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
Run #5
ECO
500 ms
200000 kB
200000 kB
Filters
Status
DSP type
Model type
View
Data set
Variant
Sort
General
F1-score
Precision
Recall
Run #5 (Nov 26 2025, 16:29:03, finished)
86%
spectr-conv1d-dense-de1
PERFORMANCE
LATENCY
2 ms of
500 ms
RAM
26 kB of
200000 kB
ROM
868 kB of
200000 kB
DSP
NN
Unused
TIME-SERIES INPUT
5000 ms
|
500 ms
|
Enabled
SPECTROGRAM
0.05 | 0.05 | -52
ACCURACY (OVERALL)
CLASSIFICATION
0.005 | 100 | 32 | 86%
| Type | Filters | Kernel | Rate |
|---|---|---|---|
| conv1d | 8 | 7 | - |
| conv1d | 16 | 3 | - |
| conv1d | 32 | 3 | - |
| dropout | - | - | 0.5 |
CLASSIFICATION
0.0005 | 50 | 86%
| Type | Filters | Kernel | Rate |
|---|---|---|---|
| dense | 128 | - | - |
| dropout | - | - | 0.1 |
| dense | 32 | - | - |
1 11/26/2025, 4:52:48 PM
spectr-dense-conv1d-5c3
PERFORMANCE
LATENCY
500 ms
RAM
200000 kB
ROM
200000 kB
Unused
TIME-SERIES INPUT
5000 ms
|
500 ms
|
Enabled
SPECTRAL-ANALYSIS
2048
ACCURACY (KERAS)
CLASSIFICATION
0.0005 | 50 | 93%
| Type | Filters | Kernel | Rate |
|---|---|---|---|
| dense | 128 | - | - |
| dropout | - | - | 0.1 |
| dense | 32 | - | - |
CLASSIFICATION
0.005 | 100 | 32
| Type | Filters | Kernel | Rate |
|---|---|---|---|
| conv1d | 8 | 7 | - |
| conv1d | 16 | 3 | - |
| conv1d | 32 | 3 | - |
| dropout | - | - | 0.5 |
0 11/26/2025, 4:36:07 PM
Training output
Hide
Click 'Run EON Tuner' to begin
