def giou(boxlist1, boxlist2, scope=None):
"""Computes pairwise generalized IOU between two boxlists.
Args:
boxlist1: BoxList holding N boxes
boxlist2: BoxList holding M boxes
scope: name scope.
Returns:
a tensor with shape [N, M] representing the pairwise GIoU loss.
"""
with tf.name_scope(scope, 'PairwiseGIoU'):
n = boxlist1.num_boxes()
m = boxlist2.num_boxes()
boxes1 = tf.repeat(boxlist1.get(), repeats=m, axis=0)
boxes2 = tf.tile(boxlist2.get(), multiples=[n, 1])
return tf.reshape(ops.giou(boxes1, boxes2), [n, m])
def _compute_loss(self, prediction_tensor, target_tensor, weights):
"""Compute loss function.
Args:
prediction_tensor: A float tensor of shape [batch_size, num_anchors, 4]
representing the decoded predicted boxes
target_tensor: A float tensor of shape [batch_size, num_anchors, 4]
representing the decoded target boxes
weights: a float tensor of shape [batch_size, num_anchors]
Returns:
loss: a float tensor of shape [batch_size, num_anchors] tensor
representing the value of the loss function.
"""
batch_size, num_anchors, _ = shape_utils.combined_static_and_dynamic_shape(
prediction_tensor)
predicted_boxes = tf.reshape(prediction_tensor, [-1, 4])
target_boxes = tf.reshape(target_tensor, [-1, 4])
per_anchor_iou_loss = 1 - ops.giou(predicted_boxes, target_boxes)
return tf.reshape(tf.reshape(weights, [-1]) * per_anchor_iou_loss,
[batch_size, num_anchors])