updates

utils/datasets.py

@@ -74,7 +74,7 @@ class LoadImages:  # for inference
             print('image %g/%g %s: ' % (self.count, self.nF, path), end='')
 
         # Padded resize
-        img, _, _, _ = letterbox(img0, height=self.height)
+        img, _, _, _ = letterbox_rect(img0, height=self.height)
 
         # Normalize RGB
         img = img[:, :, ::-1].transpose(2, 0, 1)  # BGR to RGB
@@ -239,9 +239,11 @@ def letterbox(img, height=416, color=(127.5, 127.5, 127.5)):
     # Resize a rectangular image to a padded square
     shape = img.shape[:2]  # shape = [height, width]
     ratio = float(height) / max(shape)  # ratio  = old / new
-    new_shape = (round(shape[1] * ratio), round(shape[0] * ratio))
+    new_shape = (round(shape[1] * ratio), round(shape[0] * ratio))  # new_shape = [width, height]
+
     dw = (height - new_shape[0]) / 2  # width padding
     dh = (height - new_shape[1]) / 2  # height padding
+
     top, bottom = round(dh - 0.1), round(dh + 0.1)
     left, right = round(dw - 0.1), round(dw + 0.1)
     img = cv2.resize(img, new_shape, interpolation=cv2.INTER_AREA)  # resized, no border
@@ -249,6 +251,22 @@ def letterbox(img, height=416, color=(127.5, 127.5, 127.5)):
     return img, ratio, dw, dh
 
 
+def letterbox_rect(img, height=416, color=(127.5, 127.5, 127.5)):
+    # Resize a rectangular image to a 32 pixel multiple rectangle
+    shape = img.shape[:2]  # shape = [height, width]
+    ratio = float(height) / max(shape)  # ratio  = old / new
+    new_shape = (round(shape[1] * ratio), round(shape[0] * ratio))  # new_shape = [width, height]
+
+    dw = np.mod(height - new_shape[0], 32) / 2  # width padding
+    dh = np.mod(height - new_shape[1], 32) / 2  # height padding
+
+    top, bottom = int(round(dh - 0.1)), int(round(dh + 0.1))
+    left, right = int(round(dw - 0.1)), int(round(dw + 0.1))
+    img = cv2.resize(img, new_shape, interpolation=cv2.INTER_AREA)  # resized, no border
+    img = cv2.copyMakeBorder(img, top, bottom, left, right, cv2.BORDER_CONSTANT, value=color)  # padded square
+    return img, ratio, dw, dh
+
+
 def random_affine(img, targets=(), degrees=(-10, 10), translate=(.1, .1), scale=(.9, 1.1), shear=(-2, 2),
                   borderValue=(127.5, 127.5, 127.5)):
     # torchvision.transforms.RandomAffine(degrees=(-10, 10), translate=(.1, .1), scale=(.9, 1.1), shear=(-10, 10))

utils/utils.py

@@ -100,11 +100,11 @@ def xywh2xyxy(x):
     return y
 
 
-def scale_coords(img_size, coords, img0_shape):
-    # Rescale x1, y1, x2, y2 from 416 to image size
-    gain = float(img_size) / max(img0_shape)  # gain  = old / new
-    pad_x = (img_size - img0_shape[1] * gain) / 2  # width padding
-    pad_y = (img_size - img0_shape[0] * gain) / 2  # height padding
+def scale_coords(img1_shape, coords, img0_shape):
+    # Rescale coords1 (xyxy) from img1_shape to img0_shape
+    gain = max(img1_shape[1:3]) / max(img0_shape[:2])  # gain  = old / new
+    pad_x = (img1_shape[2] - img0_shape[1] * gain) / 2  # width padding
+    pad_y = (img1_shape[1] - img0_shape[0] * gain) / 2  # height padding
     coords[:, [0, 2]] -= pad_x
     coords[:, [1, 3]] -= pad_y
     coords[:, :4] /= gain