Update.

[picoclvr.git] / tasks.py

diff --git a/tasks.py b/tasks.py
index df3fd81..5583fc8 100755 (executable)
--- a/tasks.py
+++ b/tasks.py
@@ -60,6 +60,83 @@ class Task:
         pass
 
 
+######################################################################
+
+
+class Problem:
+    def generate(nb):
+        pass
+
+    def perf(seq, logger):
+        pass
+
+
+class ProblemByheart(Problem):
+    def __init__(self):
+        nb_seq, len_prompt, len_result = 100, 5, 5
+        self.seq = torch.randint(10, (nb_seq, len_prompt + 1 + len_result))
+        self.seq[:,len_prompt]=-1
+
+    def generate_sequences(self, nb):
+        return self.seq[torch.randint(self.seq.size(0), (nb,))]
+
+class SandBox(Task):
+    def __init__(
+        self,
+        nb_train_samples,
+        nb_test_samples,
+        batch_size,
+        logger=None,
+        device=torch.device("cpu"),
+    ):
+        super().__init__()
+
+        self.batch_size = batch_size
+
+        problems = [ ProblemByheart() ]
+        nb_common_codes = 100
+
+        def generate_sequences(nb_samples):
+            problem_indexes = torch.randint(len(problems), (nb_samples,))
+            nb_samples_per_problem = torch.one_hot(problem_indexes).sum(0)
+            print(f"{nb_samples_per_problem}")
+            all_seq = []
+            for nb, p in zip(nb_samples_per_problem,problems):
+                all_seq.append(p.generate_sequences(nb_samples_per_problem[nb]))
+            return all_seq
+
+        train_seq = generate_sequences(nb_train_samples)
+        test_seq = generate_sequences(nb_test_samples)
+
+        for strain, stest in zip(train_seq, test_seq):
+            s = torch.cat((strain,stest),0)
+
+        self.nb_codes = max(self.train_input.max(), self.test_input.max()) + 1
+
+    def batches(self, split="train", nb_to_use=-1, desc=None):
+        assert split in {"train", "test"}
+        input = self.train_input if split == "train" else self.test_input
+        if nb_to_use > 0:
+            input = input[:nb_to_use]
+        if desc is None:
+            desc = f"epoch-{split}"
+        for batch in tqdm.tqdm(
+            input.split(self.batch_size), dynamic_ncols=True, desc=desc
+        ):
+            yield batch
+
+    def vocabulary_size(self):
+        return self.nb_codes
+
+    def produce_results(
+        self, n_epoch, model, result_dir, logger, deterministic_synthesis
+    ):
+        # logger(
+        # f"accuracy_test {n_epoch} nb_total {test_nb_total} nb_correct {test_nb_correct} accuracy {(100.0*test_nb_correct)/test_nb_total:.02f}%"
+        # )
+        pass
+
+
 ######################################################################
 
 import picoclvr
@@ -108,6 +185,8 @@ class PicoCLVR(Task):
         pruner_train=None,
         pruner_eval=None,
     ):
+        super().__init__()
+
         def generate_descr(nb, cache_suffix, pruner):
             return picoclvr.generate(
                 nb,
@@ -296,6 +375,8 @@ class MNIST(Task):
     def __init__(
         self, nb_train_samples, nb_test_samples, batch_size, device=torch.device("cpu")
     ):
+        super().__init__()
+
         self.nb_train_samples = (nb_train_samples,)
         self.nb_test_samples = (nb_test_samples,)
         self.batch_size = batch_size
@@ -366,6 +447,8 @@ class Maze(Task):
         nb_walls,
         device=torch.device("cpu"),
     ):
+        super().__init__()
+
         self.batch_size = batch_size
         self.height = height
         self.width = width
@@ -537,6 +620,8 @@ class Snake(Task):
         prompt_length,
         device=torch.device("cpu"),
     ):
+        super().__init__()
+
         self.batch_size = batch_size
         self.height = height
         self.width = width
@@ -635,6 +720,8 @@ class Stack(Task):
         fraction_values_for_train=None,
         device=torch.device("cpu"),
     ):
+        super().__init__()
+
         self.batch_size = batch_size
         self.nb_steps = nb_steps
         self.nb_stacks = nb_stacks
@@ -782,6 +869,8 @@ class Expr(Task):
         batch_size,
         device=torch.device("cpu"),
     ):
+        super().__init__()
+
         self.batch_size = batch_size
         self.device = device
 
@@ -959,7 +1048,10 @@ class World(Task):
         vqae_nb_epochs,
         logger=None,
         device=torch.device("cpu"),
+        device_storage=torch.device("cpu"),
     ):
+        super().__init__()
+
         self.batch_size = batch_size
         self.device = device
 
@@ -978,12 +1070,13 @@ class World(Task):
             nb_epochs=vqae_nb_epochs,
             logger=logger,
             device=device,
+            device_storage=device_storage,
         )
 
         print(f"{train_action_seq.size()=}")
 
-        train_frame_seq = self.frame2seq(train_frames)
-        test_frame_seq = self.frame2seq(test_frames)
+        train_frame_seq = self.frame2seq(train_frames).to(device_storage)
+        test_frame_seq = self.frame2seq(test_frames).to(device_storage)
 
         nb_frame_codes = max(train_frame_seq.max(), test_frame_seq.max()) + 1
         nb_action_codes = max(train_action_seq.max(), test_action_seq.max()) + 1
@@ -993,6 +1086,7 @@ class World(Task):
         self.nb_codes = nb_frame_codes + nb_action_codes
 
         train_frame_seq = train_frame_seq.reshape(train_frame_seq.size(0) // 2, 2, -1)
+        print(f"{train_action_seq.device=} {nb_frame_codes.device=}")
         train_action_seq += nb_frame_codes
         self.train_input = torch.cat(
             (train_frame_seq[:, 0, :], train_action_seq, train_frame_seq[:, 1, :]), 1
@@ -1014,7 +1108,7 @@ class World(Task):
         for batch in tqdm.tqdm(
             input.split(self.batch_size), dynamic_ncols=True, desc=desc
         ):
-            yield batch
+            yield batch.to(self.device)
 
     def vocabulary_size(self):
         return self.nb_codes
@@ -1026,7 +1120,7 @@ class World(Task):
             2 * self.len_frame_seq + self.len_action_seq, device=self.device
         )[None, :]
 
-        input = self.test_input[:64]
+        input = self.test_input[:64].to(self.device)
         result = input.clone()
 
         ar_mask = (