本文整理汇总了Python中maskrcnn_benchmark.modeling.matcher.Matcher.BELOW_LOW_THRESHOLD属性的典型用法代码示例。如果您正苦于以下问题：Python Matcher.BELOW_LOW_THRESHOLD属性的具体用法？Python Matcher.BELOW_LOW_THRESHOLD怎么用？Python Matcher.BELOW_LOW_THRESHOLD使用的例子？那么恭喜您, 这里精选的属性代码示例或许可以为您提供帮助。您也可以进一步了解该属性所在类maskrcnn_benchmark.modeling.matcher.Matcher的用法示例。
在下文中一共展示了Matcher.BELOW_LOW_THRESHOLD属性的7个代码示例，这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞，您的评价将有助于系统推荐出更棒的Python代码示例。
示例1: prepare_targets
# 需要导入模块: from maskrcnn_benchmark.modeling.matcher import Matcher [as 别名]
# 或者: from maskrcnn_benchmark.modeling.matcher.Matcher import BELOW_LOW_THRESHOLD [as 别名]
def prepare_targets(self, proposals, targets):
labels = []
regression_targets = []
for proposals_per_image, targets_per_image in zip(proposals, targets):
matched_targets = self.match_targets_to_proposals(
proposals_per_image, targets_per_image
)
matched_idxs = matched_targets.get_field("matched_idxs")
labels_per_image = matched_targets.get_field("labels")
labels_per_image = labels_per_image.to(dtype=torch.int64)
# Label background (below the low threshold)
bg_inds = matched_idxs == Matcher.BELOW_LOW_THRESHOLD
labels_per_image[bg_inds] = 0
# Label ignore proposals (between low and high thresholds)
ignore_inds = matched_idxs == Matcher.BETWEEN_THRESHOLDS
labels_per_image[ignore_inds] = -1 # -1 is ignored by sampler
# compute regression targets
regression_targets_per_image = self.box_coder.encode(
matched_targets.bbox, proposals_per_image.bbox
)
labels.append(labels_per_image)
regression_targets.append(regression_targets_per_image)
return labels, regression_targets 示例2: prepare_targets
# 需要导入模块: from maskrcnn_benchmark.modeling.matcher import Matcher [as 别名]
# 或者: from maskrcnn_benchmark.modeling.matcher.Matcher import BELOW_LOW_THRESHOLD [as 别名]
def prepare_targets(self, proposals, targets):
labels = []
keypoints = []
for proposals_per_image, targets_per_image in zip(proposals, targets):
matched_targets = self.match_targets_to_proposals(
proposals_per_image, targets_per_image
)
matched_idxs = matched_targets.get_field("matched_idxs")
labels_per_image = matched_targets.get_field("labels")
labels_per_image = labels_per_image.to(dtype=torch.int64)
# this can probably be removed, but is left here for clarity
# and completeness
# TODO check if this is the right one, as BELOW_THRESHOLD
neg_inds = matched_idxs == Matcher.BELOW_LOW_THRESHOLD
labels_per_image[neg_inds] = 0
keypoints_per_image = matched_targets.get_field("keypoints")
within_box = _within_box(
keypoints_per_image.keypoints, matched_targets.bbox
)
vis_kp = keypoints_per_image.keypoints[..., 2] > 0
is_visible = (within_box & vis_kp).sum(1) > 0
labels_per_image[~is_visible] = -1
labels.append(labels_per_image)
keypoints.append(keypoints_per_image)
return labels, keypoints 示例3: prepare_targets
# 需要导入模块: from maskrcnn_benchmark.modeling.matcher import Matcher [as 别名]
# 或者: from maskrcnn_benchmark.modeling.matcher.Matcher import BELOW_LOW_THRESHOLD [as 别名]
def prepare_targets(self, proposals, targets):
labels = []
masks = []
for proposals_per_image, targets_per_image in zip(proposals, targets):
matched_targets = self.match_targets_to_proposals(
proposals_per_image, targets_per_image
)
matched_idxs = matched_targets.get_field("matched_idxs")
labels_per_image = matched_targets.get_field("labels")
labels_per_image = labels_per_image.to(dtype=torch.int64)
# this can probably be removed, but is left here for clarity
# and completeness
neg_inds = matched_idxs == Matcher.BELOW_LOW_THRESHOLD
labels_per_image[neg_inds] = 0
# mask scores are only computed on positive samples
positive_inds = torch.nonzero(labels_per_image > 0).squeeze(1)
segmentation_masks = matched_targets.get_field("masks")
segmentation_masks = segmentation_masks[positive_inds]
positive_proposals = proposals_per_image[positive_inds]
masks_per_image = project_masks_on_boxes(
segmentation_masks, positive_proposals, self.discretization_size
)
labels.append(labels_per_image)
masks.append(masks_per_image)
return labels, masks 示例4: prepare_targets
# 需要导入模块: from maskrcnn_benchmark.modeling.matcher import Matcher [as 别名]
# 或者: from maskrcnn_benchmark.modeling.matcher.Matcher import BELOW_LOW_THRESHOLD [as 别名]
def prepare_targets(self, anchors, targets):
labels = []
regression_targets = []
for anchors_per_image, targets_per_image in zip(anchors, targets):
matched_targets = self.match_targets_to_anchors(
anchors_per_image, targets_per_image, self.copied_fields
)
matched_idxs = matched_targets.get_field("matched_idxs")
labels_per_image = self.generate_labels_func(matched_targets)
labels_per_image = labels_per_image.to(dtype=torch.float32)
# Background (negative examples)
bg_indices = matched_idxs == Matcher.BELOW_LOW_THRESHOLD
