X-Git-Url: https://fleuret.org/cgi-bin/gitweb/gitweb.cgi?a=blobdiff_plain;f=tasks.py;h=d787c59e7dce1e70ec6a5b2b386c955b4536b018;hb=c951702f59f869c58d59b59f60a4931d890a13dc;hp=2c2f9140ec337ae5cac4c490a40d97a92fa54fe1;hpb=0e1e208852b83f6a3d59e5caabd2f0f1f4bde94e;p=picoclvr.git

diff --git a/tasks.py b/tasks.py
index 2c2f914..d787c59 100755
--- a/tasks.py
+++ b/tasks.py
@@ -1426,7 +1426,7 @@ import grid
 
 class Grid(Task):
     # Make a tensor from a list of strings
-    def tensorize(self, descr):
+    def str2tensor(self, descr):
         token_descr = [s.strip().split(" ") for s in descr]
         l = max([len(s) for s in token_descr])
         token_descr = [s + ["#"] * (l - len(s)) for s in token_descr]
@@ -1434,7 +1434,7 @@ class Grid(Task):
         return torch.tensor(id_descr, device=self.device)
 
     # Make a list of strings from a tensor
-    def detensorize(self, x):
+    def tensor2str(self, x):
         return [" ".join([self.id2token[t.item()] for t in r]) for r in x]
 
     # trim all the tensors in the tuple z to remove as much token from
@@ -1495,12 +1495,12 @@ class Grid(Task):
         self.token2id = dict([(t, n) for n, t in enumerate(tokens)])
         self.id2token = dict([(n, t) for n, t in enumerate(tokens)])
         self.t_nul = self.token2id["#"]
-        self.t_true = self.token2id["<true>"]
-        self.t_false = self.token2id["<false>"]
+        self.t_true = self.token2id["true"]
+        self.t_false = self.token2id["false"]
 
         # Tokenize the train and test sets
-        self.train_input = self.tensorize(self.train_descr)
-        self.test_input = self.tensorize(self.test_descr)
+        self.train_input = self.str2tensor(self.train_descr)
+        self.test_input = self.str2tensor(self.test_descr)
 
     def batches(self, split="train"):
         assert split in {"train", "test"}
@@ -1519,9 +1519,11 @@ class Grid(Task):
         correct = self.test_input[:1000]
         result = correct.clone()
         ar_mask = torch.logical_or(result == self.t_true, result == self.t_false).long()
-        result *= 1 - ar_mask
+        result *= 1 - ar_mask  # paraaaaanoiaaaaaaa
+
+        logger(f"----------------------------------------------------------")
 
-        for e in self.detensorize(result[:10]):
+        for e in self.tensor2str(result[:10]):
             logger(f"test_before {e}")
 
         masked_inplace_autoregression(
@@ -1533,14 +1535,18 @@ class Grid(Task):
             device=self.device,
         )
 
-        for e in self.detensorize(result[:10]):
-            logger(f"test_after {e}")
+        logger(f"----------------------------------------------------------")
+
+        for e in self.tensor2str(result[:10]):
+            logger(f"test_after  {e}")
+
+        logger(f"----------------------------------------------------------")
 
         nb_total = ar_mask.sum().item()
         nb_correct = ((correct == result).long() * ar_mask).sum().item()
 
-        logger(f"test_performance {nb_total=} {nb_correct=}")
-        logger(f"main_test_accuracy {nb_correct / nb_total}")
+        logger(f"test_performance {n_epoch} {nb_total=} {nb_correct=}")
+        logger(f"main_test_accuracy {n_epoch} {nb_correct / nb_total}")
 
 
 ######################################################################