import datetime import os import time import ffmpeg import torch import cv2 import numpy as np from multiprocessing import Process, Manager from threading import Thread from read_data import LoadImages, LoadStreams import torch.backends.cudnn as cudnn import torch.nn.functional as F import torchvision from algorithm.yolov5.models.common import DetectMultiBackend from algorithm.Remote_sense.nms_rotated import nms_rotated_ext from PIL import Image, ImageDraw, ImageFont pi = 3.141592 class Remote_Sense(): time_reference = datetime.datetime.now() counter_frame = 0 processed_fps = 0 def __init__(self,video_path=None): self.device = torch.device("cuda" if torch.cuda.is_available() else "cpu") #self.model = torch.load('weight/remote_sensing/oriented.pt', map_location=self.device)['model'].float().fuse() self.model = DetectMultiBackend(weights='weight/remote_sensing/oriented.pt', dnn=True, rotation = True) # self.model.Detect.rotations = True self.classes = self.model.names self.frame = [None] if video_path is not None: self.video_name = video_path else: self.video_name = 'vid2.mp4' # A default video file self.imgsz = 2048 self.dataset = LoadImages(path =self.video_name, img_size = self.imgsz) self.names = self.model.names def use_webcam(self, source): # self.dataset.release() # Release any existing video capture # self.cap = cv2.VideoCapture(0) # Open default webcam # print('use_webcam') source = source cudnn.benchmark = True self.dataset = LoadStreams(source, img_size=self.imgsz) def class_to_label(self, x): return self.classes[int(x)] def get_frame(self): colors = Colors() for im0s in self.dataset: # print(self.dataset.mode) # print(self.dataset) if self.dataset.mode == 'stream': image = im0s[0].copy() else: image = im0s.copy() img = image[:, :, ::-1].transpose(2, 0, 1) # BGR to RGB, to 3x416x416 img0 = img.copy() img = torch.tensor(img0) img = img.float() # uint8 to fp16/32 img /= 255.0 # 0 - 255 to 0.0 - 1.0 if img.ndimension() == 3: img = img.unsqueeze(0) img = img.to(self.device) self.model.to(self.device) result = self.model(img) pred = result[0] pred = non_max_suppression_obb(pred, conf_thres=0.1, iou_thres=0.2, multi_label=True, max_det=1000) # print(pred) txt = "" for i, det in enumerate(pred): # per image pred_poly = rbox2poly(det[:, :5]) # (n, [x1 y1 x2 y2 x3 y3 x4 y4]) annotator = Annotator(image, line_width=3, example=str(self.names)) if len(det): pred_poly = scale_polys(img.shape[2:], pred_poly, image.shape) det = torch.cat((pred_poly, det[:, -2:]), dim=1) # (n, [poly conf cls]) # Print results for c in det[:, -1].unique(): n = (det[:, -1] == c).sum() # detections per class txt += f"{n} {self.names[int(c)]}{'s' * (n > 1)}, " # add to string for *poly, conf, cls in reversed(det): c = int(cls) label = None # print(poly, label) annotator.poly_label(poly, label, color=colors(c, True)) im0 = annotator.result() # Draw the number of people on the frame and display it ret, jpeg = cv2.imencode(".jpg", im0) return jpeg.tobytes(), txt class Colors: # Ultralytics color palette https://ultralytics.com/ def __init__(self): # hex = matplotlib.colors.TABLEAU_COLORS.values() hexs = ('FF3838', 'FF9D97', 'FF701F', 'FFB21D', 'CFD231', '48F90A', '92CC17', '3DDB86', '1A9334', '00D4BB', '2C99A8', '00C2FF', '344593', '6473FF', '0018EC', '8438FF', '520085', 