Update.

[mygpt.git] / main.py

diff --git a/main.py b/main.py
index ac1e2e3..82caebe 100755 (executable)
--- a/main.py
+++ b/main.py
@@ -24,9 +24,6 @@ parser = argparse.ArgumentParser(description = 'My own GPT.')
 parser.add_argument('--log_filename',
                     type = str, default = 'train.log')
 
-parser.add_argument('--download',
-                    action='store_true', default = False)
-
 parser.add_argument('--seed',
                     type = int, default = 0)
 
@@ -173,6 +170,7 @@ class TaskPicoCLVR(Task):
 
             descr = [ s.strip().split(' ') for s in descr ]
             l = max([ len(s) for s in descr ])
+            #descr = [ [ '<unk>' ] * (l - len(s)) + s for s in descr ]
             descr = [ s + [ '<unk>' ] * (l - len(s)) for s in descr ]
 
             return descr
@@ -194,6 +192,7 @@ class TaskPicoCLVR(Task):
         self.token2id = dict([ (t, n) for n, t in enumerate(tokens) ])
         self.id2token = dict([ (n, t) for n, t in enumerate(tokens) ])
 
+        # Tokenize the train and test sets
         t = [ [ self.token2id[u] for u in s ] for s in self.train_descr ]
         self.train_input = torch.tensor(t, device = self.device)
         t = [ [ self.token2id[u] for u in s ] for s in self.test_descr ]