Tabnine Logo
WeightInit
Code IndexAdd Tabnine to your IDE (free)

How to use
WeightInit
in
org.deeplearning4j.nn.weights

Best Java code snippets using org.deeplearning4j.nn.weights.WeightInit (Showing top 4 results out of 315)

origin: Waikato/wekaDeeplearning4j

@Test
public void testWeightInit() throws Exception {
 List<WeightInit> skipWeightInits = new ArrayList<>();
 skipWeightInits.add(WeightInit.IDENTITY);
 for (WeightInit wi : WeightInit.values()) {
  if (skipWeightInits.contains(wi)) {
   continue;
  }
  NeuralNetConfiguration conf = new NeuralNetConfiguration();
  conf.setWeightInit(wi);
  checkAppliedParameters(conf, wi, BaseLayer::getWeightInit);
 }
}
origin: org.deeplearning4j/deeplearning4j-play

if (nParams > 0) {
  WeightInit wi = bl.getWeightInit();
  String str = wi.toString();
  if (wi == WeightInit.DISTRIBUTION) {
    str += bl.getDist();
origin: org.deeplearning4j/deeplearning4j-play_2.10

if (nParams > 0) {
  WeightInit wi = bl.getWeightInit();
  String str = wi.toString();
  if (wi == WeightInit.DISTRIBUTION) {
    str += bl.getDist();
origin: org.deeplearning4j/deeplearning4j-play_2.11

if (nParams > 0) {
  WeightInit wi = bl.getWeightInit();
  String str = wi.toString();
  if (wi == WeightInit.DISTRIBUTION) {
    str += bl.getDist();
org.deeplearning4j.nn.weightsWeightInit

Javadoc

Weight initialization scheme

DISTRIBUTION: Sample weights from a provided distribution

ZERO: Generate weights as zeros

SIGMOID_UNIFORM: A version of XAVIER_UNIFORM for sigmoid activation functions. U(-r,r) with r=4*sqrt(6/(fanIn + fanOut))

UNIFORM: Uniform U[-a,a] with a=1/sqrt(fanIn). "Commonly used heuristic" as per Glorot and Bengio 2010

XAVIER: As per Glorot and Bengio 2010: Gaussian distribution with mean 0, variance 2.0/(fanIn + fanOut)

XAVIER_UNIFORM: As per Glorot and Bengio 2010: Uniform distribution U(-s,s) with s = sqrt(6/(fanIn + fanOut))

XAVIER_FAN_IN: Similar to Xavier, but 1/fanIn -> Caffe originally used this.

XAVIER_LEGACY: Xavier weight init in DL4J up to 0.6.0. XAVIER should be preferred.

RELU: He et al. (2015), "Delving Deep into Rectifiers". Normal distribution with variance 2.0/nIn

RELU_UNIFORM: He et al. (2015), "Delving Deep into Rectifiers". Uniform distribution U(-s,s) with s = sqrt(6/fanIn)

Most used methods

  • toString
  • values

Popular in Java

  • Reading from database using SQL prepared statement
  • getApplicationContext (Context)
  • getSharedPreferences (Context)
  • getOriginalFilename (MultipartFile)
    Return the original filename in the client's filesystem.This may contain path information depending
  • File (java.io)
    An "abstract" representation of a file system entity identified by a pathname. The pathname may be a
  • URLEncoder (java.net)
    This class is used to encode a string using the format required by application/x-www-form-urlencoded
  • Collection (java.util)
    Collection is the root of the collection hierarchy. It defines operations on data collections and t
  • Reference (javax.naming)
  • Table (org.hibernate.mapping)
    A relational table
  • SAXParseException (org.xml.sax)
    Encapsulate an XML parse error or warning.> This module, both source code and documentation, is in t
  • Top Vim plugins
Tabnine Logo
  • Products

    Search for Java codeSearch for JavaScript code
  • IDE Plugins

    IntelliJ IDEAWebStormVisual StudioAndroid StudioEclipseVisual Studio CodePyCharmSublime TextPhpStormVimGoLandRubyMineEmacsJupyter NotebookJupyter LabRiderDataGripAppCode
  • Company

    About UsContact UsCareers
  • Resources

    FAQBlogTabnine AcademyTerms of usePrivacy policyJava Code IndexJavascript Code Index
Get Tabnine for your IDE now