A god's gift, that's what I would call the the invention of Neural Network("God" here being the creator of the Neural Networks(Atheist here)). I am not a strong Maths person, actually not a maths person at all. But, for my little HAL9000 I had to learn the elvish language. Not like pick up books and sleep with them. Please, Neural Networks enthusiast don't need to do that to begin their adventure. I started with the Udacity course of it, which talked about Decision Trees, Regression, and finally Neural Networks(and a lot more which I skipped). And boy I saw that Math after a long time. Honestly I haven't done any calculus in like a year or two. But then all of those basic concepts came rushing back and made me realize it is not that tough. For those who are in it and have just begun, Gradient Descent IS Back Propagation. I had to search this to know that, I mean no one wrote or told this directly. And since that course was very theoretical, I had to look somewhere else and found the perfect place. Prefect because it is text(I love text, text over videos any day), and also that it is practical.With knowledge in hand and laziness in heart, I searched for an ANN library for JAVA and there it was, neuroph. Simple, easy and powerful. No, it became simple, easy and powerful after a lot of Googling. I find the lack of proper wiki disturbing.
Now, now, I have some basic idea how ANNs work, have a library to make them, and have successfully tested it, what should I do next? The answer is to make an effing service built on top of the Grid because people hate empty jar of cookies. I might not have told you before but we got the network(Grid not the neural) working, we have tested it, and it can send packets and do amazing stuff which it currently doesn't do. So, if you think you can make amazing stuff on it, ping me. So, services, well one thing we plan to do is to make a media streaming app. So, just listen to cool music, other people's cool music, without the internet. Think of it like Twitch, actually exactly like twitch, there goes our originality. Talking of originality, I thought of making a recommendation system based on what your taste in music is, and then suggesting streams based on that.
Plan:
To have a multilayer perceptron with 128 input neurons and 1 output and 64 being in the hidden layer. I will get the raw data from MP3 as shown in here, and as that raw data is sliced, I will be taking 128 data points from each slice. And for testing purposes I will just mark the slice data points as good or bad(0.0 or 1.0). So, a full song will create a huge data set with each row having 128 inputs and one output. That data set will be fed to the ANN and it will learn through back propagation.Execution:
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| package com.example.StreamerNeuron; | |
| import android.app.Activity; | |
| import android.media.*; | |
| import android.os.Bundle; | |
| import org.neuroph.core.data.DataSet; | |
| import org.neuroph.nnet.MultiLayerPerceptron; | |
| import org.neuroph.nnet.learning.MomentumBackpropagation; | |
| import org.neuroph.util.TransferFunctionType; | |
| import java.io.IOException; | |
| import java.nio.ByteBuffer; | |
| public class MyActivity extends Activity { | |
| protected MediaExtractor extractor; | |
| protected MediaCodec codec; | |
| protected int inputBufIndex; | |
| boolean doStop=false; | |
| MultiLayerPerceptron mlp; | |
| DataSet datset; | |
| MomentumBackpropagation learningRule ; | |
| private void decodeLoop(String file, boolean evil) throws IOException { | |
| ByteBuffer[] codecInputBuffers; | |
| ByteBuffer[] codecOutputBuffers; | |
| // extractor gets information about the stream | |
| extractor = new MediaExtractor(); | |
| try { | |
| extractor.setDataSource(file); | |
| } catch (Exception e) { | |
| return; | |
