init

app.py

@@ -0,0 +1,186 @@
+import gradio as gr
+import cv2
+import numpy as np
+from ultralytics import YOLO
+from PIL import Image
+import io
+import os
+
+# --- Load models ---
+print("Loading models...")
+try:
+    model_v1 = YOLO("v1.pt")
+    model_v1l = YOLO("v1l.pt")
+    print("Models loaded successfully!")
+except Exception as e:
+    print(f"Error loading models: {e}")
+    raise
+
+
+def ensemble_predict(image, conf_threshold=0.25):
+    """
+    Run ensemble inference on input image using v1 and v1l models
+    Returns annotated image and detection results
+    """
+    if image is None:
+        return None, "No image provided"
+    
+    # Convert PIL Image to OpenCV format
+    if isinstance(image, Image.Image):
+        image_cv = cv2.cvtColor(np.array(image), cv2.COLOR_RGB2BGR)
+    else:
+        image_cv = image
+    
+    # Predict dengan kedua model
+    results_v1 = model_v1.predict(
+        source=image_cv, conf=conf_threshold, save=False, verbose=False
+    )[0]
+    results_v1l = model_v1l.predict(
+        source=image_cv, conf=conf_threshold, save=False, verbose=False
+    )[0]
+    
+    # Ensemble: voting class dengan weighted confidence
+    ensemble_results = []
+    
+    for box_v1 in results_v1.boxes:
+        cls_v1 = int(box_v1.cls[0])
+        conf_v1 = float(box_v1.conf[0])
+        xyxy_v1 = box_v1.xyxy[0].cpu().numpy()
+        
+        # Cek deteksi terkait di v1l (dengan IoU threshold)
+        best_match = None
+        best_iou = 0
+        
+        for box_v1l in results_v1l.boxes:
+            xyxy_v1l = box_v1l.xyxy[0].cpu().numpy()
+            
+            # Hitung IoU
+            x1_min, y1_min, x1_max, y1_max = xyxy_v1
+            x2_min, y2_min, x2_max, y2_max = xyxy_v1l
+            
+            inter_x1 = max(x1_min, x2_min)
+            inter_y1 = max(y1_min, y2_min)
+            inter_x2 = min(x1_max, x2_max)
+            inter_y2 = min(y1_max, y2_max)
+            
+            if inter_x2 > inter_x1 and inter_y2 > inter_y1:
+                inter_area = (inter_x2 - inter_x1) * (inter_y2 - inter_y1)
+                box1_area = (x1_max - x1_min) * (y1_max - y1_min)
+                box2_area = (x2_max - x2_min) * (y2_max - y2_min)
+                union_area = box1_area + box2_area - inter_area
+                iou = inter_area / union_area if union_area > 0 else 0
+                
+                if iou > best_iou:
+                    best_iou = iou
+                    best_match = box_v1l
+        
+        if best_iou > 0.3:  # Jika ada overlap significant
+            cls_v1l = int(best_match.cls[0])
+            conf_v1l = float(best_match.conf[0])
+            
+            # Voting: jika kedua model setuju class, gunakan weighted avg confidence
+            if cls_v1 == cls_v1l:
+                final_cls = cls_v1
+                final_conf = (conf_v1 + conf_v1l) / 2
+            else:
+                # Jika beda class, ambil yang confidence-nya lebih tinggi
+                if conf_v1 >= conf_v1l:
+                    final_cls = cls_v1
+                    final_conf = conf_v1
+                else:
+                    final_cls = cls_v1l
+                    final_conf = conf_v1l
+        else:
+            # Jika tidak ada match, gunakan v1 saja
+            final_cls = cls_v1
+            final_conf = conf_v1
+        
+        ensemble_results.append((xyxy_v1, final_cls, final_conf))
+    
+    # --- Create annotated image ---
+    annotated = image_cv.copy()
+    
+    # Color mapping untuk setiap class
+    colors = [(0, 128, 0), (128, 0, 0), (0, 0, 128), (128, 128, 0)]
+    
+    # Scale font based on image size
+    image_height = image_cv.shape[0]
+    base_font_scale = max(0.6, image_height / 1000.0)  # Scale with image height
+    base_thickness = max(2, int(image_height / 500.0))
+    
+    results_text = "=== Ensemble Prediction Results ===\n"
+    
+    for xyxy, cls, conf in ensemble_results:
+        x1, y1, x2, y2 = xyxy.astype(int)
+        label = model_v1.names[cls]
+        text = f"{label} {conf*100:.1f}%"
+        
+        results_text += f"Label: {label}\nConfidence: {conf:.3f}\nBBox: [{x1}, {y1}, {x2}, {y2}]\n\n"
+        
+        # Pilih warna berdasarkan class
+        color = colors[cls % len(colors)]
+        
+        # Draw bounding box with scaled thickness
+        cv2.rectangle(annotated, (x1, y1), (x2, y2), color, base_thickness)
+        
+        # Draw label background with scaled font
+        font = cv2.FONT_HERSHEY_SIMPLEX
+        text_size = cv2.getTextSize(text, font, base_font_scale, base_thickness)[0]
+        
+        cv2.rectangle(
+            annotated,
+            (x1, y1 - text_size[1] - 8),
+            (x1 + text_size[0] + 8, y1),
+            color,
+            -1,
+        )
+        cv2.putText(
+            annotated,
+            text,
+            (x1 + 4, y1 - 4),
+            font,
+            base_font_scale,
+            (255, 255, 255),
+            base_thickness,
+        )
+    
+    if len(ensemble_results) == 0:
+        results_text += "No detections found."
+    
+    # Convert BGR to RGB for display
+    annotated_rgb = cv2.cvtColor(annotated, cv2.COLOR_BGR2RGB)
+    
+    return annotated_rgb, results_text
+
+
+# --- Create Gradio Interface ---
+with gr.Blocks(title="YonkersNet") as demo:
+    gr.Markdown("# YonkersNet")
+    gr.Markdown(
+        "A Yolo model trained for detecting anime breast size, using ensemble method."
+    )
+    
+    with gr.Row():
+        with gr.Column():
+            image_input = gr.Image(label="Upload Image", type="pil")
+            conf_slider = gr.Slider(
+                minimum=0.0,
+                maximum=1.0,
+                value=0.25,
+                step=0.05,
+                label="Confidence Threshold",
+            )
+            gr.Markdown("Sometimes at the rare moment the model isn't really confidence yet to predict. Lowering the threshold can be solve that.")
+            predict_btn = gr.Button("Run Detection", variant="primary")
+        
+        with gr.Column():
+            image_output = gr.Image(label="Detection Result")
+            results_output = gr.Textbox(label="Detection Results", lines=10)
+    
+    predict_btn.click(
+        fn=ensemble_predict, inputs=[image_input, conf_slider], outputs=[image_output, results_output]
+    )
+
+
+if __name__ == "__main__":
+    demo.queue().launch(share=True)

requirements.txt

@@ -0,0 +1,7 @@
+ultralytics>=8.0.0
+gradio>=4.0.0
+opencv-python>=4.8.0
+numpy>=1.24.0
+pillow>=10.0.0
+torch>=2.0.0
+torchvision>=0.15.0

v1.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a8bfc0819093d2776f9045e6810ef163ca36f3d4bf9c631174db4d22d301e4f
+size 6245354

v1l.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90441396f0866b7ddeea70166c17368138a1294e7a19fbabcdb654f21e22f0f0
+size 6252586