1,CNN:目前最合适的卷积层数:20~25层
http://vlg.cs.dartmouth.edu/c3d/
numpy pandas matplotlib scipy sympy pylab
http://ufldl.stanford.edu/wiki/index.php/UFLDL_Tutorial
scikit-learn
http://lamda.nju.edu.cn/weixs/project/CNNTricks/CNNTricks.html
https://www.zhihu.com/question/38102762
http://vis-www.cs.umass.edu/lfw/results.html
模型准确性
http://kyonhuang.top/Andrew-Ng-Deep-Learning-notes/
notes
https://scipy.github.io/old-wiki/pages/PyLab
https://docs.scipy.org/doc/numpy/user/quickstart.html
tensorflow scipy
https://blog.csdn.net/qq_22749699/article/details/78526147
face net
https://blog.csdn.net/u014380165/article/details/78906898
MTCNN算法
http://people.duke.edu/~ccc14/pcfb/analysis.html
Practical Computing for Biologists
- Maths:
- Linear algebra
- Probability and statistics
- Numerical optimization
- Calculus
- Image processing: or generally digital signal processing.
- Digital filters: Gaussian blur
- Image transformations: rotations, translations, scaling and many more.
- Scale space theorem for natural stimuli processing. Basically implemented using image pyramids, the so called multi-scale approach.
- Machine learning (ML): A very important area that is changing many AI sub-fields. You need to know about:
- Convolutional neural networks (CNN).
- Fully connected neural networks.
- Support vector machines (SVM)
- Recurrent neural networks (RNN) such as long-short-term-memory (LSTM) or gated recurrent unit (GRU) networks.
- Generative adversarial networks (GAN): For many tasks like image-to-image translation. Image enhancements, art style transfer and so on.
- Autoencoders: For noise reduction and image compression.
- Programming:
- C/C++: You can use OpenCV for CV implementations or build your own from scratch using C/C++.
- Java: OpenCV is also available in Java.
- Python: You can again use OpenCV in Python language. Probably this is a better choice as Python is a very high-level easy to learn language.