X-Git-Url: https://fleuret.org/cgi-bin/gitweb/gitweb.cgi?a=blobdiff_plain;f=problems.py;h=632c059e41075c314cf8e9a473a6e53ec299aa01;hb=07c40deef359a676eea9b063e8f5f8a2254cad13;hp=22b651795b0501331c69fd24c3ea499779576e48;hpb=0d86d8ca945722438d3c85cd01b3740269ed3546;p=picoclvr.git

diff --git a/problems.py b/problems.py
index 22b6517..632c059 100755
--- a/problems.py
+++ b/problems.py
@@ -24,8 +24,6 @@ class Problem:
 
 
 ####################
-
-
 class ProblemDegradation(Problem):
     def __init__(self, nb_state_tokens=5, nb_time_steps=12, value_max=25, hard=False):
         assert value_max // nb_state_tokens >= 2
@@ -285,9 +283,145 @@ class ProblemAddition(Problem):
         return "".join(self.id2char[x.item()] for x in seq)
 
 
+####################
+
+
+class ProblemMixing(Problem):
+    def __init__(self, height=4, width=4, nb_time_steps=9, hard=False):
+        self.height = height
+        self.width = width
+        self.nb_time_steps = nb_time_steps
+        self.hard = hard
+
+    def start_random(self, nb):
+        y = torch.arange(self.height * self.width).reshape(1, -1).expand(nb, -1)
+
+        # m = (torch.rand(y.size()).sort(dim=-1).indices < y.size(1) // 2).long()
+
+        i = (
+            torch.arange(self.height)
+            .reshape(1, -1, 1)
+            .expand(nb, self.height, self.width)
+        )
+        j = (
+            torch.arange(self.width)
+            .reshape(1, 1, -1)
+            .expand(nb, self.height, self.width)
+        )
+
+        ri = torch.randint(self.height, (nb,)).reshape(nb, 1, 1)
+        rj = torch.randint(self.width, (nb,)).reshape(nb, 1, 1)
+
+        m = 1 - torch.logical_or(i == ri, j == rj).long().flatten(1)
+
+        y = (y * m + self.height * self.width * (1 - m)).reshape(
+            nb, self.height, self.width
+        )
+
+        return y
+
+    def start_error(self, x):
+        i = torch.arange(self.height, device=x.device).reshape(1, -1, 1).expand_as(x)
+        j = torch.arange(self.width, device=x.device).reshape(1, 1, -1).expand_as(x)
+
+        ri = (
+            (x == self.height * self.width).long().sum(dim=-1).argmax(-1).view(-1, 1, 1)
+        )
+        rj = (
+            (x == self.height * self.width).long().sum(dim=-2).argmax(-1).view(-1, 1, 1)
+        )
+
+        m = 1 - torch.logical_or(i == ri, j == rj).long().flatten(1)
+
+        x = x.flatten(1)
+        u = torch.arange(self.height * self.width, device=x.device).reshape(1, -1)
+
+        d = (x - (m * u + (1 - m) * self.height * self.width)).abs().sum(-1)
+        return d
+
+    def moves(self, x):
+        y = (
+            x[:, None, :, :]
+            .expand(-1, self.height * 2 + self.width * 2, -1, -1)
+            .clone()
+        )
+        k = 0
+
+        for i in range(self.height):
+            y[:, k, i, :] = y[:, k, i, :].roll(dims=-1, shifts=-1)
+            k += 1
+            y[:, k, i, :] = y[:, k, i, :].roll(dims=-1, shifts=1)
+            k += 1
+
+        for j in range(self.width):
+            y[:, k, :, j] = y[:, k, :, j].roll(dims=-1, shifts=-1)
+            k += 1
+            y[:, k, :, j] = y[:, k, :, j].roll(dims=-1, shifts=1)
+            k += 1
+
+        return y
+
+    def generate_sequences(self, nb):
+        x = self.start_random(nb)
+
+        seq = [x.flatten(1)]
+
+        for t in range(self.nb_time_steps - 1):
+            y = self.moves(x)
+            x = y[torch.arange(nb), torch.randint(y.size(1), (nb,))]
+            seq.append(x.flatten(1))
+
+        if self.hard:
+            seq.reverse()
+
+        seq = torch.cat(seq, dim=1)
+        return seq, seq.new_full(seq.size(), 1, dtype=torch.int64)
+
+    def compute_nb_correct(self, input, ar_mask, result):
+        a = [
+            x.reshape(result.size(0), self.height, self.width)
+            for x in result.split(self.height * self.width, dim=1)
+        ]
+        if self.hard:
+            a.reverse()
+
+        x = a[0]
+
+        d = self.start_error(x)
+
+        for t in range(self.nb_time_steps - 1):
+            x0, x = a[t], a[t + 1]
+            y = self.moves(x0)
+            d = d + (x[:, None] - y).abs().sum((-1, -2)).min(dim=-1).values
+
+        nb_total, nb_correct = result.size(0), (d == 0).long().sum().item()
+
+        return nb_total, nb_correct
+
+    def seq2str(self, seq):
+        return " | ".join(
+            [
+                " ".join(
+                    [
+                        "-".join(
+                            [
+                                f"{x:02d}" if x < self.height * self.width else "**"
+                                for x in s
+                            ]
+                        )
+                        for s in r.split(self.width)
+                    ]
+                )
+                for r in seq.split(self.height * self.width)
+            ]
+        )
+
+
+####################
+
 if __name__ == "__main__":
-    p = ProblemDegradation(hard=False)
+    p = ProblemMixing()
     s, m = p.generate_sequences(10000)
-    for x in s[:100]:
+    for x in s[:5]:
         print(p.seq2str(x))
     print(p.compute_nb_correct(None, None, s))