Update app.py

app.py

@@ -1,33 +1,26 @@
-import os
-import gradio as gr
-from transformers import pipeline
-from transformers import DetrForSegmentation, DetrConfig
+from transformers import DetrImageProcessor, DetrForObjectDetection
+import torch
+from PIL import Image
+import requests
 
-# Initialize the configuration for DetrForObjectDetection
-config = DetrConfig.from_pretrained("facebook/detr-resnet-50")
+url = "http://images.cocodataset.org/val2017/000000039769.jpg"
+image = Image.open(requests.get(url, stream=True).raw)
 
-# Create the model for object detection using the specified configuration
-model = DetrForSegmentation.from_pretrained("facebook/detr-resnet-50", config=config)
+# you can specify the revision tag if you don't want the timm dependency
+processor = DetrImageProcessor.from_pretrained("facebook/detr-resnet-50", revision="no_timm")
+model = DetrForObjectDetection.from_pretrained("facebook/detr-resnet-50", revision="no_timm")
 
-# Updated function call
-results = processed_image(model, image, size={'longest_edge': 800})
+inputs = processor(images=image, return_tensors="pt")
+outputs = model(**inputs)
 
-def get_pipeline_prediction(pil_image):
-    # first get the pipeline output given the pil image
-    pipeline_output = od_pipe(pil_image)
-    # Then Process the image using the pipeline output
-    processed_image = render_results_in_image(pil_image,
-                                            pipeline_output)
-   
-    return processed_image
+# convert outputs (bounding boxes and class logits) to COCO API
+# let's only keep detections with score > 0.9
+target_sizes = torch.tensor([image.size[::-1]])
+results = processor.post_process_object_detection(outputs, target_sizes=target_sizes, threshold=0.9)[0]
 
-
-demo = gr.Interface(
-  fn=get_pipeline_prediction,
-  inputs=gr.Image(label="Input image", 
-                  type="pil"),
-  outputs=gr.Image(label="Output image with predicted instances",
-                   type="pil")
-)
-
-demo.launch
+for score, label, box in zip(results["scores"], results["labels"], results["boxes"]):
+    box = [round(i, 2) for i in box.tolist()]
+    print(
+            f"Detected {model.config.id2label[label.item()]} with confidence "
+            f"{round(score.item(), 3)} at location {box}"
+    )