'CB38FF', 'FF95C8', 'FF37C7') self.palette = [self.hex2rgb(f'#{c}') for c in hexs] self.n = len(self.palette) def __call__(self, i, bgr=False): c = self.palette[int(i) % self.n] return (c[2], c[1], c[0]) if bgr else c @staticmethod def hex2rgb(h): # rgb order (PIL) return tuple(int(h[1 + i:1 + i + 2], 16) for i in (0, 2, 4)) class Annotator: def __init__(self, im, line_width=None, font_size=None, font='Arial.ttf', pil=False, example='abc'): assert im.data.contiguous, 'Image not contiguous. Apply np.ascontiguousarray(im) to Annotator() input images.' self.pil = pil or not is_ascii(example) or is_chinese(example) if self.pil: # use PIL self.im = im if isinstance(im, Image.Image) else Image.fromarray(im) self.im_cv2 = im self.draw = ImageDraw.Draw(self.im) self.font = 'Arial.Unicode.ttf' else: # use cv2 self.im = im self.im_cv2 = im self.lw = line_width or max(round(sum(im.shape) / 2 * 0.003), 2) # line width def box_label(self, box, label='', color=(128, 128, 128), txt_color=(255, 255, 255)): # Add one xyxy box to image with label if self.pil or not is_ascii(label): self.draw.rectangle(box, width=self.lw, outline=color) # box if label: w, h = self.font.getsize(label) # text width, height outside = box[1] - h >= 0 # label fits outside box self.draw.rectangle([box[0], box[1] - h if outside else box[1], box[0] + w + 1, box[1] + 1 if outside else box[1] + h + 1], fill=color) # self.draw.text((box[0], box[1]), label, fill=txt_color, font=self.font, anchor='ls') # for PIL>8.0 self.draw.text((box[0], box[1] - h if outside else box[1]), label, fill=txt_color, font=self.font) else: # cv2 p1, p2 = (int(box[0]), int(box[1])), (int(box[2]), int(box[3])) cv2.rectangle(self.im, p1, p2, color, thickness=self.lw, lineType=cv2.LINE_AA) if label: tf = max(self.lw - 1, 1) # font thickness w, h = cv2.getTextSize(label, 0, fontScale=self.lw / 3, thickness=tf)[0] # text width, height outside = p1[1] - h - 3 >= 0 # label fits outside box p2 = p1[0] + w, p1[1] - h - 3 if outside else p1[1] + h + 3 cv2.rectangle(self.im, p1, p2, color, -1, cv2.LINE_AA) # filled cv2.putText(self.im, label, (p1[0], p1[1] - 2 if outside else p1[1] + h + 2), 0, self.lw / 3, txt_color, thickness=tf, lineType=cv2.LINE_AA) def poly_label(self, poly, label='', color=(128, 128, 128), txt_color=(255, 255, 255)): if isinstance(poly, torch.Tensor): poly = poly.cpu().numpy() if isinstance(poly[0], torch.Tensor): poly = [x.cpu().numpy() for x in poly] polygon_list = np.array([(poly[0], poly[1]), (poly[2], poly[3]), \ (poly[4], poly[5]), (poly[6], poly[7])], np.int32) cv2.drawContours(image=self.im_cv2, contours=[polygon_list], contourIdx=-1, color=color, thickness=self.lw) if label: tf = max(self.lw - 1, 1) # font thicknes xmax, xmin, ymax, ymin = max(poly[0::2]), min(poly[0::2]), max(poly[1::2]), min(poly[1::2]) x_label, y_label = int((xmax + xmin)/2), int((ymax + ymin)/2) w, h = cv2.getTextSize(label, 0, fontScale=self.lw / 3, thickness=tf)[0] # text width, height cv2.rectangle( self.im_cv2, (x_label, y_label), (x_label + w + 1, y_label + int(1.5*h)), color, -1, cv2.LINE_AA ) cv2.putText(self.im_cv2, label, (x_label, y_label + h), 0, self.lw / 3, txt_color, thickness=tf, lineType=cv2.LINE_AA) self.im = self.im_cv2 if isinstance(self.im_cv2, Image.Image) else