Update app.py

app.py

@@ -1,15 +1,15 @@
 import numpy as np
 import torch
 from torch.utils.data import TensorDataset, DataLoader, RandomSampler, SequentialSampler
-from transformers import BertForSequenceClassification,BertTokenizer
+# from transformers import BertForSequenceClassification,BertTokenizer
 
 import gradio as gr
 from typing import Dict
 
 
 num_labels=14
-model = BertForSequenceClassification.from_pretrained("owaiskha9654/Multi-Label-Classification-of-PubMed-Articles", num_labels=num_labels)
-tokenizer = BertTokenizer.from_pretrained('owaiskha9654/Multi-Label-Classification-of-PubMed-Articles', do_lower_case=True) 
+#model = BertForSequenceClassification.from_pretrained("owaiskha9654/Multi-Label-Classification-of-PubMed-Articles", num_labels=num_labels)
+#tokenizer = BertTokenizer.from_pretrained('owaiskha9654/Multi-Label-Classification-of-PubMed-Articles', do_lower_case=True) 
 
 
 def Multi_Label_Classification_of_Pubmed_Articles(model_input: str) -> Dict[str, float]:
@@ -23,10 +23,10 @@ def Multi_Label_Classification_of_Pubmed_Articles(model_input: str) -> Dict[str,
     test_attention_masks = test_encodings['attention_mask']
         # Make tensors out of data
     test_inputs = torch.tensor(test_input_ids)
-    test_labels = torch.tensor(test_labels)
+    #test_labels = torch.tensor(test_labels)
     test_masks = torch.tensor(test_attention_masks)
     # Create test dataloader
-    test_data = TensorDataset(test_inputs, test_masks, test_labels,)# test_token_types)
+    test_data = TensorDataset(test_inputs, test_masks, )#test_labels, test_token_types)
     test_sampler = SequentialSampler(test_data)
     test_dataloader = DataLoader(test_data, sampler=test_sampler, batch_size=batch_size)
     
@@ -34,7 +34,7 @@ def Multi_Label_Classification_of_Pubmed_Articles(model_input: str) -> Dict[str,
     model.eval()
     
     #track variables
-    logit_preds,true_labels,pred_labels,tokenized_texts = [],[],[],[]
+    logit_preds,pred_labels,tokenized_texts = [],[],[]
     
     # Predict
     for i, batch in enumerate(test_dataloader):
@@ -53,15 +53,15 @@ def Multi_Label_Classification_of_Pubmed_Articles(model_input: str) -> Dict[str,
     
         tokenized_texts.append(b_input_ids)
         logit_preds.append(b_logit_pred)
-        true_labels.append(b_labels)
+        #true_labels.append(b_labels)
         pred_labels.append(pred_label)
     
     # Flatten outputs
     tokenized_texts = [item for sublist in tokenized_texts for item in sublist]
     pred_labels = [item for sublist in pred_labels for item in sublist]
-    true_labels = [item for sublist in true_labels for item in sublist]
+#     true_labels = [item for sublist in true_labels for item in sublist]
     # Converting flattened binary values to boolean values
-    true_bools = [tl==1 for tl in true_labels]
+#     true_bools = [tl==1 for tl in true_labels]
     
 
     #prediction = model.predict(tokenized)[0]
@@ -69,7 +69,7 @@ def Multi_Label_Classification_of_Pubmed_Articles(model_input: str) -> Dict[str,
     #    "negative": float(prediction[0]),
     #    "positive": float(prediction[1])
     #}
-    return true_bools
+    return pred_labels
 
 
 model_input = gr.Textbox("Input text here", show_label=False)
@@ -127,4 +127,4 @@ app = gr.Interface(
     analytics_enabled=False,
 )
 
-app.launch(enable_queue=True)
+app.launch(inline=True,share=True)