| } | |
| MediaFormat format = extractor.getTrackFormat(0); | |
| String mime = format.getString(MediaFormat.KEY_MIME); | |
| // the actual decoder | |
| codec = MediaCodec.createDecoderByType(mime); | |
| codec.configure(format, null /* surface */, null /* crypto */, 0 /* flags */); | |
| codec.start(); | |
| codecInputBuffers = codec.getInputBuffers(); | |
| codecOutputBuffers = codec.getOutputBuffers(); | |
| extractor.selectTrack(0); | |
| // start decoding | |
| final long kTimeOutUs = 500; | |
| MediaCodec.BufferInfo info = new MediaCodec.BufferInfo(); | |
| boolean sawInputEOS = false; | |
| boolean sawOutputEOS = false; | |
| int noOutputCounter = 0; | |
| int noOutputCounterLimit = 50; | |
| int packetsRecieved = 0; | |
| int interval =0; | |
| while (!sawOutputEOS && | |
| noOutputCounter < | |
| noOutputCounterLimit | |
| && !doStop) { | |
| noOutputCounter++; | |
| if (!sawInputEOS) { | |
| inputBufIndex = codec.dequeueInputBuffer(kTimeOutUs); | |
| if (inputBufIndex >= 0) { | |
| ByteBuffer dstBuf = codecInputBuffers[inputBufIndex]; | |
| int sampleSize = | |
| extractor.readSampleData(dstBuf, 0 /* offset */); | |
| long presentationTimeUs = 0; | |
| if (sampleSize < | |
| 0) { | |
| sawInputEOS = true; | |
| sampleSize = 0; | |
| } else { | |
| presentationTimeUs = extractor.getSampleTime(); | |
| } // can throw illegal state exception (???) | |
| codec.queueInputBuffer( | |
| inputBufIndex, | |
| 0 /* offset */, | |
| sampleSize, | |
| presentationTimeUs, | |
| sawInputEOS ? MediaCodec.BUFFER_FLAG_END_OF_STREAM : 0); | |
| if (!sawInputEOS) { | |
| extractor.advance(); | |
| } | |
| } | |
| } | |
| int res = codec.dequeueOutputBuffer(info, kTimeOutUs); | |
| if (res >= 0) { | |
| if (info.size > | |
| 0) { | |
| noOutputCounter = 0; | |
| } | |
| int outputBufIndex = res; | |
| ByteBuffer buf = codecOutputBuffers[outputBufIndex]; | |
| final byte[] chunk = new byte[info.size]; | |
| buf.get(chunk); | |
| buf.clear(); | |
| if (chunk.length > | |
| 0) { | |
| packetsRecieved++; | |
| if(packetsRecieved==2) | |
| interval=chunk.length/128; | |
| double[] train = new double[128]; | |
| int counter =0; | |
| for (int i=0; i<chunk.length;i++) { | |
| Double db=chunk[i]*1.0 + 127; | |
| if(packetsRecieved>2) | |
| if(counter<128 && i%interval==0){ | |
| train[counter]=db; | |
| counter++; | |
| } | |
| } | |
| if(packetsRecieved>=70&&packetsRecieved<=150) | |
| datset.addRow(train, evil?new double[]{0.0}:new double[]{1.0}); | |
| } | |
| codec.releaseOutputBuffer(outputBufIndex, false /* render */); | |
| if ((info.flags & MediaCodec.BUFFER_FLAG_END_OF_STREAM) != 0) { | |
| sawOutputEOS = true; | |
| } | |
| } else if (res == MediaCodec.INFO_OUTPUT_BUFFERS_CHANGED) { | |
| codecOutputBuffers = codec.getOutputBuffers(); | |
| } | |
| } | |
| mlp.learn(datset,learningRule); | |
| System.out.println("learnt"); | |
| relaxResources(true); | |
| } | |
| private void relaxResources(Boolean release) { | |
| if (codec != null) { | |
| if (release) { | |
| codec.stop(); | |
| codec.release(); | |
| codec = null; | |
| } | |
| } | |
| } | |
| boolean isNew(DataSet dat, double[] tst){ | |
| double error=0; | |
| double[] errorMatrix = new double[dat.getRows().size()]; | |
| for(int i=0; i<dat.getRows().size();i++){ | |
| for(int j=0; j< 128; j++){ | |
| error+=Math.abs(dat.getRowAt(i).getInput()[j]-tst[j]); | |
| } | |
| errorMatrix[i]=error/128; | |
| error=0; | |
| } | |
| int aha=0; | |
| for(int k=0; k<errorMatrix.length ; k++) | |
| if(errorMatrix[k]<6) | |
| aha++; | |
| return (aha<(0.1*dat.getRows().size())); | |
| } | |
| @Override | |
| public void onCreate(Bundle savedInstanceState) { | |
| super.onCreate(savedInstanceState); | |
| setContentView(R.layout.main); | |
| mlp = new MultiLayerPerceptron(TransferFunctionType.SIGMOID, 128,64,1); | |
