def _find_subpixel_maxima(x, kernel_size, sigma, upsample_factor, coordinate_scale=1, confidence_scale=255.): kernel = gaussian_kernel_2d(kernel_size, sigma) kernel = tf.expand_dims(kernel, 0) x_shape = tf.shape(x) rows = x_shape[1] cols = x_shape[2] max_vals = tf.reduce_max(tf.reshape(x, [-1, rows * cols]), axis=1) max_vals = tf.reshape(max_vals, [-1, 1]) / confidence_scale row_pad = rows // 2 - kernel_size // 2 col_pad = cols // 2 - kernel_size // 2 padding = [[0, 0], [row_pad, row_pad - 1], [col_pad, col_pad - 1]] kernel = tf.pad(kernel, padding) row_center = row_pad + (kernel_size // 2) col_center = col_pad + (kernel_size // 2) center = tf.stack([row_center, col_center]) center = tf.expand_dims(center, 0) center = tf.cast(center, dtype=tf.float32) shifts = _upsampled_registration(x, kernel, upsample_factor) shifts = center - shifts shifts *= coordinate_scale maxima = tf.concat([shifts[:, ::-1], max_vals], -1) return maxima
def sparse_bool_mask(x, mask, axis=0): # Only necessary if indices may have non-unique elements indices = tf.boolean_mask(tf.range(tf.shape(x)[axis]), mask) n_indices = tf.size(indices) # Get indices for the axis idx = x.indices[:, axis] # Find where indices match the selection eq = tf.equal(tf.expand_dims(idx, 1), tf.cast(indices, tf.int64)) # TODO this has quadratic cost # Mask for selected values sel = tf.reduce_any(eq, axis=1) # Selected values values_new = tf.boolean_mask(x.values, sel, axis=0) # New index value for selected elements n_indices = tf.cast(n_indices, tf.int64) idx_new = tf.reduce_sum(tf.cast(eq, tf.int64) * tf.range(n_indices), axis=1) idx_new = tf.boolean_mask(idx_new, sel, axis=0) # New full indices tensor indices_new = tf.boolean_mask(x.indices, sel, axis=0) indices_new = tf.concat([ indices_new[:, :axis], tf.expand_dims(idx_new, 1), indices_new[:, axis + 1:] ], axis=1) # New shape shape_new = tf.concat( [x.dense_shape[:axis], [n_indices], x.dense_shape[axis + 1:]], axis=0) return tf.SparseTensor(indices_new, values_new, shape_new)
def call(self, inputs): print("xxxx",inputs) expanded_tensor = ktf.expand_dims(inputs[0], -1) multiples = [1, self.number_of_transforms, 1, 1, 1] tiled_tensor = ktf.tile(expanded_tensor, multiples=multiples) repeated_tensor = ktf.reshape(tiled_tensor, ktf.shape(inputs[0]) * np.array([self.number_of_transforms, 1, 1, 1])) affine_transforms = inputs[1] / self.affine_mul affine_transforms = ktf.reshape(affine_transforms, (-1, 8)) tranformed = tf_affine_transform(repeated_tensor, affine_transforms) res = ktf.reshape(tranformed, [-1, self.number_of_transforms] + self.image_size) res = ktf.transpose(res, [0, 2, 3, 1, 4]) #Use masks if len(inputs) == 3: mask = ktf.transpose(inputs[2], [0, 2, 3, 1]) mask = ktf.image.resize_images(mask, self.image_size[:2], method=ktf.image.ResizeMethod.NEAREST_NEIGHBOR) res = res * ktf.expand_dims(mask, axis=-1) if self.aggregation_fn == 'none': res = ktf.reshape(res, [-1] + self.image_size[:2] + [self.image_size[2] * self.number_of_transforms]) elif self.aggregation_fn == 'max': res = ktf.reduce_max(res, reduction_indices=[-2]) elif self.aggregation_fn == 'avg': counts = ktf.reduce_sum(mask, reduction_indices=[-1]) counts = ktf.expand_dims(counts, axis=-1) res = ktf.reduce_sum(res, reduction_indices=[-2]) res /= counts res = ktf.where(ktf.is_nan(res), ktf.zeros_like(res), res) return res
