def create_maze(h=11, w=17, nb_walls=8):
- a, k = 0, 0
+ assert h % 2 == 1 and w % 2 == 1
- while k < nb_walls:
+ nb_attempts, nb_added_walls = 0, 0
+
+ while nb_added_walls < nb_walls:
while True:
- if a == 0:
+ if nb_attempts == 0:
m = torch.zeros(h, w, dtype=torch.int64)
m[0, :] = 1
m[-1, :] = 1
r = torch.rand(4)
if r[0] <= 0.5:
+ # Add a vertical wall
i1, i2, j = (
int((r[1] * h).item()),
int((r[2] * h).item()),
)
i1, i2, j = i1 - i1 % 2, i2 - i2 % 2, j - j % 2
i1, i2 = min(i1, i2), max(i1, i2)
+
+ # If this wall does not hit another one, add it
if i2 - i1 > 1 and i2 - i1 <= h / 2 and m[i1 : i2 + 1, j].sum() <= 1:
m[i1 : i2 + 1, j] = 1
break
+
else:
+ # Add an horizontal wall
i, j1, j2 = (
int((r[1] * h).item()),
int((r[2] * w).item()),
)
i, j1, j2 = i - i % 2, j1 - j1 % 2, j2 - j2 % 2
j1, j2 = min(j1, j2), max(j1, j2)
+
+ # If this wall does not hit another one, add it
if j2 - j1 > 1 and j2 - j1 <= w / 2 and m[i, j1 : j2 + 1].sum() <= 1:
m[i, j1 : j2 + 1] = 1
break
- a += 1
- if a > 10 * nb_walls:
- a, k = 0, 0
+ nb_attempts += 1
+
+ if nb_attempts > 10 * nb_walls:
+ nb_attempts, nb_added_walls = 0, 0
- k += 1
+ nb_added_walls += 1
return m
mazes,
target_paths=None,
predicted_paths=None,
- score_paths=None,
- score_truth=None,
path_correct=None,
path_optimal=None,
):
colors[mazes.reshape(-1)].reshape(mazes.size() + (-1,)).permute(0, 3, 1, 2)
)
- if score_truth is not None:
- score_truth = score_truth.cpu()
- c_score_truth = score_truth.unsqueeze(1).expand(-1, 3, -1, -1)
- c_score_truth = (
- c_score_truth * colors[4].reshape(1, 3, 1, 1)
- + (1 - c_score_truth) * colors[0].reshape(1, 3, 1, 1)
- ).long()
- c_mazes = (mazes.unsqueeze(1) != v_empty) * c_mazes + (
- mazes.unsqueeze(1) == v_empty
- ) * c_score_truth
-
imgs = c_mazes.unsqueeze(1)
if target_paths is not None:
)
imgs = torch.cat((imgs, c_predicted_paths.unsqueeze(1)), 1)
- if score_paths is not None:
- score_paths = score_paths.cpu()
- c_score_paths = score_paths.unsqueeze(1).expand(-1, 3, -1, -1)
- c_score_paths = (
- c_score_paths * colors[4].reshape(1, 3, 1, 1)
- + (1 - c_score_paths) * colors[0].reshape(1, 3, 1, 1)
- ).long()
- c_score_paths = c_score_paths * (mazes.unsqueeze(1) == v_empty) + c_mazes * (
- mazes.unsqueeze(1) != v_empty
- )
- imgs = torch.cat((imgs, c_score_paths.unsqueeze(1)), 1)
-
img = torch.tensor([255, 255, 0]).view(1, -1, 1, 1)
# NxKxCxHxW
-1, -1, imgs.size(3) + 2, 1 + imgs.size(1) * (1 + imgs.size(4))
).clone()
+ print(f"{img.size()=} {imgs.size()=}")
+
for k in range(imgs.size(1)):
img[
:,
if __name__ == "__main__":
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
- mazes, paths = create_maze_data(8)
+ mazes, paths, policies = create_maze_data(8)
mazes, paths = mazes.to(device), paths.to(device)
- save_image("test.png", mazes, paths, paths)
+ save_image("test.png", mazes=mazes, target_paths=paths, predicted_paths=paths)
print(path_correctness(mazes, paths))
######################################################################