added preprocessing to CNNSupervisedTrainer and fixed tests

src/main/resources/templates/gluon/CNNDataLoader.ftl

@@ -65,48 +65,6 @@ class ${tc.fileNameWithoutEnding}:
 
         return train_iter, test_iter, data_mean, data_std, train_images, test_images
 
-    def load_data_img(self, batch_size, img_size):
-        train_h5, test_h5 = self.load_h5_files()
-        width = img_size[0]
-        height = img_size[1]
-
-        comb_data = {}
-        data_mean = {}
-        data_std = {}
-
-        for input_name in self._input_names_:
-            train_data = train_h5[input_name][:]
-            test_data = test_h5[input_name][:]
-
-            train_shape = train_data.shape
-            test_shape = test_data.shape
-
-            comb_data[input_name] = mx.nd.zeros((train_shape[0]+test_shape[0], train_shape[1], width, height))
-            for i, img in enumerate(train_data):
-                img = img.transpose(1,2,0)
-                comb_data[input_name][i] = cv2.resize(img, (width, height)).reshape((train_shape[1],width,height))
-            for i, img in enumerate(test_data):
-                img = img.transpose(1, 2, 0)
-                comb_data[input_name][i+train_shape[0]] = cv2.resize(img, (width, height)).reshape((train_shape[1], width, height))
-
-            data_mean[input_name + '_'] = nd.array(comb_data[input_name][:].mean(axis=0))
-            data_std[input_name + '_'] = nd.array(comb_data[input_name][:].asnumpy().std(axis=0) + 1e-5)
-
-        comb_label = {}
-        for output_name in self._output_names_:
-            train_labels = train_h5[output_name][:]
-            test_labels = test_h5[output_name][:]
-            comb_label[output_name] = np.append(train_labels, test_labels, axis=0)
-
-
-        train_iter = mx.io.NDArrayIter(data=comb_data,
-                                       label=comb_label,
-                                       batch_size=batch_size)
-
-        test_iter = None
-
-        return train_iter, test_iter, data_mean, data_std
-
     def load_preprocessed_data(self, batch_size, preproc_lib):
         train_h5, test_h5 = self.load_h5_files()
 
@@ -148,6 +106,9 @@ class ${tc.fileNameWithoutEnding}:
             data_mean[input_name + '_'] = nd.array(train_data[input_name][:].mean(axis=0))
             data_std[input_name + '_'] = nd.array(train_data[input_name][:].asnumpy().std(axis=0) + 1e-5)
 
+        if 'images' in train_h5:
+            train_images = train_h5['images']
+
         train_iter = mx.io.NDArrayIter(data=train_data,
                                        label=train_label,
                                        batch_size=batch_size)
@@ -178,11 +139,14 @@ class ${tc.fileNameWithoutEnding}:
             for output_name in self._output_names_:
                 test_label[output_name][i] = getattr(shape_output, output_name + "_out")
 
+        if 'images' in test_h5:
+            test_images = test_h5['images']
+
         test_iter = mx.io.NDArrayIter(data=test_data,
                                        label=test_label,
                                        batch_size=batch_size)
 
-        return train_iter, test_iter, data_mean, data_std
+        return train_iter, test_iter, data_mean, data_std, train_images, test_images
 
     def preprocess_data(self, instance_wrapper, input_wrapper, index, data_h5):
         for input_name in self._input_names_:

src/main/resources/templates/gluon/CNNGanTrainer.ftl

@@ -114,7 +114,7 @@ class ${tc.fileNameWithoutEnding}:
 #        if preprocessing:
 #            train_iter, test_iter, data_mean, data_std = self._data_loader.load_preprocessed_data(batch_size, preproc_lib)
 #        else:
-#            train_iter, test_iter, data_mean, data_std = self._data_loader.load_data(batch_size, img_resize)
+#            train_iter, test_iter, data_mean, data_std = self._data_loader.load_data(batch_size)
 
         if 'weight_decay' in optimizer_params:
             optimizer_params['wd'] = optimizer_params['weight_decay']
@@ -166,16 +166,6 @@ class ${tc.fileNameWithoutEnding}:
             loss_function = mx.gluon.loss.SigmoidBinaryCrossEntropyLoss()
             activation_name = 'sigmoid'
 
