Update README.md
Browse files
README.md
CHANGED
|
@@ -64,6 +64,12 @@ model = SetFitModel.from_pretrained("automatedMotiveCoder/setfit")
|
|
| 64 |
preds = model("I loved the spiderman movie!")
|
| 65 |
```
|
| 66 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 67 |
<!--
|
| 68 |
### Downstream Use
|
| 69 |
|
|
|
|
| 64 |
preds = model("I loved the spiderman movie!")
|
| 65 |
```
|
| 66 |
|
| 67 |
+
When using the `predict_proba()` method, the predicted probabilities for
|
| 68 |
+
all classes might not sum to 1. This is because the model loaded uses a
|
| 69 |
+
One-vs-Rest classification approach, which means the model treats each
|
| 70 |
+
class as a binary classification problem. As a result, the probabilities
|
| 71 |
+
are independent, and their sum may exceed or fall below 1.
|
| 72 |
+
|
| 73 |
<!--
|
| 74 |
### Downstream Use
|
| 75 |
|