VGG.Builder (Deep Java Library 0.25.0 - model-zoo API)

java.lang.Object
- ai.djl.basicmodelzoo.cv.classification.VGG.Builder

Enclosing class:: VGG

public static final class VGG.Builder
extends java.lang.Object

The Builder to construct a VGG object.

Constructor Summary

Constructors
Constructor Description

Builder()

Method Summary

All Methods Instance Methods Concrete Methods
Modifier and Type	Method	Description
`ai.djl.nn.Block`	`build()`	Builds a `VGG` block.
`VGG.Builder`	`setConvArch(int[][] convArch)`	Sets the number of blocks according to the user.
`VGG.Builder`	`setNumLayers(int numLayers)`	Sets the number of layers.
`VGG.Builder`	`setOutSize(long outSize)`	Sets the size of the output.

Methods inherited from class java.lang.Object
clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

- Constructor Detail
  - Builder
```
public Builder()
```
- Method Detail
  - setNumLayers
```
public VGG.Builder setNumLayers(int numLayers)
```
    Sets the number of layers. It is equal to total sum of numConvs in convArch + 3.
    
    Parameters:
    
    numLayers - the number of layers in the network. default is 11.
    
    Returns:
    
    this Builder
  - setConvArch
```
public VGG.Builder setConvArch(int[][] convArch)
```
    Sets the number of blocks according to the user. It can be of multiple types, VGG-11, VGG-13, VGG-16, VGG-19.
    
    Parameters:
    
    convArch - 2-D array consisting of number of convolutions and the number of channels.
    
    Returns:
    
    this Builder
  - setOutSize
```
public VGG.Builder setOutSize(long outSize)
```
    Sets the size of the output.
    
    Parameters:
    
    outSize - the output size
    
    Returns:
    
    this Builder
  - build
```
public ai.djl.nn.Block build()
```
    Builds a VGG block.
    
    Returns:
    
    the VGG block