ultralytics 8.0.65 YOLOv8 Pose models (#1347)
Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> Co-authored-by: Mert Can Demir <validatedev@gmail.com> Co-authored-by: Laughing <61612323+Laughing-q@users.noreply.github.com> Co-authored-by: Fabian Greavu <fabiangreavu@gmail.com> Co-authored-by: Yonghye Kwon <developer.0hye@gmail.com> Co-authored-by: Eric Pedley <ericpedley@gmail.com> Co-authored-by: JustasBart <40023722+JustasBart@users.noreply.github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: Aarni Koskela <akx@iki.fi> Co-authored-by: Sergio Sanchez <sergio.ssm.97@gmail.com> Co-authored-by: Bogdan Gheorghe <112427971+bogdan-galileo@users.noreply.github.com> Co-authored-by: Jaap van de Loosdrecht <jaap@vdlmv.nl> Co-authored-by: Noobtoss <96134731+Noobtoss@users.noreply.github.com> Co-authored-by: nerdyespresso <106761627+nerdyespresso@users.noreply.github.com> Co-authored-by: Farid Inawan <frdteknikelektro@gmail.com> Co-authored-by: Laughing-q <1185102784@qq.com> Co-authored-by: Alexander Duda <Alexander.Duda@me.com> Co-authored-by: Mehran Ghandehari <mehran.maps@gmail.com> Co-authored-by: Snyk bot <snyk-bot@snyk.io> Co-authored-by: majid nasiri <majnasai@gmail.com>
This commit is contained in:
Ayush Chaurasia
GitHub
parent
9af3e69b1a
commit
1cb92d7f42
57 changed files with 1578 additions and 489 deletions
|
|
@ -281,28 +281,23 @@ def clip_boxes(boxes, shape):
|
|||
boxes[..., [1, 3]] = boxes[..., [1, 3]].clip(0, shape[0]) # y1, y2
|
||||
|
||||
|
||||
def clip_coords(boxes, shape):
|
||||
def clip_coords(coords, shape):
|
||||
"""
|
||||
Clip bounding xyxy bounding boxes to image shape (height, width).
|
||||
Clip line coordinates to the image boundaries.
|
||||
|
||||
Args:
|
||||
boxes (torch.Tensor or numpy.ndarray): Bounding boxes to be clipped.
|
||||
shape (tuple): The shape of the image. (height, width)
|
||||
coords (torch.Tensor) or (numpy.ndarray): A list of line coordinates.
|
||||
shape (tuple): A tuple of integers representing the size of the image in the format (height, width).
|
||||
|
||||
Returns:
|
||||
None
|
||||
|
||||
Note:
|
||||
The input `boxes` is modified in-place, there is no return value.
|
||||
(None): The function modifies the input `coordinates` in place, by clipping each coordinate to the image boundaries.
|
||||
"""
|
||||
if isinstance(boxes, torch.Tensor): # faster individually
|
||||
boxes[:, 0].clamp_(0, shape[1]) # x1
|
||||
boxes[:, 1].clamp_(0, shape[0]) # y1
|
||||
boxes[:, 2].clamp_(0, shape[1]) # x2
|
||||
boxes[:, 3].clamp_(0, shape[0]) # y2
|
||||
if isinstance(coords, torch.Tensor): # faster individually
|
||||
coords[..., 0].clamp_(0, shape[1]) # x
|
||||
coords[..., 1].clamp_(0, shape[0]) # y
|
||||
else: # np.array (faster grouped)
|
||||
boxes[:, [0, 2]] = boxes[:, [0, 2]].clip(0, shape[1]) # x1, x2
|
||||
boxes[:, [1, 3]] = boxes[:, [1, 3]].clip(0, shape[0]) # y1, y2
|
||||
coords[..., 0] = coords[..., 0].clip(0, shape[1]) # x
|
||||
coords[..., 1] = coords[..., 1].clip(0, shape[0]) # y
|
||||
|
||||
|
||||
def scale_image(im1_shape, masks, im0_shape, ratio_pad=None):
|
||||
|
|
@ -577,17 +572,18 @@ def process_mask_upsample(protos, masks_in, bboxes, shape):
|
|||
|
||||
def process_mask(protos, masks_in, bboxes, shape, upsample=False):
|
||||
"""
|
||||
It takes the output of the mask head, and applies the mask to the bounding boxes. This is faster but produces
|
||||
downsampled quality of mask
|
||||
Apply masks to bounding boxes using the output of the mask head.
|
||||
|
||||
Args:
|
||||
protos (torch.Tensor): [mask_dim, mask_h, mask_w]
|
||||
masks_in (torch.Tensor): [n, mask_dim], n is number of masks after nms
|
||||
bboxes (torch.Tensor): [n, 4], n is number of masks after nms
|
||||
shape (tuple): the size of the input image (h,w)
|
||||
protos (torch.Tensor): A tensor of shape [mask_dim, mask_h, mask_w].
