B ӻd@sHdZddlmZddlmZddZddZdd Zd d Zd d ZdS)z-Utility methods related to kernelized layers.) array_ops)math_opscCs8t|j}|dkr td||dkr4t|dS|S)zFIf input tensor is a vector (i.e., has rank 1), converts it to matrix.)z8The input tensor should have rank 1 or 2. Given rank: {}rr)lenshape ValueErrorformatr expand_dims)uZu_rankr `/var/www/html/venv/lib/python3.7/site-packages/tensorflow/python/keras/utils/kernelized_utils.py _to_matrixs  rcCst|}t|}|j}|j}|d|dkrDtd|d|dtt|dd|ddg}tt|d|dddg}||fS)zFAligns x and y tensors to allow computations over pairs of their rows.rzLThe outermost dimensions of the input tensors should match. Given: {} vs {}.r)rrrr rZtiler )xyZx_matrixZy_matrixZx_shapeZy_shapeZx_tileZy_tiler r r _align_matrices srcCs t|}t|}tj||ddS)NT)Z transpose_b)rrmatmul)r vr r r inner_product2srcCs:t||\}}tt||d}t| d||S)aComputes exact Gaussian kernel value(s) for tensors x and y and stddev. The Gaussian kernel for vectors u, v is defined as follows: K(u, v) = exp(-||u-v||^2 / (2* stddev^2)) where the norm is the l2-norm. x, y can be either vectors or matrices. If they are vectors, they must have the same dimension. If they are matrices, they must have the same number of columns. In the latter case, the method returns (as a matrix) K(u, v) values for all pairs (u, v) where u is a row from x and v is a row from y. Args: x: a tensor of rank 1 or 2. It's shape should be either [dim] or [m, dim]. y: a tensor of rank 1 or 2. It's shape should be either [dim] or [n, dim]. stddev: The width of the Gaussian kernel. Returns: A single value (scalar) with shape (1, 1) (if x, y are vectors) or a matrix of shape (m, n) with entries K(u, v) (where K is the Gaussian kernel) for all (u,v) pairs where u, v are rows from x and y respectively. Raises: ValueError: if the shapes of x, y are not compatible. r)rr reduce_sumZsquared_differenceexp)rrstddev x_aligned y_alignedZdiff_squared_l2_normr r r exact_gaussian_kernel8srcCs8t||\}}ttt||d}t| |S)aComputes exact Laplacian kernel value(s) for tensors x and y using stddev. The Laplacian kernel for vectors u, v is defined as follows: K(u, v) = exp(-||u-v|| / stddev) where the norm is the l1-norm. x, y can be either vectors or matrices. If they are vectors, they must have the same dimension. If they are matrices, they must have the same number of columns. In the latter case, the method returns (as a matrix) K(u, v) values for all pairs (u, v) where u is a row from x and v is a row from y. Args: x: a tensor of rank 1 or 2. It's shape should be either [dim] or [m, dim]. y: a tensor of rank 1 or 2. It's shape should be either [dim] or [n, dim]. stddev: The width of the Gaussian kernel. Returns: A single value (scalar) with shape (1, 1) if x, y are vectors or a matrix of shape (m, n) with entries K(u, v) (where K is the Laplacian kernel) for all (u,v) pairs where u, v are rows from x and y respectively. Raises: ValueError: if the shapes of x, y are not compatible. r)rrrabssubtractr)rrrrrZ diff_l1_normr r r exact_laplacian_kernelVsrN) __doc__Ztensorflow.python.opsrrrrrrrr r r r s