Correct prediction probabilities

erssebaggala · web-flow · commit d29b93f092fc · 2018-07-14T00:05:39.000+03:00
Correct the prediction probabilities for Iris setosa and Iris virginica 
to match the prediction values in the image
diff --git a/samples/core/tutorials/eager/custom_training_walkthrough.ipynb b/samples/core/tutorials/eager/custom_training_walkthrough.ipynb
@@ -573,7 +573,7 @@
         "  </td></tr>\n",
         "</table>\n",
         "\n",
-        "When the model from Figure 2 is trained and fed an unlabeled example, it yields three predictions: the likelihood that this flower is the given Iris species. This prediction is called *[inference](https://developers.google.com/machine-learning/crash-course/glossary#inference)*. For this example, the sum of the output predictions is 1.0. In Figure 2, this prediction breaks down as: `0.03` for *Iris setosa*, `0.95` for *Iris versicolor*, and `0.02` for *Iris virginica*. This means that the model predicts—with 95% probability—that an unlabeled example flower is an *Iris versicolor*."
+        "When the model from Figure 2 is trained and fed an unlabeled example, it yields three predictions: the likelihood that this flower is the given Iris species. This prediction is called *[inference](https://developers.google.com/machine-learning/crash-course/glossary#inference)*. For this example, the sum of the output predictions is 1.0. In Figure 2, this prediction breaks down as: `0.02` for *Iris setosa*, `0.95` for *Iris versicolor*, and `0.03` for *Iris virginica*. This means that the model predicts—with 95% probability—that an unlabeled example flower is an *Iris versicolor*."
       ]
     },
     {
@@ -1225,4 +1225,4 @@
       "outputs": []
     }
   ]
-}
+}

Original file line number	Diff line number	Diff line change
`@@ -573,7 +573,7 @@`
`573`	`573`	`" </td></tr>\n",`
`574`	`574`	`"</table>\n",`
`575`	`575`	`"\n",`
`576`		- "When the model from Figure 2 is trained and fed an unlabeled example, it yields three predictions: the likelihood that this flower is the given Iris species. This prediction is called [inference](https://developers.google.com/machine-learning/crash-course/glossary#inference). For this example, the sum of the output predictions is 1.0. In Figure 2, this prediction breaks down as: `0.03` for Iris setosa, `0.95` for Iris versicolor, and `0.02` for Iris virginica. This means that the model predicts—with 95% probability—that an unlabeled example flower is an Iris versicolor."
	`576`	+ "When the model from Figure 2 is trained and fed an unlabeled example, it yields three predictions: the likelihood that this flower is the given Iris species. This prediction is called [inference](https://developers.google.com/machine-learning/crash-course/glossary#inference). For this example, the sum of the output predictions is 1.0. In Figure 2, this prediction breaks down as: `0.02` for Iris setosa, `0.95` for Iris versicolor, and `0.03` for Iris virginica. This means that the model predicts—with 95% probability—that an unlabeled example flower is an Iris versicolor."
`577`	`577`	`]`
`578`	`578`	`},`
`579`	`579`	`{`
`@@ -1225,4 +1225,4 @@`
`1225`	`1225`	`"outputs": []`
`1226`	`1226`	`}`
`1227`	`1227`	`]`
`1228`		`-}`
	`1228`	`+}`