🖥
🖥
🖥
🖥
AugeLab Studio Manual
English
Ask or search…
K
Comment on page

Model EfficientNet

Model EfficientNet Node Documentation

The Model EfficientNet node in AugeLab Studio represents the EfficientNet model for deep learning tasks.

Node Overview

The Model EfficientNet node allows you to create an EfficientNet model for image classification. It has the following properties:
  • Node Title: Model EfficientNet
  • Node ID: OP_NODE_AI_EFFICIENTNET

Inputs

The Model EfficientNet node requires the following input:
  • Input Image: Connect an image data source to the node.

Outputs

The Model EfficientNet node outputs the created EfficientNet model.

Node Interaction

  1. 1.
    Drag and drop the Model EfficientNet node from the node library onto the canvas in AugeLab Studio.
  2. 2.
    Connect an image data source to the node.
  3. 3.
    Configure the node properties:
    • Model Type: Choose the EfficientNet model type from the dropdown list.
    • Input Size: Specify the input size of the images.
    • Pooling: Choose the pooling mode (Maximum, Average, or None).
  4. 4.
    The EfficientNet model will be created and outputted by the node.

Implementation Details

The Model EfficientNet node is implemented as a subclass of the NodeCNN base class. It overrides the evalAi method to create the EfficientNet model.
  • The Model EfficientNet node requires an image data source as input.
  • The node validates the input size and ensures it is greater than or equal to 32.
  • The node checks if the input images are in RGB format and raises an error if they are not.
  • The EfficientNet model is created using the specified model type, input size, and pooling mode.
  • The created model is added to the PNNModel object.
  • The PNNModel object, containing the EfficientNet model, is returned as the output.

Usage

  1. 1.
    Drag and drop the Model EfficientNet node from the node library onto the canvas in AugeLab Studio.
  2. 2.
    Connect an image data source to the node.
  3. 3.
    Configure the node properties:
    • Model Type: Choose the EfficientNet model type (B0, B1, B2, etc.).
    • Input Size: Specify the input size of the images.
    • Pooling: Choose the pooling mode (Maximum, Average, or None).
  4. 4.
    The EfficientNet model will be created based on the specified configuration.
  5. 5.
    Use the output EfficientNet model for image classification tasks or connect it to other nodes for further processing.

Notes

  • The Model EfficientNet node allows you to create EfficientNet models for image classification.
  • It expects the Keras library to be installed.
  • The node requires an image data source as input.
  • The input images should be in RGB format. Grayscale images are not supported.
  • The EfficientNet models have different complexity levels, denoted by B0, B1, B2, etc. Choose the appropriate model type based on your requirements.
  • The input size specifies the height and width dimensions of the input images. It should be greater than or equal to 32.
  • The pooling mode determines how the spatial dimensions of the output are reduced. Choose between Maximum, Average, or No pooling.
  • The output EfficientNet model can be used for image classification tasks.
  • Connect the output of the Model EfficientNet node to other nodes for further processing, such as training, evaluation, or prediction.
  • Experiment with different EfficientNet model types, input sizes, and pooling modes to achieve optimal results for your image classification tasks.
  • The Model EfficientNet node is particularly useful for computer vision tasks, such as object recognition or image classification.