def _col_kernel(upsampled_region_size, upsample_factor, axis_offsets, data_shape): data_shape_float = tf.cast(data_shape, tf.float32) col_constant = tf.cast(data_shape_float[2] * upsample_factor, tf.complex64) col_constant = (-1j * 2 * np.pi / col_constant) col_kernel_a = tf.range(0, data_shape_float[2], dtype=tf.float32) col_kernel_a = fftshift1d(col_kernel_a) col_kernel_a = tf.reshape(col_kernel_a, (-1, 1)) col_kernel_a -= tf.floor(data_shape_float[2] / 2.) col_kernel_a = tf.reshape(col_kernel_a, (1, -1)) col_kernel_a = tf.tile(col_kernel_a, (data_shape[0], 1)) col_kernel_b = tf.range(0, upsampled_region_size, dtype=tf.float32) col_kernel_b = tf.reshape(col_kernel_b, (1, -1)) col_kernel_b = tf.tile(col_kernel_b, (data_shape[0], 1)) col_kernel_b = tf.transpose(col_kernel_b) col_kernel_b -= tf.transpose(axis_offsets[:, 1]) col_kernel_b = tf.transpose(col_kernel_b) col_kernel_a = tf.expand_dims(col_kernel_a, 1) col_kernel_b = tf.expand_dims(col_kernel_b, -1) col_kernel = col_kernel_a * col_kernel_b col_kernel = tf.transpose(col_kernel, perm=(0, 2, 1)) col_kernel = col_constant * tf.cast(col_kernel, tf.complex64) col_kernel = tf.exp(col_kernel) return col_kernel
def _row_kernel(upsampled_region_size, upsample_factor, axis_offsets, data_shape): data_shape_float = tf.cast(data_shape, tf.float32) row_constant = tf.cast(data_shape_float[1] * upsample_factor, tf.complex64) row_constant = (-1j * 2 * np.pi / row_constant) row_kernel_a = tf.range(0, upsampled_region_size, dtype=tf.float32) row_kernel_a = tf.reshape(row_kernel_a, (1, -1)) row_kernel_a = tf.tile(row_kernel_a, (data_shape[0], 1)) row_kernel_a = tf.transpose(row_kernel_a) row_kernel_a = row_kernel_a - axis_offsets[:, 0] row_kernel_b = tf.range(0, data_shape_float[1], dtype=tf.float32) row_kernel_b = fftshift1d(row_kernel_b) row_kernel_b = tf.reshape(row_kernel_b, (1, -1)) row_kernel_b = tf.tile(row_kernel_b, (data_shape[0], 1)) row_kernel_b = row_kernel_b - tf.floor(data_shape_float[1] / 2.) row_kernel_a = tf.expand_dims(row_kernel_a, 1) row_kernel_b = tf.expand_dims(row_kernel_b, -1) row_kernel = tf.transpose(row_kernel_a) * row_kernel_b row_kernel = tf.transpose(row_kernel, perm=(0, 2, 1)) row_kernel = row_constant * tf.cast(row_kernel, tf.complex64) row_kernel = tf.exp(row_kernel) return row_kernel
def nn_loss(self, reference, target, neighborhood_size=(3, 3)): v_pad = neighborhood_size[0] // 2 h_pad = neighborhood_size[1] // 2 val_pad = ktf.pad(reference, [[0, 0], [v_pad, v_pad], [h_pad, h_pad], [0, 0]], mode='CONSTANT', constant_values=-10000) reference_tensors = [] for i_begin in range(0, neighborhood_size[0]): i_end = i_begin - neighborhood_size[0] + 1 i_end = None if i_end == 0 else i_end for j_begin in range(0, neighborhood_size[1]): j_end = j_begin - neighborhood_size[0] + 1 j_end = None if j_end == 0 else j_end sub_tensor = val_pad[:, i_begin:i_end, j_begin:j_end, :] reference_tensors.append(ktf.expand_dims(sub_tensor, -1)) reference = ktf.concat(reference_tensors, axis=-1) target = ktf.expand_dims(target, axis=-1) abs = ktf.abs(reference - target) norms = ktf.reduce_sum(abs, reduction_indices=[-2]) loss = ktf.reduce_min(norms, reduction_indices=[-1]) return loss
