update README.md about sample of sklearn for testing the SKLearn Serv… (

kubeflow#1184)
magdalenakuhn17 · Nov 6, 2020 · 20256a7 · 20256a7
1 parent 82ec9ce
commit 20256a7
Showing 1 changed file with 3 additions and 2 deletions.
diff --git a/docs/samples/sklearn/README.md b/docs/samples/sklearn/README.md
@@ -16,7 +16,8 @@ dump(clf, 'model.joblib')
 Then, we can install and run the [SKLearn Server](../../../python/sklearnserver) using the generated model and test for prediction. Models can be on local filesystem, S3 compatible object storage, Azure Blob Storage, or Google Cloud Storage.
 
 ```shell
-python -m sklearnserver --model_dir model.joblib --model_name svm
+# we should indicate the directory containing the model file (model.joblib) by --model_dir
+python -m sklearnserver --model_dir ./  --model_name svm
 ```
 
 We can also use the inbuilt sklearn support for sample datasets and do some simple predictions
@@ -110,4 +111,4 @@ spec:
       sklearn:
         storageUri: "gs://kfserving-samples/models/sklearn/iris"
         runtimeVersion: X.X.X
-```
+```