Update app.py

app.py

@@ -35,10 +35,10 @@ class BertClassifier(nn.Module):
 @st.cache(suppress_st_warning=True)
 def build_model():
     model = BertClassifier(n_classes=len(labels))
-    st.markdown("Model created")
+    # st.markdown("Model created")
     model.load_state_dict(torch.load('model_weights_1.pt', map_location=torch.device('cpu')))
     model.eval()
-    st.markdown("Model weights loaded")
+    #st.markdown("Model weights loaded")
     return model
     
 def inference(txt):
@@ -87,11 +87,21 @@ def infer_and_display_result(txt):
 
 
 st.title('Big-data cloud application for actionable scientific article topic analytics using in-memory computing and stuff.')    
+st.subtitle('test application for ML-2 class, YSDA-2022' )
 image = Image.open('dilbert_big_data.jpg')
 st.image(image)
 st.write('test application for ML-2 class, YSDA-2022' )
-# st.markdown("<img width=200px src='https://i.pinimg.com/736x/11/33/19/113319f0ffe91f4bb0f468914b9916da.jpg'>", unsafe_allow_html=True)
-# st.markdown("###Predict topic by abstract.")
+
+comment = """
+this application estimates probability that certain article belongs to one of the following classes based on Arxiv Category Taxonomy:
+
+- 'cs.NE': 'Neural and Evolutionary Computing',
+- 'cs.CL': 'Computation and Language',
+- 'cs.AI': 'Artificial Intelligence',
+- 'stat.ML': 'Machine Learning (stat)',
+- 'cs.CV': 'Computer Vision',
+- 'cs.LG': 'Machine Learning' """.replace("'", '')
+st.markdown()
 
 text1 = st.text_area("ENTER ARTICLE TITLE HERE")
 text2 = st.text_area("ENTER ARTICLE ABSTRACT HERE")
@@ -102,7 +112,7 @@ model = build_model()
 action = st.button('click here to infer topic')  
 if action:
     if len(text) < 3:
-        st.write("this text is too short or empty. try again")
+        st.subtitle("this text is too short or empty. try again")
     else:        
         infer_and_display_result(text)