Adapt the resize to cv2 version to keep consistent with that used in training.

app.py

@@ -15,10 +15,17 @@ config = Config()
 device = config.device
 
 
+
+def array_to_pil_image(image, size=(1024, 1024)):
+    image = cv2.resize(image, size, interpolation=cv2.INTER_LINEAR)
+    image = Image.fromarray(image).convert('RGB')
+    return image
+
+
 class ImagePreprocessor():
     def __init__(self, resolution=(1024, 1024)) -> None:
         self.transform_image = transforms.Compose([
-            transforms.Resize(resolution),
+            # transforms.Resize(resolution),    # 1. keep consistent with the cv2.resize used in training 2. redundant with that in path_to_image()
             transforms.ToTensor(),
             transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225]),
         ])
@@ -43,11 +50,12 @@ model.eval()
 # def predict(image_1, image_2):
 #     images = [image_1, image_2]
 def predict(image, resolution='1024x1024'):
+    # Image is a RGB numpy array.
+    resolution = [int(int(reso)//32*32) for reso in resolution.strip().split('x')]
     images = [image]
     image_shapes = [image.shape[:2] for image in images]
-    images = [Image.fromarray(image) for image in images]
+    images = [array_to_pil_image(image, resolution) for image in images]
 
-    resolution = [int(int(reso)//32*32) for reso in resolution.strip().split('x')]
     image_preprocessor = ImagePreprocessor(resolution=resolution)
     images_proc = []
     for image in images: