update sample 7 inference pipeline

articles/samples/text-classification-wiki.md

@@ -78,7 +78,7 @@ After the model is trained, we would use the **Score Model** and **Evaluate Mode
 For **Feature Hashing** module, it is easy to perform feature engineer on scoring flow as training flow. Use **Feature Hashing** module directly to process the input text data.
 
 For **Extract N-Gram Feature from Text** module, we would connect the **Result Vocabulary output** from the training dataflow to the **Input Vocabulary** on the scoring dataflow, and set the **Vocabulary mode** parameter to **ReadOnly**.
-[![Graph of n-gram score](./media/text-classification-wiki/n-gram.png)](./media/text-classification-wiki/n-gram.png)
+![Graph of n-gram score](./media/text-classification-wiki/n-gram.png)
 
 After finishing the engineering step, **Score Model** could be used to generate predictions for the test dataset by using the trained model. To check the result, select the output port of **Score Model** and then select **Visualize**.
 
@@ -89,11 +89,11 @@ To check the result, select the output port of the **Evaluate Model** and then s
 
 After submitting the training pipeline above successfully, you can register the output of the circled module as dataset.
 
-:::image type="content" source="./media/text-classification-wiki/extract-n-gram-output-voc-register-dataset.png" alt-text="register dataset" border="true":::
+![register dataset of output vocabulary](./media/text-classification-wiki/extract-n-gram-output-voc-register-dataset.png)
 
 Then you can create real-time inference pipeline. After creating inference pipeline, you need to adjust your inference pipeline manually like following:
 
-:::image type="content" source="./media/text-classification-wiki/extract-n-gram-inference-pipeline.png" alt-text="inference pipeline" border="true":::
+![inference pipeline](./media/text-classification-wiki/extract-n-gram-inference-pipeline.png)
 
 Then submit the inference pipeline, and deploy a real-time endpoint.