Deep learning configuration on Win 10

1. Install NVIDIA CUDA Toolkit and cuDNN Archive:

https://developer.nvidia.com/cuda-toolkit-archive

https://developer.nvidia.com/rdp/cudnn-archive

https://developer.nvidia.com/cuda-gpus

2. Then setup the Environment (i.e. CUDA package path):

https://medium.com/@soumyadipmajumder/complete-guide-to-tensorflow-gpu-installation-on-windows-10-36e5858640e9

3. Install Anaconda together with Python and Jupyter notebook:

https://www.anaconda.com/distribution/

4. Then open Anaconda Powershell Prompt, install tensor flow, keras, ... with below command:

conda install -c conda-forge tensorflow  #（CPU version）

conda install -c conda-forge tensorflow-gpu  #（GPU version）

conda install -c conda-forge keras

conda install -c conda-forge opencv

conda install -c conda-forge numpy

conda install -c conda-forge scipy

conda install -c conda-forge matplotlib

conda install -c conda-forge pandas

...