def seq2str(self, seq):
return "[NOT IMPLEMENTED]"
+ def compute_nb_correct(self, input, ar_mask, result):
+ nb_total = ar_mask.sum().item()
+ nb_correct = ((result == input).long() * ar_mask).sum().item()
+ return nb_total, nb_correct
####################
-class ProblemLevel0(Problem):
- def __init__(self, nb_sentences=100, len_prompt=5, len_result=5):
+class ProblemTwoCuts(Problem):
+ def __init__(self, len_total=50, nb_values=100, global_constraint=True):
+ self.len_total = len_total
+ self.nb_values = nb_values
+ self.global_constraint = global_constraint
+
+ def generate_sequences_internal(self, nb):
+ return u,v,a,b,c
+
+ def generate_sequences(self,nb):
+
+ u = torch.randint(self.len_total, (nb,))
+ v = torch.randint(self.len_total, (nb,))
+
+ a = torch.randint(self.nb_values, (nb,))
+ b = torch.randint(self.nb_values, (nb,))
+ c = torch.randint(self.nb_values, (nb,))
+
+ while True:
+ to_compute = torch.logical_or(u>=v-self.len_total//10,u<v-self.len_total//5)
+ to_compute =torch.logical_or(to_compute, u == 0)
+ to_compute =torch.logical_or(to_compute, v == self.len_total)
+ n = to_compute.long().sum()
+ if n == 0:
+ break
+ else:
+ u[to_compute] = torch.randint(self.len_total, (n,))
+ v[to_compute] = torch.randint(self.len_total, (n,))
+
+ while True:
+ to_compute = a==b
+ to_compute = torch.logical_or(to_compute,b==c)
+ to_compute = torch.logical_or(to_compute,a==c)
+
+ if self.global_constraint:
+ to_compute = torch.logical_or(to_compute,(a*u+b*(v-u)+c*(self.len_total-v)) // self.len_total != self.nb_values//2)
+
+ n = to_compute.long().sum()
+ if n == 0:
+ break
+ else:
+ a[to_compute] = torch.randint(self.nb_values, (n,))
+ b[to_compute] = torch.randint(self.nb_values, (n,))
+ c[to_compute] = torch.randint(self.nb_values, (n,))
+
+ assert (u>=v).long().sum() == 0
+ assert (a==b).long().sum() == 0
+ assert (a==c).long().sum() == 0
+ assert (c==b).long().sum() == 0
+
+ t = torch.arange(self.len_total)
+ seq = (t[None,:] < u[:,None]).long() * a[:,None] + \
+ (t[None,:] >= u[:,None]).long() * (t[None,:] < v[:,None]).long() * b[:,None] + \
+ (t[None,:] >= v[:,None]).long() * c[:,None]
+
+ return seq,seq.new_full(seq.size(), 1, dtype=torch.int64)
+
+ def compute_nb_correct(self, input, ar_mask, result):
+ nb_total = result.size(0)
+ nb_correct = 0
+ i = torch.arange(result.size(1), device=result.device)
+
+ for k in range(nb_total):
+ s = result[k]
+ a = s[0]
+ uu = (s != a).nonzero()
+ if uu.size(0) > 0:
+ u = uu.min()
+ b = s[u]
+ vv = torch.logical_and(s != b, i >= u).nonzero()
+ if vv.size(0) > 0:
+ v = vv.min()
+ c = s[v]
+ ww = torch.logical_and(s != c, i >= v).nonzero()
+ if ww.size(0) == 0:
+ if not self.global_constraint or (a*u+b*(v-u)+c*(self.len_total-v)) // self.len_total == self.nb_values//2:
+ nb_correct += 1
+
+ return nb_total, nb_correct
+
+ def seq2str(self, seq):
+ return " ".join( [ f"{x:02d}" for x in seq ] )
+
+####################
+
+
+class ProblemTwoTargets(Problem):
+ def __init__(self, len_total=10, len_targets=3):
+ assert len_targets >= 3
+ assert len_total >= 3 * len_targets - 1
+ self.len_total = len_total
+ self.len_targets = len_targets
+
+ def generate_sequences(self, nb):
+ k = torch.arange(self.len_total)[None, :]
+ s = torch.randint(10, (nb, self.len_total))
+ l = torch.rand(nb, self.len_total)
+ l = l * (k <= self.len_total - self.len_targets).long()
+ k1 = l.argmax(dim=1, keepdim=True)
+ m = (k != k1).long() * (k != k1 + self.len_targets - 1).long()
+ s = s * m + 10 * (1 - m)
+ l = l * (
+ 1
+ - (k + self.len_targets - 1 >= k1).long()
+ * (k < k1 + self.len_targets).long()
+ )
+ k2 = l.argmax(dim=1, keepdim=True)
+ m = (k != k2).long() * (k != k2 + self.len_targets - 1).long()
+ s = s * m + 11 * (1 - m)
+ a1 = s.gather(dim=1, index=k1 + 1 + torch.arange(self.len_targets - 2)[None, :])
+ a2 = s.gather(dim=1, index=k2 + 1 + torch.arange(self.len_targets - 2)[None, :])
+ sequences = torch.cat(
+ (
+ s,
+ torch.full((nb, 1), 12),
+ a1,
+ torch.full((nb, 1), 12),
+ a2,
+ torch.full((nb, 1), 12),
+ ),
+ 1,
+ )
+ ar_mask = (sequences == 12).long()
+ ar_mask = (ar_mask.cumsum(1) - ar_mask).clamp(max=1)
+ return sequences, ar_mask
+
+ def seq2str(self, seq):
+ return "".join("0123456789-+|"[x.item()] for x in seq)
+
+
+####################
+
+
+class ProblemByHeart(Problem):
+ def __init__(self, nb_sentences=100, len_prompt=8, len_result=8):
self.seq = torch.randint(10, (nb_sentences, len_prompt + 1 + len_result))
self.seq[:, len_prompt] = 10
ar_mask = (ar_mask.cumsum(1) - ar_mask).clamp(max=1)
return sequences, ar_mask
+ def seq2str(self, seq):
+ return "".join("0123456789|"[x.item()] for x in seq)
+
-class ProblemLevel1(Problem):
- def __init__(self, nb_operators=100, len_source=5, len_result=8):
+####################
+
+
+class ProblemLearnOperator(Problem):
+ def __init__(self, nb_operators=100, len_source=6, len_result=9):
self.len_source = len_source
self.len_result = len_result
self.len_nb_operator = int(math.log(nb_operators) / math.log(10)) + 1
// 10 ** torch.arange(self.len_nb_operator - 1, -1, -1)
) % 10
marker1 = torch.full((nb, 1), 10)
- # source = torch.randint(10, (nb, self.len_source))
source = torch.rand(nb, 10).sort(dim=1).indices[:, : self.len_source]
marker2 = torch.full((nb, 1), 11)
result = operators.bmm(source[:, :, None]).squeeze(-1)
return "".join("0123456789|>"[x.item()] for x in seq)
-class ProblemLevel2(Problem):
+####################
+
+
+class ProblemGuessOperator(Problem):
def __init__(self, len_source=5, len_result=8):
self.len_source = len_source
self.len_result = len_result
return "".join(self.id2char[x.item()] for x in seq)
-# class ProblemUnion(Problem):
-# 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
-
-# for strain, stest in zip(train_seq, test_seq):
-# s = torch.cat((strain, stest), 0)
+if __name__ == "__main__":
+ p = ProblemTwoCuts(12)
+ s, m = p.generate_sequences(10000)
+ print(p.compute_nb_correct(None, None, s))
projects / picoclvr.git / blobdiff