-<<<<<<< HEAD
-=======
-<#list tc.architecture.streams as stream>
-        input_shape = <#list tc.getStreamInputDimensions(stream) as dimensions>${tc.join(dimensions, ",")}</#list>
-</#list>
-        shape_list = list(input_shape)
-        shape_list[0] = batch_size
-        input_shape = tuple(shape_list)
-
->>>>>>> cdd27689fde2eae0cb6e022d18400f7a696b2f58
         metric_dis = mx.metric.create(eval_metric)
         metric_gen = mx.metric.create(eval_metric)
         <#include "gan/InputGenerator.ftl">

src/main/resources/templates/gluon/CNNSupervisedTrainer.ftl

@@ -192,7 +192,8 @@ class ${tc.fileNameWithoutEnding}:
               context='gpu',
               save_attention_image=False,
               use_teacher_forcing=False,
-              normalize=True):
+              normalize=True,
+              preprocessing = False):
         if context == 'gpu':
             mx_context = mx.gpu()
         elif context == 'cpu':
@@ -200,6 +201,12 @@ class ${tc.fileNameWithoutEnding}:
         else:
             logging.error("Context argument is '" + context + "'. Only 'cpu' and 'gpu are valid arguments'.")
 
+        if preprocessing:
+            preproc_lib = "CNNPreprocessor_${tc.fileNameWithoutEnding?keep_after("CNNSupervisedTrainer_")}_executor"
+            train_iter, test_iter, data_mean, data_std, train_images, test_images = self._data_loader.load_preprocessed_data(batch_size, preproc_lib)
+        else:
+            train_iter, test_iter, data_mean, data_std, train_images, test_images = self._data_loader.load_data(batch_size)
+
         if 'weight_decay' in optimizer_params:
             optimizer_params['wd'] = optimizer_params['weight_decay']
             del optimizer_params['weight_decay']
@@ -215,8 +222,6 @@ class ${tc.fileNameWithoutEnding}:
             del optimizer_params['step_size']
             del optimizer_params['learning_rate_decay']
 
-        train_iter, test_iter, data_mean, data_std, train_images, test_images = self._data_loader.load_data(batch_size)
-
         if normalize:
             self._net_creator.construct(context=mx_context, data_mean=data_mean, data_std=data_std)
         else:

src/main/resources/templates/gluon/CNNTrainer.ftl

@@ -43,6 +43,9 @@ if __name__ == "__main__":
 <#if (config.normalize)??>
         normalize=${config.normalize?string("True","False")},
 </#if>
+<#if (config.preprocessingName)??>
+        preprocessing=${config.preprocessingName???string("True","False")},
+</#if>
 <#if (config.useTeacherForcing)??>
         use_teacher_forcing='${config.useTeacherForcing?string("True","False")}',
 </#if>

src/test/resources/target_code/CNNDataLoader_Alexnet.py

@@ -64,48 +64,6 @@ class CNNDataLoader_Alexnet:
 
         return train_iter, test_iter, data_mean, data_std, train_images, test_images
 
-    def load_data_img(self, batch_size, img_size):
-        train_h5, test_h5 = self.load_h5_files()
-        width = img_size[0]
-        height = img_size[1]
-
-        comb_data = {}
-        data_mean = {}
-        data_std = {}
-
-        for input_name in self._input_names_:
-            train_data = train_h5[input_name][:]
-            test_data = test_h5[input_name][:]
-
-            train_shape = train_data.shape
-            test_shape = test_data.shape
-
-            comb_data[input_name] = mx.nd.zeros((train_shape[0]+test_shape[0], train_shape[1], width, height))
-            for i, img in enumerate(train_data):
-                img = img.transpose(1,2,0)
-                comb_data[input_name][i] = cv2.resize(img, (width, height)).reshape((train_shape[1],width,height))
-            for i, img in enumerate(test_data):
-                img = img.transpose(1, 2, 0)
-                comb_data[input_name][i+train_shape[0]] = cv2.resize(img, (width, height)).reshape((train_shape[1], width, height))
-
-            data_mean[input_name + '_'] = nd.array(comb_data[input_name][:].mean(axis=0))
-            data_std[input_name + '_'] = nd.array(comb_data[input_name][:].asnumpy().std(axis=0) + 1e-5)
-
-        comb_label = {}
-        for output_name in self._output_names_:
-            train_labels = train_h5[output_name][:]
-            test_labels = test_h5[output_name][:]
-            comb_label[output_name] = np.append(train_labels, test_labels, axis=0)
-
-
-        train_iter = mx.io.NDArrayIter(data=comb_data,
-                                       label=comb_label,
-                                       batch_size=batch_size)
-
-        test_iter = None
-
-        return train_iter, test_iter, data_mean, data_std
-
     def load_preprocessed_data(self, batch_size, preproc_lib):
         train_h5, test_h5 = self.load_h5_files()
 
