add D-Fine preprocessor

preprocessor_config.json

@@ -1,3 +1,6 @@
 {
-    "processor_class": "DFineProcessor"
-}  
+    "processor_class": "DFineProcessor",
+    "auto_map": {
+      "AutoProcessor": "d-fine--processor_dfine.DFineProcessor"
+    }
+}

processor_dfine.py

@@ -0,0 +1,69 @@
+from transformers import ProcessorMixin
+from PIL import Image
+import torch
+import torchvision.transforms as T
+import numpy as np
+import os
+import json
+
+class DFineProcessor(ProcessorMixin):
+    processor_class = "DFineProcessor"
+
+    def __init__(self, size=640):
+        self.size = size
+
+    def resize_with_aspect_ratio(self, image, size):
+        orig_w, orig_h = image.size
+        ratio = min(size / orig_w, size / orig_h)
+        new_w, new_h = int(orig_w * ratio), int(orig_h * ratio)
+        image = image.resize((new_w, new_h), Image.BILINEAR)
+
+        new_image = Image.new("RGB", (size, size))
+        pad_w, pad_h = (size - new_w) // 2, (size - new_h) // 2
+        new_image.paste(image, (pad_w, pad_h))
+        return new_image, ratio, pad_w, pad_h
+
+    def __call__(self, images, return_tensors="pt"):
+        if not isinstance(images, list):
+            images = [images]
+
+        processed_images = []
+        ratios = []
+        pad_ws = []
+        pad_hs = []
+
+        for image in images:
+            if isinstance(image, np.ndarray):
+                image = Image.fromarray(image[..., ::-1]) if image.shape[-1] == 3 else Image.fromarray(image)
+
+            if not isinstance(image, Image.Image):
+                raise ValueError("All inputs must be PIL images.")
+            resized_img, ratio, pad_w, pad_h = self.resize_with_aspect_ratio(image, self.size)
+            tensor_img = T.ToTensor()(resized_img)
+            processed_images.append(tensor_img)
+            ratios.append(ratio)
+            pad_ws.append(pad_w)
+            pad_hs.append(pad_h)
+
+        torch_imgs = torch.stack(processed_images)
+        ratios = torch.tensor(ratios)
+        pad_w = torch.tensor(pad_ws)
+        pad_h = torch.tensor(pad_hs)
+        orig_target_sizes = torch.tensor([[self.size, self.size]])
+
+        return {
+            "images": torch_imgs,
+            "orig_target_sizes": orig_target_sizes,
+            "ratio": ratios,
+            "pad_w": pad_w,
+            "pad_h": pad_h,
+        }
+
+    def save_pretrained(self, save_directory):
+        os.makedirs(save_directory, exist_ok=True)
+        with open(os.path.join(save_directory, "preprocessor_config.json"), "w") as f:
+            json.dump({"processor_class": self.__class__.__name__}, f)
+
+    @classmethod
+    def from_pretrained(cls, pretrained_model_name_or_path, **kwargs):
+        return cls()