def call(self, inputs): mask = ktf.transpose(inputs[2], [0, 2, 3, 1]) # mask = ktf.image.resize_images(mask, self.image_size[:2], method=ktf.image.ResizeMethod.NEAREST_NEIGHBOR) if self.number_of_transforms == 11: # return inputs[0] * K.tile(ktf.expand_dims(1-mask[:,:,:,0], axis=3),(1,1,1,inputs[0].shape[-1])) return inputs[0] * ktf.expand_dims(1 - mask[:, :, :, 0], axis=3) else: return inputs[0] * ktf.expand_dims( K.clip(1 - K.sum(mask, 3), 0, 1), axis=3)
def tf_repeat_1d(x, repeats): """ Repeats each value `x[i]` a number of times `repeats[i]`. :param x: a rank 1 tensor; :param repeats: a rank 1 tensor; :return: a rank 1 tensor, of shape `(sum(repeats), )`. """ x = tf.expand_dims(x, 1) max_repeats = tf.reduce_max(repeats) tile_repeats = [1, max_repeats] arr_tiled = tf.tile(x, tile_repeats) mask = tf.less(tf.range(max_repeats), tf.expand_dims(repeats, 1)) result = tf.reshape(tf.boolean_mask(arr_tiled, mask), [-1]) return result
def gaussian_kernel_1d(size, sigma): size = tf.constant(size, dtype=tf.float32) sigma = tf.constant(sigma, dtype=tf.float32) x = tf.range(-(size // 2), (size // 2) + 1, dtype=tf.float32) kernel = 1 / (sigma * tf.sqrt(2 * np.pi)) kernel *= tf.exp(-0.5 * (x / sigma)**2) return tf.expand_dims(kernel, axis=-1)
def call(self, inputs): image = inputs[0] if len(inputs) == 2: style = inputs[1] style_mean, style_var = ktf.nn.moments(style, self.spatial_axis, keep_dims=True) else: style_mean = ktf.expand_dims( ktf.expand_dims(inputs[1], self.spatial_axis[0]), self.spatial_axis[1]) style_var = ktf.expand_dims( ktf.expand_dims(inputs[2], self.spatial_axis[0]), self.spatial_axis[1]) image_mean, image_var = ktf.nn.moments(image, self.spatial_axis, keep_dims=True) out = ktf.nn.batch_normalization(image, image_mean, image_var, style_mean, ktf.sqrt(style_var), self.eps) return out
def call(self, inputs): if len(inputs) == 3: X, A, I = inputs self.data_mode = 'graph' else: X, A = inputs I = tf.zeros(tf.shape(X)[:1], dtype=tf.int32) self.data_mode = 'single' if K.ndim(I) == 2: I = I[:, 0] A_is_sparse = K.is_sparse(A) # Get mask y = K.dot(X, K.l2_normalize(self.kernel)) N = K.shape(X)[-2] indices = ops.top_k(y[:, 0], I, self.ratio, self.top_k_var) mask = tf.scatter_nd(tf.expand_dims(indices, 1), tf.ones_like(indices), (N, )) # Multiply X and y to make layer differentiable features = X * self.gating_op(y) axis = 0 if len(K.int_shape( A)) == 2 else 1 # Cannot use negative axis in tf.boolean_mask # Reduce X X_pooled = tf.boolean_mask(features, mask, axis=axis) # Compute A^2 if A_is_sparse: A_dense = tf.sparse.to_dense(A) else: A_dense = A A_squared = K.dot(A, A_dense) # Reduce A A_pooled = tf.boolean_mask(A_squared, mask, axis=axis) A_pooled = tf.boolean_mask(A_pooled, mask, axis=axis + 1) if A_is_sparse: A_pooled = tf.contrib.layers.dense_to_sparse(A_pooled) output = [X_pooled, A_pooled] # Reduce I if self.data_mode == 'graph': I_pooled = tf.boolean_mask(I[:, None], mask)[:, 0] output.append(I_pooled) if self.return_mask: output.append(mask) return output
