New scale_segments() function (#9570)

* Rename scale_coords to scale_boxes

* add scale_segments

utils/general.py

@@ -725,7 +725,7 @@ def xywhn2xyxy(x, w=640, h=640, padw=0, padh=0):
 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
+        clip_boxes(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
@@ -769,7 +769,23 @@ def resample_segments(segments, n=1000):
     return segments
 
 
-def scale_coords(img1_shape, coords, img0_shape, ratio_pad=None):
+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):
     # 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
@@ -778,15 +794,15 @@ def scale_coords(img1_shape, coords, img0_shape, ratio_pad=None):
         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
+    segments[:, 0] -= pad[0]  # x padding
+    segments[:, 1] -= pad[1]  # y padding
+    segments /= gain
+    clip_segments(segments, img0_shape)
+    return segments
 
 
-def clip_coords(boxes, shape):
-    # Clip bounding xyxy bounding boxes to image shape (height, width)
+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
@@ -797,6 +813,16 @@ def clip_coords(boxes, shape):
         boxes[:, [1, 3]] = boxes[:, [1, 3]].clip(0, shape[0])  # y1, y2
 
 
+def clip_segments(boxes, shape):
+    # Clip segments (xy1,xy2,...) to image shape (height, width)
+    if isinstance(boxes, torch.Tensor):  # faster individually
+        boxes[:, 0].clamp_(0, shape[1])  # x
+        boxes[:, 1].clamp_(0, shape[0])  # y
+    else:  # np.array (faster grouped)
+        boxes[:, 0] = boxes[:, 0].clip(0, shape[1])  # x
+        boxes[:, 1] = boxes[:, 1].clip(0, shape[0])  # y
+
+
 def non_max_suppression(
         prediction,
         conf_thres=0.25,
@@ -980,7 +1006,7 @@ def apply_classifier(x, model, img, im0):
             d[:, :4] = xywh2xyxy(b).long()
 
             # Rescale boxes from img_size to im0 size
-            scale_coords(img.shape[2:], d[:, :4], im0[i].shape)
+            scale_boxes(img.shape[2:], d[:, :4], im0[i].shape)
 
             # Classes
             pred_cls1 = d[:, 5].long()

utils/loggers/comet/__init__.py

@@ -28,7 +28,7 @@ import torchvision.transforms as T
 import yaml
 
 from utils.dataloaders import img2label_paths
-from utils.general import check_dataset, scale_coords, xywh2xyxy
+from utils.general import check_dataset, scale_boxes, xywh2xyxy
 from utils.metrics import box_iou
 
 COMET_PREFIX = "comet://"
@@ -293,14 +293,14 @@ class CometLogger:
             pred[:, 5] = 0
 
         predn = pred.clone()
-        scale_coords(image.shape[1:], predn[:, :4], shape[0], shape[1])
+        scale_boxes(image.shape[1:], predn[:, :4], shape[0], shape[1])
 
         labelsn = None
         if nl:
             tbox = xywh2xyxy(labels[:, 1:5])  # target boxes
-            scale_coords(image.shape[1:], tbox, shape[0], shape[1])  # native-space labels
+            scale_boxes(image.shape[1:], tbox, shape[0], shape[1])  # native-space labels
             labelsn = torch.cat((labels[:, 0:1], tbox), 1)  # native-space labels
-            scale_coords(image.shape[1:], predn[:, :4], shape[0], shape[1])  # native-space pred
+            scale_boxes(image.shape[1:], predn[:, :4], shape[0], shape[1])  # native-space pred
 
         return predn, labelsn
 

utils/plots.py

@@ -20,7 +20,7 @@ import torch
 from PIL import Image, ImageDraw, ImageFont
 
 from utils import TryExcept, threaded
-from utils.general import (CONFIG_DIR, FONT, LOGGER, check_font, check_requirements, clip_coords, increment_path,
+from utils.general import (CONFIG_DIR, FONT, LOGGER, check_font, check_requirements, clip_boxes, increment_path,
                            is_ascii, xywh2xyxy, xyxy2xywh)
 from utils.metrics import fitness
 from utils.segment.general import scale_image
@@ -565,7 +565,7 @@ def save_one_box(xyxy, im, file=Path('im.jpg'), gain=1.02, pad=10, square=False,
         b[:, 2:] = b[:, 2:].max(1)[0].unsqueeze(1)  # attempt rectangle to square
     b[:, 2:] = b[:, 2:] * gain + pad  # box wh * gain + pad
     xyxy = xywh2xyxy(b).long()
-    clip_coords(xyxy, im.shape)
+    clip_boxes(xyxy, im.shape)
     crop = im[int(xyxy[0, 1]):int(xyxy[0, 3]), int(xyxy[0, 0]):int(xyxy[0, 2]), ::(1 if BGR else -1)]
     if save:
         file.parent.mkdir(parents=True, exist_ok=True)  # make directory