def test_paa_head_loss():
"""Tests paa head loss when truth is empty and non-empty."""
class mock_skm(object):
def GaussianMixture(self, *args, **kwargs):
return self
def fit(self, loss):
pass
def predict(self, loss):
components = np.zeros_like(loss, dtype=np.long)
return components.reshape(-1)
def score_samples(self, loss):
scores = np.random.random(len(loss))
return scores
paa_head.skm = mock_skm()
s = 256
img_metas = [{
'img_shape': (s, s, 3),
'scale_factor': 1,
'pad_shape': (s, s, 3)
}]
train_cfg = mmcv.Config(
dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.1,
neg_iou_thr=0.1,
min_pos_iou=0,
ignore_iof_thr=-1),
allowed_border=-1,
pos_weight=-1,
debug=False))
# since Focal Loss is not supported on CPU
self = PAAHead(
num_classes=4,
in_channels=1,
train_cfg=train_cfg,
loss_cls=dict(
type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0),
loss_bbox=dict(type='GIoULoss', loss_weight=1.3),
loss_centerness=dict(
type='CrossEntropyLoss', use_sigmoid=True, loss_weight=0.5))
feat = [
torch.rand(1, 1, s // feat_size, s // feat_size)
for feat_size in [4, 8, 16, 32, 64]
]
self.init_weights()
cls_scores, bbox_preds, iou_preds = self(feat)
# Test that empty ground truth encourages the network to predict background
gt_bboxes = [torch.empty((0, 4))]
gt_labels = [torch.LongTensor([])]
gt_bboxes_ignore = None
empty_gt_losses = self.loss(cls_scores, bbox_preds, iou_preds, gt_bboxes,
gt_labels, img_metas, gt_bboxes_ignore)
# When there is no truth, the cls loss should be nonzero but there should
# be no box loss.
empty_cls_loss = empty_gt_losses['loss_cls']
empty_box_loss = empty_gt_losses['loss_bbox']
empty_iou_loss = empty_gt_losses['loss_iou']
assert empty_cls_loss.item() > 0, 'cls loss should be non-zero'
assert empty_box_loss.item() == 0, (
'there should be no box loss when there are no true boxes')
assert empty_iou_loss.item() == 0, (
'there should be no box loss when there are no true boxes')
# When truth is non-empty then both cls and box loss should be nonzero for
# random inputs
gt_bboxes = [
torch.Tensor([[23.6667, 23.8757, 238.6326, 151.8874]]),
]
gt_labels = [torch.LongTensor([2])]
one_gt_losses = self.loss(cls_scores, bbox_preds, iou_preds, gt_bboxes,
gt_labels, img_metas, gt_bboxes_ignore)
onegt_cls_loss = one_gt_losses['loss_cls']
onegt_box_loss = one_gt_losses['loss_bbox']
onegt_iou_loss = one_gt_losses['loss_iou']
assert onegt_cls_loss.item() > 0, 'cls loss should be non-zero'
assert onegt_box_loss.item() > 0, 'box loss should be non-zero'
assert onegt_iou_loss.item() > 0, 'box loss should be non-zero'
n, c, h, w = 10, 4, 20, 20
mlvl_tensor = [torch.ones(n, c, h, w) for i in range(5)]
results = levels_to_images(mlvl_tensor)
assert len(results) == n
assert results[0].size() == (h * w * 5, c)
assert self.with_score_voting
cls_scores = [torch.ones(4, 5, 5)]
bbox_preds = [torch.ones(4, 5, 5)]
iou_preds = [torch.ones(1, 5, 5)]
mlvl_anchors = [torch.ones(5 * 5, 4)]
img_shape = None
scale_factor = [0.5, 0.5]
cfg = mmcv.Config(
dict(
nms_pre=1000,
min_bbox_size=0,
score_thr=0.05,
nms=dict(type='nms', iou_threshold=0.6),
max_per_img=100))
rescale = False
self._get_bboxes_single(
cls_scores,
bbox_preds,
iou_preds,
mlvl_anchors,
img_shape,
scale_factor,
cfg,
rescale=rescale)
def test_autoassign_head_loss():
"""Tests autoassign head loss when truth is empty and non-empty."""