def batch_map_coordinates(input, coords, order=1): """Batch version of tf_map_coordinates""" input_shape = tf.shape(input) batch_size = input_shape[0] input_size = input_shape[1] #coords = tf.reshape(coords, (batch_size, -1, 2)) n_coords = tf.shape(coords)[1] coords = tf.clip_by_value(coords, 0, tf.cast(input_size, 'float32') - 1) coords_tl = tf.cast(tf.floor(coords), 'int32') coords_br = tf.cast(tf.ceil(coords), 'int32') coords_bl = tf.stack([coords_tl[..., 0], coords_br[..., 1]], axis=-1) coords_tr = tf.stack([coords_br[..., 0], coords_tl[..., 1]], axis=-1) idx = tf.range(batch_size) idx = tf.expand_dims(idx, -1) idx = tf.tile(idx, [1, n_coords]) idx = tf.reshape(idx, [-1]) def _get_vals_by_coords(input, coords): coords_0_flat = tf.reshape(coords[..., 0], [-1]) coords_1_flat = tf.reshape(coords[..., 1], [-1]) indices = tf.stack([idx, coords_0_flat, coords_1_flat], axis=-1) vals = tf.gather_nd(input, indices) vals = tf.reshape(vals, (batch_size, n_coords)) return vals vals_tl = _get_vals_by_coords(input, coords_tl) vals_br = _get_vals_by_coords(input, coords_br) vals_bl = _get_vals_by_coords(input, coords_bl) vals_tr = _get_vals_by_coords(input, coords_tr) h_offset = coords[..., 0] - tf.cast(coords_tl[..., 0], tf.float32) h_int_t = (((1.0 - h_offset) * vals_tl) + (h_offset * vals_tr)) h_int_b = (((1.0 - h_offset) * vals_bl) + (h_offset * vals_br)) v_offset = coords[..., 1] - tf.cast(coords_tl[..., 1], tf.float32) int_vals = (((1.0 - v_offset) * h_int_t) + (v_offset * h_int_b)) return int_vals
def batch_map_offsets(input, offsets, order=1): """Batch map offsets into input Adds index of every entry to the entry to make it's interpolation relevant to it's location """ input_shape = tf.shape(input) batch_size = input_shape[0] input_w = input_shape[1] input_h = input_shape[2] offsets = tf.reshape(offsets, (batch_size, -1, 2)) ind_add = tf.meshgrid(tf.range(input_w), tf.range(input_h), indexing='ij') ind_add = tf.stack(ind_add, axis=-1) ind_add = tf.cast(ind_add, 'float32') ind_add = tf.reshape(ind_add, (-1, 2)) ind_add = tf.expand_dims(ind_add, 0) ind_add = tf.tile(ind_add, [batch_size, 1, 1]) coords = offsets + ind_add int_vals = batch_map_coordinates(input, coords) return int_vals
