changes to quick test lenet-train using more builtins (that need CUDA)

these builtins still need proper script wrapping

scripts/nn/networks/lenet-train.daph

@@ -100,24 +100,28 @@ def predict(X:matrix, C, Hin, Win, W1:matrix, b1:matrix, W2:matrix, b2:matrix, W
     # Compute forward pass
     ## layer 1: conv1 -> relu1 -> pool1
     outc1, Houtc1, Woutc1 = conv2d.forward(X_batch, W1, b1, C, Hin, Win, Hf, Wf, stride, stride, pad, pad);
-    outr1 = relu.forward(outc1);
+    outr1 = relu(outc1);
+    #outr1 = relu.forward(outc1);
     outp1, Houtp1, Woutp1 = max_pool2d.forward(outr1, F1, Houtc1, Woutc1, 2, 2, 2, 2, 0, 0);
 print("predict fwd layer 1 done");
     ## layer 2: conv2 -> relu2 -> pool2
     outc2, Houtc2, Woutc2 = conv2d.forward(outp1, W2, b2, F1, Houtp1, Woutp1, Hf, Wf, stride, stride, pad, pad);
-    outr2 = relu.forward(outc2);
+    #outr2 = relu.forward(outc2);
+    outr2 = relu(outc2);
     outp2, Houtp2, Woutp2 = max_pool2d.forward(outr2, F2, Houtp1, Woutp1, 2, 2, 2, 2, 0, 0);
 print("predict fwd layer 2 done");
     ## layer 3:  affine3 -> relu3 -> dropout
 #    outa3 = affine.forward(outp2, W3, b3);
 outa3 = affine(outp2, W3, b3);
-    outr3 = relu.forward(outa3);
+    #outr3 = relu.forward(outa3);
+    outr3 = relu(outa3);
     outd3, maskd3 = dropout.forward(outr3, 0.5, -1);
 print("predict fwd layer 3 done");
     ## layer 4:  affine4 -> softmax
     #outa4 = affine.forward(outd3, W4, b4);
     outa4 = affine(outd3, W4, b4);
-    probs_batch = softmax.forward(outa4);
+    #probs_batch = softmax.forward(outa4);
+    probs_batch = softmax(outa4);
 print("predict fwd layer 4 done");
     # Store predictions
     probs[beg:end,] = probs_batch;
@@ -218,25 +222,29 @@ print("start training layer 1");
       ## layer 1: conv1 -> relu1 -> pool1
       outc1, Houtc1, Woutc1 = conv2d.forward(X_batch, W1, b1, C, Hin, Win, Hf, Wf, stride, stride, pad, pad);
 print("conv1 done");
-      outr1 = relu.forward(outc1);
+      #outr1 = relu.forward(outc1);
+      outr1 = relu(outc1);
       print("layer 1 relu done");
       outp1, Houtp1, Woutp1 = max_pool2d.forward(outr1, F1, Houtc1, Woutc1, 2, 2, 2, 2, 0, 0);
 print("train fwd layer 1 done");
       ## layer 2: conv2 -> relu2 -> pool2
       outc2, Houtc2, Woutc2 = conv2d.forward(outp1, W2, b2, F1, Houtp1, Woutp1, Hf, Wf, stride, stride, pad, pad);
-      outr2 = relu.forward(outc2);
+      #outr2 = relu.forward(outc2);
+      outr2 = relu(outc2);
       outp2, Houtp2, Woutp2 = max_pool2d.forward(outr2, F2, Houtp1, Woutp1, 2, 2, 2, 2, 0, 0);
 print("train fwd layer 2 done");
       ## layer 3:  affine3 -> relu3 -> dropout
       #outa3 = affine.forward(outp2, W3, b3);
       outa3 = affine(outp2, W3, b3);
-      outr3 = relu.forward(outa3);
+      #outr3 = relu.forward(outa3);
+      outr3 = relu(outa3);
       outd3, maskd3 = dropout.forward(outr3, 0.5, -1);
 print("train fwd layer 3 done");
       ## layer 4:  affine4 -> softmax
       #outa4 = affine.forward(outd3, W4, b4);
       outa4 = affine(outd3, W4, b4);
-      probs = softmax.forward(outa4);
+      #probs = softmax.forward(outa4);
+      probs = softmax(outa4);
 print("train fwd layer 4 done");
       # Compute loss & accuracy for training & validation data every 100 iterations.
       if (i % 100 == 0)