try 3

app.py

@@ -1,7 +1,10 @@
 import gradio as gr
-from transformers import AutoImageProcessor, AutoModelForObjectDetection
+from huggingface_hub import hf_hub_download
+from PIL import Image
 import torch
+from transformers import AutoImageProcessor, AutoModelForObjectDetection
 
+gr.load("models/microsoft/table-transformer-structure-recognition").launch()
 # Load the processor and model for table structure recognition
 processor = AutoImageProcessor.from_pretrained("microsoft/table-transformer-structure-recognition")
 model = AutoModelForObjectDetection.from_pretrained("microsoft/table-transformer-structure-recognition")
@@ -17,19 +20,11 @@ def predict(image):
 
     # Extract bounding boxes and class labels
     predicted_boxes = outputs.pred_boxes[0].cpu().numpy()  # First image
-    predicted_class_logits = outputs.logits[0].cpu().numpy()  # Class logits for the first image
-    predicted_classes = predicted_class_logits.argmax(-1)  # Get class predictions
+    predicted_classes = outputs.logits.argmax(-1).cpu().numpy()  # Class predictions
     class_names = model.config.id2label  # Get the class name mapping
-    
-    # Filter predictions to only include columns based on class name
-    column_boxes = []
-    for idx, class_id in enumerate(predicted_classes):
-        class_name = class_names[class_id]
-        if "column" in class_name.lower():  # Check if the class name contains 'column'
-            column_boxes.append(predicted_boxes[idx])
-
-    # Return the bounding boxes for columns
-    return {"boxes": column_boxes, "classes": ["column"] * len(column_boxes)}
+    print(class_names)
+    # Return the bounding boxes for display
+    return {"boxes": predicted_boxes.tolist(), "classes": predicted_classes.tolist()}
 
 # Set up the Gradio interface
 interface = gr.Interface(