stockmarket pattern detection yolov8

Introduction

The YOLOv8s Stock Market Pattern Detection model is an object detection framework developed to identify chart patterns in real-time stock market trading video data. It assists traders and investors by automating pattern analysis for timely decision-making.

Architecture

The YOLOv8s model is based on the YOLO (You Only Look Once) framework, designed for real-time detection of crucial stock market patterns. It integrates advanced bounding box techniques and pattern-specific feature extraction for identifying patterns like 'Head and shoulders bottom', 'Head and shoulders top', 'M_Head', 'StockLine', 'Triangle', and 'W_Bottom'.

Training

The model was trained on a custom dataset comprising 9000 annotated images for training and 800 for validation. It was fine-tuned using a Jupyter Notebook environment and optimized for minimal detection loss over multiple epochs. Metrics include a mean Average Precision (mAP) score of 0.932 for all patterns. Training was conducted using an NVIDIA GeForce RTX 3080 card.

Guide: Running Locally

1. Install Dependencies

   • Use the following command to install the required packages:

     pip install ultralyticsplus==0.0.28 ultralytics==8.0.43
     

2. Load Model and Video

   • Load the model and set parameters for confidence and IoU thresholds.
   • Open and process video files using OpenCV.

3. Perform Real-Time Detection

   • Execute YOLOv8 inference on video frames and visualize results.

4. Cloud GPUs

   • For optimized performance, consider using cloud GPU services such as Google Cloud or AWS.

from ultralyticsplus import YOLO, render_result
import cv2

# Load model
model = YOLO('foduucom/stockmarket-pattern-detection-yolov8')

# Set parameters
model.overrides['conf'] = 0.25
model.overrides['iou'] = 0.45

# Initialize video capture
video_path = "path/to/your/video/file.mp4"
cap = cv2.VideoCapture(video_path)

# Process video frames
while cap.isOpened():
    success, frame = cap.read()
    if success:
        results = model(frame)
        annotated_frame = results[0].plot()
        cv2.imshow("YOLOv8 Inference", annotated_frame)
        if cv2.waitKey(1) & 0xFF == ord("q"):
            break
    else:
        break

cap.release()
cv2.destroyAllWindows()

License

For inquiries regarding licensing and collaboration, please contact FODUU AI at info@foduu.com.