Can not run notebook TFOS_spark_demo.ipynb on Standalone Spark Cluster. about tensorflowonspark HOT 3 CLOSED

Py4JJavaErrorTraceback (most recent call last)
in ()
10 labels = sc.textFile(args.labels).map(lambda ln: [float(x) for x in ln.split(',')])
11 dataRDD = images.zip(labels)
---> 12 cluster.train(dataRDD, args.epochs)

/tmp/spark-ea1c6092-e39f-477f-a8ec-7bb8f1f6c233/userFiles-51194885-1afc-49c0-8538-6c538d1ffe2a/tfspark.zip/com/yahoo/ml/tf/TFCluster.py in train(self, dataRDD, num_epochs, qname)
69
70 unionRDD = self.sc.union(rdds)
---> 71 unionRDD.foreachPartition(TFSparkNode.train(self.cluster_info, qname))
72
73 def inference(self, dataRDD, qname='input'):

/root/TensorFlowOnSpark/spark-1.6.0-bin-hadoop2.6/python/pyspark/rdd.pyc in foreachPartition(self, f)
762 except TypeError:
763 return iter([])
--> 764 self.mapPartitions(func).count() # Force evaluation
765
766 def collect(self):

/root/TensorFlowOnSpark/spark-1.6.0-bin-hadoop2.6/python/pyspark/rdd.pyc in count(self)
1002 3
1003 """
-> 1004 return self.mapPartitions(lambda i: [sum(1 for _ in i)]).sum()
1005
1006 def stats(self):

/root/TensorFlowOnSpark/spark-1.6.0-bin-hadoop2.6/python/pyspark/rdd.pyc in sum(self)
993 6.0
994 """
--> 995 return self.mapPartitions(lambda x: [sum(x)]).fold(0, operator.add)
996
997 def count(self):

/root/TensorFlowOnSpark/spark-1.6.0-bin-hadoop2.6/python/pyspark/rdd.pyc in fold(self, zeroValue, op)
867 # zeroValue provided to each partition is unique from the one provided
868 # to the final reduce call
--> 869 vals = self.mapPartitions(func).collect()
870 return reduce(op, vals, zeroValue)
871

/root/TensorFlowOnSpark/spark-1.6.0-bin-hadoop2.6/python/pyspark/rdd.pyc in collect(self)
769 """
770 with SCCallSiteSync(self.context) as css:
--> 771 port = self.ctx._jvm.PythonRDD.collectAndServe(self._jrdd.rdd())
772 return list(_load_from_socket(port, self._jrdd_deserializer))
773

/root/TensorFlowOnSpark/spark-1.6.0-bin-hadoop2.6/python/lib/py4j-0.9-src.zip/py4j/java_gateway.py in call(self, *args)
811 answer = self.gateway_client.send_command(command)
812 return_value = get_return_value(
--> 813 answer, self.gateway_client, self.target_id, self.name)
814
815 for temp_arg in temp_args:

/root/TensorFlowOnSpark/spark-1.6.0-bin-hadoop2.6/python/pyspark/sql/utils.pyc in deco(*a, **kw)
43 def deco(*a, **kw):
44 try:
---> 45 return f(*a, **kw)
46 except py4j.protocol.Py4JJavaError as e:
47 s = e.java_exception.toString()

/root/TensorFlowOnSpark/spark-1.6.0-bin-hadoop2.6/python/lib/py4j-0.9-src.zip/py4j/protocol.py in get_return_value(answer, gateway_client, target_id, name)
306 raise Py4JJavaError(
307 "An error occurred while calling {0}{1}{2}.\n".
--> 308 format(target_id, ".", name), value)
309 else:
310 raise Py4JError(

