ibm bluemix - IBM Watson Visual recognition{"code":400,"error":"Cannot execute learning task. : no classifier name given"} -


when try train classifier 2 positive classes , api key (each class contains around 1200 images) in watson visual recognition, returns "no classifier name given" - have provided. code:

     $ curl -x post -f "blank_positive_examples=@c:\users\rahansen\desktop\altmuligt\training\no_ocd\no_ocd.zip" -f "ocd_positive_examples=@c:\users\rahansen\desktop\altmuligt\training\ocd\ocd.zip" -f "name=disease" "https://gateway-a.watsonplatform.net/visual-recognition/api/v3/classifiers?api_key={x}&version=2016-05-20"       {"code":400,"error":"cannot execute learning task.  : no classifier name given"} 

what have done far:

  1. removed special characters in file names thought might problem:
  2. tried give other names classifeir, e.g. "name=ocd"
  3. i tried train on smaller dataset, 40 images in each positive class , works fine. maybe size of dataset problem. however, according watson training guidelines, comply size regulations: https://www.ibm.com/watson/developercloud/doc/visual-recognition/customizing.html btw. have free subscription.

do has recommendations how solve classifier training problem?

this can occur when there's problem processing zip files. try simplifying training files. instance, use 100 examples class, can add more via retraining later. it's train measure performance , add more training samples.


Comments

Popular posts from this blog

php - Vagrant up error - Uncaught Reflection Exception: Class DOMDocument does not exist -

vue.js - Create hooks for automated testing -

.htaccess - ERR_TOO_MANY_REDIRECTS htaccess -