Add xyxy2xywhn() (#3765)

* Edit Comments for numpy2torch tensor process

Edit Comments for numpy2torch tensor process

* add xyxy2xywhn

add xyxy2xywhn

* add xyxy2xywhn

* formatting

* pass arguments

pass arguments

* edit comment for xyxy2xywhn()

edit comment for xyxy2xywhn()

* cleanup datasets.py

Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>

utils/datasets.py

@@ -23,8 +23,8 @@ from PIL import Image, ExifTags
 from torch.utils.data import Dataset
 from tqdm import tqdm
 
-from utils.general import check_requirements, check_file, check_dataset, xyxy2xywh, xywh2xyxy, xywhn2xyxy, xyn2xy, \
-    segment2box, segments2boxes, resample_segments, clean_str
+from utils.general import check_requirements, check_file, check_dataset, xywh2xyxy, xywhn2xyxy, xyxy2xywhn, \
+    xyn2xy, segment2box, segments2boxes, resample_segments, clean_str
 from utils.torch_utils import torch_distributed_zero_first
 
 # Parameters
@@ -192,7 +192,7 @@ class LoadImages:  # for inference
         img = letterbox(img0, self.img_size, stride=self.stride)[0]
 
         # Convert
-        img = img[:, :, ::-1].transpose(2, 0, 1)  # BGR to RGB, to 3x416x416
+        img = img[:, :, ::-1].transpose(2, 0, 1)  # BGR to RGB and HWC to CHW
         img = np.ascontiguousarray(img)
 
         return path, img, img0, self.cap
@@ -255,7 +255,7 @@ class LoadWebcam:  # for inference
         img = letterbox(img0, self.img_size, stride=self.stride)[0]
 
         # Convert
-        img = img[:, :, ::-1].transpose(2, 0, 1)  # BGR to RGB, to 3x416x416
+        img = img[:, :, ::-1].transpose(2, 0, 1)  # BGR to RGB and HWC to CHW
         img = np.ascontiguousarray(img)
 
         return img_path, img, img0, None
@@ -336,7 +336,7 @@ class LoadStreams:  # multiple IP or RTSP cameras
         img = np.stack(img, 0)
 
         # Convert
-        img = img[:, :, :, ::-1].transpose(0, 3, 1, 2)  # BGR to RGB, to bsx3x416x416
+        img = img[:, :, :, ::-1].transpose(0, 3, 1, 2)  # BGR to RGB and BHWC to BCHW
         img = np.ascontiguousarray(img)
 
         return self.sources, img, img0, None
@@ -552,9 +552,7 @@ class LoadImagesAndLabels(Dataset):  # for training/testing
 
         nL = len(labels)  # number of labels
         if nL:
-            labels[:, 1:5] = xyxy2xywh(labels[:, 1:5])  # convert xyxy to xywh
-            labels[:, [2, 4]] /= img.shape[0]  # normalized height 0-1
-            labels[:, [1, 3]] /= img.shape[1]  # normalized width 0-1
+            labels[:, 1:5] = xyxy2xywhn(labels[:, 1:5], w=img.shape[1], h=img.shape[0])  # xyxy to xywh normalized
 
         if self.augment:
             # flip up-down