Image.fromarray(self.im_cv2) def rectangle(self, xy, fill=None, outline=None, width=1): # Add rectangle to image (PIL-only) self.draw.rectangle(xy, fill, outline, width) def text(self, xy, text, txt_color=(255, 255, 255)): # Add text to image (PIL-only) w, h = self.font.getsize(text) # text width, height self.draw.text((xy[0], xy[1] - h + 1), text, fill=txt_color, font=self.font) def result(self): # Return annotated image as array return np.asarray(self.im) def time_synchronized(): # pytorch-accurate time if torch.cuda.is_available(): torch.cuda.synchronize() return time.time() def rbox2poly_single(rrect): """ rrect:[x_ctr,y_ctr,w,h,angle] to poly:[x0,y0,x1,y1,x2,y2,x3,y3] """ x_ctr, y_ctr, width, height, angle = rrect[:5] tl_x, tl_y, br_x, br_y = -width/2, -height/2, width/2, height/2 rect = np.array([[tl_x, br_x, br_x, tl_x], [tl_y, tl_y, br_y, br_y]]) R = np.array([[np.cos(angle), -np.sin(angle)], [np.sin(angle), np.cos(angle)]]) poly = R.dot(rect) x0, x1, x2, x3 = poly[0, :4] + x_ctr y0, y1, y2, y3 = poly[1, :4] + y_ctr poly = np.array([x0, y0, x1, y1, x2, y2, x3, y3], dtype=np.float32) poly = get_best_begin_point_single(poly) return poly def is_ascii(s=''): # Is string composed of all ASCII (no UTF) characters? (note str().isascii() introduced in python 3.7) s = str(s) # convert list, tuple, None, etc. to str return len(s.encode().decode('ascii', 'ignore')) == len(s) def is_chinese(s='人工智能'): import re # Is string composed of any Chinese characters? return re.search('[\u4e00-\u9fff]', s) def scale_boxes(img1_shape, boxes, img0_shape, ratio_pad=None): # Rescale boxes (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] boxes[..., [0, 2]] -= pad[0] # x padding boxes[..., [1, 3]] -= pad[1] # y padding boxes[..., :4] /= gain clip_boxes(boxes, img0_shape) return boxes def scale_segments(img1_shape, segments, img0_shape, ratio_pad=None, normalize=False): # 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] segments[:, 0] -= pad[0] # x padding segments[:, 1] -= pad[1] # y padding segments /= gain clip_segments(segments, img0_shape) if normalize: segments[:, 0] /= img0_shape[1] # width segments[:, 1] /= img0_shape[0] # height return segments def clip_boxes(boxes, shape): # Clip boxes (xyxy) 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 def clip_segments(segments, shape): # Clip segments (xy1,xy2,...) to image shape (height, width) 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 masks2segments(masks, strategy='largest'): # Convert masks(n,160,160) into segments(n,xy) segments = [] for x in masks.int().cpu().numpy().astype('uint8'): c = cv2.findContours(x, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)[0] if c: if strategy == 'concat': # concatenate all segments c = np.concatenate([x.reshape(-1, 2) for x in c]) elif strategy == 'largest': # select largest segment c = np.array(c[np.array([len(x) for x in c]).argmax()]).reshape(-1, 2) else: c = np.zeros((0, 2)) # no segments found segments.append(c.astype('float32')) return segments def process_mask(protos, masks_in, bboxes, shape, upsample=False): """ Crop before upsample. proto_out: [mask_dim, mask_h, mask_w] out_masks: [n, mask_dim], n is number of masks after nms bboxes: [n, 4], n is number of masks after nms