s = 256
img_metas = [{
'img_shape': (s, s, 3),
'scale_factor': 1,
'pad_shape': (s, s, 3)
}]
train_cfg = mmcv.Config(
dict(assigner=None, allowed_border=-1, pos_weight=-1, debug=False))
self = AutoAssignHead(num_classes=4,
in_channels=1,
train_cfg=train_cfg,
loss_cls=dict(type='CrossEntropyLoss',
use_sigmoid=True,
loss_weight=1.0),
loss_bbox=dict(type='GIoULoss', loss_weight=1.3))
feat = [
torch.rand(1, 1, s // feat_size, s // feat_size)
for feat_size in [4, 8, 16, 32, 64]
]
self.init_weights()
cls_scores, bbox_preds, objectnesses = self(feat)
# Test that empty ground truth encourages the network to predict background
gt_bboxes = [torch.empty((0, 4))]
gt_labels = [torch.LongTensor([])]
gt_bboxes_ignore = None
empty_gt_losses = self.loss(cls_scores, bbox_preds, objectnesses,
gt_bboxes, gt_labels, img_metas,
gt_bboxes_ignore)
# When there is no truth, the cls loss should be nonzero but there should
# be no box loss.
empty_pos_loss = empty_gt_losses['loss_pos']
empty_neg_loss = empty_gt_losses['loss_neg']
empty_center_loss = empty_gt_losses['loss_center']
assert empty_neg_loss.item() > 0, 'cls loss should be non-zero'
assert empty_pos_loss.item() == 0, (
'there should be no box loss when there are no true boxes')
assert empty_center_loss.item() == 0, (
'there should be no box loss when there are no true boxes')
# When truth is non-empty then both cls and box loss should be nonzero for
# random inputs
gt_bboxes = [
torch.Tensor([[23.6667, 23.8757, 238.6326, 151.8874]]),
]
gt_labels = [torch.LongTensor([2])]
one_gt_losses = self.loss(cls_scores, bbox_preds, objectnesses, gt_bboxes,
gt_labels, img_metas, gt_bboxes_ignore)
onegt_pos_loss = one_gt_losses['loss_pos']
onegt_neg_loss = one_gt_losses['loss_neg']
onegt_center_loss = one_gt_losses['loss_center']
assert onegt_pos_loss.item() > 0, 'cls loss should be non-zero'
assert onegt_neg_loss.item() > 0, 'box loss should be non-zero'
assert onegt_center_loss.item() > 0, 'box loss should be non-zero'
n, c, h, w = 10, 4, 20, 20
mlvl_tensor = [torch.ones(n, c, h, w) for i in range(5)]
results = levels_to_images(mlvl_tensor)
assert len(results) == n
assert results[0].size() == (h * w * 5, c)
cls_scores = [torch.ones(2, 4, 5, 5)]
bbox_preds = [torch.ones(2, 4, 5, 5)]
iou_preds = [torch.ones(2, 1, 5, 5)]
mlvl_anchors = [torch.ones(5 * 5, 2)]
img_shape = None
scale_factor = [0.5, 0.5]
cfg = mmcv.Config(
dict(nms_pre=1000,
min_bbox_size=0,
score_thr=0.05,
nms=dict(type='nms', iou_threshold=0.6),
max_per_img=100))
rescale = False
self._get_bboxes(cls_scores,
bbox_preds,
iou_preds,
mlvl_anchors,
img_shape,
scale_factor,
cfg,
rescale=rescale)
def loss(self,
cls_scores,
bbox_preds,
objectnesses,
gt_bboxes,
gt_labels,
img_metas,
gt_bboxes_ignore=None):
"""Compute loss of the head.
Args:
cls_scores (list[Tensor]): Box scores for each scale level,
each is a 4D-tensor, the channel number is
num_points * num_classes.
bbox_preds (list[Tensor]): Box energies / deltas for each scale
level, each is a 4D-tensor, the channel number is
num_points * 4.
objectnesses (list[Tensor]): objectness for each scale level, each
is a 4D-tensor, the channel number is num_points * 1.
gt_bboxes (list[Tensor]): Ground truth bboxes for each image with
shape (num_gts, 4) in [tl_x, tl_y, br_x, br_y] format.
gt_labels (list[Tensor]): class indices corresponding to each box
img_metas (list[dict]): Meta information of each image, e.g.,
image size, scaling factor, etc.
gt_bboxes_ignore (None | list[Tensor]): specify which bounding
boxes can be ignored when computing the loss.
Returns:
dict[str, Tensor]: A dictionary of loss components.
