- Model Optimization
- Model Serving
- Language Model
- Object Detection & Object Tracking
- Pose Estimation
- 머신러닝/딥러닝을 공부하고 있습니다.
- Computer Vision, NLP, Speech, Multi-modal 등 다양한 분야를 수행합니다.
- 서비스와 연구 경험으로 유연한 업무가 가능합니다.
- Programming Language: Python, C/C++
- Machine Learning: Computer Vision, NLP, Speech, Multi-modal
- Framework/Library: Pytorch, TensorFlow, Flask, Django, React
- Tools: Git/Github, Vim
- Environment: Linux, Window, Mac OS, AWS
- ETC: Graphic Design, Photoshop, Illutrator, InDesign, Premlere, Blender
- Implement Transformer with PyTorch, Multi30, Torchtext
- Intelligent Korean Sentence Construction with Speech-to-text, Text Summarization
- De-identify Personal Data in Everyday Life with Object Detection, OCR, Token Classification
- Cow's Standing Behavior Object Detection System Using YOLOv7
- Implement Style Transfer with Pytorch, TensorFlow