Add random interpolation method augmentation (#6826)

* add random_interpolation option to make model robust to interpolation methods

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* Fix precommit error

* Update augmentations.py

* Update augmentations.py

* Update augmentations.py

* Update datasets.py

* Update datasets.py

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>

utils/datasets.py

@@ -397,6 +397,7 @@ def img2label_paths(img_paths):
 class LoadImagesAndLabels(Dataset):
     # YOLOv5 train_loader/val_loader, loads images and labels for training and validation
     cache_version = 0.6  # dataset labels *.cache version
+    rand_interp_methods = [cv2.INTER_NEAREST, cv2.INTER_LINEAR, cv2.INTER_CUBIC, cv2.INTER_AREA, cv2.INTER_LANCZOS4]
 
     def __init__(self,
                  path,
@@ -665,8 +666,8 @@ class LoadImagesAndLabels(Dataset):
             h0, w0 = im.shape[:2]  # orig hw
             r = self.img_size / max(h0, w0)  # ratio
             if r != 1:  # if sizes are not equal
-                im = cv2.resize(im, (int(w0 * r), int(h0 * r)),
-                                interpolation=cv2.INTER_LINEAR if (self.augment or r > 1) else cv2.INTER_AREA)
+                interp = cv2.INTER_LINEAR if self.augment else cv2.INTER_AREA  # random.choice(self.rand_interp_methods)
+                im = cv2.resize(im, (int(w0 * r), int(h0 * r)), interpolation=interp)
             return im, (h0, w0), im.shape[:2]  # im, hw_original, hw_resized
         else:
             return self.ims[i], self.im_hw0[i], self.im_hw[i]  # im, hw_original, hw_resized