Update app.py

app.py

@@ -11,7 +11,7 @@ import os
 import huggingface_hub
 from huggingface_hub import hf_hub_download, login
 import model_archs
-from model_archs import BertClassifier, LogisticRegressionTorch, SimpleCNN, MLP, Pool2BN
+from model_archs import BertClassifier, LogisticRegressionTorch, SimpleCNN, MLP, Pool2BN, ResNet1d
 import tangermeme
 from tangermeme.utils import one_hot_encode
 
@@ -144,11 +144,11 @@ def analyze_dna(username, password, sequence, model_name):
 
         model, tokenizer = load_model(model_name)
 
-        def get_logits(seq, model_name):
+        def get_logits(sequence, model_name):
             
             if model_name == 'GENA-Bert':
                 
-                inputs = tokenizer(seq, truncation=True, padding='max_length', max_length=512, return_tensors="pt", return_token_type_ids=False)
+                inputs = tokenizer(sequence, truncation=True, padding='max_length', max_length=512, return_tensors="pt", return_token_type_ids=False)
                 with torch.no_grad():
                     logits = model(input_ids=inputs['input_ids'], attention_mask=inputs['attention_mask'])
                 return logits
@@ -159,13 +159,15 @@ def analyze_dna(username, password, sequence, model_name):
                 pad_char = 'N'
                 
                 # Truncate sequence
-                seq = seq[:SEQUENCE_LENGTH]
+                sequence = sequence[:SEQUENCE_LENGTH]
 
                 # Pad sequences to the desired length
-                seq = seq.ljust(SEQUENCE_LENGTH, pad_char)[:SEQUENCE_LENGTH]
+                sequence = sequence.ljust(SEQUENCE_LENGTH, pad_char)[:SEQUENCE_LENGTH]
 
                 # Apply one-hot encoding to the sequence
-                input_tensor = one_hot_encode(seq).unsqueeze(0).float() 
+                input_tensor = one_hot_encode(sequence).unsqueeze(0).float() 
+                print(f'shape of input tensor{input_tensor.shape}')
+                model.eval()
                 with torch.no_grad():
                     logits = model(input_tensor)
                 return logits