def det_post_process_combined(params, cls_outputs, box_outputs, scales,
min_score_thresh, max_boxes_to_draw):
"""A combined version of det_post_process with dynamic batch size support."""
batch_size = tf.shape(list(cls_outputs.values())[0])[0]
cls_outputs_all = []
box_outputs_all = []
# Concatenates class and box of all levels into one tensor.
for level in range(params['min_level'], params['max_level'] + 1):
if params['data_format'] == 'channels_first':
cls_outputs[level] = tf.transpose(cls_outputs[level], [0, 2, 3, 1])
box_outputs[level] = tf.transpose(box_outputs[level], [0, 2, 3, 1])
cls_outputs_all.append(
tf.reshape(cls_outputs[level],
[batch_size, -1, params['num_classes']]))
box_outputs_all.append(
tf.reshape(box_outputs[level], [batch_size, -1, 4]))
cls_outputs_all = tf.concat(cls_outputs_all, 1)
box_outputs_all = tf.concat(box_outputs_all, 1)
# Create anchor_label for picking top-k predictions.
eval_anchors = anchors.Anchors(params['min_level'], params['max_level'],
params['num_scales'],
params['aspect_ratios'],
params['anchor_scale'],
params['image_size'])
anchor_boxes = eval_anchors.boxes
scores = tf.math.sigmoid(cls_outputs_all)
# apply bounding box regression to anchors
boxes = anchors.decode_box_outputs_tf(box_outputs_all, anchor_boxes)
boxes = tf.expand_dims(boxes, axis=2)
scales = tf.expand_dims(scales, axis=-1)
nmsed_boxes, nmsed_scores, nmsed_classes, valid_detections = (
tf.image.combined_non_max_suppression(boxes,
scores,
max_boxes_to_draw,
max_boxes_to_draw,
score_threshold=min_score_thresh,
clip_boxes=False))
del valid_detections # to be used in futue.
image_ids = tf.cast(tf.tile(tf.expand_dims(tf.range(batch_size), axis=1),
[1, max_boxes_to_draw]),
dtype=tf.float32)
y = nmsed_boxes[..., 0] * scales
x = nmsed_boxes[..., 1] * scales
height = nmsed_boxes[..., 2] * scales - y
width = nmsed_boxes[..., 3] * scales - x
detection_list = [
# Format: (image_ids, y, x, height, width, score, class)
image_ids,
y,
x,
height,
width,
nmsed_scores,
tf.cast(nmsed_classes + 1, tf.float32)
]
detections = tf.stack(detection_list, axis=2, name='detections')
return detections
def pre_nms(params, cls_outputs, box_outputs) -> Tuple[T, T, T]:
"""Detection post processing before nms.
It takes the multi-level class and box predictions from network, merge them
into unified tensors, and compute boxes, scores, and classes.
Args:
params: a dict of parameters.
cls_outputs: a list of tensors for classes, each tensor denotes a level
of logits with shape [N, H, W, num_class * num_anchors].
box_outputs: a list of tensors for boxes, each tensor ddenotes a level of
boxes with shape [N, H, W, 4 * num_anchors].
Returns:
A tuple of (boxes, scores, classes).
"""
cls_outputs, box_outputs = merge_class_box_level_outputs(
params, cls_outputs, box_outputs)
cls_outputs, box_outputs, classes, indices = topk_class_boxes(
params, cls_outputs, box_outputs)
# get boxes by apply bounding box regression to anchors.
eval_anchors = anchors.Anchors(params['min_level'], params['max_level'],
params['num_scales'], params['aspect_ratios'],
params['anchor_scale'], params['image_size'])
anchor_boxes = tf.gather(eval_anchors.boxes, indices)
boxes = anchors.decode_box_outputs_tf(box_outputs, anchor_boxes)
# convert logits to scores.
scores = tf.math.sigmoid(cls_outputs)
return boxes, scores, classes
