Adiuvo_BrainChip_VWW - Transfer learning

Edge Impulse Experts / Adiuvo_BrainChip_VWW Public

Target: BrainChip AKD1000 or AKD1500 Clone this project

Brainchip Akida models are not available. We've temporarily suspended training new Akida models. Existing models still work (incl. deployment), but retraining is not available. More info.

Neural Network settings

Training settings

Number of training cycles

Please provide a valid number of training cycles (numeric only)

Learning rate

Please provide a valid number for the learning rate (between 0 and 1)

Training processor

Please provide a valid training processor option

Data augmentation

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

Batch size

Auto-weight classes

Profile int8 model

Neural network architecture

Save

1
2
import math, random
 
 
הההההההההההההההההההההההההההההההההההההההההההההההההההההההההההההההההההההההההההההההההההההההההההההההההההההההההההההההההההההההההההההההההההההההההההההההההההההההההההההההההההההההההההההההההההההההההההההההההההההההההההההההההההההההההההההההההההההההההההההההההההההההההההההההה
XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX

Input layer (27,648 features)

AkidaNet (alpha=0.25) @160x160x3 (no final dense layer, 0.1 dropout)

Output layer (2 classes)

Model

Did you know? You can customize your model through the Expert view (click on to switch),
or can even bring your own model (in PyTorch, Keras or scikit-learn).

Model	Author
EfficientNet Community A collection of high-end image classification models, with transfer learning weights, scaling from 4 to 28M parameters. Great for complex usecases on Linux.	Edge Impulse Inc.

The backbone is the foundational element of a neural network model, responsible for extracting meaningful features from input data, enabling subsequent parts to perform anomaly scoring or classification.

Description	Author
EfficientNet V2B0 Uses around 339K RAM based on your input size, and between 240-1675K ROM depending on the number of layers, with default compiler settings. Supports both RGB and grayscale.	Edge Impulse
MobileNetV2 0.35 Uses around 249K RAM based on your input size, and between 69-134K ROM depending on the number of layers, with default compiler settings. Supports both RGB and grayscale.	Edge Impulse
MobileNetV2 0.50 Uses around 256K RAM based on your input size, and between 78-168K ROM depending on the number of layers, with default compiler settings. Supports both RGB and grayscale.	Edge Impulse
MobileNetV2 0.75 Uses around 489K RAM based on your input size, and between 109-266K ROM depending on the number of layers, with default compiler settings. Supports both RGB and grayscale.	Edge Impulse
MobileNetV2 1.0 Uses around 499K RAM based on your input size, and between 126-372K ROM depending on the number of layers, with default compiler settings. Supports both RGB and grayscale.	Edge Impulse
MobileNetV2 0.1 Uses around 238K RAM based on your input size, and 58K ROM, with default compiler settings. Supports both RGB and grayscale.	Edge Impulse

The scoring function operates on the features extracted by the backbone, and returns anomaly scores for each segment of the image.

Description	Author	Recommended
AkidaNet (alpha=0.25) @160x160x3 A pre-trained multi-layer convolutional network designed to efficiently classify images.	Edge Impulse
AkidaNet (alpha=0.50) @160x160x3 A pre-trained multi-layer convolutional network designed to efficiently classify images.	Edge Impulse
AkidaNet (alpha=1.00) @160x160x3 A pre-trained multi-layer convolutional network designed to efficiently classify images.	Edge Impulse
AkidaNet (alpha=0.25) @224x224x3 A pre-trained multi-layer convolutional network designed to efficiently classify images.	Edge Impulse
AkidaNet (alpha=0.50) @224x224x3 A pre-trained multi-layer convolutional network designed to efficiently classify images.	Edge Impulse
AkidaNet (alpha=1.00) @224x224x3 A pre-trained multi-layer convolutional network designed to efficiently classify images.	Edge Impulse
EfficientNet B0 Transfer learning model based on efficientnetb0_notop.h5 weights. This is a much larger model than MobileNet for Linux devices and accelerators.	Edge Impulse
EfficientNet A collection of high-end image classification models, with transfer learning weights, scaling from 4 to 28M parameters. Great for complex usecases on Linux.	Edge Impulse
NVIDIA TAO Image Classification Image classification model for general purpose use. Configurable backbones optimized for targets from MCU to GPU. Only supports RGB images. Pre-trained weights only support 224x224 resolution. Image width and height must be greater than 32. Training requires GPU.	Edge Impulse

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

	Name
	Joshua Buck Edge Impulse staff

Neural Network settings

Training settings

Augmentation settings

Advanced training settings

Neural network architecture

Model