shape:input_image_size, (h, w) return: h, w, n """ c, mh, mw = protos.shape # CHW ih, iw = shape # print(masks_in.shape, protos.shape) masks = (masks_in @ protos.float().view(c, -1)).sigmoid().view(-1, mh, mw) # CHW downsampled_bboxes = bboxes.clone() downsampled_bboxes[:, 0] *= mw / iw downsampled_bboxes[:, 2] *= mw / iw downsampled_bboxes[:, 3] *= mh / ih downsampled_bboxes[:, 1] *= mh / ih masks = crop_mask(masks, downsampled_bboxes) # CHW if upsample: masks = F.interpolate(masks[None], shape, mode='bilinear', align_corners=False)[0] # CHW return masks.gt_(0.5) def crop_mask(masks, boxes): """ "Crop" predicted masks by zeroing out everything not in the predicted bbox. Vectorized by Chong (thanks Chong). Args: - masks should be a size [h, w, n] tensor of masks - boxes should be a size [n, 4] tensor of bbox coords in relative point form """ n, h, w = masks.shape x1, y1, x2, y2 = torch.chunk(boxes[:, :, None], 4, 1) # x1 shape(1,1,n) r = torch.arange(w, device=masks.device, dtype=x1.dtype)[None, None, :] # rows shape(1,w,1) c = torch.arange(h, device=masks.device, dtype=x1.dtype)[None, :, None] # cols shape(h,1,1) return masks * ((r >= x1) * (r < x2) * (c >= y1) * (c < y2)) def scale_image(im1_shape, masks, im0_shape, ratio_pad=None): """ img1_shape: model input shape, [h, w] img0_shape: origin pic shape, [h, w, 3] masks: [h, w, num] """ # Rescale coordinates (xyxy) from im1_shape to im0_shape if ratio_pad is None: # calculate from im0_shape gain = min(im1_shape[0] / im0_shape[0], im1_shape[1] / im0_shape[1]) # gain = old / new pad = (im1_shape[1] - im0_shape[1] * gain) / 2, (im1_shape[0] - im0_shape[0] * gain) / 2 # wh padding else: pad = ratio_pad[1] top, left = int(pad[1]), int(pad[0]) # y, x bottom, right = int(im1_shape[0] - pad[1]), int(im1_shape[1] - pad[0]) if len(masks.shape) < 2: raise ValueError(f'"len of masks shape" should be 2 or 3, but got {len(masks.shape)}') masks = masks[top:bottom, left:right] # masks = masks.permute(2, 0, 1).contiguous() # masks = F.interpolate(masks[None], im0_shape[:2], mode='bilinear', align_corners=False)[0] # masks = masks.permute(1, 2, 0).contiguous() masks = cv2.resize(masks, (im0_shape[1], im0_shape[0])) if len(masks.shape) == 2: masks = masks[:, :, None] return masks 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 non_max_suppression_obb(prediction, conf_thres=0.25, iou_thres=0.45, classes=None, agnostic=False, multi_label=False, labels=(), max_det=1500): """Runs Non-Maximum Suppression (NMS) on inference results_obb Args: prediction (tensor): (b, n_all_anchors, [cx cy l s obj num_cls theta_cls]) agnostic (bool): True = NMS will be applied between elements of different categories labels : () or Returns: list of detections, len=batch_size, on (n,7) tensor per image [xylsθ, conf, cls] θ ∈ [-pi/2, pi/2) """ nc = prediction.shape[2] - 5 - 180 # number of classes xc = prediction[..., 4] > conf_thres # candidates class_index = nc + 5 # Checks assert 0 <= conf_thres <= 1, f'Invalid Confidence threshold {conf_thres}, valid values are between 0.0 and 1.0' assert 0 <= iou_thres <= 1, f'Invalid IoU {iou_thres}, valid values are between 0.0 and 1.0' # Settings max_wh = 4096 # min_wh, max_wh = 2, 4096 # (pixels) minimum and maximum box width and height max_nms = 30000 # maximum number