Fix API method name: use inference() instead of infer_image()

The DepthAnything3 API uses inference() method, not infer_image().

Changes:
- Call model.inference([image]) with a list of images
- Returns a Prediction object with .depth attribute
- Extract depth map with prediction.depth[0]

This fixes the AttributeError:
'DepthAnything3' object has no attribute 'infer_image'

Co-authored-by: Cursor <cursoragent@cursor.com>

simple_app.py

@@ -135,7 +135,9 @@ class SimpleDepthApp:
                     # Measure ONLY inference time
                     inference_start = time.time()
                     with torch.no_grad():
-                        depth = model.infer_image(image_np)
+                        # API expects a list of images, returns Prediction object
+                        prediction = model.inference([image_np])
+                        depth = prediction.depth[0]  # Get first (and only) depth map
                     inference_time = time.time() - inference_start
                     
                     inference_times.append(inference_time)
@@ -234,7 +236,13 @@ class SimpleDepthApp:
                     final_status = "❌ Error processing images. Check console for details."
                     metrics_msg = ""
                 else:
-                    final_status = "✅ Done! Download your depth maps below."
+                    # Check if all images were processed successfully
+                    success_rate = metrics['images_processed'] / metrics['total_images'] if metrics['total_images'] > 0 else 0
+                    if metrics['images_processed'] < metrics['total_images']:
+                        skipped = metrics['total_images'] - metrics['images_processed']
+                        final_status = f"✅ Done! Processed {metrics['images_processed']} images. ({skipped} skipped due to errors)"
+                    else:
+                        final_status = f"✅ Done! All {metrics['images_processed']} images processed successfully."
                     
                     # Format metrics for display
                     throughput = 1/metrics['avg_time_per_image'] if metrics['avg_time_per_image'] > 0 else 0
@@ -244,7 +252,7 @@ class SimpleDepthApp:
 | Metric | Value |
 |--------|-------|
 | **Total Images Found** | {metrics['total_images']} |
-| **Images Successfully Processed** | {metrics['images_processed']} |
+| **Successfully Processed** | {metrics['images_processed']} ({success_rate*100:.0f}%) |
 | **Total Inference Time** | {metrics['total_inference_time']:.2f}s |
 | **Average Time per Image** | {metrics['avg_time_per_image']:.3f}s |
 | **Throughput** | {throughput:.2f} images/second |

simple_batch_process.py

@@ -81,7 +81,9 @@ def process_images_from_directory(input_dir: str, output_dir: str, model):
             # Predict depth (measure inference time only)
             inference_start = time.time()
             with torch.no_grad():
-                depth = model.infer_image(image_np)
+                # API expects a list of images, returns Prediction object
+                prediction = model.inference([image_np])
+                depth = prediction.depth[0]  # Get first (and only) depth map
             inference_time = time.time() - inference_start
             inference_times.append(inference_time)