本文整理汇总了Python中utils.keypoints.flip_heatmaps方法的典型用法代码示例。如果您正苦于以下问题：Python keypoints.flip_heatmaps方法的具体用法？Python keypoints.flip_heatmaps怎么用？Python keypoints.flip_heatmaps使用的例子？那么恭喜您, 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utils.keypoints的用法示例。
在下文中一共展示了keypoints.flip_heatmaps方法的3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: im_detect_keypoints_hflip
# 需要导入模块: from utils import keypoints [as 别名]
# 或者: from utils.keypoints import flip_heatmaps [as 别名]
def im_detect_keypoints_hflip(model, im, target_scale, target_max_size, boxes):
"""Computes keypoint predictions on the horizontally flipped image.
Function signature is the same as for im_detect_keypoints_aug.
"""
# Compute keypoints for the flipped image
im_hf = im[:, ::-1, :]
boxes_hf = box_utils.flip_boxes(boxes, im.shape[1])
blob_conv, im_scale = im_conv_body_only(model, im_hf, target_scale, target_max_size)
heatmaps_hf = im_detect_keypoints(model, im_scale, boxes_hf, blob_conv)
# Invert the predicted keypoints
heatmaps_inv = keypoint_utils.flip_heatmaps(heatmaps_hf)
return heatmaps_inv 示例2: im_detect_keypoints_hflip
# 需要导入模块: from utils import keypoints [as 别名]
# 或者: from utils.keypoints import flip_heatmaps [as 别名]
def im_detect_keypoints_hflip(model, im, target_scale, target_max_size, boxes):
"""Computes keypoint predictions on the horizontally flipped image.
Function signature is the same as for im_detect_keypoints_aug.
"""
# Compute keypoints for the flipped image
im_hf = im[:, ::-1, :]
boxes_hf = box_utils.flip_boxes(boxes, im.shape[1])
im_scale = im_conv_body_only(model, im_hf, target_scale, target_max_size)
heatmaps_hf = im_detect_keypoints(model, im_scale, boxes_hf)
# Invert the predicted keypoints
heatmaps_inv = keypoint_utils.flip_heatmaps(heatmaps_hf)
return heatmaps_inv 示例3: im_detect_keypoints_hflip
# 需要导入模块: from utils import keypoints [as 别名]
# 或者: from utils.keypoints import flip_heatmaps [as 别名]
def im_detect_keypoints_hflip(model, im, boxes):
"""Computes keypoint predictions on the horizontally flipped image.
Function signature is the same as for im_detect_keypoints_aug.
"""
# Compute keypoints for the flipped image
im_hf = im[:, ::-1, :]
boxes_hf = box_utils.flip_boxes(boxes, im.shape[1])
im_scales = im_conv_body_only(model, im_hf)
heatmaps_hf = im_detect_keypoints(model, im_scales, boxes_hf)
# Invert the predicted keypoints
heatmaps_inv = keypoint_utils.flip_heatmaps(heatmaps_hf)
return heatmaps_inv