add the original ResNet scripits

Examples/Image/Miscellaneous/ImageNet/ResNetOriginal/README.md

@@ -9,15 +9,12 @@
 |Training  |Stochastic gradient descent with momentum.
 
 ## Details
-The network configurations and experiment settings in this this folder resemble the ones in the original [ResNet paper](http://arxiv.org/abs/1512.03385) with few minor changes inspired by [this work](https://github.com/facebook/fb.resnet.torch).
-The following table contains results as well as links to pre-trained models that can be used in various applications.
+The network configurations and experiment settings in this this folder resemble the ones in the original [ResNet paper](http://arxiv.org/abs/1512.03385) strictly without any extra optimization.
+The following table contains results.
 
 | Network       | Top-1 error | Top-5 error | Model
 | ------------- | ----------- | ----------- | ----------
-| ResNet-18     | 29.57       | 10.41       | [Download](https://www.cntk.ai/resnet/ResNet_18.model)
-| ResNet-34     | 27.31       | 8.97        | [Download](https://www.cntk.ai/resnet/ResNet_34.model)
-| ResNet-50     | 24.74       | 7.56        | [Download](https://www.cntk.ai/resnet/ResNet_50.model)
-| ResNet-152    | 22.57       | 6.44        | [Download](https://www.cntk.ai/resnet/ResNet_152.model)
+| ResNet-50     | 24.58       | 7.43        |
 
 ## Notes
 This work is an implementation of ResNets in CNTK. If you are interested in the original implementation of ResNet, follow [this link](https://github.com/KaimingHe/deep-residual-networks).

Examples/Image/Miscellaneous/ImageNet/ResNetOriginal/ResNet_50.cntk

@@ -56,10 +56,6 @@ Train=[
     
     reader=[
         readerType="ImageReader"
-        # Map file which maps images to labels using the following format:
-        # <full path to image><tab><numerical label (0-based class id)>
-        # Example:
-        # C:\Data\ImageNet\2012\train\n01440764\n01440764_10026.JPEG<tab>0
         file="$DataDir$/train_map.txt"
         # Randomize images before every epoch. Possible values: None, Auto. Default: Auto.
         randomize="Auto"
@@ -78,22 +74,6 @@ Train=[
             # Crop scale ratio jitter type.
             # Possible values: None, UniRatio, UniLength, UniArea. Default: UniRatio
             jitterType="UniRatio"
-            # Interpolation to use when scaling image to width x height size.
-            # Possible values: nearest, linear, cubic, lanczos. Default: linear.
-            #interpolations="cubic"
-            # Aspect ratio jitter radius. Default is 0 (disabled).
-            #aspectRatioRadius=0:0.2
-            # Brightness, contrast and color jittering. Default is 0 (disabled).
-            # Using 0 in the first epoch so the network can process original images.
-            #brightnessRadius=0:0.2
-            #contrastRadius=0:0.2
-            #saturationRadius=0:0.4
-            # Intensity jittering: enabled if file is specified and intensityStdDev > 0. 
-            # The file stores 1x3 vector (eigenvalues) and 3x3 matrix (eigenvectors) in OpenCV XML format.
-            #intensityFile="$ConfigDir$/ImageNet1K_intensity.xml"
-            # StdDev for intensity jittering. Start from the second epoch.
-            #intensityStdDev=0:0.1
-            # Mean subtraction: enabled if file is specified.
             # The file stores mean values for each pixel in OpenCV matrix XML format.
             meanFile="$ConfigDir$/ImageNet1K_mean.xml"
         ]
@@ -107,15 +87,11 @@ PBN=[
     action="pbn"
     modelPath="$ModelDir$/ResNet_50"
     # Set minibatch size for testing.
-    minibatchSize=32
+    minibatchSize=256
     iters=30
 
     reader=[
         readerType="ImageReader"
-        # Map file which maps images to labels using the following format:
-        # <full path to image><tab><numerical label (0-based class id)>
-        # Example:
-        # C:\Data\ImageNet\2012\train\n01440764\n01440764_10026.JPEG<tab>0
         file="$DataDir$/train_map.txt"
         # Randomize images before every epoch. Possible values: None, Auto. Default: Auto.
         randomize="Auto"
@@ -134,22 +110,6 @@ PBN=[
             # Crop scale ratio jitter type.
             # Possible values: None, UniRatio, UniLength, UniArea. Default: UniRatio
             jitterType="UniRatio"
-            # Interpolation to use when scaling image to width x height size.
-            # Possible values: nearest, linear, cubic, lanczos. Default: linear.
-            #interpolations="cubic"
-            # Aspect ratio jitter radius. Default is 0 (disabled).
-            #aspectRatioRadius=0:0.2
-            # Brightness, contrast and color jittering. Default is 0 (disabled).
-            # Using 0 in the first epoch so the network can process original images.
-            #brightnessRadius=0:0.2
-            #contrastRadius=0:0.2
-            #saturationRadius=0:0.4
-            # Intensity jittering: enabled if file is specified and intensityStdDev > 0. 
-            # The file stores 1x3 vector (eigenvalues) and 3x3 matrix (eigenvectors) in OpenCV XML format.
-            #intensityFile="$ConfigDir$/ImageNet1K_intensity.xml"
-            # StdDev for intensity jittering. Start from the second epoch.
-            #intensityStdDev=0:0.1
-            # Mean subtraction: enabled if file is specified.
             # The file stores mean values for each pixel in OpenCV matrix XML format.
             meanFile="$ConfigDir$/ImageNet1K_mean.xml"
         ]