def call(self, inputs, output_shape=None):
updates, mask = inputs[0], inputs[1]
with tf.compat.v1.variable_scope(self.name):
mask = K.cast(mask, "int32")
input_shape = tf.shape(updates, out_type="int32")
# calculation new shape
if output_shape is None:
output_shape = (
input_shape[0],
input_shape[1] * self.size[0],
input_shape[2] * self.size[1],
input_shape[3],
)
self.output_shape1 = output_shape
# calculation indices for batch, height, width and feature maps
one_like_mask = K.ones_like(mask, dtype="int32")
batch_shape = K.concatenate([[input_shape[0]], [1], [1], [1]],
axis=0)
batch_range = K.reshape(tf.range(output_shape[0], dtype="int32"),
shape=batch_shape)
b = one_like_mask * batch_range
y = mask // (output_shape[2] * output_shape[3])
x = (mask // output_shape[3]) % output_shape[2]
feature_range = tf.range(output_shape[3], dtype="int32")
f = one_like_mask * feature_range
# transpose indices & reshape update values to one dimension
updates_size = tf.size(updates)
indices = K.transpose(
K.reshape(K.stack([b, y, x, f]), [4, updates_size]))
values = K.reshape(updates, [updates_size])
ret = tf.scatter_nd(indices, values, output_shape)
return ret
def call(self, QKVs):
"""Core logic of multi-head self attention.
Args:
QKVs (list): inputs of multi-head self attention i.e. query, key and value.
Returns:
object: ouput tensors.
"""
if len(QKVs) == 3:
Q_seq, K_seq, V_seq = QKVs
Q_len, V_len = None, None
elif len(QKVs) == 5:
Q_seq, K_seq, V_seq, Q_len, V_len = QKVs
Q_seq = K.dot(Q_seq, self.WQ)
Q_seq = K.reshape(Q_seq,
shape=(-1, K.shape(Q_seq)[1], self.multiheads,
self.head_dim))
Q_seq = K.permute_dimensions(Q_seq, pattern=(0, 2, 1, 3))
K_seq = K.dot(K_seq, self.WK)
K_seq = K.reshape(K_seq,
shape=(-1, K.shape(K_seq)[1], self.multiheads,
self.head_dim))
K_seq = K.permute_dimensions(K_seq, pattern=(0, 2, 1, 3))
V_seq = K.dot(V_seq, self.WV)
V_seq = K.reshape(V_seq,
shape=(-1, K.shape(V_seq)[1], self.multiheads,
self.head_dim))
V_seq = K.permute_dimensions(V_seq, pattern=(0, 2, 1, 3))
A = einsum("abij, abkj -> abik", Q_seq, K_seq) / K.sqrt(
K.cast(self.head_dim, dtype="float32"))
A = K.permute_dimensions(
A, pattern=(0, 3, 2, 1)
) # A.shape=[batch_size,K_sequence_length,Q_sequence_length,self.multiheads]
A = self.Mask(A, V_len, "add")
A = K.permute_dimensions(A, pattern=(0, 3, 2, 1))
if self.mask_right:
ones = K.ones_like(A[:1, :1])
lower_triangular = K.tf.matrix_band_part(ones,
num_lower=-1,
num_upper=0)
mask = (ones - lower_triangular) * 1e12
A = A - mask
A = K.softmax(A)
O_seq = einsum("abij, abjk -> abik", A, V_seq)
O_seq = K.permute_dimensions(O_seq, pattern=(0, 2, 1, 3))
O_seq = K.reshape(O_seq,
shape=(-1, K.shape(O_seq)[1], self.output_dim))
O_seq = self.Mask(O_seq, Q_len, "mul")
return O_seq
def yolo_eval(yolo_outputs,
anchors,
num_classes,
image_shape,
max_boxes=80,
score_threshold=.5,
iou_threshold=.5):
"""Evaluate YOLO model on given input and return filtered boxes."""
