Mxnet Combat deep Learning on Windows: Neural Net

Premise:

• Assume that you have installed mxnet and Python language packs on Windows.
• Assuming the Mxnet installation directory is D:\mxnet
• Assuming the wget is installed.

You can refer to this article

Open a command prompt for Windows:

Execute the following command to enter the directory

D:CD D:\mxnet\example\neural-style

Modify the download.sh command, modify it to the following, and save the execution to download the relevant data file.

#!/bin/bash# because of some kind of wall reason, may need to set up the proxy, removes the # can #set Http_proxy=http://127.0.0.1:1080#set https_proxy=https:// 127.0.0.1:1080mkdir-p MODELCD model# Add--no-check-certificate to avoid error without certificate wget--no-check-certificate https://github.com /dmlc/web-data/raw/master/mxnet/neural-style/model/vgg19.paramscd. Mkdir-p Inputcd inputwget--no-check-certificate https://github.com/dmlc/web-data/raw/master/mxnet/neural-style/ Input/img_4343.jpgwget--no-check-certificate https://github.com/dmlc/web-data/raw/master/mxnet/neural-style/ INPUT/STARRY_NIGHT.JPGCD. Mkdir-p output

To the website, download the compiled NumPy, scipy, and scikit-image three WHL files

Execute the following command to install the package

Pip Install Numpy-1.11.0+mkl-cp35-cp35m-win_amd64.whlpip install Scipy-0.17.0-cp35-none-win_amd64.whlpip Install Scikit_image-0.12.3-cp35-cp35m-win_amd64.whl

Perform the following command to train

Python run.py--content-image input/img_4343.jpg--style-image input/starry_night.jpg

　　

　　

　　

Mxnet Combat deep Learning on Windows: Neural Net