I am a senior Artificial Intelligence developer specializing in computer vision. I bring over 6 years of experience in the AI programming field, encompassing machine learning, deep learning, and data science. Throughout my career, I have successfully delivered numerous projects, showcasing expertise in the following areas:
1. Object detection
2. Image segmentation (semantic and instance)
3. OCR
4. Stable Diffusion and Generative AI
5. 3D Rendering and Augmented Reality
6. 3D image reconstruction
7. Key-point detection
8. Pose estimation
9. Image classification
10. Face and person re-identification
11. Face verification
12. GAN (Generative Adversarial Networks)
13. Depth estimation
14. Object tracking and counting
15. Action recognition
16. GUI development
17. Data mining and analysis
18. Time series forecasting
19. Text Mining and Classification
I have hands-on experience with renowned models such as YOLOV5, YOLOV6, YOLOV7, YOLOV8, YOLO-NAS, Segment Anything Model (SAM), Mask-RCNN, DeepLabV3, U-Net, EfficientNet, FaceNet, Arcface, DeepSort, ByteTrack, MediaPipe, 3DGAN, Pix2Pix, DCGAN, CycleGAN, StyleGANV2, Stable Diffusion, Tesseract, PaddleOCR, etc. My primary programming language is Python, and I am an expert in working with TensorFlow, Keras, PyTorch, OpenCV, NumPy, Matplotlib, SciPy, Pandas, Scikit-learn, Flask, PyQt, and Tkinter. Additionally, I am proficient in Matlab, C, C++, and MySQL.