| datset= new DataSet(128,1); | |
| learningRule= new MomentumBackpropagation(); | |
| learningRule.setLearningRate(0.2); | |
| learningRule.setMaxError(0.01); | |
| learningRule.setMomentum(0.7); | |
| new Thread( | |
| new Runnable() { | |
| @Override | |
| public void run() { | |
| try { | |
| decodeLoop("/sdcard/heavyTune.mp3",true); | |
| decodeLoop("/sdcard/tt.mp3",false); | |
| decodeLoop2("/sdcard/testTune.mp3"); | |
| } catch (IOException e) { | |
| e.printStackTrace(); | |
| } | |
| } | |
| } | |
| ).start(); | |
| } | |
| private void decodeLoop2(String file) throws IOException { | |
| ByteBuffer[] codecInputBuffers; | |
| ByteBuffer[] codecOutputBuffers; | |
| // extractor gets information about the stream | |
| extractor = new MediaExtractor(); | |
| try { | |
| extractor.setDataSource(file); | |
| } catch (Exception e) { | |
| return; | |
| } | |
| MediaFormat format = extractor.getTrackFormat(0); | |
| String mime = format.getString(MediaFormat.KEY_MIME); | |
| // the actual decoder | |
| codec = MediaCodec.createDecoderByType(mime); | |
| codec.configure(format, null /* surface */, null /* crypto */, 0 /* flags */); | |
| codec.start(); | |
| codecInputBuffers = codec.getInputBuffers(); | |
| codecOutputBuffers = codec.getOutputBuffers(); | |
| extractor.selectTrack(0); | |
| // start decoding | |
| final long kTimeOutUs = 500; | |
| MediaCodec.BufferInfo info = new MediaCodec.BufferInfo(); | |
| boolean sawInputEOS = false; | |
| boolean sawOutputEOS = false; | |
| int noOutputCounter = 0; | |
| int noOutputCounterLimit = 50; | |
| int packetsRecieved = 0; | |
| int interval =0; | |
| while (!sawOutputEOS && | |
| noOutputCounter < | |
| noOutputCounterLimit | |
| && !doStop) { | |
| noOutputCounter++; | |
| if (!sawInputEOS) { | |
| inputBufIndex = codec.dequeueInputBuffer(kTimeOutUs); | |
| if (inputBufIndex >= 0) { | |
| ByteBuffer dstBuf = codecInputBuffers[inputBufIndex]; | |
| int sampleSize = | |
| extractor.readSampleData(dstBuf, 0 /* offset */); | |
| long presentationTimeUs = 0; | |
| if (sampleSize < | |
| 0) { | |
| sawInputEOS = true; | |
| sampleSize = 0; | |
| } else { | |
| presentationTimeUs = extractor.getSampleTime(); | |
| } // can throw illegal state exception (???) | |
| codec.queueInputBuffer( | |
| inputBufIndex, | |
| 0 /* offset */, | |
| sampleSize, | |
| presentationTimeUs, | |
| sawInputEOS ? MediaCodec.BUFFER_FLAG_END_OF_STREAM : 0); | |
| if (!sawInputEOS) { | |
| extractor.advance(); | |
| } | |
| } | |
| } | |
| int res = codec.dequeueOutputBuffer(info, kTimeOutUs); | |
| if (res >= 0) { | |
| if (info.size > | |
| 0) { | |
| noOutputCounter = 0; | |
| } | |
| int outputBufIndex = res; | |
| ByteBuffer buf = codecOutputBuffers[outputBufIndex]; | |
| final byte[] chunk = new byte[info.size]; | |
| buf.get(chunk); | |
| buf.clear(); | |
| if (chunk.length > | |
| 0) { | |
| packetsRecieved++; | |
| if(packetsRecieved==2) | |
| interval=chunk.length/128; | |
| double[] train = new double[128]; | |
| int counter =0; | |
| for (int i=0; i<chunk.length;i++) { | |
| Double db=20*(Math.log10(Math.abs(chunk[i]))); | |
| if(db.isInfinite()) | |
| db=0.0; | |
| if(packetsRecieved>2) | |
| if(counter<128 && i%interval==0){ | |
| train[counter]=db; | |
| counter++; | |
| } | |
| } | |
| if(isNew(datset,train)) | |
| System.out.println("Yes it is new"); | |
| mlp.setInput(train); | |
| mlp.calculate(); | |
| System.out.println("Output is "+mlp.getOutput()[0]); | |
| } | |
| codec.releaseOutputBuffer(outputBufIndex, false /* render */); | |
| if ((info.flags & MediaCodec.BUFFER_FLAG_END_OF_STREAM) != 0) { | |
| sawOutputEOS = true; | |
| } | |
| } else if (res == MediaCodec.INFO_OUTPUT_BUFFERS_CHANGED) { | |
| codecOutputBuffers = codec.getOutputBuffers(); | |
| } | |
| } | |
| relaxResources(true); | |
| } | |
| } |
No comments:
Post a Comment