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
assert n < nmax
+def path_optimality(ref_paths, paths):
+ return (ref_paths == v_path).long().flatten(1).sum(1) == (
+ paths == v_path
+ ).long().flatten(1).sum(1)
+
+
def path_correctness(mazes, paths):
- still_ok = (mazes - (paths * (paths < 4))).view(mazes.size(0), -1).abs().sum(1) == 0
+ still_ok = (mazes - (paths * (paths != v_path))).view(mazes.size(0), -1).abs().sum(
+ 1
+ ) == 0
reached = still_ok.new_zeros(still_ok.size())
current, pred_current = paths.clone(), paths.new_zeros(paths.size())
goal = (mazes == v_goal).long()
mazes,
target_paths=None,
predicted_paths=None,
- score_paths=None,
- score_truth=None,
path_correct=None,
+ path_optimal=None,
):
colors = torch.tensor(
[
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
- if path_correct is None:
- path_correct = torch.zeros(imgs.size(0)) <= 1
- path_correct = path_correct.cpu().long().view(-1, 1, 1, 1)
- img = torch.tensor([224, 224, 224]).view(1, -1, 1, 1) * path_correct + torch.tensor(
- [255, 0, 0]
- ).view(1, -1, 1, 1) * (1 - path_correct)
+ if path_optimal is not None:
+ path_optimal = path_optimal.cpu().long().view(-1, 1, 1, 1)
+ img = (
+ img * (1 - path_optimal)
+ + torch.tensor([0, 255, 0]).view(1, -1, 1, 1) * path_optimal
+ )
+
+ if path_correct is not None:
+ path_correct = path_correct.cpu().long().view(-1, 1, 1, 1)
+ img = img * path_correct + torch.tensor([255, 0, 0]).view(1, -1, 1, 1) * (
+ 1 - path_correct
+ )
+
img = img.expand(
-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))
######################################################################