import problem
-class Reasoning(problem.Problem):
+class Grids(problem.Problem):
named_colors = [
("white", [255, 255, 255]),
("red", [255, 0, 0]),
predicted_answers=None,
nrow=4,
):
- prompts = prompts.reshape(prompts.size(0), self.height, -1)
- answers = answers.reshape(answers.size(0), self.height, -1)
+ S = self.height * self.width
+ As = prompts[:, 0 * (S + 1) : 0 * (S + 1) + S].view(-1, self.height, self.width)
+ f_As = prompts[:, 1 * (S + 1) : 1 * (S + 1) + S].view(
+ -1, self.height, self.width
+ )
+ Bs = prompts[:, 2 * (S + 1) : 2 * (S + 1) + S].view(-1, self.height, self.width)
+ prompts = torch.cat([As, f_As, Bs], dim=2)
+ answers = answers.reshape(answers.size(0), self.height, self.width)
if predicted_prompts is None:
predicted_prompts = 255
c = c.long()[:, None]
c = (
(1 - ((c == 1).long() + (c == 0).long() + (c == -1).long()))
- * torch.tensor([192, 192, 192], device=c.device)
+ * torch.tensor([64, 64, 64], device=c.device)
+ (c == 1).long() * torch.tensor([0, 255, 0], device=c.device)
+ (c == 0).long() * torch.tensor([255, 255, 255], device=c.device)
+ (c == -1).long() * torch.tensor([255, 0, 0], device=c.device)
if n < nb_rec - 1:
f_X[i1, j1] = c[-1]
+ def contact(self, X, i, j, q):
+ nq, nq_diag = 0, 0
+ no = 0
+
+ for ii, jj in [
+ (i - 1, j - 1),
+ (i - 1, j),
+ (i - 1, j + 1),
+ (i, j - 1),
+ (i, j + 1),
+ (i + 1, j - 1),
+ (i + 1, j),
+ (i + 1, j + 1),
+ ]:
+ if ii >= 0 and ii < self.height and jj >= 0 and jj < self.width:
+ if X[ii, jj] != 0 and X[ii, jj] != q:
+ no += 1
+
+ for ii, jj in [
+ (i - 1, j - 1),
+ (i - 1, j + 1),
+ (i + 1, j - 1),
+ (i + 1, j + 1),
+ ]:
+ if ii >= 0 and ii < self.height and jj >= 0 and jj < self.width:
+ if X[ii, jj] == q and X[i, jj] != q and X[ii, j] != q:
+ nq_diag += 1
+
+ for ii, jj in [(i - 1, j), (i, j - 1), (i, j + 1), (i + 1, j)]:
+ if ii >= 0 and ii < self.height and jj >= 0 and jj < self.width:
+ if X[ii, jj] == q:
+ nq += 1
+
+ return no, nq, nq_diag
+
def task_count(self, A, f_A, B, f_B):
N = torch.randint(4, (1,)) + 2
c = torch.randperm(len(self.colors) - 1)[:N] + 1
for X, f_X in [(A, f_A), (B, f_B)]:
-
- def contact(i, j, q):
- nq, nq_diag = 0, 0
- no = 0
-
- for ii, jj in [
- (i - 1, j - 1),
- (i - 1, j),
- (i - 1, j + 1),
- (i, j - 1),
- (i, j + 1),
- (i + 1, j - 1),
- (i + 1, j),
- (i + 1, j + 1),
- ]:
- if ii >= 0 and ii < self.height and jj >= 0 and jj < self.width:
- if X[ii, jj] != 0 and X[ii, jj] != q:
- no += 1
-
- for ii, jj in [
- (i - 1, j - 1),
- (i - 1, j + 1),
- (i + 1, j - 1),
- (i + 1, j + 1),
- ]:
- if ii >= 0 and ii < self.height and jj >= 0 and jj < self.width:
- if X[ii, jj] == q and X[i, jj] != q and X[ii, j] != q:
- nq_diag += 1
-
- for ii, jj in [(i - 1, j), (i, j - 1), (i, j + 1), (i + 1, j)]:
- if ii >= 0 and ii < self.height and jj >= 0 and jj < self.width:
- if X[ii, jj] == q:
- nq += 1
-
- return no, nq, nq_diag
-
nb = torch.zeros(N, dtype=torch.int64)
q = torch.randint(N, (self.height * self.width,))
k = torch.randperm(self.height * self.width)
for p in range(self.height * self.width):
i, j = k[p] % self.height, k[p] // self.height
- no, nq, nq_diag = contact(i, j, c[q[p]])
+ no, nq, nq_diag = self.contact(X, i, j, c[q[p]])
if no == 0 and nq_diag == 0:
if nq == 0:
if nb[q[p]] < self.width:
X[i, j] = c[1]
f_X[0:2, 0:2] = c[1]
+ def task_islands(self, A, f_A, B, f_B):
+ for X, f_X in [(A, f_A), (B, f_B)]:
+ while True:
+ i, j = torch.randint(self.height, (1,)), torch.randint(self.width, (1,))
+ if (
+ i == 0
+ or i == self.height - 1
+ or j == 0
+ or j == self.width - 1
+ or X[i, j] == 1
+ ):
+ break
+ while True:
+ di, dj = torch.randint(3, (2,)) - 1
+ if abs(di) + abs(dj) > 0:
+ break
+ X[i, j] = 1
+ while True:
+ i, j = i + di, j + dj
+ if i < 0 or i >= self.height or j < 0 or j >= self.width:
+ break
+ b = (
+ i == 0
+ or i == self.height - 1
+ or j == 0
+ or j == self.width - 1
+ or X[i, j] == 1
+ )
+ X[i, j] = 1
+ if b:
+ break
+
######################################################################
def all_tasks(self):
self.task_trajectory,
self.task_bounce,
self.task_scale,
+ # self.task_islands,
]
def generate_prompts_and_answers(self, nb, tasks=None, device="cpu"):
if tasks is None:
tasks = self.all_tasks()
- prompts = torch.zeros(nb, self.height, self.width * 3, dtype=torch.int64)
- answers = torch.zeros(nb, self.height, self.width, dtype=torch.int64)
- w = self.width
+ S = self.height * self.width
+ prompts = torch.zeros(nb, 3 * S + 2, dtype=torch.int64)
+ answers = torch.zeros(nb, S, dtype=torch.int64)
for prompt, answer in tqdm.tqdm(
zip(prompts, answers),
desc="world generation",
total=prompts.size(0),
):
- A = prompt[:, 0 * w : 1 * w]
- f_A = prompt[:, 1 * w : 2 * w]
- B = prompt[:, 2 * w : 3 * w]
- f_B = answer
+ A = prompt[0 * (S + 1) : 0 * (S + 1) + S].view(self.height, self.width)
+ f_A = prompt[1 * (S + 1) : 1 * (S + 1) + S].view(self.height, self.width)
+ B = prompt[2 * (S + 1) : 2 * (S + 1) + S].view(self.height, self.width)
+ f_B = answer.view(self.height, self.width)
task = tasks[torch.randint(len(tasks), (1,))]
task(A, f_A, B, f_B)
if __name__ == "__main__":
import time
- nb = 4
+ nb = 48
- reasoning = Reasoning()
+ grids = Grids()
- for t in reasoning.all_tasks():
+ for t in grids.all_tasks():
+ # for t in [grids.task_islands]:
print(t.__name__)
- prompts, answers = reasoning.generate_prompts_and_answers(nb, tasks=[t])
- reasoning.save_quizzes("/tmp", t.__name__, prompts[:nb], answers[:nb], nrow=1)
+ prompts, answers = grids.generate_prompts_and_answers(nb, tasks=[t])
+ grids.save_quizzes("/tmp", t.__name__, prompts[:nb], answers[:nb], nrow=4)
exit(0)
+ nb = 72
+
start_time = time.perf_counter()
- prompts, answers = reasoning.generate_prompts_and_answers(nb)
+ prompts, answers = grids.generate_prompts_and_answers(nb)
delay = time.perf_counter() - start_time
print(f"{prompts.size(0)/delay:02f} seq/s")
- # m = torch.randint(2, (prompts.size(0),))
- # predicted_prompts = m * (torch.randint(2, (prompts.size(0),)) * 2 - 1)
- # predicted_answers = (1 - m) * (torch.randint(2, (prompts.size(0),)) * 2 - 1)
+ m = torch.randint(2, (prompts.size(0),))
+ predicted_prompts = m * (torch.randint(2, (prompts.size(0),)) * 2 - 1)
+ predicted_answers = (1 - m) * (torch.randint(2, (prompts.size(0),)) * 2 - 1)
- reasoning.save_quizzes(
+ grids.save_quizzes(
"/tmp",
"test",
prompts[:nb],
answers[:nb],
# You can add a bool to put a frame around the predicted parts
- # predicted_prompts[:nb],
- # predicted_answers[:nb],
+ predicted_prompts[:nb],
+ predicted_answers[:nb],
)