@@ -147,6 +105,9 @@ class CNNDataLoader_Alexnet:
             data_mean[input_name + '_'] = nd.array(train_data[input_name][:].mean(axis=0))
             data_std[input_name + '_'] = nd.array(train_data[input_name][:].asnumpy().std(axis=0) + 1e-5)
 
+        if 'images' in train_h5:
+            train_images = train_h5['images']
+
         train_iter = mx.io.NDArrayIter(data=train_data,
                                        label=train_label,
                                        batch_size=batch_size)
@@ -177,11 +138,14 @@ class CNNDataLoader_Alexnet:
             for output_name in self._output_names_:
                 test_label[output_name][i] = getattr(shape_output, output_name + "_out")
 
+        if 'images' in test_h5:
+            test_images = test_h5['images']
+
         test_iter = mx.io.NDArrayIter(data=test_data,
                                        label=test_label,
                                        batch_size=batch_size)
 
-        return train_iter, test_iter, data_mean, data_std
+        return train_iter, test_iter, data_mean, data_std, train_images, test_images
 
     def preprocess_data(self, instance_wrapper, input_wrapper, index, data_h5):
         for input_name in self._input_names_:

src/test/resources/target_code/CNNDataLoader_CifarClassifierNetwork.py

@@ -64,48 +64,6 @@ class CNNDataLoader_CifarClassifierNetwork:
 
         return train_iter, test_iter, data_mean, data_std, train_images, test_images
 
-    def load_data_img(self, batch_size, img_size):
-        train_h5, test_h5 = self.load_h5_files()
-        width = img_size[0]
-        height = img_size[1]
-
-        comb_data = {}
-        data_mean = {}
-        data_std = {}
-
-        for input_name in self._input_names_:
-            train_data = train_h5[input_name][:]
-            test_data = test_h5[input_name][:]
-
-            train_shape = train_data.shape
-            test_shape = test_data.shape
-
-            comb_data[input_name] = mx.nd.zeros((train_shape[0]+test_shape[0], train_shape[1], width, height))
-            for i, img in enumerate(train_data):
-                img = img.transpose(1,2,0)
-                comb_data[input_name][i] = cv2.resize(img, (width, height)).reshape((train_shape[1],width,height))
-            for i, img in enumerate(test_data):
-                img = img.transpose(1, 2, 0)
-                comb_data[input_name][i+train_shape[0]] = cv2.resize(img, (width, height)).reshape((train_shape[1], width, height))
-
-            data_mean[input_name + '_'] = nd.array(comb_data[input_name][:].mean(axis=0))
-            data_std[input_name + '_'] = nd.array(comb_data[input_name][:].asnumpy().std(axis=0) + 1e-5)
-
-        comb_label = {}
-        for output_name in self._output_names_:
-            train_labels = train_h5[output_name][:]
-            test_labels = test_h5[output_name][:]
-            comb_label[output_name] = np.append(train_labels, test_labels, axis=0)
-
-
-        train_iter = mx.io.NDArrayIter(data=comb_data,
-                                       label=comb_label,
-                                       batch_size=batch_size)
-
-        test_iter = None
-
-        return train_iter, test_iter, data_mean, data_std
-
     def load_preprocessed_data(self, batch_size, preproc_lib):
         train_h5, test_h5 = self.load_h5_files()
 
@@ -147,6 +105,9 @@ class CNNDataLoader_CifarClassifierNetwork:
             data_mean[input_name + '_'] = nd.array(train_data[input_name][:].mean(axis=0))
             data_std[input_name + '_'] = nd.array(train_data[input_name][:].asnumpy().std(axis=0) + 1e-5)
 
