in hadoop/src/main/java/org/tensorflow/hadoop/example/TFRecordFileMRExample.java [79:104]
public static boolean convert(String jobName,
Class<? extends Mapper> mapperClass,
Class<? extends Writable> outputKeyClass,
Class<? extends Writable> outputValueClass,
Class<? extends InputFormat> inFormatClass,
Class<? extends OutputFormat> outFormatClass,
Path input,
Path output) throws InterruptedException, IOException, ClassNotFoundException {
Configuration conf = new Configuration();
Job job = Job.getInstance(conf, jobName);
job.setJarByClass(mapperClass);
job.setMapperClass(mapperClass);
job.setNumReduceTasks(0);
job.setInputFormatClass(inFormatClass);
job.setOutputFormatClass(outFormatClass);
job.setOutputKeyClass(outputKeyClass);
job.setOutputValueClass(outputValueClass);
final FileSystem fs = FileSystem.get(output.toUri(), conf);
fs.delete(output, true);
FileInputFormat.addInputPath(job, input);
FileOutputFormat.setOutputPath(job, output);
return job.waitForCompletion(true);
}