Question

private static String[] testFiles = new String[]     {"img01.JPG","img02.JPG","img03.JPG","img04.JPG","img06.JPG","img07.JPG","img05.JPG"};
 // private static String testFilespath = "/home/student/Desktop/images";
private static String testFilespath ="hdfs://localhost:54310/user/root/images";
//private static String indexpath = "/home/student/Desktop/indexDemo";
private static  String testExtensive="/home/student/Desktop/images";

public static class MapClass extends MapReduceBase
implements Mapper<Text, Text, Text, Text> {
private Text input_image = new Text();
private Text input_vector = new Text();
    @Override
public void map(Text key, Text value,OutputCollector<Text, Text> output,Reporter       reporter) throws IOException {

 System.out.println("CorrelogramIndex Method:");  
       String featureString;
int MAXIMUM_DISTANCE = 16;
AutoColorCorrelogram.Mode mode = AutoColorCorrelogram.Mode.FullNeighbourhood;
for (String identifier : testFiles) {
            try (FileInputStream fis = new FileInputStream(testFilespath + "/" +    identifier)) {
  //Document doc = builder.createDocument(fis, identifier);
//FileInputStream imageStream = new FileInputStream(testFilespath + "/" + identifier);
BufferedImage bimg = ImageIO.read(fis);
 AutoColorCorrelogram vd = new AutoColorCorrelogram(MAXIMUM_DISTANCE, mode);
                 vd.extract(bimg);
               featureString = vd.getStringRepresentation();
               double[] bytearray=vd.getDoubleHistogram();
              System.out.println("image: "+ identifier + " " + featureString );

        }
             System.out.println(" ------------- ");
input_image.set(identifier);
input_vector.set(featureString);
   output.collect(input_image, input_vector);
              }

     }
   }

  public static class Reduce extends MapReduceBase
  implements Reducer<Text, Text, Text, Text> {

    @Override
public void reduce(Text key, Iterator<Text> values,
                   OutputCollector<Text, Text> output, 
                   Reporter reporter) throws IOException {
  String out_vector="";

  while (values.hasNext()) {
   out_vector.concat(values.next().toString());
 }
  output.collect(key, new Text(out_vector));
  }
}

static int printUsage() {
System.out.println("image_mapreduce [-m <maps>] [-r <reduces>] <input> <output>");
ToolRunner.printGenericCommandUsage(System.out);
return -1;
}


@Override
  public int run(String[] args) throws Exception {
JobConf conf = new JobConf(getConf(), image_mapreduce.class);
conf.setJobName("image_mapreduce");

// the keys are words (strings)
conf.setOutputKeyClass(Text.class);
// the values are counts (ints)
conf.setOutputValueClass(Text.class);

conf.setMapperClass(MapClass.class);        
//  conf.setCombinerClass(Reduce.class);
conf.setReducerClass(Reduce.class);

List<String> other_args = new ArrayList<String>();
for(int i=0; i < args.length; ++i) {
  try {
    if ("-m".equals(args[i])) {
      conf.setNumMapTasks(Integer.parseInt(args[++i]));
    } else if ("-r".equals(args[i])) {
      conf.setNumReduceTasks(Integer.parseInt(args[++i]));
    } else {
      other_args.add(args[i]);
    }
  } catch (NumberFormatException except) {
    System.out.println("ERROR: Integer expected instead of " + args[i]);
    return printUsage();
  } catch (ArrayIndexOutOfBoundsException except) {
    System.out.println("ERROR: Required parameter missing from " +
                       args[i-1]);
    return printUsage();
  }
}



   FileInputFormat.setInputPaths(conf, other_args.get(0));
    //FileInputFormat.setInputPaths(conf,new    Path("hdfs://localhost:54310/user/root/images"));
FileOutputFormat.setOutputPath(conf, new Path(other_args.get(1)));

JobClient.runJob(conf);
return 0;
}


 public static void main(String[] args) throws Exception {
int res = ToolRunner.run(new Configuration(), new image_mapreduce(), args);
System.exit(res);
 }

}

`我正在编写一个程序，它将多个图像文件作为输入，存储在hdfs和amp;提取地图功能中的功能。如何在FileInputStream中指定读取图像的路径（某些参数）？或者有没有办法读取多个图像文件？

我想做的是： - 将hdfs中的多个图像文件作为输入 - 提取地图功能中的功能。 - 迭代减少。请帮我编写代码或更好的方法。

Answer 1

使用HIPI library - 它会将一组图像存储到ImageBundle中（这样可以更有效地将各个图像文件存储在HDFS中）。他们也有几个例子。

至于您的代码，您需要指定您计划使用的输入和输出格式。没有当前输入格式可以传递整个文件，但您可以只扩展FileInputFormat并创建一个发出<Text, BytesWritable>对的RecordReader，其中键是文件名，值是图像文件的字节。

实际上 Hadoop - The Definitive Guide 有一个这种确切输入格式的示例：

Answer 2

如果要将所有图像作为输入发送到MR任务，只需将conf.setFileInputPath（）设置为输入目录即可如果要在特定文件夹中发送选择性图像您可以在设置conf.setFileInputPath（）时添加多个路径;

一种方法是为每个图像创建一个Path []。或者只是将其设置为包含所有路径的逗号分隔字符串。阅读以下文档

http://hadoop.apache.org/docs/current/api/org/apache/hadoop/mapred/FileInputFormat.html

还有一件事你必须将Map输入格式设置为Text，ByteArray 从ByteArray输入中获取图像特征，而不是创建新的fileinputstream。

如何在map-reduce中从hdfs读取多个图像文件作为输入？

2 个答案: