Refactors examples to match diy-nn-refactor branch (#195)

* neural noteplayer example * example inspired by Eyeo 2019 Rebecca Fiebrink talk * rename musical mouse example * example tweaks and oscillator * adds refactoring examples * updates examples based in refactor * updates xor" * rm unused co2net * updates examples for regression * updates musical note example * adds experimental normalizationOptions * adds example of multi layered network * changes activations * adds simple classification example * changes .normalize() to .normalizeData() * updates all examples to handle array of .predict() or .classify() output
ml5js · Oct 2, 2019 · 1dd01a0 · 1dd01a0
1 parent 1dda807
commit 1dd01a0
Show file tree

Hide file tree

Showing 20 changed files with 487 additions and 2,490 deletions.
diff --git a/p5js/NeuralNetwork/NeuralNetwork_Simple-Classification/index.html b/p5js/NeuralNetwork/NeuralNetwork_Simple-Classification/index.html
@@ -0,0 +1,19 @@
+<html>
+
+<head>
+  <meta charset="UTF-8">
+  <title>Neural Network</title>
+
+  <script src="https://cdnjs.cloudflare.com/ajax/libs/p5.js/0.8.0/p5.min.js"></script>
+  <script src="https://cdnjs.cloudflare.com/ajax/libs/p5.js/0.8.0/addons/p5.dom.min.js"></script>
+  <script src="http://localhost:8080/ml5.js" type="text/javascript"></script>
+</head>
+
+<body>
+  <h1>Neural Network Classification</h1>
+  <label for="avatar">Load Model:</label>
+  <input type="file" id="load" multiple />
+  <script src="sketch.js"></script>
+</body>
+
+</html>
diff --git a/p5js/NeuralNetwork/NeuralNetwork_Simple-Classification/sketch.js b/p5js/NeuralNetwork/NeuralNetwork_Simple-Classification/sketch.js
@@ -0,0 +1,56 @@
+// Copyright (c) 2018 ml5
+//
+// This software is released under the MIT License.
+// https://opensource.org/licenses/MIT
+
+/* ===
+ml5 Example
+Image classification using MobileNet and p5.js
+This example uses a callback pattern to create the classifier
+=== */
+let nn;
+
+const options = {
+  inputs: 1,
+  outputs: 2,
+  task: 'classification',
+  debug: true
+}
+
+function setup(){
+  createCanvas(400, 400);
+  nn = ml5.neuralNetwork(options);
+
+
+  console.log(nn)
+  createTrainingData();
+  nn.normalizeData();
+
+  const trainingOptions={
+    batchSize: 24,
+    epochs: 32
+  }
+
+  nn.train(trainingOptions,finishedTraining); // if you want to change the training options
+  // nn.train(finishedTraining); // use the default training options
+}
+
+function finishedTraining(){
+
+  nn.classify([300], function(err, result){
+    console.log(result);
+  })
+
+}
+
+function createTrainingData(){
+    for(let i = 0; i < 400; i++){
+      if(i%2 === 0){
+        const x = random(0, width/2);
+        nn.addData( [x],  ['left'])
+      } else {
+        const x = random(width/2, width);
+        nn.addData( [x],  ['right'])
+      }
+    }
+}
diff --git a/p5js/NeuralNetwork/NeuralNetwork_Simple-Regression/sketch.js b/p5js/NeuralNetwork/NeuralNetwork_Simple-Regression/sketch.js
@@ -23,7 +23,7 @@ function setup(){
 
   console.log(nn)
   createTrainingData();
-  nn.data.normalize();
+  nn.normalizeData();
 
   const trainingOptions={
     batchSize: 24,
@@ -39,7 +39,7 @@ async function finishedTraining(){
   await Promise.all(
     [...new Array(400).fill(null).map( async (item, idx) =>  {
       let results = await nn.predict([idx]);
-      let prediction = results.outputs
+      let prediction = results[0]
       let x = idx
       let y = prediction.value
       fill(255, 0, 0);

diff --git a/p5js/NeuralNetwork/NeuralNetwork_XOR/sketch.js b/p5js/NeuralNetwork/NeuralNetwork_XOR/sketch.js
@@ -15,17 +15,18 @@ function setup() {
     inputs: 2,
     outputs: 1,
     learningRate: 0.25,
+    debug:true
     // hiddenUnits: 2
   }
   model = ml5.neuralNetwork(options);
 
   //model = ml5.neuralNetwork(2, 1);
-  model.data.addData([0, 0], [0]);
-  model.data.addData([1, 0], [1]);
-  model.data.addData([0, 1], [1]);
-  model.data.addData([1, 1], [0]);
-  model.data.normalize();
-  model.train({ epochs: 200 }, whileTraining, finishedTraining);
+  model.addData([0, 0], [0]);
+  model.addData([1, 0], [1]);
+  model.addData([0, 1], [1]);
+  model.addData([1, 1], [0]);
+  model.normalizeData();
+  model.train({ epochs: 50 }, whileTraining, finishedTraining);
 
 }
 
@@ -50,7 +51,11 @@ function finishedTraining() {
 }
 
 function gotResults(error, results) {
-  console.log(results.values[0]);
+  if(error){
+    console.log(err)
+    return
+  }
+  console.log(results[0].value);
 }
 
 function draw() {

diff --git a/p5js/NeuralNetwork/NeuralNetwork_basics/sketch.js b/p5js/NeuralNetwork/NeuralNetwork_basics/sketch.js
@@ -16,8 +16,7 @@ function setup() {
     inputs: 3,
     outputs: 2,
     task: 'regression',
-    // activationOutput: 'sigmoid',
-    // activationHidden: 'sigmoid'
+    debug:true
   };
   // Create Neural Network
   nn = ml5.neuralNetwork(options);
@@ -96,7 +95,7 @@ function trainModel() {
     //     output1: training_target[1],
     //   });
 
-    nn.data.addData(training_input, training_target)
+    nn.addData(training_input, training_target)
 
   }
 
@@ -105,7 +104,7 @@ function trainModel() {
     batchSize: 12
   }
   // Train
-  nn.data.normalize();
+  nn.normalizeData();
   nn.train(trainingOptions, finishedTraining);
 }
 
@@ -127,6 +126,7 @@ function predict() {
 function gotResults(error, results) {
   if (error) console.log(error);
   if (results) {
-    console.log(results.output);
+    console.log(results);
+    results.tensor.print()
   }
 }