of boxes into torchvision.ops.nms() time_limit = 30.0 # seconds to quit after # redundant = True # require redundant detections multi_label &= nc > 1 # multiple labels per box (adds 0.5ms/img) t = time.time() output = [torch.zeros((0, 7), device=prediction.device)] * prediction.shape[0] for xi, x in enumerate(prediction): # image index, image inference # Apply constraints # x[((x[..., 2:4] < min_wh) | (x[..., 2:4] > max_wh)).any(1), 4] = 0 # width-height x = x[xc[xi]] # confidence, (tensor): (n_conf_thres, [cx cy l s obj num_cls theta_cls]) # Cat apriori labels if autolabelling if labels and len(labels[xi]): l = labels[xi] v = torch.zeros((len(l), nc + 5), device=x.device) v[:, :4] = l[:, 1:5] # box v[:, 4] = 1.0 # conf v[range(len(l)), l[:, 0].long() + 5] = 1.0 # cls x = torch.cat((x, v), 0) # If none remain process next image if not x.shape[0]: continue # Compute conf x[:, 5:class_index] *= x[:, 4:5] # conf = obj_conf * cls_conf _, theta_pred = torch.max(x[:, class_index:], 1, keepdim=True) # [n_conf_thres, 1] θ ∈ int[0, 179] theta_pred = (theta_pred - 90) / 180 * pi # [n_conf_thres, 1] θ ∈ [-pi/2, pi/2) # Detections matrix nx7 (xyls, θ, conf, cls) θ ∈ [-pi/2, pi/2) if multi_label: i, j = (x[:, 5:class_index] > conf_thres).nonzero(as_tuple=False).T # () x = torch.cat((x[i, :4], theta_pred[i], x[i, j + 5, None], j[:, None].float()), 1) else: # best class only conf, j = x[:, 5:class_index].max(1, keepdim=True) x = torch.cat((x[:, :4], theta_pred, conf, j.float()), 1)[conf.view(-1) > conf_thres] # Filter by class if classes is not None: x = x[(x[:, 6:7] == torch.tensor(classes, device=x.device)).any(1)] # Apply finite constraint # if not torch.isfinite(x).all(): # x = x[torch.isfinite(x).all(1)] # Check shape n = x.shape[0] # number of boxes if not n: # no boxes continue elif n > max_nms: # excess boxes x = x[x[:, 5].argsort(descending=True)[:max_nms]] # sort by confidence # Batched NMS c = x[:, 6:7] * (0 if agnostic else max_wh) # classes rboxes = x[:, :5].clone() rboxes[:, :2] = rboxes[:, :2] + c # rboxes (offset by class) scores = x[:, 5] # scores _, i = obb_nms(rboxes, scores, iou_thres) if i.shape[0] > max_det: # limit detections i = i[:max_det] output[xi] = x[i] if (time.time() - t) > time_limit: print(f'WARNING: NMS time limit {time_limit}s exceeded') break # time limit exceeded return output def obb_nms(dets, scores, iou_thr, device_id=None): """ RIoU NMS - iou_thr. Args: dets (tensor/array): (num, [cx cy w h θ]) θ∈[-pi/2, pi/2) scores (tensor/array): (num) iou_thr (float): (1) Returns: dets (tensor): (n_nms, [cx cy w h θ]) inds (tensor): (n_nms), nms index of dets """ if isinstance(dets, torch.Tensor): is_numpy = False dets_th = dets elif isinstance(dets, np.ndarray): is_numpy = True device = 'cpu' if device_id is None else f'cuda:{device_id}' dets_th = torch.from_numpy(dets).to(device) else: raise TypeError('dets must be eithr a Tensor or numpy array, ' f'but got {type(dets)}') if dets_th.numel() == 0: # len(dets) inds = dets_th.new_zeros(0, dtype=torch.int64) else: # same bug will happen when bboxes is too small too_small = dets_th[:, [2, 3]].min(1)[0] < 0.001 # [n] if too_small.all(): # all the bboxes is too small inds = dets_th.new_zeros(0, dtype=torch.int64) else: ori_inds = torch.arange(dets_th.size(0)) # 