def encode_labels(self, gt_boxes, gt_labels):
target_boxes = box_list.BoxList(gt_boxes)
encoded_classes, _, encoded_boxes, _, matches = self.assigner.assign(
self.default_boxes, target_boxes, gt_labels)
num_matched_boxes = tf.reduce_sum(
tf.cast(tf.not_equal(matches.match_results, -1), tf.float32))
return encoded_classes, encoded_boxes, num_matched_boxes
def accuracy_function(self, inputs, logits):
"""Returns the ops to measure the mean precision of the model."""
try:
from cnn_quantization.tf_cnn_benchmarks import ssd_dataloader # pylint: disable=g-import-not-at-top
from tensorflow_models.object_detection.box_coders import faster_rcnn_box_coder # pylint: disable=g-import-not-at-top
from tensorflow_models.object_detection.core import box_coder # pylint: disable=g-import-not-at-top
from tensorflow_models.object_detection.core import box_list # pylint: disable=g-import-not-at-top
except ImportError:
raise ImportError(
'To use the COCO dataset, you must clone the '
'repo https://github.com/tensorflow/models and add '
'tensorflow/models and tensorflow/models/research to '
'the PYTHONPATH, and compile the protobufs; '
'To evaluate using COCO'
'metric, download and install Python COCO API from'
'https://github.com/cocodataset/cocoapi')
# Unpack model output back to locations and confidence scores of predictions
# pred_locs: relative locations (coordiates) of objects in all SSD boxes
# shape: [batch_size, NUM_SSD_BOXES, 4]
# pred_labels: confidence scores of objects being of all categories
# shape: [batch_size, NUM_SSD_BOXES, label_num]
pred_locs, pred_labels = tf.split(logits, [4, self.label_num], 2)
ssd_box_coder = faster_rcnn_box_coder.FasterRcnnBoxCoder(
scale_factors=ssd_constants.BOX_CODER_SCALES)
anchors = box_list.BoxList(
tf.convert_to_tensor(ssd_dataloader.DefaultBoxes()('ltrb')))
pred_boxes = box_coder.batch_decode(encoded_boxes=pred_locs,
box_coder=ssd_box_coder,
anchors=anchors)
pred_scores = tf.nn.softmax(pred_labels, axis=2)
# TODO(haoyuzhang): maybe use `gt_boxes` and `gt_classes` for visualization.
_, gt_boxes, gt_classes, source_id, raw_shape = inputs # pylint: disable=unused-variable
return {
(constants.UNREDUCED_ACCURACY_OP_PREFIX + ssd_constants.PRED_BOXES):
pred_boxes,
(constants.UNREDUCED_ACCURACY_OP_PREFIX + ssd_constants.PRED_SCORES):
pred_scores,
# TODO(haoyuzhang): maybe use these values for visualization.
# constants.UNREDUCED_ACCURACY_OP_PREFIX+'gt_boxes': gt_boxes,
# constants.UNREDUCED_ACCURACY_OP_PREFIX+'gt_classes': gt_classes,
(constants.UNREDUCED_ACCURACY_OP_PREFIX + ssd_constants.SOURCE_ID):
source_id,
(constants.UNREDUCED_ACCURACY_OP_PREFIX + ssd_constants.RAW_SHAPE):
raw_shape
}
def __init__(self):
similarity_calc = region_similarity_calculator.IouSimilarity()
matcher = argmax_matcher.ArgMaxMatcher(
matched_threshold=ssd_constants.MATCH_THRESHOLD,
unmatched_threshold=ssd_constants.MATCH_THRESHOLD,
negatives_lower_than_unmatched=True,
force_match_for_each_row=True)
box_coder = faster_rcnn_box_coder.FasterRcnnBoxCoder(
scale_factors=ssd_constants.BOX_CODER_SCALES)
self.default_boxes = DefaultBoxes()('ltrb')
self.default_boxes = box_list.BoxList(
tf.convert_to_tensor(self.default_boxes))
self.assigner = target_assigner.TargetAssigner(
similarity_calc, matcher, box_coder)
