dawndj / CASA0018 Public

Transfer learning settings

Training settings

Training processor

Please provide a valid training processor option

Number of training cycles

Number of training cycles should be a number

Learning rate

Learning rate should be a number

Model size

Use pretrained weights

Freeze % of layers

Freeze % of layers should be a number

Last layers

Last layers should not be empty

Data augmentation

Data augmentation should not be empty

Valid options: flip, crop, brightness

Advanced training settings

Validation set size

Please provide a valid number for the train/validate split (between 0 and 1)

Split train/validation set on metadata key

Profile int8 model

Batch size

Batch size should be a number

Early stopping

Early stopping patience

Early stopping patience should be a number

Early stopping min. delta

Early stopping min. delta should be a number

Neural network architecture

Save

Input layer (27,648 features)

EfficientNet

Output layer (4 classes)

Model

Model version:

Last training performance (validation set)

Accuracy

76.9%

Loss

0.58

Confusion matrix (validation set)

Metrics (validation set)

Metric	Value
Area under ROC Curve	0.96
Weighted average Precision	0.86
Weighted average Recall	0.77
Weighted average F1 score	0.76

Data explorer (classified samples)

On-device performance

Engine:

Inferencing time

59760 ms.

Peak RAM usage

1.3M

Flash usage

4.3M

Last training performance (validation set)

Accuracy

84.6%

Loss

0.54

Confusion matrix (validation set)

Metrics (validation set)

Metric	Value
Area under ROC Curve	0.97
Weighted average Precision	0.89
Weighted average Recall	0.85
Weighted average F1 score	0.83

Data explorer (classified samples)

On-device performance

Engine:

Inferencing time

858835 ms.

Peak RAM usage

2.6M

Flash usage

15.4M

Every learning block has a threshold. This can be the minimum confidence that a neural network needs to have, or the maximum anomaly score before a sample is tagged as an anomaly. You can configure these thresholds to tweak the sensitivity of these learning blocks. This affects both live classification and model testing.

Transfer learning

Minimum confidence rating

Should be numeric

These users will be notified over email when this job finishes.

	Name
	d dawndj

Configure your target device for model performance calculations, and to enable target specific optimizations.

We're always looking for ways to improve Edge Impulse. If you have any feedback, please let us know!

Subject

This field is required

How was your experience?

This field is required

You'll need a free Edge Impulse account to clone this project. Create an account to add your own data, modify models, and join the largest community of embedded machine learning developers!

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

YEARLY

$400 /month

billed annually

SAVE 15%

MONTHLY

$475 /month

billed monthly

First name*

Please enter your first name

Last name*

Please enter your last name

Company email*

Please enter a valid email address

Company name*

Please enter your company name

Country*

Could you please provide more details about your use case, including any specific hardware requirements and the challenges you're currently facing?*

Please enter your use case details

Edge Impulse needs the contact information you provide to us to contact you about our products and services. You may unsubscribe from these communications at any time. For information on how to unsubscribe, as well as our privacy practices and commitment to protecting your privacy, please review our Privacy Policy.

Transfer learning settings

Training settings

Augmentation settings

Advanced training settings

Neural network architecture

Model

Last training performance (validation set)

Accuracy

Loss

Confusion matrix (validation set)

Metrics (validation set)

Data explorer (classified samples)

Settings

On-device performance

Inferencing time

Peak RAM usage

Flash usage

Last training performance (validation set)

Accuracy

Loss

Confusion matrix (validation set)

Metrics (validation set)

Data explorer (classified samples)

Settings

On-device performance

Inferencing time

Peak RAM usage

Flash usage