TF1.6 compatibility

Author: leewyang

examples/mnist/mnist_data_setup.py

@@ -110,7 +110,7 @@ def readMNIST(sc, output, format):
     tfRDD = sc.newAPIHadoopFile(output, "org.tensorflow.hadoop.io.TFRecordFileInputFormat",
                                 keyClass="org.apache.hadoop.io.BytesWritable",
                                 valueClass="org.apache.hadoop.io.NullWritable")
-    imageRDD = tfRDD.map(lambda x: fromTFExample(str(x[0])))
+    imageRDD = tfRDD.map(lambda x: fromTFExample(bytes(x[0])))
 
   num_images = imageRDD.count()
   num_labels = labelRDD.count() if labelRDD is not None else num_images

examples/mnist/spark/mnist_spark.py

@@ -54,7 +54,7 @@ def toNumpy(bytestr):
     label = numpy.array(features['label'].int64_list.value)
     return (image, label)
 
-  dataRDD = images.map(lambda x: toNumpy(str(x[0])))
+  dataRDD = images.map(lambda x: toNumpy(bytes(x[0])))
 else:
   if args.format == "csv":
     images = sc.textFile(args.images).map(lambda ln: [int(x) for x in ln.split(',')])

examples/mnist/spark/mnist_spark_dataset.py

@@ -54,7 +54,7 @@ def toNumpy(bytestr):
     label = numpy.array(features['label'].int64_list.value)
     return (image, label)
 
-  dataRDD = images.map(lambda x: toNumpy(str(x[0])))
+  dataRDD = images.map(lambda x: toNumpy(bytes(x[0])))
 else:  # args.format == "csv":
   images = sc.textFile(args.images).map(lambda ln: [int(x) for x in ln.split(',')])
   labels = sc.textFile(args.labels).map(lambda ln: [float(x) for x in ln.split(',')])