+        if 'images' in train_h5:
+            train_images = train_h5['images']
+
         train_iter = mx.io.NDArrayIter(data=train_data,
                                        label=train_label,
                                        batch_size=batch_size)
@@ -177,11 +138,14 @@ class CNNDataLoader_CifarClassifierNetwork:
             for output_name in self._output_names_:
                 test_label[output_name][i] = getattr(shape_output, output_name + "_out")
 
+        if 'images' in test_h5:
+            test_images = test_h5['images']
+
         test_iter = mx.io.NDArrayIter(data=test_data,
                                        label=test_label,
                                        batch_size=batch_size)
 
-        return train_iter, test_iter, data_mean, data_std
+        return train_iter, test_iter, data_mean, data_std, train_images, test_images
 
     def preprocess_data(self, instance_wrapper, input_wrapper, index, data_h5):
         for input_name in self._input_names_:

src/test/resources/target_code/CNNDataLoader_Invariant.py

@@ -64,48 +64,6 @@ class CNNDataLoader_Invariant:
 
         return train_iter, test_iter, data_mean, data_std, train_images, test_images
 
-    def load_data_img(self, batch_size, img_size):
-        train_h5, test_h5 = self.load_h5_files()
-        width = img_size[0]
-        height = img_size[1]
-
-        comb_data = {}
-        data_mean = {}
-        data_std = {}
-
-        for input_name in self._input_names_:
-            train_data = train_h5[input_name][:]
-            test_data = test_h5[input_name][:]
-
-            train_shape = train_data.shape
-            test_shape = test_data.shape
-
-            comb_data[input_name] = mx.nd.zeros((train_shape[0]+test_shape[0], train_shape[1], width, height))
-            for i, img in enumerate(train_data):
-                img = img.transpose(1,2,0)
-                comb_data[input_name][i] = cv2.resize(img, (width, height)).reshape((train_shape[1],width,height))
-            for i, img in enumerate(test_data):
-                img = img.transpose(1, 2, 0)
-                comb_data[input_name][i+train_shape[0]] = cv2.resize(img, (width, height)).reshape((train_shape[1], width, height))
-
-            data_mean[input_name + '_'] = nd.array(comb_data[input_name][:].mean(axis=0))
-            data_std[input_name + '_'] = nd.array(comb_data[input_name][:].asnumpy().std(axis=0) + 1e-5)
-
-        comb_label = {}
-        for output_name in self._output_names_:
-            train_labels = train_h5[output_name][:]
-            test_labels = test_h5[output_name][:]
-            comb_label[output_name] = np.append(train_labels, test_labels, axis=0)
-
-
-        train_iter = mx.io.NDArrayIter(data=comb_data,
-                                       label=comb_label,
-                                       batch_size=batch_size)
-
-        test_iter = None
-
-        return train_iter, test_iter, data_mean, data_std
-
     def load_preprocessed_data(self, batch_size, preproc_lib):
         train_h5, test_h5 = self.load_h5_files()
 
@@ -147,6 +105,9 @@ class CNNDataLoader_Invariant:
             data_mean[input_name + '_'] = nd.array(train_data[input_name][:].mean(axis=0))
             data_std[input_name + '_'] = nd.array(train_data[input_name][:].asnumpy().std(axis=0) + 1e-5)
 
+        if 'images' in train_h5:
+            train_images = train_h5['images']
+
         train_iter = mx.io.NDArrayIter(data=train_data,
                                        label=train_label,
                                        batch_size=batch_size)
@@ -177,11 +138,14 @@ class CNNDataLoader_Invariant:
             for output_name in self._output_names_:
                 test_label[output_name][i] = getattr(shape_output, output_name + "_out")
 
+        if 'images' in test_h5:
+            test_images = test_h5['images']
+
         test_iter = mx.io.NDArrayIter(data=test_data,
                                        label=test_label,
                                        batch_size=batch_size)
 
