我们从Python开源项目中，提取了以下7个代码示例，用于说明如何使用tensorflow.sparse_reorder()。
def get_sparse_penalty_matrix(num_classes): '''Creates a sparse graph-fused lasso penalty matrix (zero'th order trendfiltering) under the assumption that the class bins are arranged along an evenly spaced p-dimensional grid.''' bins = [np.arange(c) for c in num_classes] idx_map = {t: idx for idx, t in enumerate(itertools.product(*bins))} indices = [] values = [] rows = 0 for idx1,t1 in enumerate(itertools.product(*bins)): for dim in xrange(len(t1)): if t1[dim] < (num_classes[dim]-1): t2 = t_offset(t1, dim, 1) idx2 = idx_map[t2] indices.append([rows, idx1]) values.append(1) indices.append([rows, idx2]) values.append(-1) rows += 1 # tensorflow version #D_shape = [rows, np.prod(num_classes)] #return tf.sparse_reorder(tf.SparseTensor(indices=indices, values=values, shape=D_shape)) # Use scipy's sparse libraries until tensorflow's sparse matrix multiplication is implemented fully D_shape = (rows, np.prod(num_classes)) row_indices = [x for x,y in indices] col_indices = [y for x,y in indices] return coo_matrix((values, (row_indices, col_indices)), shape=D_shape)
def scipy_sparse_coo_to_tensorflow_sparse(x): values = x.data indices = list(zip(x.row, x.col)) shape = x.shape return tf.sparse_reorder(tf.SparseTensor(indices=indices, values=values, dense_shape=shape))
def _generate_sketch_matrix(rand_h, rand_s, output_dim): """ Return a sparse matrix used for tensor sketch operation in compact bilinear pooling Args: rand_h: an 1D numpy array containing indices in interval `[0, output_dim)`. rand_s: an 1D numpy array of 1 and -1, having the same shape as `rand_h`. output_dim: the output dimensions of compact bilinear pooling. Returns: a sparse matrix of shape [input_dim, output_dim] for tensor sketch. """ # Generate a sparse matrix for tensor count sketch rand_h = rand_h.astype(np.int64) rand_s = rand_s.astype(np.float32) assert(rand_h.ndim==1 and rand_s.ndim==1 and len(rand_h)==len(rand_s)) assert(np.all(rand_h >= 0) and np.all(rand_h < output_dim)) input_dim = len(rand_h) indices = np.concatenate((np.arange(input_dim)[..., np.newaxis], rand_h[..., np.newaxis]), axis=1) sparse_sketch_matrix = tf.sparse_reorder( tf.SparseTensor(indices, rand_s, [input_dim, output_dim])) return sparse_sketch_matrix
def chebyshev5(self, x, L, Fout, K): N, M, Fin = x.get_shape() N, M, Fin = int(N), int(M), int(Fin) # Rescale Laplacian and store as a TF sparse tensor. Copy to not modify the shared L. L = scipy.sparse.csr_matrix(L) L = graph.rescale_L(L, lmax=2) L = L.tocoo() indices = np.column_stack((L.row, L.col)) L = tf.SparseTensor(indices, L.data, L.shape) L = tf.sparse_reorder(L) # Transform to Chebyshev basis x0 = tf.transpose(x, perm=[1, 2, 0]) # M x Fin x N x0 = tf.reshape(x0, [M, Fin*N]) # M x Fin*N x = tf.expand_dims(x0, 0) # 1 x M x Fin*N def concat(x, x_): x_ = tf.expand_dims(x_, 0) # 1 x M x Fin*N return tf.concat(0, [x, x_]) # K x M x Fin*N if K > 1: x1 = tf.sparse_tensor_dense_matmul(L, x0) x = concat(x, x1) for k in range(2, K): x2 = 2 * tf.sparse_tensor_dense_matmul(L, x1) - x0 # M x Fin*N x = concat(x, x2) x0, x1 = x1, x2 x = tf.reshape(x, [K, M, Fin, N]) # K x M x Fin x N x = tf.transpose(x, perm=[3,1,2,0]) # N x M x Fin x K x = tf.reshape(x, [N*M, Fin*K]) # N*M x Fin*K # Filter: Fin*Fout filters of order K, i.e. one filterbank per feature pair. W = self._weight_variable([Fin*K, Fout], regularization=False) x = tf.matmul(x, W) # N*M x Fout return tf.reshape(x, [N, M, Fout]) # N x M x Fout
def chebyshev5(self, x, L, Fout, K, regularization=False): N, M, Fin = x.get_shape() N, M, Fin = int(N), int(M), int(Fin) # Rescale Laplacian and store as a TF sparse tensor. Copy to not modify the shared L. L = scipy.sparse.csr_matrix(L) L = graph.rescale_L(L, lmax=2) L = L.tocoo() indices = np.column_stack((L.row, L.col)) L = tf.SparseTensor(indices, L.data, L.shape) L = tf.sparse_reorder(L) # Transform to Chebyshev basis x0 = tf.transpose(x, perm=[1, 2, 0]) # M x Fin x N x0 = tf.reshape(x0, [M, Fin*N]) # M x Fin*N x = tf.expand_dims(x0, 0) # 1 x M x Fin*N def concat(x, x_): x_ = tf.expand_dims(x_, 0) # 1 x M x Fin*N return tf.concat(0, [x, x_]) # K x M x Fin*N if K > 1: x1 = tf.sparse_tensor_dense_matmul(L, x0) x = concat(x, x1) for k in range(2, K): x2 = 2 * tf.sparse_tensor_dense_matmul(L, x1) - x0 # M x Fin*N x = concat(x, x2) x0, x1 = x1, x2 x = tf.reshape(x, [K, M, Fin, N]) # K x M x Fin x N x = tf.transpose(x, perm=[3,1,2,0]) # N x M x Fin x K x = tf.reshape(x, [N*M, Fin*K]) # N*M x Fin*K # Filter: Fin*Fout filters of order K, i.e. one filterbank per feature pair. W = self._weight_variable([Fin*K, Fout], regularization=regularization) x = tf.matmul(x, W) # N*M x Fout return tf.reshape(x, [N, M, Fout]) # N x M x Fout
def _train_fprop(self, state_below): idx, val = state_below X = tf.SparseTensor(tf.cast(idx, 'int64'), val, shape=[self.batchsize, self.prev_dim]) X_order = tf.sparse_reorder(X) XW = tf.sparse_tensor_dense_matmul(X_order, self.W, adjoint_a=False, adjoint_b=False) return tf.add(XW, self.b)
