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
Cortex-M4F 80MHz
100 ms
128 kB
1024 kB
Filters
Status
DSP type
Model type
View
Data set
Variant
Sort
General
F1-score
Precision
Recall
PERFORMANCE
LATENCY
258 ms of
100 ms
Exceeds target by 158 ms
RAM
50 kB of
128 kB
ROM
46 kB of
1024 kB
DSP
NN
Unused
IMAGE INPUT
64
|
64
IMAGE
RGB
ACCURACY (KERAS)
CLASSIFICATION
0.0005 | 10 | 28%
| Type | Filters | Kernel | Rate |
|---|---|---|---|
| conv2d | 8 | 3 | - |
| conv2d | 16 | 3 | - |
| dropout | - | - | 0.25 |
4/18/2023, 1:26:04 PM
PERFORMANCE
LATENCY
224 ms of
100 ms
Exceeds target by 124 ms
RAM
58 kB of
128 kB
ROM
114 kB of
1024 kB
DSP
NN
Unused
IMAGE INPUT
96
|
96
IMAGE
Grayscale
ACCURACY (KERAS-TRANSFER-IMAGE)
TRANSFER LEARNING (IMAGES)
0.0005 | 20 | 22%
MobileNetV1 0.1
64
|
0.5
|
4/18/2023, 1:25:51 PM
PERFORMANCE
LATENCY
183 ms of
100 ms
Exceeds target by 83 ms
RAM
27 kB of
128 kB
ROM
40 kB of
1024 kB
DSP
NN
Unused
IMAGE INPUT
32
|
32
IMAGE
RGB
ACCURACY (KERAS)
CLASSIFICATION
0.0005 | 10 | 0%
| Type | Filters | Kernel | Rate |
|---|---|---|---|
| conv2d | 16 | 3 | - |
| conv2d | 32 | 3 | - |
| dropout | - | - | 0.25 |
4/18/2023, 1:25:53 PM
PERFORMANCE
LATENCY
111 ms of
100 ms
Exceeds target by 11 ms
RAM
19 kB of
128 kB
ROM
52 kB of
1024 kB
DSP
NN
Unused
IMAGE INPUT
32
|
32
IMAGE
Grayscale
ACCURACY (KERAS)
CLASSIFICATION
0.0005 | 10 | 0%
| Type | Filters | Kernel | Rate |
|---|---|---|---|
| conv2d | 8 | 3 | - |
| conv2d | 16 | 3 | - |
| conv2d | 32 | 3 | - |
| conv2d | 64 | 3 | - |
| dropout | - | - | 0.5 |
4/18/2023, 1:24:57 PM
Training output
Hide
Click 'Run EON Tuner' to begin