-        return train_iter, test_iter, data_mean, data_std
+        return train_iter, test_iter, data_mean, data_std, train_images, test_images
 
     def preprocess_data(self, instance_wrapper, input_wrapper, index, data_h5):
         for input_name in self._input_names_:

src/test/resources/target_code/CNNDataLoader_MultipleStreams.py

@@ -64,48 +64,6 @@ class CNNDataLoader_MultipleStreams:
 
         return train_iter, test_iter, data_mean, data_std, train_images, test_images
 
-    def load_data_img(self, batch_size, img_size):
-        train_h5, test_h5 = self.load_h5_files()
-        width = img_size[0]
-        height = img_size[1]
-
-        comb_data = {}
-        data_mean = {}
-        data_std = {}
-
-        for input_name in self._input_names_:
-            train_data = train_h5[input_name][:]
-            test_data = test_h5[input_name][:]
-
-            train_shape = train_data.shape
-            test_shape = test_data.shape
-
-            comb_data[input_name] = mx.nd.zeros((train_shape[0]+test_shape[0], train_shape[1], width, height))
-            for i, img in enumerate(train_data):
-                img = img.transpose(1,2,0)
-                comb_data[input_name][i] = cv2.resize(img, (width, height)).reshape((train_shape[1],width,height))
-            for i, img in enumerate(test_data):
-                img = img.transpose(1, 2, 0)
-                comb_data[input_name][i+train_shape[0]] = cv2.resize(img, (width, height)).reshape((train_shape[1], width, height))
-
-            data_mean[input_name + '_'] = nd.array(comb_data[input_name][:].mean(axis=0))
-            data_std[input_name + '_'] = nd.array(comb_data[input_name][:].asnumpy().std(axis=0) + 1e-5)
-
-        comb_label = {}
-        for output_name in self._output_names_:
-            train_labels = train_h5[output_name][:]
-            test_labels = test_h5[output_name][:]
-            comb_label[output_name] = np.append(train_labels, test_labels, axis=0)
-
-
-        train_iter = mx.io.NDArrayIter(data=comb_data,
-                                       label=comb_label,
-                                       batch_size=batch_size)
-
-        test_iter = None
-
-        return train_iter, test_iter, data_mean, data_std
-
     def load_preprocessed_data(self, batch_size, preproc_lib):
         train_h5, test_h5 = self.load_h5_files()
 
@@ -147,6 +105,9 @@ class CNNDataLoader_MultipleStreams:
             data_mean[input_name + '_'] = nd.array(train_data[input_name][:].mean(axis=0))
             data_std[input_name + '_'] = nd.array(train_data[input_name][:].asnumpy().std(axis=0) + 1e-5)
 
+        if 'images' in train_h5:
+            train_images = train_h5['images']
+
         train_iter = mx.io.NDArrayIter(data=train_data,
                                        label=train_label,
                                        batch_size=batch_size)
@@ -177,11 +138,14 @@ class CNNDataLoader_MultipleStreams:
             for output_name in self._output_names_:
                 test_label[output_name][i] = getattr(shape_output, output_name + "_out")
 
+        if 'images' in test_h5:
+            test_images = test_h5['images']
+
         test_iter = mx.io.NDArrayIter(data=test_data,
                                        label=test_label,
                                        batch_size=batch_size)
 
-        return train_iter, test_iter, data_mean, data_std
+        return train_iter, test_iter, data_mean, data_std, train_images, test_images
 
     def preprocess_data(self, instance_wrapper, input_wrapper, index, data_h5):
         for input_name in self._input_names_:

src/test/resources/target_code/CNNDataLoader_RNNencdec.py

@@ -64,48 +64,6 @@ class CNNDataLoader_RNNencdec:
 
         return train_iter, test_iter, data_mean, data_std, train_images, test_images
 
-    def load_data_img(self, batch_size, img_size):
-        train_h5, test_h5 = self.load_h5_files()
-        width = img_size[0]
-        height = img_size[1]
-
-        comb_data = {}
-        data_mean = {}
-        data_std = {}
-
-        for input_name in self._input_names_:
-            train_data = train_h5[input_name][:]
-            test_data = test_h5[input_name][:]
-
-            train_shape = train_data.shape
-            test_shape = test_data.shape
-
-            comb_data[input_name] = mx.nd.zeros((train_shape[0]+test_shape[0], train_shape[1], width, height))
-            for i, img in enumerate(train_data):
-                img = img.transpose(1,2,0)
-                comb_data[input_name][i] = cv2.resize(img, (width, height)).reshape((train_shape[1],width,height))
-            for i, img in enumerate(test_data):
-                img = img.transpose(1, 2, 0)
-                comb_data[input_name][i+train_shape[0]] = cv2.resize(img, (width, height)).reshape((train_shape[1], width, height))
-
-            data_mean[input_name + '_'] = nd.array(comb_data[input_name][:].mean(axis=0))
-            data_std[input_name + '_'] = nd.array(comb_data[input_name][:].asnumpy().std(axis=0) + 1e-5)
-
-        comb_label = {}
-        for output_name in self._output_names_:
-            train_labels = train_h5[output_name][:]
-            test_labels = test_h5[output_name][:]
-            comb_label[output_name] = np.append(train_labels, test_labels, axis=0)
-
-
-        train_iter = mx.io.NDArrayIter(data=comb_data,
-                                       label=comb_label,
-                                       batch_size=batch_size)
-
-        test_iter = None
-
-        return train_iter, test_iter, data_mean, data_std
-
     def load_preprocessed_data(self, batch_size, preproc_lib):
         train_h5, test_h5 = self.load_h5_files()
 
