def _parse_eval_data(self, data):
"""Generates images and labels that are usable for model training.
Args:
data: a dict of Tensors produced by the decoder.
Returns:
images: the image tensor.
labels: a dict of Tensors that contains labels.
"""
shape = tf.shape(data['image'])
image = data['image'] / 255
boxes = data['groundtruth_boxes']
width = shape[0]
height = shape[1]
image, boxes = yolo_preprocess_ops.fit_preserve_aspect_ratio(
image, boxes, width=width, height=height, target_dim=self._image_w)
boxes = yolo_box_ops.yxyx_to_xcycwh(boxes)
# Find the best anchor for the ground truth labels to maximize the iou
best_anchors = yolo_preprocess_ops.get_best_anchor(
boxes, self._anchors, width=self._image_w, height=self._image_h)
boxes = yolo_preprocess_ops.pad_max_instances(boxes,
self._max_num_instances,
0)
classes = yolo_preprocess_ops.pad_max_instances(
data['groundtruth_classes'], self._max_num_instances, 0)
best_anchors = yolo_preprocess_ops.pad_max_instances(
best_anchors, self._max_num_instances, 0)
area = yolo_preprocess_ops.pad_max_instances(data['groundtruth_area'],
self._max_num_instances,
0)
is_crowd = yolo_preprocess_ops.pad_max_instances(
tf.cast(data['groundtruth_is_crowd'], tf.int32),
self._max_num_instances, 0)
labels = {
'source_id': data['source_id'],
'bbox': tf.cast(boxes, self._dtype),
'classes': tf.cast(classes, self._dtype),
'area': tf.cast(area, self._dtype),
'is_crowd': is_crowd,
'best_anchors': tf.cast(best_anchors, self._dtype),
'width': width,
'height': height,
'num_detections': tf.shape(data['groundtruth_classes'])[0],
}
grid = self._build_grid(labels,
self._image_w,
batch=False,
use_tie_breaker=self._use_tie_breaker)
labels.update({'grid_form': grid})
return image, labels
def test_pad_max_instances(self, input_shape, instances, pad_axis):
expected_output_shape = input_shape
expected_output_shape[pad_axis] = instances
output = preprocess_ops.pad_max_instances(np.ones(input_shape),
instances,
pad_axis=pad_axis)
self.assertAllEqual(expected_output_shape, tf.shape(output).numpy())