Layer - Cropping2d

Cropping2d

Apply cropping to the two-dimentional input.

Constructor

〔Method 1〕Use cropping

TSP.layers.Cropping2d( { cropping : [ [2, 2], [1, 1] ] } );

〔Method 2〕Use shape

TSP.layers.Cropping2d( { shape : [ Int, Int, Int ] } );

Fig. 1 - Cropping2d layer collapse and expand

Arguments

Name Tag	Type	Instruction	Usage Notes and Examples
cropping ⭐📦️	[Int[]]	Cropping value	cropping : [ [2, 3], [1, 2] ] means to crop at left=2, right=3, top=1, bottom=2
name 🔧	String	Name of this layer. Highly recommend to arrange to make code more readable.	name: "layerName"
color ⚙️🎨️	color format	Color of layer	Cropping2d default is #cefc86
closeButton ⚙️🎨️	Dict	Close button appearance control dict, more about close button	display : Boolean. true[default] Show button, false Hide button ratio : Int. Times to normal size, default is 1 For example, 2 means twice the normal size
initStatus ⚙️️🎦	String	Layer status at beginning. Open or Close	close[default] : Closed at beginning
animation- TimeRatio ⚙️🎦️	Int	The speed of open and close animation	Integer for multiple of speed. For example, 2 for 2 times of basic speed.

Properties

.inputShape : Int[]

The shape of input tensor, for example inputShape = [ 28, 28, 3 ] represents 3 feature maps and each one is 28 by 28.

After model.init() data is available, otherwise is undefined.

.outputShape : Int[]

The shape of output tensor is 3-dimensional. 3️⃣

dataFormat is channel last. for example outputShape = [ 32, 32, 4 ] represents the output through this layer has 4 feature maps and each one is 32 by 32

After model.init() data is available, otherwise is undefined.

.neuralValue : Int[]

The intermediate raw data after this layer.

After load and model.predict() data is available, otherwise is undefined.

.name : String

The custom name for this layer.

Once created, you can get it.

.layerType : String

Type of this layer, return a constant: string Cropping2d.

Once created, you can get it.

Method

.apply( layer ) : void

This method only used in Functional Model (Non-sequential, Graph structure).

Link this layer to layer which is the previous layer.

To crete a link between this layer and the previous layer. You don't need to use this method specifically to create links in Sequential Model; Instead, you can simply add layers along the lines of Keras or TensorFlow.js build the model syntax.

let inputLayer = new TSP.layers.GreyscaleInput( {

    shape: [28, 28]

} );

let croppingLayer = new TSP.layers.Cropping2d( {

    cropping : [ [2, 2], [1, 1] ]

} );

croppingLayer.apply( inputLayer );

.openLayer() : void

Click on the layer directly to open it by interacting directly with the object in the 3D scene.

In code, calling the method to open it.

let croppingLayer = new TSP.layers.Cropping2d( {

    // configure some parameters for Cropping2d.

} );

model.add( croppingLayer );

// ... add more layers for model.

model.init();

// Call openLayer API to open layer.

croppingLayer.openLayer();

.closeLayer() : void

To close by interacting directly with objects in a 3D scene by clicking the close button.

In code, calling the method to close it.

let croppingLayer = new TSP.layers.Cropping2d( {

    // configure some parameters for Cropping2d.

} );

model.add( croppingLayer );

// ... add more layers for model.

model.init();

// If this layer already opened, call closeLayer API to close layer.

croppingLayer.closeLayer();

Example

Declare an instance of Cropping2d to facilitate reuse

let croppingLayer = new TSP.layers.Cropping2d( {

    cropping : [ [2, 2], [1, 1] ],
    animationTimeRatio: 2,
    name: "cropping2d1",
    opacityRatio: 2
    initStatus: "open"

} );

model.add( croppingLayer );

Add Cropping2d directly

model.add(new TSP.layers.Cropping2d( {

    cropping : [ [2, 2], [1, 1] ],
    name: "cropping2d2"

} ));

Use Case

When you add cropping layer with Keras | TensorFlow | tfjs in your model the corresponding API is Cropping2d in TensorSpace.

Framework	Documentation
Keras️	keras.layers.Cropping2D(cropping=((0, 0), (0, 0)))
TensorFlow	tf.keras.layers.Cropping2D
TensorFlow.js️	tf.layers.cropping2D (config)

Tag Lookup

Tag Icon	Meaning	Instruction
⭐️	Required	Must be provided, cannot be empty. Meanwhile constructor works properly if this arguments provided. Control arguments use default value.
🔧	Suggest	Recommended for giving. The API can work without them.
⚙️	Optional	As an auxiliary adjustment parameter when used, selectively added according to the specific situation The parameters here have no effect on the structure of the layer (3D visualized form).
📦	Model	Configure the properties of the Layer. It changes the output shape.
🎨	Style	Override the properties in TSP.model (model configuration)
🎦	Animation	Override the properties in TSP.model (model configuration)

Source Code

tensorspace/src/layer/intermediate/Cropping2d.js