Py4JJavaError: An error occurred while calling z:org.apache.spark.api.python.PythonRDD.collectAndServe.
: org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 13.0 failed 4 times, most recent failure: Lost task 0.3 in stage 13.0 (TID 160, 10.16.5.60): org.apache.spark.api.python.PythonException: Traceback (most recent call last):
File "/root/TensorFlowOnSpark/spark-1.6.0-bin-hadoop2.6/python/lib/pyspark.zip/pyspark/worker.py", line 111, in main
process()
File "/root/TensorFlowOnSpark/spark-1.6.0-bin-hadoop2.6/python/lib/pyspark.zip/pyspark/worker.py", line 106, in process
serializer.dump_stream(func(split_index, iterator), outfile)
File "/root/TensorFlowOnSpark/spark-1.6.0-bin-hadoop2.6/python/pyspark/rdd.py", line 2346, in pipeline_func
return func(split, prev_func(split, iterator))
File "/root/TensorFlowOnSpark/spark-1.6.0-bin-hadoop2.6/python/pyspark/rdd.py", line 2346, in pipeline_func
return func(split, prev_func(split, iterator))
File "/root/TensorFlowOnSpark/spark-1.6.0-bin-hadoop2.6/python/pyspark/rdd.py", line 2346, in pipeline_func
return func(split, prev_func(split, iterator))
File "/root/TensorFlowOnSpark/spark-1.6.0-bin-hadoop2.6/python/pyspark/rdd.py", line 317, in func
return f(iterator)
File "/root/TensorFlowOnSpark/spark-1.6.0-bin-hadoop2.6/python/pyspark/rdd.py", line 759, in func
r = f(it)
File "/tmp/spark-ea1c6092-e39f-477f-a8ec-7bb8f1f6c233/userFiles-51194885-1afc-49c0-8538-6c538d1ffe2a/tfspark.zip/com/yahoo/ml/tf/TFSparkNode.py", line 235, in _train
File "/usr/lib/python2.7/multiprocessing/managers.py", line 667, in temp
token, exp = self._create(typeid, *args, **kwds)
File "/usr/lib/python2.7/multiprocessing/managers.py", line 567, in _create
id, exposed = dispatch(conn, None, 'create', (typeid,)+args, kwds)
File "/usr/lib/python2.7/multiprocessing/managers.py", line 105, in dispatch
raise convert_to_error(kind, result)
RemoteError:

Traceback (most recent call last):
File "/usr/lib/python2.7/multiprocessing/managers.py", line 207, in handle_request
result = func(c, *args, **kwds)
File "/usr/lib/python2.7/multiprocessing/managers.py", line 386, in create
obj = callable(*args, **kwds)
File "./tfspark.zip/com/yahoo/ml/tf/TFManager.py", line 29, in
TFManager.register('get_queue', callable=lambda qname: qdict[qname])
KeyError: 'input'

at org.apache.spark.api.python.PythonRunner$$anon$1.read(PythonRDD.scala:166)
at org.apache.spark.api.python.PythonRunner$$anon$1.<init>(PythonRDD.scala:207)
at org.apache.spark.api.python.PythonRunner.compute(PythonRDD.scala:125)
at org.apache.spark.api.python.PythonRDD.compute(PythonRDD.scala:70)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66)
at org.apache.spark.scheduler.Task.run(Task.scala:89)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:213)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
at java.lang.Thread.run(Thread.java:745)

Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1431)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1419)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1418)
at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1418)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:799)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:799)
at scala.Option.foreach(Option.scala:236)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:799)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1640)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1599)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1588)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:620)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1832)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1845)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1858)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1929)
at org.apache.spark.rdd.RDD$$anonfun$collect$1.apply(RDD.scala:927)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:150)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:111)
at org.apache.spark.rdd.RDD.withScope(RDD.scala:316)
at org.apache.spark.rdd.RDD.collect(RDD.scala:926)
at org.apache.spark.api.python.PythonRDD$.collectAndServe(PythonRDD.scala:405)
at org.apache.spark.api.python.PythonRDD.collectAndServe(PythonRDD.scala)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:498)
at py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:231)
at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:381)
at py4j.Gateway.invoke(Gateway.java:259)
at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:133)
at py4j.commands.CallCommand.execute(CallCommand.java:79)
at py4j.GatewayConnection.run(GatewayConnection.java:209)
at java.lang.Thread.run(Thread.java:745)
Caused by: org.apache.spark.api.python.PythonException: Traceback (most recent call last):
File "/root/TensorFlowOnSpark/spark-1.6.0-bin-hadoop2.6/python/lib/pyspark.zip/pyspark/worker.py", line 111, in main
process()
File "/root/TensorFlowOnSpark/spark-1.6.0-bin-hadoop2.6/python/lib/pyspark.zip/pyspark/worker.py", line 106, in process
serializer.dump_stream(func(split_index, iterator), outfile)
File "/root/TensorFlowOnSpark/spark-1.6.0-bin-hadoop2.6/python/pyspark/rdd.py", line 2346, in pipeline_func
return func(split, prev_func(split, iterator))
File "/root/TensorFlowOnSpark/spark-1.6.0-bin-hadoop2.6/python/pyspark/rdd.py", line 2346, in pipeline_func
return func(split, prev_func(split, iterator))
File "/root/TensorFlowOnSpark/spark-1.6.0-bin-hadoop2.6/python/pyspark/rdd.py", line 2346, in pipeline_func
return func(split, prev_func(split, iterator))
File "/root/TensorFlowOnSpark/spark-1.6.0-bin-hadoop2.6/python/pyspark/rdd.py", line 317, in func
return f(iterator)
File "/root/TensorFlowOnSpark/spark-1.6.0-bin-hadoop2.6/python/pyspark/rdd.py", line 759, in func
r = f(it)
File "/tmp/spark-ea1c6092-e39f-477f-a8ec-7bb8f1f6c233/userFiles-51194885-1afc-49c0-8538-6c538d1ffe2a/tfspark.zip/com/yahoo/ml/tf/TFSparkNode.py", line 235, in _train
File "/usr/lib/python2.7/multiprocessing/managers.py", line 667, in temp
token, exp = self._create(typeid, *args, **kwds)
File "/usr/lib/python2.7/multiprocessing/managers.py", line 567, in _create
id, exposed = dispatch(conn, None, 'create', (typeid,)+args, kwds)
File "/usr/lib/python2.7/multiprocessing/managers.py", line 105, in dispatch
raise convert_to_error(kind, result)
RemoteError:

Traceback (most recent call last):
File "/usr/lib/python2.7/multiprocessing/managers.py", line 207, in handle_request
result = func(c, *args, **kwds)
File "/usr/lib/python2.7/multiprocessing/managers.py", line 386, in create
obj = callable(*args, **kwds)
File "./tfspark.zip/com/yahoo/ml/tf/TFManager.py", line 29, in
TFManager.register('get_queue', callable=lambda qname: qdict[qname])
KeyError: 'input'

at org.apache.spark.api.python.PythonRunner$$anon$1.read(PythonRDD.scala:166)
at org.apache.spark.api.python.PythonRunner$$anon$1.<init>(PythonRDD.scala:207)
at org.apache.spark.api.python.PythonRunner.compute(PythonRDD.scala:125)
at org.apache.spark.api.python.PythonRDD.compute(PythonRDD.scala:70)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66)
at org.apache.spark.scheduler.Task.run(Task.scala:89)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:213)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)

from tensorflowonspark.

@geometrybase Please describe the steps that you reached this problem, and share a screenshot of your notebook. We need to be able to reproduce the problem before offering a fix.

From your log, it seems that you are using EC2. If so, did you try out TFOS_demo.ipynb?
Your problem seems to be around TFOS_spark_demo.ipynb. Beforer you run that notebook,
please produce csv files per conversion w/ "--output csv --format csv".

from tensorflowonspark.

Closed due to inactivity

from tensorflowonspark.