LoRa & LLM-enabled Drive-through Kiosk AptilTag Detection - Impulses

Experiments

Name	Input	DSP Blocks	Learn Blocks	f32_V_Acc	f32_T_Acc	i8_V_Acc	i8_T_Acc	f32_Latency	i8_Latency	i8_RAM	i8_Flash	f32_RAM	f32_Flash
Impulse #4	320×320	Image	FOMO MobileNetV2 0.35	100.0%	88.9%	100.0%	-		7253 ms.	1.1M	81.3K	-	-	View impulse
Impulse #5	180×180	Image	FOMO MobileNetV2 0.35	100.0%	94.4%	80.0%	-	7 ms.	2825 ms.	391.0K	82.5K	1.4M	114.0K	View impulse
Impulse #6	96×96	Image	FOMO MobileNetV2 0.35	100.0%	94.4%	100.0%	-	7 ms.	436 ms.	137.7K	82.4K	435.2K	114.0K	View impulse
Impulse #7	48×48	Image	FOMO MobileNetV2 0.35	100.0%	83.3%	100.0%	-	7 ms.	181 ms.	59.3K	82.4K	121.3K	113.9K	View impulse

Impulse information

Tags - Impulse tags

Source - Impulse source (Manual vs EON Tuner)

Created by - The user who originally created this impulse

Key metrics

f32_V_Acc - Accuracy (float32, validation set)

f32_T_Acc - Accuracy (float32, test set)

i8_V_Acc - Accuracy (int8, validation set)

i8_T_Acc - Accuracy (int8, test set)

f32_Latency - float32 Latency for the complete impulse.

i8_Latency - int8 Latency for the complete impulse.

i8_RAM - int8 RAM for the complete impulse.

i8_Flash - int8 Flash for the complete impulse.

f32_RAM - float32 RAM for the complete impulse.

f32_Flash - float32 Flash for the complete impulse.

Input block config

Img_Height - Image height

Img_Width - Image width

Resize_Mode - Resize mode

Processing block config

Norm - Normalization

Col_dep - Image > Color depth (Processing Block #1)

Learn block config

Model - ML Model architecture (Learn Block #1)

Tc - Training cycles (Learn Block #1)

Lr - Learning rate (Learn Block #1)

Lo - Use learned optimizer? (Learn Block #1)

Acw - Auto-weight classes (Learn Block #1)

Data_Aug - Data augmentation (Learn Block #1)

Val_Size - Validation set size (Learn Block #1)

Val_Key - Split train/validation set on metadata key (Learn Block #1)

Mode - Visual / expert mode (Learn Block #1)

Thr_St - Score threshold (Learn Block #1)

Accuracy metrics

f32_V_Precision - float32 Precision (non-background) (validation set)

f32_V_Recall - float32 Recall (non-background) (validation set)

f32_V_F1 - float32 F1 Score (non-background) (validation set)

f32_T_Precision - float32 Precision (non-background) (test set)

f32_T_Recall - float32 Recall (non-background) (test set)

f32_T_F1 - float32 F1 Score (non-background) (test set)

i8_V_Precision - int8 Precision (non-background) (validation set)

i8_V_Recall - int8 Recall (non-background) (validation set)

i8_V_F1 - int8 F1 Score (non-background) (validation set)

Post-processing block config

No columns

Target device

Define your target device requirements to inform model optimizations and performance calculations. No device yet? Use the default settings which you can change at any time.

Target device

Processor family

Clock rate

| MHz

Max

Custom device name

Application budget

Specify the available RAM and ROM for the model's operation, along with the maximum allowed latency for your specific application. Not sure yet? Start with the defaults and modify them later on.

RAM

| KB

Max

ROM

| KB

Max

Latency

| ms

Max

Experiments

Impulse #4

Impulse #5

Impulse #6

Impulse #7