This project was designed for learning tensorflow by just one example for beginners. More specifically, it's aimmed to achive the goal as follow:
- Understanding the key concepts of addressing compuation in tensorflow
- Implementing your machine learning, especially deep learning, model using this concepts.
- Learn to debug the problem and optimize the program under the tensorflow framework.
This project implemented a face recongnition model, actually face verification model. The model was trained on the CASIA-WEBFACE and tested on the LFW.
First the key concepts of tensorflow programming and components that constitude the model was introduced. Then a basic model taking advantages of both was implemented. Finally, the optimization was made to improve the basic model as far as both training speed and test accuracy were concerned.
- The key concepts
- Graph
- Session
- Tensor
- Operation
- Components
- Variables
- Name and scope
- Optimizer and trainer
- Convolution network
- Save and restore
- tensorboard
- custom layer
- Work togother
- Modularization
- Project template
- Code togother
- Optimization
- speed:
- timeline
- data management
- multi-gpu
- accuracy
- resnet
- insight
- speed: