add note about instance limit (aws#102)

Author: jesterhazy

sagemaker-python-sdk/mxnet_gluon_cifar10/cifar10.ipynb

@@ -95,7 +95,10 @@
    "source": [
     "## Run the training script on SageMaker\n",
     "\n",
-    "The ```MXNet``` class allows us to run our training function as a distributed training job on SageMaker infrastructure. We need to configure it with our training script, an IAM role, the number of training instances, and the training instance type. In this case we will run our training job on two `ml.p2.xlarge` instances."
+    "The ```MXNet``` class allows us to run our training function as a distributed training job on SageMaker infrastructure. We need to configure it with our training script, an IAM role, the number of training instances, and the training instance type. In this case we will run our training job on two `ml.p2.xlarge` instances.\n",
+    "\n",
+    "**Note:** you may need to request a limit increase in order to use two ``ml.p2.xlarge`` instances. If you \n",
+    "want to try the example without requesting an increase, just change the ``train_instance_count`` value to ``1``."
    ]
   },
   {

sagemaker-python-sdk/mxnet_gluon_cifar10/cifar10.py

@@ -1,12 +1,11 @@
 from __future__ import print_function
 
+import json
 import logging
+import os
 import time
 
-import json
 import mxnet as mx
-import numpy as np
-import os
 from mxnet import autograd as ag
 from mxnet import gluon
 from mxnet.gluon.model_zoo import vision as models
@@ -28,7 +27,7 @@ def train(current_host, hosts, num_cpus, num_gpus, channel_input_dirs, model_dir
     if len(hosts) == 1:
         kvstore = 'device' if num_gpus > 0 else 'local'
     else:
-        kvstore = 'dist_sync'  # TODO retest 'dist_sync_device'
+        kvstore = 'dist_device_sync'
 
     ctx = [mx.gpu(i) for i in range(num_gpus)] if num_gpus > 0 else [mx.cpu()]
     net = models.get_model('resnet34_v2', ctx=ctx, pretrained=False, classes=10)