 PM

87%
mfcc-conv2d-30c
PERFORMANCE
LATENCY
12 ms of 100 ms
RAM
15 kB of 1024 kB
ROM
33 kB of 2048 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

MFCC

0.05 | 0.05 | 32

ACCURACY (KERAS)
CLASSIFICATION

0.005 | 100 | 87%

Type Filters Kernel Rate
Data augmentation
conv2d 8 3 -
conv2d 16 3 -
conv2d 32 3 -
dropout - - 0.5

5/22/2023, 7:15:04 PM

87%
mfcc-conv1d-560
PERFORMANCE
LATENCY
23 ms of 100 ms
RAM
18 kB of 1024 kB
ROM
27 kB of 2048 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

MFCC

0.05 | 0.025 | 40

ACCURACY (KERAS)
CLASSIFICATION

0.005 | 100 | 87%

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

5/22/2023, 6:53:35 PM