Update index.html

index.html

@@ -24,15 +24,19 @@ from transformers_js import import_transformers_js, as_url
 import gradio as gr
 
 
+IMAGE_SIZE = 256;
+
 transformers = await import_transformers_js()
 AutoProcessor = transformers.AutoProcessor
 AutoModel = transformers.AutoModel
 RawImage = transformers.RawImage
 
-processor = await AutoProcessor.from_pretrained('Xenova/yolov9-c');
-# TODO: Resize the input image
+processor = await AutoProcessor.from_pretrained('Xenova/yolov9-c')
+
+# For this demo, we resize the image to IMAGE_SIZE x IMAGE_SIZE
+processor.feature_extractor.size = { "width": IMAGE_SIZE, "height": IMAGE_SIZE }
 
-model = await AutoModel.from_pretrained('Xenova/yolov9-c');
+model = await AutoModel.from_pretrained('Xenova/yolov9-c')
 
 
 async def detect(image_path):
@@ -41,7 +45,7 @@ async def detect(image_path):
     processed_input = await processor(image)
 
     # Predict bounding boxes
-    result = await model(images=processed_input["pixel_values"]);
+    result = await model(images=processed_input["pixel_values"])
 
     outputs = result["outputs"]  # Tensor
     np_outputs = outputs.numpy()  # [xmin, ymin, xmax, ymax, score, id][]
@@ -49,10 +53,10 @@ async def detect(image_path):
         # List[Tuple[numpy.ndarray | Tuple[int, int, int, int], str]]
         (
             (
-                int(xmin),
-                int(ymin),
-                int(xmax),
-                int(ymax),
+                int(xmin * image.width / IMAGE_SIZE),
+                int(ymin * image.height / IMAGE_SIZE),
+                int(xmax * image.width / IMAGE_SIZE),
+                int(ymax * image.height / IMAGE_SIZE),
             ),
             model.config.id2label[str(int(id))],
         )