Update app.py

app.py

@@ -48,33 +48,30 @@ def Kmers_funct(seq,num):
     return l
 
 def ACE(file):
+    test_seq = file
+    all = []
+    for j in range(2, 11):
+        X = Kmers_funct([test_seq], j)
+        all.extend(X)
     model = MyModel()
     model.load_state_dict(torch.load("best_model.pth", map_location=torch.device('cpu')), strict=False)
     model = model.to(device)
     model.eval()
     tokenizer = AutoTokenizer.from_pretrained(model_checkpoint)
-    test_sequences = file
     max_len = 30
-    test_data = tokenizer(test_sequences, max_length=max_len, padding="max_length",truncation=True, return_tensors='pt')
-    out_probability = []
-    with torch.no_grad():
-        predict = model(test_data)
-        out_probability.extend(np.max(np.array(predict.cpu()),axis=1).tolist())
-        test_argmax = np.argmax(predict.cpu(), axis=1).tolist()
-    id2str = {0:"non-ACE", 1:"ACE"}
-    return id2str[test_argmax[0]], out_probability[0]
 
-def main(file):
-    test_seq = file
-    all = []
     seq_all = []
     output_all = []
     probability_all = []
-    for j in range(2, 11):
-        X = Kmers_funct([test_seq], j)
-        all.extend(X)
     for seq in all:
-        output, probability = ACE(str(seq))
+        test_data = tokenizer(seq, max_length=max_len, padding="max_length",truncation=True, return_tensors='pt')
+        out_probability = []
+        predict = model(test_data)
+        out_probability.extend(np.max(np.array(predict.cpu()),axis=1).tolist())
+        test_argmax = np.argmax(predict.cpu(), axis=1).tolist()
+        id2str = {0:"non-ACE", 1:"ACE"}
+        output = id2str[test_argmax[0]]
+        probability = out_probability[0]
         seq_all.append(seq)
         output_all.append(output)
         probability_all.append(probability)
@@ -87,8 +84,7 @@ def main(file):
     summary_df.to_csv('output.csv', index=False)
     return 'outputs.csv'
 
-
-iface = gr.Interface(fn=main,
+iface = gr.Interface(fn=ACE,
                      inputs="text", 
                      outputs= "file")
 iface.launch()