Serverless function for YOLOv5

[aseprohman]

Search before asking

• I have searched the YOLOv5 issues and discussions and found no similar questions.

Question

hello @glenn-jocher et all,

Has anyone tried to install the yolov5 framework into the serverless function in the CVAT (Computer Vision Annotation Tool) tools? I want to use the automatic annotation feature in CVAT with custom DL model.
maybe there is a tutorial I can learn for this case ? thanks a lot

Additional

No response

[glenn-jocher]

@aseprohman interesting question. I don't experience with this myself but perhaps someone in the community does.

[aseprohman]

I'm still trying to install, here is documentation link from CVAT website :

https://openvinotoolkit.github.io/cvat/docs/administration/advanced/installation_automatic_annotation

If it is successfully implemented, I think this automation tool can make a lot of annotation jobs more easier and less tedious :)

[aseprohman]

Hello @glenn-jocher et all ,

I have tried to deploy a serverless function example that already run from openvino with yolov3 model for automatic annotations in cvat. The response data provided looks like in the image on the right terminal console, while the left terminal console is the "xywh" format from yolov5. do you have any idea to make the "xywh" value to "int" value like in the right terminal in the serverless function yolov3 ? regards

[glenn-jocher]

@aseprohman well I'd assume some coordinate transformations are required. You can see examples of coordinate transformations and operations in general.py:

yolov5/utils/general.py

Lines 512 to 614 in 19c8760

	def xyxy2xywh(x):
	# Convert nx4 boxes from [x1, y1, x2, y2] to [x, y, w, h] where xy1=top-left, xy2=bottom-right
	y = x.clone() if isinstance(x, torch.Tensor) else np.copy(x)
	y[:, 0] = (x[:, 0] + x[:, 2]) / 2 # x center
	y[:, 1] = (x[:, 1] + x[:, 3]) / 2 # y center
	y[:, 2] = x[:, 2] - x[:, 0] # width
	y[:, 3] = x[:, 3] - x[:, 1] # height
	return y
	def xywh2xyxy(x):
	# Convert nx4 boxes from [x, y, w, h] to [x1, y1, x2, y2] where xy1=top-left, xy2=bottom-right
	y = x.clone() if isinstance(x, torch.Tensor) else np.copy(x)
	y[:, 0] = x[:, 0] - x[:, 2] / 2 # top left x
	y[:, 1] = x[:, 1] - x[:, 3] / 2 # top left y
	y[:, 2] = x[:, 0] + x[:, 2] / 2 # bottom right x
	y[:, 3] = x[:, 1] + x[:, 3] / 2 # bottom right y
	return y
	def xywhn2xyxy(x, w=640, h=640, padw=0, padh=0):
	# Convert nx4 boxes from [x, y, w, h] normalized to [x1, y1, x2, y2] where xy1=top-left, xy2=bottom-right
	y = x.clone() if isinstance(x, torch.Tensor) else np.copy(x)
	y[:, 0] = w * (x[:, 0] - x[:, 2] / 2) + padw # top left x
	y[:, 1] = h * (x[:, 1] - x[:, 3] / 2) + padh # top left y
	y[:, 2] = w * (x[:, 0] + x[:, 2] / 2) + padw # bottom right x
	y[:, 3] = h * (x[:, 1] + x[:, 3] / 2) + padh # bottom right y
	return y
	def xyxy2xywhn(x, w=640, h=640, clip=False, eps=0.0):
	# Convert nx4 boxes from [x1, y1, x2, y2] to [x, y, w, h] normalized where xy1=top-left, xy2=bottom-right
	if clip:
	clip_coords(x, (h - eps, w - eps)) # warning: inplace clip
	y = x.clone() if isinstance(x, torch.Tensor) else np.copy(x)
	y[:, 0] = ((x[:, 0] + x[:, 2]) / 2) / w # x center
	y[:, 1] = ((x[:, 1] + x[:, 3]) / 2) / h # y center
	y[:, 2] = (x[:, 2] - x[:, 0]) / w # width
	y[:, 3] = (x[:, 3] - x[:, 1]) / h # height
	return y
	def xyn2xy(x, w=640, h=640, padw=0, padh=0):
	# Convert normalized segments into pixel segments, shape (n,2)
	y = x.clone() if isinstance(x, torch.Tensor) else np.copy(x)
	y[:, 0] = w * x[:, 0] + padw # top left x
	y[:, 1] = h * x[:, 1] + padh # top left y
	return y
	def segment2box(segment, width=640, height=640):
	# Convert 1 segment label to 1 box label, applying inside-image constraint, i.e. (xy1, xy2, ...) to (xyxy)
	x, y = segment.T # segment xy
	inside = (x >= 0) & (y >= 0) & (x <= width) & (y <= height)
	x, y, = x[inside], y[inside]
	return np.array([x.min(), y.min(), x.max(), y.max()]) if any(x) else np.zeros((1, 4)) # xyxy
	def segments2boxes(segments):
	# Convert segment labels to box labels, i.e. (cls, xy1, xy2, ...) to (cls, xywh)
	boxes = []
	for s in segments:
	x, y = s.T # segment xy
	boxes.append([x.min(), y.min(), x.max(), y.max()]) # cls, xyxy
	return xyxy2xywh(np.array(boxes)) # cls, xywh
	def resample_segments(segments, n=1000):
	# Up-sample an (n,2) segment
	for i, s in enumerate(segments):
	x = np.linspace(0, len(s) - 1, n)
	xp = np.arange(len(s))
	segments[i] = np.concatenate([np.interp(x, xp, s[:, i]) for i in range(2)]).reshape(2, -1).T # segment xy
	return segments
	def scale_coords(img1_shape, coords, img0_shape, ratio_pad=None):
	# Rescale coords (xyxy) from img1_shape to img0_shape
	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
	pad = (img1_shape[1] - img0_shape[1] * gain) / 2, (img1_shape[0] - img0_shape[0] * gain) / 2 # wh padding
	else:
	gain = ratio_pad[0][0]
	pad = ratio_pad[1]
	coords[:, [0, 2]] -= pad[0] # x padding
	coords[:, [1, 3]] -= pad[1] # y padding
	coords[:, :4] /= gain
	clip_coords(coords, img0_shape)
	return coords
	def clip_coords(boxes, shape):
	# Clip bounding xyxy bounding boxes to image shape (height, width)
	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
	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