Update.

[culture.git] / quiz_machine.py

diff --git a/quiz_machine.py b/quiz_machine.py
index 1f1046d..ae14614 100755 (executable)
--- a/quiz_machine.py
+++ b/quiz_machine.py
@@ -327,6 +327,7 @@ class QuizMachine:
         self, n_epoch, model, result_dir, deterministic_synthesis, nmax=1000
     ):
         def compute_accuracy(input, log_prefix=None):
+            input = input.to(self.device)
             ar_mask = self.make_ar_mask(input)
             result = input.clone() * (1 - ar_mask)
             seq_logproba = torch.empty(input.size(0), device=self.device)
@@ -404,26 +405,29 @@ class QuizMachine:
         input[:-nb] = input[nb:].clone()
         fresh_w_quizzes = self.generate_token_sequences(nb)
         self.reverse_random_half_in_place(fresh_w_quizzes)
-        input[-nb:] = fresh_w_quizzes.to(self.device)
+        input[-nb:] = fresh_w_quizzes.to("cpu")
 
     ######################################################################
 
     def store_c_quizzes(self, new_c_quizzes, for_train=True):
         with self.LOCK_C_QUIZZES:
             if for_train:
-                self.train_c_quizzes.append(new_c_quizzes)
+                self.train_c_quizzes.append(new_c_quizzes.to("cpu"))
             else:
-                self.test_c_quizzes.append(new_c_quizzes)
+                self.test_c_quizzes.append(new_c_quizzes.to("cpu"))
 
     ######################################################################
 
     def logproba_of_solutions(self, models, c_quizzes):
-        logproba = c_quizzes.new_zeros(c_quizzes.size(0), len(models))
+        logproba = c_quizzes.new_zeros(
+            c_quizzes.size(0), len(models), device=self.device
+        )
 
         for model in models:
             for input, l in zip(
                 c_quizzes.split(self.batch_size), logproba.split(self.batch_size)
             ):
+                input = input.to(self.device)
                 ar_mask = self.make_ar_mask(input)
                 output = model(mygpt.BracketedSequence(input)).x
                 ce = (
@@ -432,7 +436,7 @@ class QuizMachine:
                 )
                 l[:, model.id] = -ce.sum(dim=-1)
 
-        return logproba
+        return logproba.to("cpu")
 
     ###############################################################
 
@@ -561,4 +565,4 @@ class QuizMachine:
             device=self.device,
         )
 
-        return c_quizzes
+        return c_quizzes.to("cpu")