adjusted tests

src/test/resources/models/showAttendTell/Show_attend_tell.emadl

@@ -46,7 +46,6 @@ component Show_attend_tell{
        FullyConnected(units=37758) ->
        Tanh() ->
        Dropout(p=0.25) ->
-       Softmax() ->
        ArgMax() ->
        target[t]
        };

src/test/resources/models/showAttendTell/Show_attend_tell_images_as_input.emadl

@@ -17,8 +17,8 @@ component Show_attend_tell_images_as_input{
       0 -> target[0];
 
       images ->
-      Convolution(kernel=(7,7), channels=128, stride=(7,7), padding="valid") ->
-      Convolution(kernel=(4,4), channels=128, stride=(4,4), padding="valid") ->
+      Convolution(kernel=(7,7), channels=128, stride=(7,7), padding="same") ->
+      Convolution(kernel=(4,4), channels=128, stride=(4,4), padding="same") ->
       Reshape(shape=(64, 128)) ->
       features;
 
@@ -52,7 +52,6 @@ component Show_attend_tell_images_as_input{
        FullyConnected(units=37758) ->
        Tanh() ->
        Dropout(p=0.25) ->
-       Softmax() ->
        ArgMax() ->
        target[t]
        };

src/test/resources/target_code/gluon/CNNSupervisedTrainer_mnist_mnistClassifier_net.py

@@ -54,7 +54,7 @@ class SoftmaxCrossEntropyLossIgnoreIndices(gluon.loss.Loss):
             loss = -(pred * label).sum(axis=self._axis, keepdims=True)
         # ignore some indices for loss, e.g. <pad> tokens in NLP applications
         for i in self._ignore_indices:
-            loss = loss * mx.nd.logical_not(mx.nd.equal(mx.nd.argmax(pred, axis=1), mx.nd.ones_like(mx.nd.argmax(pred, axis=1))*i))
+            loss = loss * mx.nd.logical_not(mx.nd.equal(mx.nd.argmax(pred, axis=1), mx.nd.ones_like(mx.nd.argmax(pred, axis=1))*i) * mx.nd.equal(mx.nd.argmax(pred, axis=1), label))
         return loss.mean(axis=self._batch_axis, exclude=True)
 
 @mx.metric.register
@@ -278,6 +278,7 @@ class CNNSupervisedTrainer_mnist_mnistClassifier_net:
         tic = None
 
         for epoch in range(begin_epoch, begin_epoch + num_epoch):
+
             train_iter.reset()
             for batch_i, batch in enumerate(train_iter):
                 with autograd.record():
@@ -320,6 +321,7 @@ class CNNSupervisedTrainer_mnist_mnistClassifier_net:
 
             tic = None
 
+
             train_test_iter.reset()
             metric = mx.metric.create(eval_metric, **eval_metric_params)
             for batch_i, batch in enumerate(train_test_iter):