def test_detection_api(self):
program = Program()
with program_guard(program):
x = layers.data(name='x', shape=[4], dtype='float32')
y = layers.data(name='y', shape=[4], dtype='float32')
z = layers.data(name='z', shape=[4], dtype='float32', lod_level=1)
iou = layers.iou_similarity(x=x, y=y)
bcoder = layers.box_coder(
prior_box=x,
prior_box_var=y,
target_box=z,
code_type='encode_center_size')
self.assertIsNotNone(iou)
self.assertIsNotNone(bcoder)
matched_indices, matched_dist = layers.bipartite_match(iou)
self.assertIsNotNone(matched_indices)
self.assertIsNotNone(matched_dist)
gt = layers.data(
name='gt', shape=[1, 1], dtype='int32', lod_level=1)
trg, trg_weight = layers.target_assign(
gt, matched_indices, mismatch_value=0)
self.assertIsNotNone(trg)
self.assertIsNotNone(trg_weight)
gt2 = layers.data(
name='gt2', shape=[10, 4], dtype='float32', lod_level=1)
trg, trg_weight = layers.target_assign(
gt2, matched_indices, mismatch_value=0)
self.assertIsNotNone(trg)
self.assertIsNotNone(trg_weight)
print(str(program))
def test_detection_api(self):
program = Program()
with program_guard(program):
x = layers.data(name='x', shape=[4], dtype='float32')
y = layers.data(name='y', shape=[4], dtype='float32')
z = layers.data(name='z', shape=[4], dtype='float32', lod_level=1)
iou = layers.iou_similarity(x=x, y=y)
bcoder = layers.box_coder(
prior_box=x,
prior_box_var=y,
target_box=z,
code_type='encode_center_size')
self.assertIsNotNone(iou)
self.assertIsNotNone(bcoder)
matched_indices, matched_dist = layers.bipartite_match(iou)
self.assertIsNotNone(matched_indices)
self.assertIsNotNone(matched_dist)
gt = layers.data(
name='gt', shape=[1, 1], dtype='int32', lod_level=1)
trg, trg_weight = layers.target_assign(
gt, matched_indices, mismatch_value=0)
self.assertIsNotNone(trg)
self.assertIsNotNone(trg_weight)
gt2 = layers.data(
name='gt2', shape=[10, 4], dtype='float32', lod_level=1)
trg, trg_weight = layers.target_assign(
gt2, matched_indices, mismatch_value=0)
self.assertIsNotNone(trg)
self.assertIsNotNone(trg_weight)
print(str(program))
def iou_similarity(self):
program = Program()
with program_guard(program):
x = layers.data(name="x", shape=[16], dtype="float32")
y = layers.data(name="y", shape=[16], dtype="float32")
out = layers.iou_similarity(x, y, name='iou_similarity')
self.assertIsNotNone(out)
print(str(program))
def __call__(self,
location,
confidence,
gt_box,
gt_label,
landmark_predict,
lmk_label,
lmk_ignore_flag,
prior_box,
prior_box_var=None):
def _reshape_to_2d(var):
return layers.flatten(x=var, axis=2)
helper = LayerHelper('ssd_loss') #, **locals())
# Only support mining_type == 'max_negative' now.
mining_type = 'max_negative'
# The max `sample_size` of negative box, used only
# when mining_type is `hard_example`.
sample_size = None
num, num_prior, num_class = confidence.shape
conf_shape = layers.shape(confidence)
# 1. Find matched boundding box by prior box.
# 1.1 Compute IOU similarity between ground-truth boxes and prior boxes.
iou = iou_similarity(x=gt_box, y=prior_box)
# 1.2 Compute matched boundding box by bipartite matching algorithm.
matched_indices, matched_dist = bipartite_match(
iou, self.match_type, self.overlap_threshold)
# 2. Compute confidence for mining hard examples
# 2.1. Get the target label based on matched indices
gt_label = layers.reshape(x=gt_label,
shape=(len(gt_label.shape) - 1) * (0, ) +
(-1, 1))
gt_label.stop_gradient = True
target_label, _ = target_assign(gt_label,
matched_indices,
mismatch_value=self.background_label)
# 2.2. Compute confidence loss.
# Reshape confidence to 2D tensor.
confidence = _reshape_to_2d(confidence)
target_label = tensor.cast(x=target_label, dtype='int64')
target_label = _reshape_to_2d(target_label)
target_label.stop_gradient = True
conf_loss = layers.softmax_with_cross_entropy(confidence, target_label)
# 3. Mining hard examples
actual_shape = layers.slice(conf_shape, axes=[0], starts=[0], ends=[2])
actual_shape.stop_gradient = True
conf_loss = layers.reshape(x=conf_loss,
shape=(-1, 0),
actual_shape=actual_shape)
conf_loss.stop_gradient = True
neg_indices = helper.create_variable_for_type_inference(dtype='int32')
updated_matched_indices = helper.create_variable_for_type_inference(
dtype=matched_indices.dtype)
helper.append_op(type='mine_hard_examples',
inputs={
'ClsLoss': conf_loss,
'LocLoss': None,
'MatchIndices': matched_indices,
'MatchDist': matched_dist,
},
outputs={
'NegIndices': neg_indices,
'UpdatedMatchIndices': updated_matched_indices
},
attrs={
'neg_pos_ratio': self.neg_pos_ratio,
'neg_dist_threshold': self.neg_overlap,
'mining_type': mining_type,
'sample_size': sample_size,
})
# 4. Assign classification and regression targets
# 4.1. Encoded bbox according to the prior boxes.
encoded_bbox = box_coder(prior_box=prior_box,
prior_box_var=prior_box_var,
target_box=gt_box,
code_type='encode_center_size')
# 4.2. Assign regression targets
target_bbox, target_loc_weight = target_assign(
encoded_bbox,
updated_matched_indices,
mismatch_value=self.background_label)
# 4.3. Assign classification targets
target_label, target_conf_weight = target_assign(
gt_label,
updated_matched_indices,
negative_indices=neg_indices,
mismatch_value=self.background_label)
target_loc_weight = target_loc_weight * target_label
encoded_lmk_label = self.decode_lmk(lmk_label, prior_box,
prior_box_var)
target_lmk, target_lmk_weight = target_assign(
encoded_lmk_label,
updated_matched_indices,
mismatch_value=self.background_label)
lmk_ignore_flag = layers.reshape(
x=lmk_ignore_flag,
shape=(len(lmk_ignore_flag.shape) - 1) * (0, ) + (-1, 1))
target_ignore, nouse = target_assign(
lmk_ignore_flag,
updated_matched_indices,
mismatch_value=self.background_label)
target_lmk_weight = target_lmk_weight * target_ignore
landmark_predict = _reshape_to_2d(landmark_predict)
target_lmk = _reshape_to_2d(target_lmk)
target_lmk_weight = _reshape_to_2d(target_lmk_weight)
lmk_loss = layers.smooth_l1(landmark_predict, target_lmk)
lmk_loss = lmk_loss * target_lmk_weight
target_lmk.stop_gradient = True
target_lmk_weight.stop_gradient = True
target_ignore.stop_gradient = True
nouse.stop_gradient = True
# 5. Compute loss.
# 5.1 Compute confidence loss.
target_label = _reshape_to_2d(target_label)
target_label = tensor.cast(x=target_label, dtype='int64')
conf_loss = layers.softmax_with_cross_entropy(confidence, target_label)
target_conf_weight = _reshape_to_2d(target_conf_weight)
conf_loss = conf_loss * target_conf_weight
# the target_label and target_conf_weight do not have gradient.
target_label.stop_gradient = True
target_conf_weight.stop_gradient = True
# 5.2 Compute regression loss.
location = _reshape_to_2d(location)
target_bbox = _reshape_to_2d(target_bbox)
loc_loss = layers.smooth_l1(location, target_bbox)
target_loc_weight = _reshape_to_2d(target_loc_weight)
loc_loss = loc_loss * target_loc_weight
# the target_bbox and target_loc_weight do not have gradient.
target_bbox.stop_gradient = True
target_loc_weight.stop_gradient = True
# 5.3 Compute overall weighted loss.
loss = self.conf_loss_weight * conf_loss + self.loc_loss_weight * loc_loss + 0.4 * lmk_loss
# reshape to [N, Np], N is the batch size and Np is the prior box number.
loss = layers.reshape(x=loss, shape=(-1, 0), actual_shape=actual_shape)
loss = layers.reduce_sum(loss, dim=1, keep_dim=True)
if self.normalize:
normalizer = layers.reduce_sum(target_loc_weight) + 1
loss = loss / normalizer
return loss