X-Git-Url: https://fleuret.org/cgi-bin/gitweb/gitweb.cgi?a=blobdiff_plain;f=main.py;h=f8e451be4f30fdfcbd5c9212b160214f4892c069;hb=c253ddd45b809dd7389773f690a83366a17ccde6;hp=24c21f54fa1113424af6a5638eb1a49a8c231735;hpb=f04e158f0679195821a7288bbfe08f775b894096;p=picoclvr.git diff --git a/main.py b/main.py index 24c21f5..f8e451b 100755 --- a/main.py +++ b/main.py @@ -526,7 +526,7 @@ class TaskMaze(Task): self.width = width self.device = device - train_mazes, train_paths, train_policies = maze.create_maze_data( + train_mazes, train_paths, _ = maze.create_maze_data( nb_train_samples, height=height, width=width, @@ -534,9 +534,8 @@ class TaskMaze(Task): progress_bar=lambda x: tqdm.tqdm(x, dynamic_ncols=True, desc=f"data-train"), ) self.train_input = self.map2seq(train_mazes.to(device), train_paths.to(device)) - self.train_policies = train_policies.flatten(-2).to(device) - test_mazes, test_paths, test_policies = maze.create_maze_data( + test_mazes, test_paths, _ = maze.create_maze_data( nb_test_samples, height=height, width=width, @@ -544,9 +543,8 @@ class TaskMaze(Task): progress_bar=lambda x: tqdm.tqdm(x, dynamic_ncols=True, desc=f"data-test"), ) self.test_input = self.map2seq(test_mazes.to(device), test_paths.to(device)) - self.test_policies = test_policies.flatten(-2).to(device) - self.nb_codes = self.train_input.max() + 1 + 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"} @@ -560,26 +558,6 @@ class TaskMaze(Task): ): yield batch - def policy_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 - policies = self.train_policies if split == "train" else self.test_policies - input = input[:, : self.height * self.width] - policies = policies * (input != maze.v_wall)[:, None] - - if nb_to_use > 0: - input = input[:nb_to_use] - policies = policies[:nb_to_use] - - if desc is None: - desc = f"epoch-{split}" - for batch in tqdm.tqdm( - zip(input.split(self.batch_size), policies.split(self.batch_size)), - dynamic_ncols=True, - desc=desc, - ): - yield batch - def vocabulary_size(self): return self.nb_codes @@ -646,6 +624,115 @@ class TaskMaze(Task): ###################################################################### +def generate_snake_sequences( + nb, height, width, nb_colors, length, device=torch.device("cpu") +): + world = torch.randint(nb_colors, (nb, height, width), device=device) + # nb x 2 + snake_position = torch.cat( + ( + torch.randint(height, (nb, 1), device=device), + torch.randint(width, (nb, 1), device=device), + ), + 1, + ) + snake_direction = torch.randint(4, (nb, 1), device=device) + result = torch.empty(nb, 2*length, device=device, dtype=torch.int64) + count = torch.arange(nb, device=device) # [:,None] + + for l in range(length): + # nb x 3 + snake_next_direction = torch.cat( + ( + (snake_direction - 1) % 4, + snake_direction, + (snake_direction + 1) % 4, + ), + 1, + ) + + # nb x 3 + vh = (snake_next_direction + 1) % 2 * (snake_next_direction - 1) + vw = snake_next_direction % 2 * (snake_next_direction - 2) + + # nb x 3 x 2 + snake_next_speed = torch.cat((vh[:, :, None], vw[:, :, None]), 2) + snake_next_position = snake_position[:, None, :] + snake_next_speed + + # nb x 3 + val = torch.logical_and( + torch.logical_and( + snake_next_position[:, :, 0] >= 0, snake_next_position[:, :, 0] < height + ), + torch.logical_and( + snake_next_position[:, :, 1] >= 0, snake_next_position[:, :, 1] < width + ), + ).float() + val = torch.rand_like(val) * val * torch.tensor([[1.,4.,1.]], device=device) + + # nb + i = torch.arange(val.size(0), device=device) + j = val.argmax(1) + + # nb x 1 + snake_direction = snake_next_direction[i[:, None], j[:, None]] + + result[:, 2*l] = world[count, snake_position[:, 0], snake_position[:, 1]] + result[:, 2*l+1] = snake_direction[:,0] + + # nb x 2 + snake_position = snake_next_position[i[:, None], j[:, None]].squeeze(1) + + return result + +generate_snake_sequences(nb=2, height=4, width=5, nb_colors=3, length=10) +exit(0) + +class TaskSnake(Task): + def __init__( + self, + nb_train_samples, + nb_test_samples, + batch_size, + height, + width, + nb_colors, + length, + device=torch.device("cpu"), + ): + self.batch_size = batch_size + self.height = height + self.width = width + self.device = device + + self.train_input = generate_snake_sequences( + nb_train_samples, height, width, nb_colors, length, self.device + ) + self.test_input = generate_snake_sequences( + nb_test_samples, height, width, nb_colors, length, self.device + ) + + 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 picoclvr_pruner_horizontal_green(p): return not ("green" in p and ("left" in p or "right" in p)) @@ -694,6 +781,18 @@ elif args.task == "maze": device=device, ) +elif args.task == "snake": + task = TaskSnake( + nb_train_samples=args.nb_train_samples, + nb_test_samples=args.nb_test_samples, + batch_size=args.batch_size, + height=6, + width=8, + nb_colors=5, + length=100, + device=device, + ) + else: raise ValueError(f"Unknown task {args.task}")