attempt 4 of logging

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")
@@ -17,30 +20,17 @@ 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
-    class_names = model.config.id2label  # Get the class name mapping
-
-    # Collect the class IDs and labels along with the bounding boxes
-    result = []
-    for idx, class_id in enumerate(predicted_classes):
-        class_name = class_names[class_id]
-        result.append({
-            "class_id": int(class_id),
-            "class_name": class_name,
-            "bounding_box": predicted_boxes[idx].tolist()  # Convert to list for JSON serialization
-        })
-
-    # Return the bounding boxes and classes
-    return result
+    predicted_classes = outputs.logits.argmax(-1).cpu().numpy()  # Class predictions
+    # Return the bounding boxes for display
+    print("Predicted Classes (IDs):", predicted_classes)
+    print("Bounding Boxes (x1, y1, x2, y2):", predicted_boxes)
+    return {"boxes": predicted_boxes.tolist(), "classes": predicted_classes.tolist()}
 
 # Set up the Gradio interface
 interface = gr.Interface(
     fn=predict,  # The function that gets called when an image is uploaded
     inputs=gr.Image(type="pil"),  # Image input (as PIL image)
-    outputs="json",  # Outputting a JSON with the class labels, IDs, and bounding boxes
-    title="Table Structure Recognition",  # Add title for clarity
-    description="Upload an image and see the detected table columns and their corresponding class IDs.",
+    outputs="json",  # Outputting a JSON with the boxes and classes
 )
 
 # Launch the Gradio app