Updated ResNet sample.

Examples/Image/Miscellaneous/ImageNet/ResNet/Macros.ndl

@@ -122,7 +122,7 @@ ResNetNode3Inc(inp, inMap, convMap, outMap, convWCount, wScale, bValue, scValue,
     m2 = Parameter(convMap, 1, init = fixedValue, value = 0, needGradient = false)
     isd2 = Parameter(convMap, 1, init = fixedValue, value = 0, needGradient = false)
     
-    c2 = Convolution(W2, y1, 3, 3, convMap, 1, 1, zeroPadding = true)
+    c2 = Convolution(W2, y1, 3, 3, convMap, 2, 2, zeroPadding = true)
     bn2 = BatchNormalization(c2, sc2, b2, m2, isd2, eval = false, spatial = true, expAvgFactor = 1.0)
     y2 = RectifiedLinear(bn2);
     
@@ -137,7 +137,7 @@ ResNetNode3Inc(inp, inMap, convMap, outMap, convWCount, wScale, bValue, scValue,
     bn3 = BatchNormalization(c3, sc3, b3, m3, isd3, eval = false, spatial = true)
     
     # Increasing input dimension convolution
-    cProj = Convolution(wProj, inp, 1, 1, outMap, 1, 1, zeroPadding = false)
+    cProj = Convolution(wProj, inp, 1, 1, outMap, 2, 2, zeroPadding = false)
     
     p = Plus(bn3, cProj)
     y3 = RectifiedLinear(p);

Examples/Image/Miscellaneous/ImageNet/ResNet/ResNet_152.config

@@ -32,7 +32,7 @@ Train=[
     
     SGD=[
         epochSize=0
-        minibatchSize=1
+        minibatchSize=2
         learningRatesPerMB=0.1*20:0.03*10:0.01*30:0.003
         momentumPerMB=0.9
         maxEpochs=100

Examples/Image/Miscellaneous/ImageNet/ResNet/ResNet_152.ndl

@@ -104,7 +104,7 @@ DNN=[
 
     pool5 = AveragePooling(rn4_3, poolW, poolH, poolhs, poolvs)
 
-    ol = DnnLayer(1605632, labelDim, pool5, fcWScale, fcBValue)
+    ol = DnnLayer(8192, labelDim, pool5, fcWScale, fcBValue)
     
     CE = CrossEntropyWithSoftmax(labels, ol, tag = Criteria)
     Err = ErrorPrediction(labels, ol, tag = Eval)