Update README.md

README.md

@@ -63,7 +63,8 @@ labels = ['admiration', 'amusement', 'anger', 'annoyance', 'approval', 'caring',
 
 tokenizer = Tokenizer.from_pretrained("SamLowe/roberta-base-go_emotions")
 
-# optional - set pad to only pad to longest in batch, not a fixed length. Without this, the model will run slower, esp for shorter input strings.
+# Optional - set pad to only pad to longest in batch, not a fixed length.
+# (without this, the model will run slower, esp for shorter input strings)
 params = {**tokenizer.padding, "length": None}
 tokenizer.enable_padding(**params)
 
@@ -87,8 +88,11 @@ def sigmoid(_outputs):
   return 1.0 / (1.0 + np.exp(-_outputs))
 
 logits = model.run(output_names=output_names, input_feed=input_feed_dict)[0]
+# produces a numpy array, one row per input item, one col per label
 
-model_outputs = sigmoid(logits)  # produces a numpy array, one row per input item, one col per label
+# Post-processing. Gets the scores per label in range.
+# Auto done by Transformers' pipeline, but we must di it manually with ORT.
+model_outputs = sigmoid(logits) 
 
 # for example, just to show the top result per input item
 for probas in model_outputs: