deep learning

 tensorflow cuDNN cuda  Keras jupyter Miniconda

Anaconda Jupyter NotebookMXNet PyTorch TensorFlow Theano Caffe  Keras

pyimagesearch.minigooglenet  

MiniGoogLeNet  sklearn.preprocessing  LabelBinarizer  

keras ImageDataGenerator LearningRateScheduler    multi_gpu_model  

matplotlib

pyplot tensorflow numpy argparse

 https://learnopencv.com/installing-deep-learning-frameworks-on-ubuntu-with-cuda-support/

 https://www.pyimagesearch.com/2017/10/30/how-to-multi-gpu-training-with-keras-python-and-deep-learning/

 Vulkan

https://kfocus.org/wf/deep.html 

https://docs.microsoft.com/zh-tw/visualstudio/ai/installation?view=vs-2017

 NVIDIA GPU 驅動程式

CUDA 是 NVIDIA 首創的平行運算平台和程式設計模型。
cuDNN (CUDA 深度類神經網路程式庫)


Python 一直是深度學習應用程式的主要程式設計語言。

NumPy 和 SciPy

Microsoft Cognitive Toolkit (CNTK)

Microsoft Cognitive Toolkit 是整合深度學習工具組，

TensorFlow (英文) 是使用資料流程圖表進行數值計算的開放原始碼軟體程式庫。

Caffe2 是輕量型、模組化且可調整規模的深度學習架構。


Apache MXNet 是專為效率和彈性所設計的深度學習架構。

Keras (英文) 是以 Python 撰寫，能夠在 CNTK、TensorFlow 或 Theano 上執行的高階類神經網路 API。

Theano 是 Python 程式庫，可讓您有效率地定義、最佳化及評估涉及多維陣列的數學運算式。

PyTorch  Anaconda University of California

Chainer 是以彈性為目標的 Python 深度學習架構。

https://data-flair.training/blogs/deep-learning-with-python-libraries/
https://www.kite.com/blog/python/data-science-packages-python/

https://www.tertiarycourses.com.my/python-programming-courses-in-malaysia.html

https://www.thegioimaychu.vn/blog/tong-hop/nvidia-deep-learning-va-framework-hop-nhat-danh-cho-nha-phat-trien-p5375/

https://analyticsindiamag.com/top-tensorflow-based-projects-that-ml-beginners-should-try/

Top TensorFlow-Based Projects That ML Beginners Should Try
    Handwritten Text Recognition. ...
    Self-Driving MarioKart. ...
    Skyfall: Gesture-controlled Web Game. ...
    Sudoku. ...
    Plant Disease Detection Robot. ...
    Vehicle Detection, Tracking, and Counting. ...
    LSTM Human Activity Recognition. ...
    DeepSpeech.

https://www.hackster.io/tensorflow/projects

https://blogs.embarcadero.com/machine-learning-5-ways-to-use-ml-in-your-windows-apps/

https://github.com/pyscripter/python4delphi

https://blogs.embarcadero.com/?s=Machine+Learning