gpu to cpu

app.py

@@ -50,7 +50,8 @@ drop_prob = 0.1
 num_layers = 6
 max_sequence_length = 200
 kn_vocab_size = len(gujarati_vocabulary)
-device = torch.device('cuda') if torch.cuda.is_available() else torch.device('cpu')
+# device = torch.device('cuda') if torch.cuda.is_available() else torch.device('cpu')
+device =  torch.device('cpu')
 
 transformer = Transformer(d_model, 
                           ffn_hidden,

transformer.py

@@ -5,8 +5,8 @@ from torch import nn
 import torch.nn.functional as F
 
 def get_device():
-    return torch.device('cuda') if torch.cuda.is_available() else torch.device('cpu')
-    # return torch.device('cpu')
+    # return torch.device('cuda') if torch.cuda.is_available() else torch.device('cpu')
+    return torch.device('cpu')
 
 def scaled_dot_product(q, k, v, mask=None):
     d_k = q.size()[-1]