Updated

.ipynb_checkpoints/app-checkpoint.py

@@ -584,6 +584,20 @@ with gr.Blocks(css="""
         else:
             return gr.update(visible=False), gr.update(visible=True)
 
+    def predict_utils(sequence):
+        input_ids = tokenizer(" ".join(sequence), return_tensors="pt").input_ids.to(device)
+        with torch.no_grad():
+            outputs = model(input_ids).logits.detach().cpu().numpy().squeeze()
+    
+        # Calculate scores and normalize them
+        raw_scores = expit(outputs[:, 1] - outputs[:, 0])
+        normalized_scores = normalize_scores(raw_scores)
+    
+        return {
+        "raw_scores": raw_scores.tolist(),
+        "normalized_scores": normalized_scores.tolist()
+    }
+        
     mode.change(
         toggle_mode,
         inputs=[mode],
@@ -622,16 +636,6 @@ with gr.Blocks(css="""
         outputs=[predictions_output, molecule_output, download_output]
     )
 
-    def predict_utils(sequence):
-        input_ids = tokenizer(" ".join(sequence), return_tensors="pt").input_ids.to(device)
-        with torch.no_grad():
-            outputs = model(input_ids).logits.detach().cpu().numpy().squeeze()
     
-        # Calculate scores and normalize them
-        raw_scores = expit(outputs[:, 1] - outputs[:, 0])
-        normalized_scores = normalize_scores(raw_scores)
-    
-        return raw_scores,normalized_scores
-
+demo.load(predict_utils, inputs=gr.Textbox(), outputs=gr.Textbox())
 demo.launch(share=True)
-demo.api_name["predict_from_sequence"] = predict_utils

app.py

@@ -584,6 +584,20 @@ with gr.Blocks(css="""
         else:
             return gr.update(visible=False), gr.update(visible=True)
 
+    def predict_utils(sequence):
+        input_ids = tokenizer(" ".join(sequence), return_tensors="pt").input_ids.to(device)
+        with torch.no_grad():
+            outputs = model(input_ids).logits.detach().cpu().numpy().squeeze()
+    
+        # Calculate scores and normalize them
+        raw_scores = expit(outputs[:, 1] - outputs[:, 0])
+        normalized_scores = normalize_scores(raw_scores)
+    
+        return {
+        "raw_scores": raw_scores.tolist(),
+        "normalized_scores": normalized_scores.tolist()
+    }
+        
     mode.change(
         toggle_mode,
         inputs=[mode],
@@ -622,16 +636,6 @@ with gr.Blocks(css="""
         outputs=[predictions_output, molecule_output, download_output]
     )
 
-    def predict_utils(sequence):
-        input_ids = tokenizer(" ".join(sequence), return_tensors="pt").input_ids.to(device)
-        with torch.no_grad():
-            outputs = model(input_ids).logits.detach().cpu().numpy().squeeze()
     
-        # Calculate scores and normalize them
-        raw_scores = expit(outputs[:, 1] - outputs[:, 0])
-        normalized_scores = normalize_scores(raw_scores)
-    
-        return raw_scores,normalized_scores
-
+demo.load(predict_utils, inputs=gr.Textbox(), outputs=gr.Textbox())
 demo.launch(share=True)
-demo.api_name["predict_from_sequence"] = predict_utils