Build Custom Models For Image Classification on Einstein Platform

Prerequisites

Set up your Account-- Navigate to Einstein Platform Service Account .
Find your key file-- If you have already created an account, locate the einstein_platform.pem    

file that you have downloaded.
Inastall Curl-- Download it from https://curl.haxx.se/download.htm

-->The Einstein Platform Service APIs use OAuth 2.0 JWT bearer token flow for authorization. Use the Token Page to upload your key file and generate a JWT token.

Step 1: Create Data Set
Use the following command

curl -X POST -H "Authorization: Bearer <TOKEN>" -H "Cache-Control: no-cache" -H "Content-Type: multipart/form-data" -F "type=image" -F "path=http://metamind.io/images/mountainvsbeach.zip" https://api.einstein.ai/v2/vision/datasets/upload/sync

-->Replace <TOKEN> with the token which you got.

Then you will get Json code like this
{
   "id":1009061,
   "name":"mountainvsbeach",
   "createdAt":"2017-08-10T13:49:26.000+0000",
   "updatedAt":"2017-08-10T13:49:26.000+0000",
   "labelSummary":{
      "labels":[
         {
            "id":90572,
            "datasetId":1009061,
            "name":"Mountains",
            "numExamples":50
         },
         {
            "id":90573,
            "datasetId":1009061,
            "name":"Beaches",
            "numExamples":49
         }
      ]
   },
   "totalExamples":99,
   "totalLabels":2,
   "available":true,
   "statusMsg":"SUCCEEDED",
   "type":"image",
   "object":"dataset"

Step 2:Train The DataSet

Use the following command

curl -X POST -H "Authorization: Bearer <TOKEN>" -H "Cache-Control: no-cache" -H "Content-Type: multipart/form-data" -F "name=Beach and Mountain Model" -F "datasetId=<DATASET_ID>" https://api.einstein.ai/v2/vision/train

-->Replace <Token> and <Data Set Id>

Then you will get Json code like this

{  

   "datasetId":1009061,

   "datasetVersionId":0,

   "name":"Beach and Mountain Model",

   "status":"QUEUED",

   "progress":0,

   "createdAt":"2017-08-10T13:52:32.000+0000",

   "updatedAt":"2017-08-10T13:52:32.000+0000",

   "learningRate":0.0,

   "epochs":0,

   "queuePosition":3,

   "object":"training",

   "modelId":"XLCYWVMAW4H25DOXA5E7R65E6I",

   "trainParams":null,

   "trainStats":null,

   "modelType":"image"

Step 3:Classify an Image

For this example, i have referenced this picture by the file Url

Use the following command

curl -X POST -H "Authorization: Bearer <TOKEN>" -H "Cache-Control: no-cache" -H "Content-Type: multipart/form-data" -F "sampleLocation=http://einstein.ai/images/546212389.jpg" -F "modelId=<YOUR_MODEL_ID>" https://api.einstein.ai/v2/vision/predict

-->Replace <Token> and <Model Id>

Json Code:

{  

   "probabilities":[  

      {  

         "label":"Mountains",

         "probability":0.99539346

      },

      {  

         "label":"Beaches",

         "probability":0.0046065715

      }

   ],

   "object":"predictresponse"

}