Create app.py

app.py

@@ -0,0 +1,200 @@
+import gradio as gr
+from dotenv import load_dotenv
+from roboflow import Roboflow
+import tempfile
+import os
+import cv2
+import numpy as np
+from dds_cloudapi_sdk import Config, Client
+from dds_cloudapi_sdk.tasks.dinox import DinoxTask
+from dds_cloudapi_sdk.tasks.types import DetectionTarget
+from dds_cloudapi_sdk import TextPrompt
+import supervision as sv
+
+# ========== Configuration ==========
+load_dotenv()
+
+# Roboflow Config
+rf_api_key = os.getenv("ROBOFLOW_API_KEY")
+workspace = os.getenv("ROBOFLOW_WORKSPACE")
+project_name = os.getenv("ROBOFLOW_PROJECT")
+model_version = int(os.getenv("ROBOFLOW_MODEL_VERSION"))
+
+# DINO-X Config
+DINOX_API_KEY = os.getenv("DINO_X_API_KEY")
+DINOX_PROMPT = "beverage . bottle"  # Customize for competitor products
+
+# Initialize Models
+rf = Roboflow(api_key=rf_api_key)
+project = rf.workspace(workspace).project(project_name)
+yolo_model = project.version(model_version).model
+dinox_config = Config(DINOX_API_KEY)
+dinox_client = Client(dinox_config)
+
+# ========== Combined Detection Function ==========
+def detect_combined(image):
+    with tempfile.NamedTemporaryFile(delete=False, suffix=".jpg") as temp_file:
+        image.save(temp_file, format="JPEG")
+        temp_path = temp_file.name
+    try:
+        # [1] YOLO: Detect Nestlé Products
+        yolo_pred = yolo_model.predict(temp_path, confidence=60, overlap=80).json()
+        nestle_class_count = {}
+        nestle_boxes = []
+        for pred in yolo_pred['predictions']:
+            class_name = pred['class']
+            nestle_class_count[class_name] = nestle_class_count.get(class_name, 0) + 1
+            nestle_boxes.append((pred['x'], pred['y'], pred['width'], pred['height']))
+        total_nestle = sum(nestle_class_count.values())
+
+        # [2] DINO-X: Detect Competitor Products
+        image_url = dinox_client.upload_file(temp_path)
+        task = DinoxTask(
+            image_url=image_url,
+            prompts=[TextPrompt(text=DINOX_PROMPT)],
+            bbox_threshold=0.25,
+            targets=[DetectionTarget.BBox]
+        )
+        dinox_client.run_task(task)
+        dinox_pred = task.result.objects
+
+        # Filter & Count Competitors
+        competitor_class_count = {}
+        competitor_boxes = []
+        for obj in dinox_pred:
+            dinox_box = obj.bbox
+            if not is_overlap(dinox_box, nestle_boxes):
+                class_name = obj.category.strip().lower()
+                competitor_class_count[class_name] = competitor_class_count.get(class_name, 0) + 1
+                competitor_boxes.append({
+                    "class": class_name,
+                    "box": dinox_box,
+                    "confidence": obj.score
+                })
+        total_competitor = sum(competitor_class_count.values())
+
+        # [3] Format Output
+        result_text = "Product Nestle\n\n"
+        for class_name, count in nestle_class_count.items():
+            result_text += f"{class_name}: {count}\n"
+        result_text += f"\nTotal Product Nestle: {total_nestle}\n\n"
+        result_text += "Competitor Products\n\n"
+        if competitor_class_count:
+            for class_name, count in competitor_class_count.items():
+                result_text += f"{class_name}: {count}\n"
+        else:
+            result_text += "No competitors detected\n"
+        result_text += f"\nTotal Competitor: {total_competitor}"
+
+        # [4] Visualization
+        img = cv2.imread(temp_path)
+        # Nestlé (Green)
+        for pred in yolo_pred['predictions']:
+            x, y, w, h = pred['x'], pred['y'], pred['width'], pred['height']
+            cv2.rectangle(img, (int(x-w/2), int(y-h/2)), (int(x+w/2), int(y+h/2)), (0, 255, 0), 2)
+            cv2.putText(img, pred['class'], (int(x-w/2), int(y-h/2-10)), 
+                        cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 255, 0), 2)
+        # Competitors (Red)
+        for comp in competitor_boxes:
+            x1, y1, x2, y2 = comp['box']
+            cv2.rectangle(img, (int(x1), int(y1)), (int(x2), int(y2)), (0, 0, 255), 2)
+            cv2.putText(img, f"{comp['class']} {comp['confidence']:.2f}", 
+                        (int(x1), int(y1-10)), cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 0, 255), 2)
