instead cv2 LANCZOS4 resize to pil resize

library/train_util.py

@@ -71,7 +71,7 @@ import library.model_util as model_util
 import library.huggingface_util as huggingface_util
 import library.sai_model_spec as sai_model_spec
 import library.deepspeed_utils as deepspeed_utils
-from library.utils import setup_logging
+from library.utils import setup_logging, pil_resize
 
 setup_logging()
 import logging
@@ -2028,9 +2028,7 @@ class ControlNetDataset(BaseDataset):
                 # ), f"image size is small / 画像サイズが小さいようです: {image_info.absolute_path}"
                 # resize to target
                 if cond_img.shape[0] != target_size_hw[0] or cond_img.shape[1] != target_size_hw[1]:
-                    cond_img = cv2.resize(
-                        cond_img, (int(target_size_hw[1]), int(target_size_hw[0])), interpolation=cv2.INTER_LANCZOS4
-                    )
+                    cond_img=pil_resize(cond_img,(int(target_size_hw[1]), int(target_size_hw[0])))
 
             if flipped:
                 cond_img = cond_img[:, ::-1, :].copy()  # copy to avoid negative stride
@@ -2362,7 +2360,10 @@ def trim_and_resize_if_required(
 
     if image_width != resized_size[0] or image_height != resized_size[1]:
         # リサイズする
-        image = cv2.resize(image, resized_size, interpolation=cv2.INTER_AREA)  # INTER_AREAでやりたいのでcv2でリサイズ
+        if image_width > resized_size[0] and image_height > resized_size[1]:
+            image = cv2.resize(image, resized_size, interpolation=cv2.INTER_AREA)  # INTER_AREAでやりたいのでcv2でリサイズ
+        else:
+            image = pil_resize(image, resized_size)
 
     image_height, image_width = image.shape[0:2]
 

library/utils.py

@@ -7,7 +7,9 @@ from typing import *
 from diffusers import EulerAncestralDiscreteScheduler
 import diffusers.schedulers.scheduling_euler_ancestral_discrete
 from diffusers.schedulers.scheduling_euler_ancestral_discrete import EulerAncestralDiscreteSchedulerOutput
-
+import cv2
+from PIL import Image
+import numpy as np
 
 def fire_in_thread(f, *args, **kwargs):
     threading.Thread(target=f, args=args, kwargs=kwargs).start()
@@ -78,7 +80,17 @@ def setup_logging(args=None, log_level=None, reset=False):
         logger = logging.getLogger(__name__)
         logger.info(msg_init)
 
+def pil_resize(image, size, interpolation=Image.LANCZOS):
 
+    pil_image = Image.fromarray(cv2.cvtColor(image, cv2.COLOR_BGR2RGB))
+
+    # use Pillow resize
+    resized_pil = pil_image.resize(size, interpolation)
+
+    # return cv2 image
+    resized_cv2 = cv2.cvtColor(np.array(resized_pil), cv2.COLOR_RGB2BGR)
+
+    return resized_cv2
 
 # TODO make inf_utils.py