finalizing bilinear_upsampling

theano/tensor/nnet/abstract_conv.py

@@ -1556,8 +1556,7 @@ def bilinear_kernel_1D(ratio, normalize=True):
 
 def frac_bilinear_upsampling(input,
                              ratio=None,
-                             frac_ratio=None,
-                             use_1D_kernel=False):
+                             frac_ratio=None):
     """Compute bilinear upsampling
     This function will build the symbolic graph for upsampling
     a tensor by the given ratio using bilinear interpolation.
@@ -1576,11 +1575,6 @@ def frac_bilinear_upsampling(input,
         represented as (numerator, denominator). If row and col ratios are
         different frac_ratio should be a tuple of fractional ratios, i.e
         a tuple of tuples.
-    use_1D_kernel: bool
-        if set to true, row and column will be upsampled seperately by 1D
-        kernels, otherwise they are upsampled together using a 2D kernel. The
-        final result is the same, only the speed can differ, given factors such
-        as upsampling ratio.
     Returns
     -------
     symbolic 4D tensor
@@ -1598,15 +1592,11 @@ def frac_bilinear_upsampling(input,
         never both at once.
     """
 
-    if ratio and frac_ratio:
-        raise ValueError("can't use ratio and frac_ratio together")
-    if not (ratio or frac_ratio):
-        raise ValueError("No ratio (or frac_ratio) provided")
-
     T = theano.tensor
     row, col = input.shape[2:]
     up_input = input.reshape((-1, 1, row, col))
-    # redefince the ratio depending of the case
+
+    # redefince the ratio depending on the case
     if frac_ratio is None:
         if not isinstance(ratio, tuple):
             ratio = (ratio, ratio)
@@ -1642,45 +1632,33 @@ def frac_bilinear_upsampling(input,
     pad = double_pad // 2
 
     # build pyramidal kernel
-    if use_1D_kernel:
-        kern = bilinear_kernel_1D(ratio=ratio[0])[np.newaxis, np.newaxis,
-                                                  :, np.newaxis]
-    else:
     kern = bilinear_kernel_2D(ratio=ratio)[np.newaxis, np.newaxis, :, :]
 
+    # add corresponding padding
     pad_kern = T.concatenate((T.zeros(tuple(kern.shape[:2]) + (pad[0], kern.shape[-1])),
                               kern,
                               T.zeros(tuple(kern.shape[:2]) + (double_pad[0]-pad[0], kern.shape[-1]))),
                              axis=2)
-
-    if use_1D_kernel:
-        # for 1D kernel, upsample along rows
-        upsamp = T.nnet.conv2d(pad_kern, concat_mat, border_mode='valid', filter_dilation=(ratio[0], 1))
-        upsamp = upsamp.dimshuffle((1, 0, 2, 3))
-        pad_kern = bilinear_kernel_1D(ratio=ratio[1])[np.newaxis, np.newaxis, np.newaxis, :]
-
     pad_kern = T.concatenate((T.zeros(tuple(pad_kern.shape[:3]) + (pad[1],)),
                               pad_kern,
                               T.zeros(tuple(pad_kern.shape[:3]) + (double_pad[1]-pad[1],))),
                              axis=3)
-    if use_1D_kernel:
-        upsamp = T.nnet.conv2d(pad_kern, upsamp, border_mode='valid', filter_dilation=(1, ratio[1]),
-                               subsample=(1, 1))
-    else:
-        upsamp = T.nnet.conv2d(pad_kern, concat_mat, border_mode='valid', filter_dilation=ratio,
-                               subsample=subsample)
-    up_img_sh = T.ceil(T.as_tensor([row, col]) * np.array(ratio) / np.array(subsample)).astype('int64')
 
+    # upsample the input by passing it as kernl of conv and using filter_dilation
+    upsamp = T.nnet.conv2d(pad_kern, concat_mat, border_mode='valid',
+                           filter_dilation=ratio, subsample=subsample)
+
+    up_img_sh = T.ceil(T.as_tensor([row, col]) * np.array(ratio) / np.array(subsample)).astype('int64')
     return upsamp.reshape((input.shape[0], input.shape[1], up_img_sh[0], up_img_sh[1]))
 
 
 def bilinear_upsampling(input,
-                        ratio,
+                        ratio=None,
+                        frac_ratio=None,
                         batch_size=None,
                         num_input_channels=None,
                         use_1D_kernel=True):
     """Compute bilinear upsampling
-
     This function will build the symbolic graph for upsampling
     a tensor by the given ratio using bilinear interpolation.
 
