X-Git-Url: https://fleuret.org/cgi-bin/gitweb/gitweb.cgi?a=blobdiff_plain;f=main.py;h=b01ea0ae078f0e4a494b25f2971d64c2b358bfe0;hb=c3621f9a75cd4d79410d90a29dc9fdec401eaa2d;hp=bcba9ee0b2e9bedaa0cd1792cb4fe50c3afe3bbe;hpb=4e5fc31bbaf94c291f18c785b227e64bea1690cb;p=mygpt.git

diff --git a/main.py b/main.py
index bcba9ee..b01ea0a 100755
--- a/main.py
+++ b/main.py
@@ -160,8 +160,8 @@ class TaskPicoCLVR(Task):
     def tensorize(self, descr):
         token_descr = [ s.strip().split(' ') for s in descr ]
         l = max([ len(s) for s in token_descr ])
-        token_descr = [ [ '<nul>' ] * (l - len(s)) + s for s in token_descr ]
-        #token_descr = [ s + [ '<nul>' ] * (l - len(s)) for s in token_descr ]
+        #token_descr = [ [ '<nul>' ] * (l - len(s)) + s for s in token_descr ]
+        token_descr = [ s + [ '<nul>' ] * (l - len(s)) for s in token_descr ]
         id_descr = [ [ self.token2id[u] for u in s ] for s in token_descr ]
         return torch.tensor(id_descr, device = self.device)
 
@@ -188,6 +188,7 @@ class TaskPicoCLVR(Task):
         self.device = device
         nb = args.data_size if args.data_size > 0 else 250000
 
+        log_string(f'generating {nb} samples (can take some time)')
         self.train_descr = generate_descr((nb * 4) // 5)
         self.test_descr = generate_descr((nb * 1) // 5)