labels_per_image[bg_indices] = 0
# discard anchors that go out of the boundaries of the image
if "not_visibility" in self.discard_cases:
labels_per_image[~anchors_per_image.get_field("visibility")] = -1
# discard indices that are between thresholds
if "between_thresholds" in self.discard_cases:
inds_to_discard = matched_idxs == Matcher.BETWEEN_THRESHOLDS
labels_per_image[inds_to_discard] = -1
# compute regression targets
regression_targets_per_image = self.box_coder.encode(
matched_targets.bbox, anchors_per_image.bbox
)
labels.append(labels_per_image)
regression_targets.append(regression_targets_per_image)
return labels, regression_targets 示例5: prepare_targets
# 需要导入模块: from maskrcnn_benchmark.modeling.matcher import Matcher [as 别名]
# 或者: from maskrcnn_benchmark.modeling.matcher.Matcher import BELOW_LOW_THRESHOLD [as 别名]
def prepare_targets(self, proposals, targets):
labels = []
regression_targets = []
quad_regression_targets = []
for proposals_per_image, targets_per_image in zip(proposals, targets):
matched_targets = self.match_targets_to_proposals(
proposals_per_image, targets_per_image
)
matched_idxs = matched_targets.get_field("matched_idxs")
labels_per_image = matched_targets.get_field("labels")
labels_per_image = labels_per_image.to(dtype=torch.int64)
# Label background (below the low threshold)
bg_inds = matched_idxs == Matcher.BELOW_LOW_THRESHOLD
labels_per_image[bg_inds] = 0
# Label ignore proposals (between low and high thresholds)
ignore_inds = matched_idxs == Matcher.BETWEEN_THRESHOLDS
labels_per_image[ignore_inds] = -1 # -1 is ignored by sampler
# compute regression targets
regression_targets_per_image = self.box_coder.encode(
matched_targets.bbox, proposals_per_image.bbox
)
# compute quad regression targets
quad_regression_targets_per_image = self.quad_box_coder.encode(
matched_targets.quad_bbox, proposals_per_image.bbox
)
labels.append(labels_per_image)
regression_targets.append(regression_targets_per_image)
quad_regression_targets.append(quad_regression_targets_per_image)
return labels, regression_targets, quad_regression_targets 示例6: prepare_targets
# 需要导入模块: from maskrcnn_benchmark.modeling.matcher import Matcher [as 别名]
# 或者: from maskrcnn_benchmark.modeling.matcher.Matcher import BELOW_LOW_THRESHOLD [as 别名]
def prepare_targets(self, proposals, targets):
labels = []
masks = []
for proposals_per_image, targets_per_image in zip(proposals, targets):
matched_targets = self.match_targets_to_proposals(
proposals_per_image, targets_per_image
)
matched_idxs = matched_targets.get_field("matched_idxs")
labels_per_image = matched_targets.get_field("labels")
labels_per_image = labels_per_image.to(dtype=torch.int64)
# this can probably be removed, but is left here for clarity
# and completeness
neg_inds = matched_idxs == Matcher.BELOW_LOW_THRESHOLD
labels_per_image[neg_inds] = 0
# mask scores are only computed on positive samples
positive_inds = torch.nonzero(labels_per_image > 0).squeeze(1)
segmentation_masks = matched_targets.get_field("masks")
segmentation_masks = segmentation_masks[positive_inds]
positive_proposals = proposals_per_image[positive_inds]
masks_per_image = project_masks_on_rotate_boxes(
segmentation_masks, positive_proposals, self.discretization_size
)
labels.append(labels_per_image)
masks.append(masks_per_image)
return labels, masks 示例7: prepare_targets
# 需要导入模块: from maskrcnn_benchmark.modeling.matcher import Matcher [as 别名]
# 或者: from maskrcnn_benchmark.modeling.matcher.Matcher import BELOW_LOW_THRESHOLD [as 别名]
def prepare_targets(self, proposals, targets):
labels = []
words = []
word_lens = []
for proposals_per_image, targets_per_image in zip(proposals, targets):
matched_targets = self.match_targets_to_proposals(
proposals_per_image, targets_per_image
)
matched_idxs = matched_targets.get_field("matched_idxs")
labels_per_image = matched_targets.get_field("labels")
labels_per_image = labels_per_image.to(dtype=torch.int64)
# this can probably be removed, but is left here for clarity
# and completeness
neg_inds = matched_idxs == Matcher.BELOW_LOW_THRESHOLD
labels_per_image[neg_inds] = 0
# mask scores are only computed on positive samples
positive_inds = torch.nonzero(labels_per_image > 0).squeeze(1)
words_seq = matched_targets.get_field("words")
words_seq = words_seq[positive_inds]
words_len = matched_targets.get_field("word_length")
words_len = words_len[positive_inds]
# positive_proposals = proposals_per_image[positive_inds]
# masks_per_image = project_masks_on_boxes(
# segmentation_masks, positive_proposals, self.discretization_size
# )
labels.append(labels_per_image)
words.append(words_seq)
word_lens.append(words_len)
return labels, words, word_lens