Examples/Image/Classification/ResNet/Python/README.md: tune

Examples/Image/Classification/ResNet/Python/README.md

@@ -15,13 +15,13 @@ for ResNet20 and ResNet110, respectively. The ResNet20 network achieves an error
 
 ### TrainResNet_CIFAR10_Distributed.py
 
-This example code is similiar to TrainResNet_CIFAR10.py, but it adds support for distributed training via [MPI](https://en.wikipedia.org/wiki/Message_Passing_Interface). Details can be found in [here](https://github.com/Microsoft/CNTK/wiki/Multiple-GPUs-and-machines)
-Note this example requires a multi-GPU machine or mpi hosts file to distribute to multiple machines
+This example code is similar to TrainResNet_CIFAR10.py, but it adds support for distributed training via [MPI](https://en.wikipedia.org/wiki/Message_Passing_Interface). Details can be found in [here](https://github.com/Microsoft/CNTK/wiki/Multiple-GPUs-and-machines)
+Note this example requires a multi-GPU machine or mpi hosts file to distribute to multiple machines.
 
-Simple aggregation, resnet20, with a 2-GPU machine:
+Simple aggregation, ResNet20, with a 2-GPU machine:
 
 `mpiexec -n 2 python TrainResNet_CIFAR10_Distributed.py -n resnet20 -q 32`
 
-Quantized 1-bit aggregation with 50000 samples before distributed, resnet 20, with a 2-GPU machine:
+Quantized 1-bit aggregation with 50000 samples before distributed, ResNet20, with a 2-GPU machine:
 
-`mpiexec -n 2 python TrainResNet_CIFAR10_Distributed.py -n resnet20 -q 1 -a 50000`
+`mpiexec -n 2 python TrainResNet_CIFAR10_Distributed.py -n resnet20 -q 1 -a 50000`