Update pages/17_RNN_News.py

pages/17_RNN_News.py

@@ -52,6 +52,7 @@ def load_data():
     vocab = build_vocab_from_iterator(yield_tokens(train_iter), specials=["<unk>", "<pad>"])
     vocab.set_default_index(vocab["<unk>"])
 
+    # Define the text and label processing pipelines globally
     global text_pipeline, label_pipeline
     text_pipeline = lambda x: vocab(tokenizer(x))
     label_pipeline = lambda x: int(x) - 1
@@ -80,7 +81,7 @@ def train_network(net, iterator, optimizer, criterion, epochs):
         for texts, labels in iterator:
             texts, labels = texts.to(device), labels.to(device)
             optimizer.zero_grad()
-            predictions = net(texts).squeeze(1)
+            predictions = net(texts)
             loss = criterion(predictions, labels)
             loss.backward()
             optimizer.step()
@@ -102,7 +103,7 @@ def evaluate_network(net, iterator, criterion):
     with torch.no_grad():
         for texts, labels in iterator:
             texts, labels = texts.to(device), labels.to(device)
-            predictions = net(texts).squeeze(1)
+            predictions = net(texts)
             loss = criterion(predictions, labels)
             epoch_loss += loss.item()
             _, predicted = torch.max(predictions, 1)
@@ -168,8 +169,8 @@ if 'trained_model' in st.session_state and st.sidebar.button('Test Network'):
     # Display results in a table
     st.write('Ground Truth vs Predicted')
     results = pd.DataFrame({
-        'Ground Truth': [LABEL.vocab.itos[label] for label in all_labels],
-        'Predicted': [LABEL.vocab.itos[label] for label in all_predictions]
+        'Ground Truth': all_labels,
+        'Predicted': all_predictions
     })
     st.table(results.head(50))  # Display first 50 results for brevity