input_shape = K.shape(yolo_outputs)[1:3] * grid_size_multiplier
boxes = []
box_scores = []
polygons = []
for l in range(1):
_boxes, _box_scores, _polygons = yolo_boxes_and_scores(
yolo_outputs, anchors[anchor_mask[l]], num_classes, input_shape,
image_shape)
boxes.append(_boxes)
box_scores.append(_box_scores)
polygons.append(_polygons)
boxes = K.concatenate(boxes, axis=0)
box_scores = K.concatenate(box_scores, axis=0)
polygons = K.concatenate(polygons, axis=0)
mask = box_scores >= score_threshold
box_scores >= score_threshold
max_boxes_tensor = K.constant(max_boxes, dtype='int32')
boxes_ = []
scores_ = []
classes_ = []
polygons_ = []
for c in range(num_classes):
# TODO: use keras backend instead of tf.
class_boxes = tf.boolean_mask(boxes, mask[:, c])
class_polygons = tf.boolean_mask(polygons, mask[:, c])
class_box_scores = tf.boolean_mask(box_scores[:, c], mask[:, c])
nms_index = tf.image.non_max_suppression(class_boxes,
class_box_scores,
max_boxes_tensor,
iou_threshold=iou_threshold)
class_boxes = K.gather(class_boxes, nms_index)
class_box_scores = K.gather(class_box_scores, nms_index)
class_polygons = K.gather(class_polygons, nms_index)
classes = K.ones_like(class_box_scores, 'int32') * c
boxes_.append(class_boxes)
scores_.append(class_box_scores)
classes_.append(classes)
polygons_.append(class_polygons)
polygons_ = K.concatenate(polygons_, axis=0)
boxes_ = K.concatenate(boxes_, axis=0)
scores_ = K.concatenate(scores_, axis=0)
classes_ = K.concatenate(classes_, axis=0)
return boxes_, scores_, classes_, polygons_
def yolo_eval(yolo_outputs,
anchors,
num_classes,
image_shape,
max_boxes=20,
score_threshold=.6,
iou_threshold=.5):
"""Evaluate YOLO model on given input and return filtered boxes."""
num_layers = len(yolo_outputs)
anchor_mask = [[6, 7, 8], [3, 4, 5], [0, 1, 2]] if num_layers == 3 else [[
3, 4, 5
], [1, 2, 3]] # default setting
input_shape = K.shape(yolo_outputs[0])[1:3] * 32
boxes = []
box_scores = []
for l in range(num_layers):
_boxes, _box_scores = yolo_boxes_and_scores(yolo_outputs[l],
anchors[anchor_mask[l]],
num_classes, input_shape,
image_shape)
boxes.append(_boxes)
box_scores.append(_box_scores)
boxes = K.concatenate(boxes, axis=0)
box_scores = K.concatenate(box_scores, axis=0)
mask = box_scores >= score_threshold
max_boxes_tensor = K.constant(max_boxes, dtype='int32')
boxes_ = []
scores_ = []
classes_ = []
for c in range(num_classes):
# TODO: use keras backend instead of tf.
class_boxes = tf.boolean_mask(boxes, mask[:, c])
class_box_scores = tf.boolean_mask(box_scores[:, c], mask[:, c])
nms_index = tf.image.non_max_suppression(class_boxes,
class_box_scores,
max_boxes_tensor,
iou_threshold=iou_threshold)
class_boxes = K.gather(class_boxes, nms_index)
class_box_scores = K.gather(class_box_scores, nms_index)
classes = K.ones_like(class_box_scores, 'int32') * c
boxes_.append(class_boxes)
scores_.append(class_box_scores)
classes_.append(classes)
boxes_ = K.concatenate(boxes_, axis=0)
scores_ = K.concatenate(scores_, axis=0)
classes_ = K.concatenate(classes_, axis=0)
return boxes_, scores_, classes_