Upload folder using huggingface_hub

README.md

@@ -2,5 +2,5 @@
 title: MyGradioApp
 app_file: myapp.py
 sdk: gradio
-sdk_version: 5.49.1
+sdk_version: 6.0.0
 ---

myapp.py

@@ -8,37 +8,43 @@ import gradio as gr
 image_processor = DetrImageProcessor.from_pretrained("facebook/detr-resnet-50")
 model = DetrForObjectDetection.from_pretrained("facebook/detr-resnet-50")
 
-def detect_objects(image):
+# Create list of all detectable object classes for dropdown
+label_list = sorted(model.config.id2label.values(), key=str.lower)
+
+def detect_objects(image, object_type):
     # convert image from NumPy array to PIL format
     image = Image.fromarray(image)
     
     # process the image
-    inputs = image_processor(images = image, 
-                             return_tensors = "pt")
+    inputs = image_processor(images=image, return_tensors="pt")
     outputs = model(**inputs)
     
-    # create the target size in the format of (height,width)
+    # create the target size (height, width)
     target_sizes = torch.tensor([image.size[::-1]])
 
-    # detect objects in image
-    results = image_processor.post_process_object_detection(outputs,
-                                                            target_sizes = target_sizes, 
-                                                            threshold = 0.9)[0]
+    # detect objects
+    results = image_processor.post_process_object_detection(
+        outputs,
+        target_sizes=target_sizes, 
+        threshold=0.9
+    )[0]
+
     draw = ImageDraw.Draw(image)
 
     for score, label, box in zip(results["scores"], results["labels"], results["boxes"]):
-        box = [round(i, 2) for i in box.tolist()]
-        # draw bounding box around object
-        draw.rectangle(box, 
-                       outline="yellow", 
-                       width=2)
-        # display the object label
-        draw.text((box[0], box[1]-10), 
-                  model.config.id2label[label.item()], 
-                  fill="white")  
+        detected_label = model.config.id2label[label.item()]
+        if detected_label == object_type:
+            box = [round(i, 2) for i in box.tolist()]
+            draw.rectangle(box, outline="yellow", width=2)
+            draw.text((box[0], box[1] - 10), detected_label, fill="white")
+
     return image
 
-gr.Interface(detect_objects, 
-             inputs = gr.Image(width = 300, height = 300), # indicate the size of image to be passed in
-             outputs = gr.Image(width = 300, height= 300), # indicate the size of image to be returned
+gr.Interface(
+    fn=detect_objects,
+    inputs=[
+        gr.Image(width=300, height=300),
+        gr.Dropdown(choices=label_list, label="Object Type")
+    ],
+    outputs=gr.Image(width=300, height=300),
 ).launch()