Update.

[picoclvr.git] / main.py

diff --git a/main.py b/main.py
index 5b49468..56b7e1c 100755 (executable)
--- a/main.py
+++ b/main.py
@@ -14,7 +14,7 @@ import torch, torchvision
 from torch import nn
 from torch.nn import functional as F
 
-import mygpt, tasks, tensorstack
+import mygpt, tasks
 
 ######################################################################
 
@@ -127,6 +127,8 @@ parser.add_argument("--expr_nb_variables", type=int, default=5)
 
 parser.add_argument("--expr_sequence_length", type=int, default=30)
 
+parser.add_argument("--expr_input_file", type=str, default=None)
+
 ######################################################################
 
 args = parser.parse_args()
@@ -366,6 +368,20 @@ else:
 
 ######################################################################
 
+if args.task == "expr" and args.expr_input_file is not None:
+    task.produce_results(
+        nb_epochs_finished,
+        model,
+        args.result_dir,
+        log_string,
+        args.deterministic_synthesis,
+        args.expr_input_file,
+    )
+
+    exit(0)
+
+######################################################################
+
 nb_epochs = args.nb_epochs if args.nb_epochs > 0 else nb_epochs_default
 
 # Compute the entropy of the training tokens
@@ -383,20 +399,28 @@ train_set_perplexity = math.exp(entropy)
 
 train_examples = {}
 
+
 for input in task.batches(split="train"):
-    assert input.dim()==2 and input.dtype==torch.int64
+    assert input.dim() == 2 and input.dtype == torch.int64
     for x in input:
-        train_examples[x.sum().item()]=x
+        train_examples[x.sum().item()] = x
 
+nb_total, nb_collisions = 0, 0
 for input in task.batches(split="test"):
-    assert input.dim()==2 and input.dtype==torch.int64
+    assert input.dim() == 2 and input.dtype == torch.int64
     for x in input:
+        nb_total += 1
         y = train_examples.get(x.sum().item())
         if y is not None:
-            assert x.size() != y.size() or (x-y).abs().sum() > 0
+            if x.size() == y.size() and (x - y).abs().sum() == 0:
+                nb_collisions += 1
 
 del train_examples
 
+log_string(
+    f"data_check {nb_collisions*100/nb_total:.02f}% ({nb_collisions}/{nb_total}) of test samples are in the train set"
+)
+
 ##############################
 
 if args.learning_rate_schedule == "cos":