piyushghai commented on a change in pull request #13237: [MXNET-1182] Predictor example URL: https://github.com/apache/incubator-mxnet/pull/13237#discussion_r233196256
########## File path: scala-package/examples/src/main/java/org/apache/mxnetexamples/javaapi/infer/predictor/README.md ########## @@ -0,0 +1,62 @@ +# Image Classification using Java Predictor + +In this example, you will learn how to use Java Inference API to +build and run pre-trained Resnet 18 model. + +## Contents + +1. [Prerequisites](#prerequisites) +2. [Download artifacts](#download-artifacts) +3. [Setup datapath and parameters](#setup-datapath-and-parameters) +4. [Run the image inference example](#run-the-image-inference-example) + +## Prerequisites + +1. MXNet +2. MXNet Scala Package +3. [IntelliJ IDE (or alternative IDE) project setup](https://github.com/apache/incubator-mxnet/blob/master/docs/tutorials/java/mxnet_java_on_intellij.md) with the MXNet Java Package +4. wget + +## Download Artifacts + +For this tutorial, you can get the model and sample input image by running following bash file. This script will use `wget` to download these artifacts from AWS S3. + +From the `scala-package/examples/scripts/infer/imageclassifier/` folder run: + +```bash +./get_resnet_18_data.sh +``` + +**Note**: You may need to run `chmod +x get_resnet_18_data.sh` before running this script. + +### Setup Datapath and Parameters + +The available arguments are as follows: + +| Argument | Comments | +| ----------------------------- | ---------------------------------------- | +| `model-dir` | Folder path with prefix to the model (including json, params, and any synset file). | +| `input-image` | The image to run inference on. | + +## Run the image inference example + +After the previous steps, you should be able to run the code using the following script that will pass all of the required parameters to the Infer API. Review comment: Change ```InferAPI``` to ```Predictor API``` ---------------------------------------------------------------- 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