@@ -1689,46 +1667,54 @@ def bilinear_upsampling(input,
     input: symbolic 4D tensor
         mini-batch of feature map stacks, of shape (batch size,
         input channels, input rows, input columns) that will be upsampled.
-
     ratio: `int or Constant or Scalar Tensor of int* dtype`
         the ratio by which the input is upsampled in the 2D space (row and
         col size).
-
-    batch_size: None, int or Constant variable
-        The size of the first dimension of the input variable.
-        Optional, possibly used to choose an optimal implementation.
-        batch_size will be used only if num_input_channels is not None.
-
-    num_input_channels: None, int or Constant variable
-        The size of the second dimension of the input variable.
-        Optional, possibly used to choose an optimal implementation.
-        num_input_channels will be used only if batch_size is not None.
-
+    frac_ratio: None, tuple of int or tuple of tuples of int
+        The tuple defining the fractional ratio by which the input is
+        upsampled in the 2D space. One fractional ratio should be
+        represented as (numerator, denominator). If row and col ratios are
+        different frac_ratio should be a tuple of fractional ratios, i.e
+        a tuple of tuples.
     use_1D_kernel: bool
         if set to true, row and column will be upsampled seperately by 1D
         kernels, otherwise they are upsampled together using a 2D kernel. The
         final result is the same, only the speed can differ, given factors such
         as upsampling ratio.
-
     Returns
     -------
     symbolic 4D tensor
         set of feature maps generated by bilinear upsampling. Tensor
-        is of shape (batch size, num_input_channels, input row size * ratio,
-        input column size * ratio)
-
+        is of shape (batch size, num_input_channels, input row size * row ratio,
+        input column size * column ratio). Each of these ratios can be fractional.
     Notes
     -----
-
     :note: The kernel used for bilinear interpolation is fixed (not learned).
-
     :note: When the upsampling ratio is even, the last row and column is
         repeated one extra time compared to the first row and column which makes
         the upsampled tensor asymmetrical on both sides. This does not happen when
         the upsampling ratio is odd.
-
+    :note: This function must get either ratio or frac_ratio as parameter and
+        never both at once.
     """
 
+    if ratio and frac_ratio:
+        raise ValueError("can't use ratio and frac_ratio together")
+    if not (ratio or frac_ratio):
+        raise ValueError("No ratio (or frac_ratio) provided")
+
+    if frac_ratio:
+        if use_1D_kernel:
+            raise ValueError('For fractional ratios 1D kernel'
+                             'method not implemented. You may want to pass '
+                             'use_1D_kernel as False')
+
+    if not use_1D_kernel:
+        return frac_bilinear_upsampling(input,
+                                        ratio=ratio,
+                                        frac_ratio=frac_ratio)
+
+    # the remaining case if integer ratio with use_1D_kernel
     T = theano.tensor
     try:
         up_bs = batch_size * num_input_channels

theano/tensor/nnet/tests/test_abstract_conv.py

@@ -23,7 +23,6 @@ from theano.tensor.nnet.abstract_conv import AbstractConv2d_gradWeights
 from theano.tensor.nnet.abstract_conv import bilinear_kernel_1D
 from theano.tensor.nnet.abstract_conv import bilinear_kernel_2D
 from theano.tensor.nnet.abstract_conv import bilinear_upsampling
-from theano.tensor.nnet.abstract_conv import frac_bilinear_upsampling
 from theano.tensor.nnet.abstract_conv import separable_conv2d, separable_conv3d
 from theano.tensor.nnet.conv import ConvOp
 from theano.tensor.nnet.corr import (CorrMM, CorrMM_gradWeights,
@@ -1299,8 +1298,9 @@ class TestBilinearUpsampling(unittest.TestCase):
                             [[5, 6], [7, 8]],
                             [[9, 10], [11, 12]]],
                            ndmin=4).astype(theano.config.floatX)
-        up_x = frac_bilinear_upsampling(input=input_x,
-                                        frac_ratio=((7, 4), (5, 3)))
+        up_x = bilinear_upsampling(input=input_x,
+                                   frac_ratio=((7, 4), (5, 3)))#,
+                                #    use_1D_kernel=False)
         num_up_x = np.array(
             [[[[1., 1.2, 1.8, 2.],
               [1.28571429, 1.48571429, 2.08571429, 2.28571429],