TensorSpace.js
Getting Start
Basic Concepts
Model Preprocessing
Models
Layers
Merge Function
GlobalPooling2d
Global Pooling turns the feature map to 1*1. GlobalMaxPooling and GlobalAveragePooling both use this API.
Constructor
〔Method 1〕Create it directly
TSP.layers.GlobalPooling2d();
〔Method 2〕Use shape
TSP.layers.GlobalPooling2d( { shape : [ Int ] } );
Fig. 1 - GlobalPooling2d layer collapse and expand
Arguments

Name

Tag

Type

Instruction

Usage Notes and Examples

name

🔧

String Name of this layer. Highly recommend to arrange to make code more readable. name: "layerName"

color

⚙️🎨

color format Color of layer GlobalPooling2d default is blue #0074e4

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[]
filter_center_focusThe shape of input tensor, for example inputShape = [ 28, 28, 3 ] represents 3 feature maps and each one is 28 by 28.
filter_center_focusAfter model.init() data is available, otherwise is undefined.
.outputShape : Int[]
filter_center_focusThe shape of output tensor is 1-dimensional. 1️⃣
filter_center_focusdataFormat is channel last. for example outputShape = [ 3 ] represents the output through this layer has 3 outputs.
filter_center_focusAfter model.init() data is available, otherwise is undefined.
.neuralValue : Int[]
filter_center_focusThe intermediate raw data after this layer.
filter_center_focusAfter load and model.predict() data is available, otherwise is undefined.
.name : String
filter_center_focusThe custom name for this layer.
filter_center_focusOnce created, you can get it.
.layerType : String
filter_center_focusType of this layer, return a constant: string GlobalPooling2d.
filter_center_focusOnce created, you can get it.
Method
filter_center_focusThis method only used in Functional Model (Non-sequential, Graph structure).
filter_center_focusLink this layer to layer which is the previous layer.
filter_center_focusTo 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 conv2dLayer = new TSP.layers.Conv2d( {

    kernelSize: 2,
    filters: 16,
    strides: 1

} );

let globalPooling2dLayer = new TSP.layers.GlobalPooling2d();

globalPooling2dLayer.apply( conv2dLayer );
filter_center_focusClick on the layer directly to open it by interacting directly with the object in the 3D scene.
filter_center_focusIn code, calling the method to open it.
let globalPooling2dLayer = new TSP.layers.GlobalPooling2d();

model.add( globalPooling2dLayer );

// ... add more layers for model.

model.init();

// Call openLayer API to open layer.

globalPooling2dLayer.openLayer();
filter_center_focusTo close by interacting directly with objects in a 3D scene by clicking the close button.
filter_center_focus In code, calling the method to close it.
let globalPooling2dLayer = new TSP.layers.GlobalPooling2d();

model.add( globalPooling2dLayer );

// ... add more layers for model.

model.init();

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

globalPooling2dLayer.closeLayer();
Example
filter_center_focus Declare an instance of GlobalPooling2d to facilitate reuse
let globalPooling2dLayer = new TSP.layers.GlobalPooling2d( {

    name: "GlobalPooling2d1",
    initStatus: "open"

} );

model.add( globalPooling2dLayer );
filter_center_focusAdd GlobalPooling2d directly
model.add( new TSP.layers.GlobalPooling2d( {

    name: "GlobalPooling2d2",
    initStatus: "open"

} ) );
Use Case
When you add pooling layer with Keras | TensorFlow | tfjs in your model the corresponding API is Pooling2d in TensorSpace.
Framework Documentation
Keras keras.layers.GlobalMaxPooling2D(data_format='channels_last')
TensorFlow tf.keras.layers.GlobalMaxPool2D
TensorFlow.js tf.layers.globalMaxPooling2d (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/GlobalPooling2d.js