关于我
关于博客
关于工作
2021 - 至今- 计算机视觉算法工程师：浙江由由科技有限公司
- 负责边缘端图像搜索引擎的开发和部署，包括零食/蔬菜/水果/干货等非标品识别以及在NPU开发板上的模型部署
2020 - 2021- 机器视觉和图像处理算法开发工程师：江苏万维艾斯网络智能产业创新中心
- 负责多个项目开发，包括混凝土视频质量分析（视频理解 + 后端开发）、试卷信息解析（目标检测 + OCR）、2亿大小图像细胞计数（图像处理 + 目标分类）等等
关于开源
- Recognition
- Image Classification
- ZJCV/ZCls2: More Faster Object Classification Training Framework
- ZJCV/ZCls: Object Classification Training/Inferring Framework
- Fine-grained Classification
- ZJCV/DCL: [CVPR 2019] Destruction and Construction Learning for Fine-grained Image Recognition
- Video Classification
- ZJCV/X3D: [CVPR 2020] X3D: Expanding Architectures for Efficient Video Recognition
- ZJCV/TSM: [ICCV 2019] TSM: Temporal Shift Module for Efficient Video Understanding
- Face Recognition
- ZJCV/facenet: [CVPR 2015] FaceNet: A Unified Embedding for Face Recognition and Clustering
- Image Retrieval
- Train
- Distillating
- Pruning
- ZJCV/NetworkSlimming: [ICCV 2017] Learning Efficient Convolutional Networks through Network Slimming
- ZJCV/SSL: [NIPS 2016] Learning Structured Sparsity in Deep Neural Networks
- Deploy
- zjykzj/onnx: pytorch -> onnx -> onnxruntime/openvino/mnn
- Tool
- zjykzj/pnno: dataset or annotation file format conversion
- zjykzj/zlogo: A tool using logo.svg and svglib to generate custom logo
- Other
- ZJCV/RotNet: Image rotation correction based on DeepLearning
- zjykzj/MPDataset: Custom Iterable Dataset Class for Large-Scale Data Loading
年度总结