diff --git a/data/base_dataset.py b/data/base_dataset.py
index b6b9c08..1bd57d0 100644
--- a/data/base_dataset.py
+++ b/data/base_dataset.py
@@ -95,8 +95,8 @@ def get_affine_mat(opt, size):
     affine_inv = np.linalg.inv(affine)
     return affine, affine_inv, flip
 
-def apply_img_affine(img, affine_inv, method=Image.Resampling.BICUBIC):
-    return img.transform(img.size, Image.AFFINE, data=affine_inv.flatten()[:6], resample=Image.Resampling.BICUBIC)
+def apply_img_affine(img, affine_inv, method=Image.BICUBIC):
+    return img.transform(img.size, Image.AFFINE, data=affine_inv.flatten()[:6], resample=Image.BICUBIC)
 
 def apply_lm_affine(landmark, affine, flip, size):
     _, h = size
diff --git a/util/preprocess.py b/util/preprocess.py
index 4d9fc61..a6de6ea 100644
--- a/util/preprocess.py
+++ b/util/preprocess.py
@@ -142,11 +142,11 @@ def resize_n_crop_img(img, lm, t, s, target_size=224., mask=None):
     up = (h/2 - target_size/2 + float((h0/2 - t[1])*s)).astype(np.int32)
     below = up + target_size
 
-    img = img.resize((w, h), resample=Image.Resampling.BICUBIC)
+    img = img.resize((w, h), resample=Image.BICUBIC)
     img = img.crop((left, up, right, below))
 
     if mask is not None:
-        mask = mask.resize((w, h), resample=Image.Resampling.BICUBIC)
+        mask = mask.resize((w, h), resample=Image.BICUBIC)
         mask = mask.crop((left, up, right, below))
 
     lm = np.stack([lm[:, 0] - t[0] + w0/2, lm[:, 1] -
diff --git a/util/util.py b/util/util.py
index aa2fb10..0d689ca 100644
--- a/util/util.py
+++ b/util/util.py
@@ -107,9 +107,9 @@ def save_image(image_numpy, image_path, aspect_ratio=1.0):
     if aspect_ratio is None:
         pass
     elif aspect_ratio > 1.0:
-        image_pil = image_pil.resize((h, int(w * aspect_ratio)), Image.Resampling.BICUBIC)
+        image_pil = image_pil.resize((h, int(w * aspect_ratio)), Image.BICUBIC)
     elif aspect_ratio < 1.0:
-        image_pil = image_pil.resize((int(h / aspect_ratio), w), Image.Resampling.BICUBIC)
+        image_pil = image_pil.resize((int(h / aspect_ratio), w), Image.BICUBIC)
     image_pil.save(image_path)
 
 
@@ -166,13 +166,13 @@ def correct_resize_label(t, size):
     return torch.stack(resized, dim=0).to(device)
 
 
-def correct_resize(t, size, mode=Image.Resampling.BICUBIC):
+def correct_resize(t, size, mode=Image.BICUBIC):
     device = t.device
     t = t.detach().cpu()
     resized = []
     for i in range(t.size(0)):
         one_t = t[i:i + 1]
-        one_image = Image.fromarray(tensor2im(one_t)).resize(size, Image.Resampling.BICUBIC)
+        one_image = Image.fromarray(tensor2im(one_t)).resize(size, Image.BICUBIC)
         resized_t = torchvision.transforms.functional.to_tensor(one_image) * 2 - 1.0
         resized.append(resized_t)
     return torch.stack(resized, dim=0).to(device)