Added examples and description

app.py

@@ -6,9 +6,9 @@ import torch
 device = torch.device("mps" if torch.backends.mps.is_available() else "cpu")
 
 te_tokenizer = BartTokenizer.from_pretrained('facebook/bart-large-mnli')
-te_model = BartForSequenceClassification.from_pretrained('facebook/bart-large-mnli')
-qa_tokenizer = T5Tokenizer.from_pretrained("google/flan-t5-small")
-qa_model = T5ForConditionalGeneration.from_pretrained("google/flan-t5-small", device_map="auto")
+te_model = BartForSequenceClassification.from_pretrained('facebook/bart-large-mnli', device_map="auto")
+qa_tokenizer = T5Tokenizer.from_pretrained("google/flan-t5-large")
+qa_model = T5ForConditionalGeneration.from_pretrained("google/flan-t5-large", device_map="auto")
 
 def predict(context, intent, multi_class):
     input_text = "What is the opposite of " + intent + "?"
@@ -20,10 +20,9 @@ def predict(context, intent, multi_class):
     batch = ['The ' + object_output + ' is ' + intent, 'The ' + object_output + ' is ' + opposite_output, 'The ' + object_output + ' is not ' + intent, 'The ' + object_output + ' is not ' + opposite_output]
 
     outputs = []
-    print(intent, opposite_output, object_output)
     for i, hypothesis in enumerate(batch):
-        # input_ids = te_tokenizer.encode(context, hypothesis, return_tensors='pt').to(device)
-        input_ids = te_model(context, hypothesis).to(device)
+        input_ids = te_tokenizer.encode(context, hypothesis, return_tensors='pt').to(device)
+        
         # -> [contradiction, neutral, entailment]
         logits = te_model(input_ids)[0][0]
 
@@ -36,8 +35,9 @@ def predict(context, intent, multi_class):
         
     # calculate the stochastic vector for it being neither the positive or negative class
     perfect_prob = [0, 0]
-    perfect_prob[0] = (outputs[2][0] + outputs[3][1])/2
-    perfect_prob[1] = 1-perfect_prob[2][0]
+    perfect_prob[1] = max(float(outputs[2][0]), float(outputs[3][0]))
+    perfect_prob[0] = 1-perfect_prob[1]
+    # -> [entailment, contradiction] for perfect
     
     # -> [entailment, neutral, contradiction] for positive
     outputs[0] = outputs[0].flip(dims=[0])
@@ -63,7 +63,8 @@ def predict(context, intent, multi_class):
             aggregated[0] = aggregated[0] * perfect_prob[0]
     
     # to exagerate differences
-    aggregated = aggregated.exp() - 1
+    # this way 0 maps to 0
+    aggregated = aggregated.exp()-1
 
     # multiple true classes
     if (multi_class):
@@ -72,14 +73,18 @@ def predict(context, intent, multi_class):
     else:
         aggregated = aggregated.softmax(dim=0)
     aggregated = aggregated.tolist()
-    return {"agree": aggregated[0], "neutral": aggregated[1], "disagree": aggregated[2]}
+    return {"agree": aggregated[0], "neutral": aggregated[1], "disagree": aggregated[2]}, {"agree": outputs[0][0], "neutral": outputs[0][1], "disagree": outputs[0][2]}
+
+examples = [["The pants fit great, even the waist will fit me fine once I'm back to my normal weight, but the bottom is what's large. You can roll up the bottom part of the legs, or the top at the waist band for hanging out at the house, but if you have one nearby, simply have them re-hemmed.", "long"]]
 
 gradio_app = gr.Interface(
     predict,
-    inputs=[gr.Text(label="Sentence"), gr.Text(label="Class"), gr.Checkbox(label="Allow multiple true classes")],
-    outputs=[gr.Label(num_top_classes=3)],
+    examples=examples,
+    inputs=[gr.Text(label="Statement"), gr.Text(label="Class"), gr.Checkbox(label="Allow multiple true classes")],
+    outputs=[gr.Label(num_top_classes=3, label="With Postprocessing"), gr.Label(num_top_classes=3, label="Without Postprocessing")],
     title="Intent Analysis",
-    description="This model predicts whether or not the **_class_** describes the **_object described in the sentence._**"
+    description="This model predicts whether or not the **_class_** describes the **_object described in the sentence_**. <br /> The two outputs shows what TE would predict with and without the postprocessing. An example edge case for normal TE is shown below. <br /> **_It is recommended that you clone the repository to speed up processing time_**.",
+    cache_examples=True
 )
 
 gradio_app.launch(share=True)

gradio_cached_examples/18/log.csv

@@ -0,0 +1,2 @@
+With Postprocessing,Without Postprocessing,flag,username,timestamp
+"{""label"":""agree"",""confidences"":[{""label"":""agree"",""confidence"":0.37631523609161377},{""label"":""neutral"",""confidence"":0.3404143750667572},{""label"":""disagree"",""confidence"":0.28327038884162903}]}","{""label"":""neutral"",""confidences"":[{""label"":""neutral"",""confidence"":0.8370960354804993},{""label"":""disagree"",""confidence"":0.12820996344089508},{""label"":""agree"",""confidence"":0.03469394892454147}]}",,,2024-03-10 20:51:53.608441