@@ -147,6 +105,9 @@ class CNNDataLoader_RNNencdec:
             data_mean[input_name + '_'] = nd.array(train_data[input_name][:].mean(axis=0))
             data_std[input_name + '_'] = nd.array(train_data[input_name][:].asnumpy().std(axis=0) + 1e-5)
 
+        if 'images' in train_h5:
+            train_images = train_h5['images']
+
         train_iter = mx.io.NDArrayIter(data=train_data,
                                        label=train_label,
                                        batch_size=batch_size)
@@ -177,11 +138,14 @@ class CNNDataLoader_RNNencdec:
             for output_name in self._output_names_:
                 test_label[output_name][i] = getattr(shape_output, output_name + "_out")
 
+        if 'images' in test_h5:
+            test_images = test_h5['images']
+
         test_iter = mx.io.NDArrayIter(data=test_data,
                                        label=test_label,
                                        batch_size=batch_size)
 
-        return train_iter, test_iter, data_mean, data_std
+        return train_iter, test_iter, data_mean, data_std, train_images, test_images
 
     def preprocess_data(self, instance_wrapper, input_wrapper, index, data_h5):
         for input_name in self._input_names_:

src/test/resources/target_code/CNNDataLoader_RNNsearch.py

@@ -64,48 +64,6 @@ class CNNDataLoader_RNNsearch:
 
         return train_iter, test_iter, data_mean, data_std, train_images, test_images
 
-    def load_data_img(self, batch_size, img_size):
-        train_h5, test_h5 = self.load_h5_files()
-        width = img_size[0]
-        height = img_size[1]
-
-        comb_data = {}
-        data_mean = {}
-        data_std = {}
-
-        for input_name in self._input_names_:
-            train_data = train_h5[input_name][:]
-            test_data = test_h5[input_name][:]
-
-            train_shape = train_data.shape
-            test_shape = test_data.shape
-
-            comb_data[input_name] = mx.nd.zeros((train_shape[0]+test_shape[0], train_shape[1], width, height))
-            for i, img in enumerate(train_data):
-                img = img.transpose(1,2,0)
-                comb_data[input_name][i] = cv2.resize(img, (width, height)).reshape((train_shape[1],width,height))
-            for i, img in enumerate(test_data):
-                img = img.transpose(1, 2, 0)
-                comb_data[input_name][i+train_shape[0]] = cv2.resize(img, (width, height)).reshape((train_shape[1], width, height))
-
-            data_mean[input_name + '_'] = nd.array(comb_data[input_name][:].mean(axis=0))
-            data_std[input_name + '_'] = nd.array(comb_data[input_name][:].asnumpy().std(axis=0) + 1e-5)
-
-        comb_label = {}
-        for output_name in self._output_names_:
-            train_labels = train_h5[output_name][:]
-            test_labels = test_h5[output_name][:]
-            comb_label[output_name] = np.append(train_labels, test_labels, axis=0)
-
-
-        train_iter = mx.io.NDArrayIter(data=comb_data,
-                                       label=comb_label,
-                                       batch_size=batch_size)
-
-        test_iter = None
-
-        return train_iter, test_iter, data_mean, data_std
-
     def load_preprocessed_data(self, batch_size, preproc_lib):
         train_h5, test_h5 = self.load_h5_files()
 
@@ -147,6 +105,9 @@ class CNNDataLoader_RNNsearch:
             data_mean[input_name + '_'] = nd.array(train_data[input_name][:].mean(axis=0))