本文整理汇总了Python中maskrcnn_benchmark.modeling.utils.cat方法的典型用法代码示例。如果您正苦于以下问题：Python utils.cat方法的具体用法？Python utils.cat怎么用？Python utils.cat使用的例子？那么, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在类maskrcnn_benchmark.modeling.utils的用法示例。
在下文中一共展示了utils.cat方法的4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: __call__
# 需要导入模块: from maskrcnn_benchmark.modeling import utils [as 别名]
# 或者: from maskrcnn_benchmark.modeling.utils import cat [as 别名]
def __call__(self, proposals, keypoint_logits):
heatmaps = []
valid = []
for proposals_per_image in proposals:
kp = proposals_per_image.get_field("keypoints")
heatmaps_per_image, valid_per_image = project_keypoints_to_heatmap(
kp, proposals_per_image, self.discretization_size
)
heatmaps.append(heatmaps_per_image.view(-1))
valid.append(valid_per_image.view(-1))
keypoint_targets = cat(heatmaps, dim=0)
valid = cat(valid, dim=0).to(dtype=torch.uint8)
valid = torch.nonzero(valid).squeeze(1)
# torch.mean (in binary_cross_entropy_with_logits) does'nt
# accept empty tensors, so handle it sepaartely
if keypoint_targets.numel() == 0 or len(valid) == 0:
return keypoint_logits.sum() * 0
N, K, H, W = keypoint_logits.shape
keypoint_logits = keypoint_logits.view(N * K, H * W)
keypoint_loss = F.cross_entropy(keypoint_logits[valid], keypoint_targets[valid])
return keypoint_loss 示例2: __call__
# 需要导入模块: from maskrcnn_benchmark.modeling import utils [as 别名]
# 或者: from maskrcnn_benchmark.modeling.utils import cat [as 别名]
def __call__(self, proposals, keypoint_logits):
heatmaps = []
valid = []
for proposals_per_image in proposals:
kp = proposals_per_image.get_field("keypoints")
heatmaps_per_image, valid_per_image = project_keypoints_to_heatmap(
kp, proposals_per_image, self.discretization_size
)
heatmaps.append(heatmaps_per_image.view(-1))
valid.append(valid_per_image.view(-1))
keypoint_targets = cat(heatmaps, dim=0)
valid = cat(valid, dim=0).to(dtype=torch.bool)
valid = torch.nonzero(valid).squeeze(1)
# torch.mean (in binary_cross_entropy_with_logits) does'nt
# accept empty tensors, so handle it sepaartely
if keypoint_targets.numel() == 0 or len(valid) == 0:
return keypoint_logits.sum() * 0
N, K, H, W = keypoint_logits.shape
keypoint_logits = keypoint_logits.view(N * K, H * W)
keypoint_loss = F.cross_entropy(keypoint_logits[valid], keypoint_targets[valid])
return keypoint_loss 示例3: cat_boxlist_with_keypoints
# 需要导入模块: from maskrcnn_benchmark.modeling import utils [as 别名]
# 或者: from maskrcnn_benchmark.modeling.utils import cat [as 别名]
def cat_boxlist_with_keypoints(boxlists):
assert all(boxlist.has_field("keypoints") for boxlist in boxlists)
kp = [boxlist.get_field("keypoints").keypoints for boxlist in boxlists]
kp = cat(kp, 0)
fields = boxlists[0].get_fields()
fields = [field for field in fields if field != "keypoints"]
boxlists = [boxlist.copy_with_fields(fields) for boxlist in boxlists]
boxlists = cat_boxlist(boxlists)
boxlists.add_field("keypoints", kp)
return boxlists 示例4: __call__
# 需要导入模块: from maskrcnn_benchmark.modeling import utils [as 别名]
# 或者: from maskrcnn_benchmark.modeling.utils import cat [as 别名]
def __call__(self, proposals, mask_logits, targets):
"""
Arguments:
proposals (list[BoxList])
mask_logits (Tensor)
targets (list[BoxList])
Return:
mask_loss (Tensor): scalar tensor containing the loss
"""
labels, mask_targets = self.prepare_targets(proposals, targets)
labels = cat(labels, dim=0)
mask_targets = cat(mask_targets, dim=0)
positive_inds = torch.nonzero(labels > 0).squeeze(1)
labels_pos = labels[positive_inds]
# torch.mean (in binary_cross_entropy_with_logits) doesn't
# accept empty tensors, so handle it separately
if mask_targets.numel() == 0:
return mask_logits.sum() * 0
mask_loss = F.binary_cross_entropy_with_logits(
mask_logits[positive_inds, labels_pos], mask_targets
)
return mask_loss