local_convolution_2d(x, W, b=None, stride=1)¶
Two-dimensional local convolution function.
Locally-connected function for 2D inputs. Works similarly to convolution_2d, except that weights are unshared, that is, a different set of filters is applied at each different patch of the input. It takes two or three variables: the input image
x, the filter weight
W, and optionally, the bias vector
Notation: here is a notation for dimensionalities.
\(n\) is the batch size.
\(c_I\) is the number of the input.
\(c_O\) is the number of output channels.
\(h\) and \(w\) are the height and width of the input image, respectively.
\(h_O\) and \(w_O\) are the height and width of the output image, respectively.
\(k_H\) and \(k_W\) are the height and width of the filters, respectively.
stride (int or pair of ints) – Stride of filter applications.
stride=(s, s)are equivalent.
Output variable. Its shape is \((n, c_I * c_O, h_O, w_O)\).
- Return type
LocalConvolution2Dfunction computes correlations between filters and patches of size \((k_H, k_W)\) in
x. But unlike
LocalConvolution2Dhas a separate filter for each patch of the input
\((h_O, w_O)\) is determined by the equivalent equation of
Convolution2D, without any padding
If the bias vector is given, then it is added to all spatial locations of the output of convolution.
LocalConvolution2Dto manage the model parameters
>>> x = np.random.uniform(0, 1, (2, 3, 7, 7)) >>> W = np.random.uniform(0, 1, (2, 5, 5, 3, 3, 3)) >>> b = np.random.uniform(0, 1, (2, 5, 5)) >>> y = F.local_convolution_2d(x, W, b) >>> y.shape (2, 2, 5, 5)