def batch_map_coordinates(input, coords, n_coords): """Batch version of tf_map_coordinates""" #init_input_shape = input.get_shape() #input = tf.reshape(input, (-1, init_input_shape[3])) #coords = tf.reshape(coords, (-1, n_coords * 2)) input_shape = input.get_shape() input_h = input_shape[1].value input_w = input_shape[2].value #batch_size = input_shape[0] #input_size = input_shape[1] #coords = tf.reshape(coords, (batch_size, -1, 2)) #n_coords = tf.shape(coords)[1] coords_h = tf.clip_by_value(coords[..., :n_coords], 0, tf.cast(input_h, 'float32') - 1) coords_w = tf.clip_by_value(coords[..., n_coords:], 0, tf.cast(input_w, 'float32') - 1) coords = tf.stack([coords_h, coords_w], axis=-1) coords_tl = tf.cast(tf.floor(coords), 'float32') coords_br = tf.cast(tf.ceil(coords), 'float32') coords_bl = tf.stack([coords_tl[..., 0], coords_br[..., 1]], axis=-1) coords_tr = tf.stack([coords_br[..., 0], coords_tl[..., 1]], axis=-1) #idx = tf.range(batch_size) #idx = tf.expand_dims(idx, -1) #idx = tf.tile(idx, [1, n_coords]) #idx = tf.reshape(idx, [-1]) def _get_vals_by_coords(input, coords, n_coords): coords_shape = tf.shape(coords) input_shape = input.get_shape() input_w = input_shape[2].value input_h = input_shape[1].value channel_size = input_shape[3].value batch_size = tf.shape(input)[0] input = tf.transpose(input, (0, 3, 1, 2)) input = tf.reshape(input, (-1, channel_size, input_h * input_w)) indices = coords[..., 0] * input_w + coords[..., 1] #indices = tf.expand_dims(indices, axis=1) #indices = tf.tile(indices, [1, channel_size, 1, 1, 1]) #indices = tf.reshape(indices, (-1, channel_size, input_h * input_w * n_coords)) #indices = tf.transpose(indices, (0, 3, 1, 2)) indices = tf.reshape(indices, (-1, input_h * input_w * n_coords)) indices = tf.cast(indices, 'int32') #indices = tf.reshape(indices, [-1]) #input = tf.reshape(input, [-1]) vals = tf.gather(input, indices[0], axis=-1) #vals = tf.map_fn(lambda x: tf.gather(x[0], x[1], axis=-1), (input,indices), dtype=tf.float32) vals = tf.reshape(vals, (-1, channel_size, input_h, input_w, n_coords)) return vals vals_tl = (1 + (coords_tl[..., 0] - coords[..., 0])) * \ (1 + (coords_tl[..., 1] - coords[..., 1])) vals_br = (1 - (coords_br[..., 0] - coords[..., 0])) * \ (1 - (coords_br[..., 1] - coords[..., 1])) vals_bl = (1 + (coords_bl[..., 0] - coords[..., 0])) * \ (1 + (coords_bl[..., 1] - coords[..., 1])) vals_tr = (1 - (coords_tr[..., 0] - coords[..., 0])) * \ (1 - (coords_tr[..., 1] - coords[..., 1])) x_vals_tl = _get_vals_by_coords(input, coords_tl, n_coords) x_vals_br = _get_vals_by_coords(input, coords_br, n_coords) x_vals_bl = _get_vals_by_coords(input, coords_bl, n_coords) x_vals_tr = _get_vals_by_coords(input, coords_tr, n_coords) #h_offset = coords[..., 0] - tf.cast(coords_tl[..., 0], tf.float32) #h_int_t = (((1.0 - h_offset) * vals_tl) + (h_offset * vals_tr)) #h_int_b = (((1.0 - h_offset) * vals_bl) + (h_offset * vals_br)) #v_offset = coords[..., 1] - tf.cast(coords_tl[..., 1], tf.float32) #int_vals = (((1.0 - v_offset) * h_int_t) + (v_offset * h_int_b)) int_vals = tf.expand_dims(vals_tl, 1) * x_vals_tl + \ tf.expand_dims(vals_br, 1) * x_vals_br + \ tf.expand_dims(vals_bl, 1) * x_vals_bl + \ tf.expand_dims(vals_tr, 1) * x_vals_tr return int_vals
def build(self, input_shape): self.xx, self.yy = ktf.meshgrid(ktf.range(self.image_size[1]), ktf.range(self.image_size[0])) self.xx = ktf.expand_dims(ktf.cast(self.xx, 'float32'), 2) self.yy = ktf.expand_dims(ktf.cast(self.yy, 'float32'), 2)