Update app.py

app.py

@@ -7,28 +7,8 @@ from transformers import AutoTokenizer, BertModel, BertForSequenceClassification
 from sklearn import metrics
 import streamlit as st
 
-# Have data for BertClass ready for our tuned model.
-class BertClass(torch.nn.Module):
-  def __init__(self):
-    super(BertClass, self).__init__()
-    self.l1 = BertModel.from_pretrained(model_path)
-    self.dropout = torch.nn.Dropout(HEAD_DROP_OUT)
-    self.classifier = torch.nn.Linear(768, 6)
-    
-  def forward(self, input_ids, attention_mask, token_type_ids):
-    output_1 = self.l1(input_ids=input_ids, attention_mask=attention_mask, token_type_ids=token_type_ids)
-    hidden_state = output_1[0]
-    pooler = hidden_state[:, 0]
-    pooler = self.dropout(pooler)
-    output = self.classifier(pooler)
-    return output
-
-# Define models to be used
+# Define Torch device. Enable CUDA if available.
 device = "cuda" if torch.cuda.is_available() else "cpu"
-bert_path = "bert-base-uncased"
-bert_tokenizer = AutoTokenizer.from_pretrained(bert_path)
-bert_model = BertForSequenceClassification.from_pretrained(bert_path, num_labels=6)
-tuned_model = model = torch.load("pytorch_bert_toxic.bin", map_location=torch.device(device))
 
 # Read and format data.
 tweets_raw = pd.read_csv("test.csv", nrows=20)
@@ -42,12 +22,30 @@ tweet_df["labels"] = label_vector
 
 # User selects model for front-end.
 option = st.selectbox("Select a text analysis model:", ("BERT", "Fine-tuned BERT"))
+
+bert_path = "bert-base-uncased"
 if option == "BERT":
-    tokenizer = bert_tokenizer
-    model = bert_model
+    tokenizer = AutoTokenizer.from_pretrained(bert_path)
+    model = BertForSequenceClassification.from_pretrained(bert_path, num_labels=6)
 else:
-    tokenizer = bert_tokenizer
-    model = tuned_model
+    tokenizer = AutoTokenizer.from_pretrained(bert_path)
+    model = torch.load("pytorch_bert_toxic.bin", map_location=torch.device(device))
+
+# Have data for BertClass ready for our tuned model.
+class BertClass(torch.nn.Module):
+  def __init__(self):
+    super(BertClass, self).__init__()
+    self.l1 = BertModel.from_pretrained(model_path)
+    self.dropout = torch.nn.Dropout(HEAD_DROP_OUT)
+    self.classifier = torch.nn.Linear(768, 6)
+    
+  def forward(self, input_ids, attention_mask, token_type_ids):
+    output_1 = self.l1(input_ids=input_ids, attention_mask=attention_mask, token_type_ids=token_type_ids)
+    hidden_state = output_1[0]
+    pooler = hidden_state[:, 0]
+    pooler = self.dropout(pooler)
+    output = self.classifier(pooler)
+    return output
 
 # Dataset for loading tables into DataLoader
 class ToxicityDataset(Dataset):