"""
assert len(cls_scores) == len(bbox_preds) == len(objectnesses)
all_num_gt = sum([len(item) for item in gt_bboxes])
featmap_sizes = [featmap.size()[-2:] for featmap in cls_scores]
all_level_points = self.prior_generator.grid_priors(
featmap_sizes,
dtype=bbox_preds[0].dtype,
device=bbox_preds[0].device)
inside_gt_bbox_mask_list, bbox_targets_list = self.get_targets(
all_level_points, gt_bboxes)
center_prior_weight_list = []
temp_inside_gt_bbox_mask_list = []
for gt_bboxe, gt_label, inside_gt_bbox_mask in zip(
gt_bboxes, gt_labels, inside_gt_bbox_mask_list):
center_prior_weight, inside_gt_bbox_mask = \
self.center_prior(all_level_points, gt_bboxe, gt_label,
inside_gt_bbox_mask)
center_prior_weight_list.append(center_prior_weight)
temp_inside_gt_bbox_mask_list.append(inside_gt_bbox_mask)
inside_gt_bbox_mask_list = temp_inside_gt_bbox_mask_list
mlvl_points = torch.cat(all_level_points, dim=0)
bbox_preds = levels_to_images(bbox_preds)
cls_scores = levels_to_images(cls_scores)
objectnesses = levels_to_images(objectnesses)
reg_loss_list = []
ious_list = []
num_points = len(mlvl_points)
for bbox_pred, encoded_targets, inside_gt_bbox_mask in zip(
bbox_preds, bbox_targets_list, inside_gt_bbox_mask_list):
temp_num_gt = encoded_targets.size(1)
expand_mlvl_points = mlvl_points[:, None, :].expand(
num_points, temp_num_gt, 2).reshape(-1, 2)
encoded_targets = encoded_targets.reshape(-1, 4)
expand_bbox_pred = bbox_pred[:, None, :].expand(
num_points, temp_num_gt, 4).reshape(-1, 4)
decoded_bbox_preds = self.bbox_coder.decode(
expand_mlvl_points, expand_bbox_pred)
decoded_target_preds = self.bbox_coder.decode(
expand_mlvl_points, encoded_targets)
with torch.no_grad():
ious = bbox_overlaps(decoded_bbox_preds,
decoded_target_preds,
is_aligned=True)
ious = ious.reshape(num_points, temp_num_gt)
if temp_num_gt:
ious = ious.max(dim=-1, keepdim=True).values.repeat(
1, temp_num_gt)
else:
ious = ious.new_zeros(num_points, temp_num_gt)
ious[~inside_gt_bbox_mask] = 0
ious_list.append(ious)
loss_bbox = self.loss_bbox(decoded_bbox_preds,
decoded_target_preds,
weight=None,
reduction_override='none')
reg_loss_list.append(loss_bbox.reshape(num_points, temp_num_gt))
cls_scores = [item.sigmoid() for item in cls_scores]
objectnesses = [item.sigmoid() for item in objectnesses]
pos_loss_list, = multi_apply(self.get_pos_loss_single, cls_scores,
objectnesses, reg_loss_list, gt_labels,
center_prior_weight_list)
pos_avg_factor = reduce_mean(
bbox_pred.new_tensor(all_num_gt)).clamp_(min=1)
pos_loss = sum(pos_loss_list) / pos_avg_factor
neg_loss_list, = multi_apply(self.get_neg_loss_single, cls_scores,
objectnesses, gt_labels, ious_list,
inside_gt_bbox_mask_list)
neg_avg_factor = sum(item.data.sum()
for item in center_prior_weight_list)
neg_avg_factor = reduce_mean(neg_avg_factor).clamp_(min=1)
neg_loss = sum(neg_loss_list) / neg_avg_factor
center_loss = []
for i in range(len(img_metas)):
if inside_gt_bbox_mask_list[i].any():
center_loss.append(
len(gt_bboxes[i]) /
center_prior_weight_list[i].sum().clamp_(min=EPS))
# when width or height of gt_bbox is smaller than stride of p3
else:
center_loss.append(center_prior_weight_list[i].sum() * 0)
center_loss = torch.stack(center_loss).mean() * self.center_loss_weight
# avoid dead lock in DDP
if all_num_gt == 0:
pos_loss = bbox_preds[0].sum() * 0
dummy_center_prior_loss = self.center_prior.mean.sum(
) * 0 + self.center_prior.sigma.sum() * 0
center_loss = objectnesses[0].sum() * 0 + dummy_center_prior_loss
loss = dict(loss_pos=pos_loss,
loss_neg=neg_loss,
loss_center=center_loss)
return loss