0 ~ n-1 ori_inds = ori_inds[~too_small] dets_th = dets_th[~too_small] # (n_filter, 5) scores = scores[~too_small] inds = nms_rotated_ext.nms_rotated(dets_th, scores, iou_thr) inds = ori_inds[inds] if is_numpy: inds = inds.cpu().numpy() return dets[inds, :], inds def poly_nms(dets, iou_thr, device_id=None): if isinstance(dets, torch.Tensor): is_numpy = False dets_th = dets elif isinstance(dets, np.ndarray): is_numpy = True device = 'cpu' if device_id is None else f'cuda:{device_id}' dets_th = torch.from_numpy(dets).to(device) else: raise TypeError('dets must be eithr a Tensor or numpy array, ' f'but got {type(dets)}') if dets_th.device == torch.device('cpu'): raise NotImplementedError inds = nms_rotated_ext.nms_poly(dets_th.float(), iou_thr) if is_numpy: inds = inds.cpu().numpy() return dets[inds, :], inds def box_iou(box1, box2, eps=1e-7): # https://github.com/pytorch/vision/blob/master/torchvision/ops/boxes.py """ Return intersection-over-union (Jaccard index) of boxes. Both sets of boxes are expected to be in (x1, y1, x2, y2) format. Arguments: box1 (Tensor[N, 4]) box2 (Tensor[M, 4]) Returns: iou (Tensor[N, M]): the NxM matrix containing the pairwise IoU values for every element in boxes1 and boxes2 """ # inter(N,M) = (rb(N,M,2) - lt(N,M,2)).clamp(0).prod(2) (a1, a2), (b1, b2) = box1.unsqueeze(1).chunk(2, 2), box2.unsqueeze(0).chunk(2, 2) inter = (torch.min(a2, b2) - torch.max(a1, b1)).clamp(0).prod(2) # IoU = inter / (area1 + area2 - inter) return inter / ((a2 - a1).prod(2) + (b2 - b1).prod(2) - inter + eps) def rbox2poly(obboxes): """ Trans rbox format to poly format. Args: rboxes (array/tensor): (num_gts, [cx cy l s θ]) θ∈[-pi/2, pi/2) Returns: polys (array/tensor): (num_gts, [x1 y1 x2 y2 x3 y3 x4 y4]) """ if isinstance(obboxes, torch.Tensor): center, w, h, theta = obboxes[:, :2], obboxes[:, 2:3], obboxes[:, 3:4], obboxes[:, 4:5] Cos, Sin = torch.cos(theta), torch.sin(theta) vector1 = torch.cat( (w/2 * Cos, -w/2 * Sin), dim=-1) vector2 = torch.cat( (-h/2 * Sin, -h/2 * Cos), dim=-1) point1 = center + vector1 + vector2 point2 = center + vector1 - vector2 point3 = center - vector1 - vector2 point4 = center - vector1 + vector2 order = obboxes.shape[:-1] return torch.cat( (point1, point2, point3, point4), dim=-1).reshape(*order, 8) else: center, w, h, theta = np.split(obboxes, (2, 3, 4), axis=-1) Cos, Sin = np.cos(theta), np.sin(theta) vector1 = np.concatenate( [w/2 * Cos, -w/2 * Sin], axis=-1) vector2 = np.concatenate( [-h/2 * Sin, -h/2 * Cos], axis=-1) point1 = center + vector1 + vector2 point2 = center + vector1 - vector2 point3 = center - vector1 - vector2 point4 = center - vector1 + vector2 order = obboxes.shape[:-1] return np.concatenate( [point1, point2, point3, point4], axis=-1).reshape(*order, 8) def scale_polys(img1_shape, polys, img0_shape, ratio_pad=None): # ratio_pad: [(h_raw, w_raw), (hw_ratios, wh_paddings)] # Rescale coords (xyxyxyxy) 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 = resized / raw 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] # h_ratios pad = ratio_pad[1] # wh_paddings polys[:, [0, 2, 4, 6]] -= pad[0] # x padding polys[:, [1, 3, 5, 7]] -= pad[1] # y padding polys[:, :8] /= gain # Rescale poly shape to img0_shape #clip_polys(polys, img0_shape) return polys