OCD cosmetics.

[mygpt.git] / main.py

diff --git a/main.py b/main.py
index cd0e1ea..6592204 100755 (executable)
--- a/main.py
+++ b/main.py
@@ -170,6 +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
@@ -191,6 +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 ]
@@ -252,14 +254,14 @@ class TaskPicoCLVR(Task):
         )
         log_string(f'wrote {image_name}')
 
-        nb_missing = sum( [
-            x[2] for x in picoclvr.nb_missing_properties(
-                descr,
-                height = self.height, width = self.width
-            )
-        ] )
+        np = picoclvr.nb_properties(
+            descr,
+            height = self.height, width = self.width
+        )
+
+        nb_requested_properties, _, nb_missing_properties = zip(*np)
 
-        log_string(f'nb_missing {nb_missing / len(descr):.02f}')
+        log_string(f'nb_requested_properties {sum(nb_requested_properties) / len(descr):.02f} nb_missing_properties {sum(nb_missing_properties) / len(descr):.02f}')
 
 ######################################################################