update raise conditions for invalid data formats

src/model_modules/advanced_paddings.py

@@ -27,7 +27,11 @@ class PadUtils:
         """
         if strides != 1:
             raise NotImplementedError("Strides other than 1 not implemented!")
+        if not all(isinstance(k, int) for k in kernel_size):
+            raise ValueError(f"The `kernel_size` argument must have a tuple of integers. Got: {kernel_size}")
+
         ks = np.array(kernel_size, dtype=np.int64)
+
         if any(k <= 0 for k in ks):
             raise ValueError(f"All values of kernel_size must be > 0. Got: {kernel_size} ")
 
@@ -36,8 +40,9 @@ class PadUtils:
             # convert numpy int to base int
             pad = [np.asscalar(v) for v in pad]
             return tuple(pad)
+            # return tuple(PadUtils.check_padding_format(pad))
         else:
-            raise NotImplementedError("even kernel size not implemented")
+            raise NotImplementedError(f"even kernel size not implemented. Got {kernel_size}")
 
     @staticmethod
     def spatial_2d_padding(padding=((1, 1), (1, 1)), data_format=None):
@@ -74,6 +79,16 @@ class PadUtils:
             if len(padding) != 2:
                 raise ValueError('`padding` should have two elements. '
                                  'Found: ' + str(padding))
+            for idx_pad, sub_pad in enumerate(padding):
+                if isinstance(sub_pad, str):
+                    raise ValueError(f'`padding[{idx_pad}]` is str but must be int')
+                if hasattr(sub_pad, '__len__'):
+                    if len(sub_pad) != 2:
+                        raise ValueError(f'`padding[{idx_pad}]` should have one or two elements. '
+                                         f'Found: {padding[idx_pad]}')
+                    if not all(isinstance(sub_k, int) for sub_k in padding[idx_pad]):
+                        raise ValueError(f'`padding[{idx_pad}]` should have one or two elements of type int. ' 
+                                         f"Found:{padding[idx_pad]} of type {[type(sub_k) for sub_k in padding[idx_pad]]}")
             height_padding = conv_utils.normalize_tuple(padding[0], 2,
                                                         '1st entry of padding')
             if not all(k >= 0 for k in height_padding):
@@ -239,17 +254,18 @@ class SymmetricPadding2D(_ZeroPadding):
 if __name__ == '__main__':
     from keras.models import Model
     from keras.layers import Conv2D, Flatten, Dense, Input
+
     kernel_1 = (3, 3)
     kernel_2 = (5, 5)
     x = np.array(range(2000)).reshape(-1, 10, 10, 1)
     y = x.mean(axis=(1, 2))
 
     x_input = Input(shape=x.shape[1:])
-    pad1 = PadUtils.get_padding_for_same(kernel_1)
+    pad1 = PadUtils.get_padding_for_same(kernel_size=kernel_1)
     x_out = ReflectionPadding2D(padding=pad1, name="RefPAD")(x_input)
     x_out = Conv2D(5, kernel_size=kernel_1, activation='relu')(x_out)
 
-    pad2 = PadUtils.get_padding_for_same(kernel_2)
+    pad2 = PadUtils.get_padding_for_same(kernel_size=kernel_2)
     x_out = SymmetricPadding2D(padding=pad2, name="SymPAD")(x_out)
     x_out = Conv2D(2, kernel_size=kernel_2, activation='relu')(x_out)
     x_out = Flatten()(x_out)
@@ -258,5 +274,6 @@ if __name__ == '__main__':
     model = Model(inputs=x_input, outputs=x_out)
     model.compile('adam', loss='mse')
     model.summary()
+    model.fit(x, y, epochs=10)