|
||||
masks_in (torch.Tensor): A tensor of shape [n, mask_dim], where n is the number of masks after NMS.
|
||||
bboxes (torch.Tensor): A tensor of shape [n, 4], where n is the number of masks after NMS.
|
||||
shape (tuple): A tuple of integers representing the size of the input image in the format (h, w).
|
||||
upsample (bool): A flag to indicate whether to upsample the mask to the original image size. Default is False.
|
||||
|
||||
Returns:
|
||||
(torch.Tensor): The processed masks.
|
||||
(torch.Tensor): A binary mask tensor of shape [n, h, w], where n is the number of masks after NMS, and h and w
|
||||
are the height and width of the input image. The mask is applied to the bounding boxes.
|
||||
"""
|
||||
|
||||
c, mh, mw = protos.shape # CHW
|
||||
|
|
@ -632,19 +628,19 @@ def process_mask_native(protos, masks_in, bboxes, shape):
|
|||
return masks.gt_(0.5)
|
||||
|
||||
|
||||
def scale_segments(img1_shape, segments, img0_shape, ratio_pad=None, normalize=False):
|
||||
def scale_coords(img1_shape, coords, img0_shape, ratio_pad=None, normalize=False):
|
||||
"""
|
||||
Rescale segment coordinates (xyxy) from img1_shape to img0_shape
|
||||
|
||||
Args:
|
||||
img1_shape (tuple): The shape of the image that the segments are from.
|
||||
segments (torch.Tensor): the segments to be scaled
|
||||
img1_shape (tuple): The shape of the image that the coords are from.
|
||||
coords (torch.Tensor): the coords to be scaled
|
||||
img0_shape (tuple): the shape of the image that the segmentation is being applied to
|
||||
ratio_pad (tuple): the ratio of the image size to the padded image size.
|
||||
normalize (bool): If True, the coordinates will be normalized to the range [0, 1]. Defaults to False
|
||||
|
||||
Returns:
|
||||
segments (torch.Tensor): the segmented image.
|
||||
coords (torch.Tensor): the segmented image.
|
||||
"""
|
||||
if ratio_pad is None: # calculate from img0_shape
|
||||
gain = min(img1_shape[0] / img0_shape[0], img1_shape[1] / img0_shape[1]) # gain = old / new
|
||||
|
|
@ -653,14 +649,15 @@ def scale_segments(img1_shape, segments, img0_shape, ratio_pad=None, normalize=F
|
|||
gain = ratio_pad[0][0]
|
||||
pad = ratio_pad[1]
|
||||
|
||||
segments[:, 0] -= pad[0] # x padding
|
||||
segments[:, 1] -= pad[1] # y padding
|
||||
segments /= gain
|
||||
clip_segments(segments, img0_shape)
|
||||
coords[..., 0] -= pad[0] # x padding
|
||||
coords[..., 1] -= pad[1] # y padding
|
||||
coords[..., 0] /= gain
|
||||
coords[..., 1] /= gain
|
||||
clip_coords(coords, img0_shape)
|
||||
if normalize:
|
||||
segments[:, 0] /= img0_shape[1] # width
|
||||
segments[:, 1] /= img0_shape[0] # height
|
||||
return segments
|
||||
coords[..., 0] /= img0_shape[1] # width
|
||||
coords[..., 1] /= img0_shape[0] # height
|
||||
return coords
|
||||
|
||||
|
||||
def masks2segments(masks, strategy='largest'):
|
||||
|
|
@ -688,23 +685,6 @@ def masks2segments(masks, strategy='largest'):
|
|||
return segments
|
||||
|
||||
|
||||
def clip_segments(segments, shape):
|
||||
"""
|
||||
It takes a list of line segments (x1,y1,x2,y2) and clips them to the image shape (height, width)
|
||||
|
||||
Args:
|
||||
segments (list): a list of segments, each segment is a list of points, each point is a list of x,y
|
||||
coordinates
|
||||
shape (tuple): the shape of the image
|
||||
"""
|
||||
if isinstance(segments, torch.Tensor): # faster individually
|
||||
segments[:, 0].clamp_(0, shape[1]) # x
|
||||
segments[:, 1].clamp_(0, shape[0]) # y
|
||||
else: # np.array (faster grouped)
|
||||
segments[:, 0] = segments[:, 0].clip(0, shape[1]) # x
|
||||
segments[:, 1] = segments[:, 1].clip(0, shape[0]) # y
|
||||
|
||||
|
||||
def clean_str(s):
|
||||
"""
|
||||
Cleans a string by replacing special characters with underscore _
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue