Edge Impulse Inc. / GPT-4o Cloud Coverage Experiment Public
Target: Cortex-M7 216MHz Clone this project
Experiments EON Tuner
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

No name set

Cortex-M7 216MHz

100 ms

340 kB

1024 kB

Filters

Status

DSP type

Model type

View

Data set

Variant

Sort

General

F1-score

Precision

Recall

23%
rgb-conv2d-c2b
PERFORMANCE
LATENCY
538 ms of 100 ms
Exceeds target by 438 ms
RAM
512 kB of 340 kB
Exceeds target by 172 kB
ROM
138 kB of 1024 kB
DSP NN Unused
IMAGE INPUT

160 |
160

IMAGE

RGB

REGRESSION

0.0005 | 100 | 23%

Type Filters Kernel Rate
conv2d 16 3 -
conv2d 32 3 -
conv2d 64 3 -
conv2d 128 3 -
dropout - - 0.25

5/31/2024, 3:13:09 PM

20%
rgb-conv2d-405
PERFORMANCE
LATENCY
32 ms of 100 ms
RAM
106 kB of 340 kB
ROM
37 kB of 1024 kB
DSP NN Unused
IMAGE INPUT

96 |
96

IMAGE

RGB

REGRESSION

0.0005 | 100 | 20%

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

5/31/2024, 2:30:30 PM

18%
rgb-conv2d-745
PERFORMANCE
LATENCY
129 ms of 100 ms
Exceeds target by 29 ms
RAM
189 kB of 340 kB
ROM
60 kB of 1024 kB
DSP NN Unused
IMAGE INPUT

96 |
96

IMAGE

RGB

REGRESSION

0.0001 | 10 | 18%

Type Filters Kernel Rate
conv2d 16 3 -
conv2d 32 3 -
conv2d 64 3 -
dropout - - 0.5

5/31/2024, 2:21:46 PM

grayscale-conv2d-b22
PERFORMANCE
LATENCY
100 ms
RAM
340 kB
ROM
1024 kB
Unused
IMAGE INPUT

224 |
224

IMAGE

Grayscale

REGRESSION

0.0001 | 100

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

grayscale-conv2d-777
PERFORMANCE
LATENCY
100 ms
RAM
340 kB
ROM
1024 kB
Unused
IMAGE INPUT

224 |
224

IMAGE

Grayscale

REGRESSION

0.0001 | 10

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

rgb-conv2d-787
PERFORMANCE
LATENCY
100 ms
RAM
340 kB
ROM
1024 kB
Unused
IMAGE INPUT

128 |
128

IMAGE

RGB

REGRESSION

0.0005 | 100

Type Filters Kernel Rate
conv2d 32 3 -
conv2d 64 3 -
conv2d 128 3 -
conv2d 256 3 -
dropout - - 0.25

rgb-conv2d-187
PERFORMANCE
LATENCY
100 ms
RAM
340 kB
ROM
1024 kB
Unused
IMAGE INPUT

96 |
96

IMAGE

RGB

REGRESSION

0.0001 | 100

Type Filters Kernel Rate
conv2d 16 3 -
conv2d 32 3 -
conv2d 64 3 -
dropout - - 0.5

grayscale-conv2d-713
PERFORMANCE
LATENCY
100 ms
RAM
340 kB
ROM
1024 kB
Unused
IMAGE INPUT

160 |
160

IMAGE

Grayscale

REGRESSION

0.0005 | 10

Type Filters Kernel Rate
conv2d 64 3 -
conv2d 128 3 -
conv2d 256 3 -
conv2d 512 3 -
dropout - - 0.5

rgb-conv2d-7b5
PERFORMANCE
LATENCY
100 ms
RAM
340 kB
ROM
1024 kB
Unused
IMAGE INPUT

96 |
96

IMAGE

RGB

REGRESSION

0.0005 | 100

Type Filters Kernel Rate
conv2d 64 3 -
conv2d 128 3 -
conv2d 256 3 -
conv2d 512 3 -
dropout - - 0.5

rgb-conv2d-d65
PERFORMANCE
LATENCY
100 ms
RAM
340 kB
ROM
1024 kB
Unused
IMAGE INPUT

224 |
224

IMAGE

RGB

REGRESSION

0.0005 | 10

Type Filters Kernel Rate
conv2d 32 3 -
conv2d 64 3 -
conv2d 128 3 -
dropout - - 0.5

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