leleamol commented on a change in pull request #13294: [MXNET-1083] Add the example to demonstrate the inference workflow using C++ API URL: https://github.com/apache/incubator-mxnet/pull/13294#discussion_r239274813
########## File path: cpp-package/example/inference/README.md ########## @@ -0,0 +1,35 @@ +# MXNet C++ Package Inference Workflow Examples + +## Building C++ Inference examples + +The examples in this folder demonstrate the **inference** workflow. +To build examples use following commands: + +- Release: **make all** +- Debug: **make debug all** + + +## Examples demonstrating inference workflow + +This directory contains following examples. In order to run the examples, ensure that the path to the MXNet shared library is added to the OS specific environment variable viz. **LD\_LIBRARY\_PATH** for Linux, Mac and Ubuntu OS and **PATH** for Windows OS. + +### [inception_inference.cpp](<https://github.com/apache/incubator-mxnet/blob/master/cpp-package/example/inference/inception_inference.cpp>) + +This example demonstrates image classification workflow with pre-trained models using MXNet C++ API. The command line parameters the example can accept are as shown below: + + ``` + ./inception_inference --help + Usage: + inception_inference --symbol <model symbol file in json format> --params <model params file> --image <path to the image used for prediction --synset file containing labels for prediction [--input_shape <dimensions of input image e.g "3 224 224"][--mean file containing mean image for normalizing the input image [--gpu] Specify this option if workflow needs to be run in gpu context Review comment: Re-organized the comments. The mean image file contains the mean values in image format. The file is also used in other feature extract example. I have added the code to use the default mean values if user does not specify this file. ---------------------------------------------------------------- This is an automated message from the Apache Git Service. To respond to the message, please log on GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: [email protected] With regards, Apache Git Services