+        output_path = "/tmp/combined_output.jpg"
+        cv2.imwrite(output_path, img)
+        return output_path, result_text
+    except Exception as e:
+        return temp_path, f"Error: {str(e)}"
+    finally:
+        if os.path.exists(temp_path):
+            os.remove(temp_path)
+
+# ========== Overlap Detection Function ==========
+def is_overlap(box1, boxes2, threshold=0.3):
+    x1_min, y1_min, x1_max, y1_max = box1
+    for b2 in boxes2:
+        x2, y2, w2, h2 = b2
+        x2_min = x2 - w2/2
+        x2_max = x2 + w2/2
+        y2_min = y2 - h2/2
+        y2_max = y2 + h2/2
+        dx = min(x1_max, x2_max) - max(x1_min, x2_min)
+        dy = min(y1_max, y2_max) - max(y1_min, y2_min)
+        if (dx >= 0) and (dy >= 0):
+            area_overlap = dx * dy
+            area_box1 = (x1_max - x1_min) * (y1_max - y1_min)
+            if area_overlap / area_box1 > threshold:
+                return True
+    return False
+
+# ========== Video Detection Function ==========
+def detect_objects_in_video(video_path):
+    temp_output_path = "/tmp/output_video.mp4"
+    temp_frames_dir = tempfile.mkdtemp()
+    try:
+        video = cv2.VideoCapture(video_path)
+        frame_rate = int(video.get(cv2.CAP_PROP_FPS))
+        frame_width = int(video.get(cv2.CAP_PROP_FRAME_WIDTH))
+        frame_height = int(video.get(cv2.CAP_PROP_FRAME_HEIGHT))
+        frame_size = (frame_width, frame_height)
+        fourcc = cv2.VideoWriter_fourcc(*'mp4v')
+        output_video = cv2.VideoWriter(temp_output_path, fourcc, frame_rate, frame_size)
+        frame_index = 0
+        while True:
+            ret, frame = video.read()
+            if not ret:
+                break
+            frame_path = os.path.join(temp_frames_dir, f"frame_{frame_index}.jpg")
+            cv2.imwrite(frame_path, frame)
+            predictions = yolo_model.predict(frame_path, confidence=60, overlap=80).json()
+            class_count = {}
+            for prediction in predictions['predictions']:
+                class_name = prediction['class']
+                class_count[class_name] = class_count.get(class_name, 0) + 1
+            text_offset = 30
+            y_position = 30
+            for class_name, count in class_count.items():
+                cv2.putText(frame, f"{class_name}: {count}", (10, y_position), 
+                            cv2.FONT_HERSHEY_SIMPLEX, 0.8, (255, 255, 255), 2, cv2.LINE_AA)
+                y_position += text_offset
+            for prediction in predictions['predictions']:
+                x, y, w, h = prediction['x'], prediction['y'], prediction['width'], prediction['height']
+                cv2.rectangle(frame, (int(x - w/2), int(y - h/2)), (int(x + w/2), int(y + h/2)), (0, 255, 0), 2)
+                cv2.putText(frame, prediction['class'], (int(x - w/2), int(y - h/2 - 10)), 
+                            cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 255, 0), 2)
+            output_video.write(frame)
+            frame_index += 1
+        video.release()
+        output_video.release()
+        return temp_output_path
+    except Exception as e:
+        return None, f"An error occurred: {e}"
+
+# ========== Gradio Interface ==========
+with gr.Blocks(theme=gr.themes.Base(primary_hue="teal", secondary_hue="teal", neutral_hue="slate")) as iface:
+    gr.Markdown("""
+    <div style="text-align: center;">
+        <h1>NESTLE - STOCK COUNTING</h1>
+    </div>
+    """)
+    with gr.Row():
+        with gr.Column():
+            input_image = gr.Image(type="pil", label="Input Image")
+            detect_image_button = gr.Button("Detect Image")
+            output_image = gr.Image(label="Detect Object")
+            output_text = gr.Textbox(label="Counting Object")
+            detect_image_button.click(
+                fn=detect_combined,
+                inputs=input_image,
+                outputs=[output_image, output_text]
+            )
+        with gr.Column():
+            input_video = gr.Video(label="Input Video")
+            detect_video_button = gr.Button("Detect Video")
+            output_video = gr.Video(label="Output Video")
+            detect_video_button.click(
+                fn=detect_objects_in_video,
+                inputs=input_video,
+                outputs=[output_video]
+            )
+iface.launch()