Update.

[culture.git] / world.py

diff --git a/world.py b/world.py
index 0392940..118a470 100755 (executable)
--- a/world.py
+++ b/world.py
@@ -22,81 +22,80 @@ colors = torch.tensor(
         [255, 0, 0],
         [0, 128, 0],
         [0, 0, 255],
         [255, 0, 0],
         [0, 128, 0],
         [0, 0, 255],

-        [255, 255, 0],
+        [255, 200, 0],

         [192, 192, 192],
     ]
 )
 
         [192, 192, 192],
     ]
 )
 

-token2char = "_X01234>"
+token2char = "_X" + "".join([str(n) for n in range(len(colors) - 2)]) + ">"

 
 
 def generate(
     nb,
     height,
     width,
 
 
 def generate(
     nb,
     height,
     width,

-    obj_length=6,
-    mask_height=3,
-    mask_width=3,
-    nb_obj=3,
+    max_nb_obj=2,
+    nb_iterations=2,

 ):
 ):

-    intact = torch.zeros(nb, height, width, dtype=torch.int64)
-    n = torch.arange(intact.size(0))
-
-    for n in range(nb):
-        for c in torch.randperm(colors.size(0) - 2)[:nb_obj] + 2:
-            z = intact[n].flatten()
-            m = (torch.rand(z.size()) * (z == 0)).argmax(dim=0)
-            i, j = m // width, m % width
+    f_start = torch.zeros(nb, height, width, dtype=torch.int64)
+    f_end = torch.zeros(nb, height, width, dtype=torch.int64)
+    n = torch.arange(f_start.size(0))
+
+    for n in tqdm.tqdm(range(nb), dynamic_ncols=True, desc="world generation"):
+        nb_fish = torch.randint(max_nb_obj, (1,)).item() + 1
+        for c in torch.randperm(colors.size(0) - 2)[:nb_fish].sort().values:
+            i, j = (
+                torch.randint(height - 2, (1,))[0] + 1,
+                torch.randint(width - 2, (1,))[0] + 1,
+            )

             vm = torch.randint(4, (1,))[0]
             vi, vj = (vm // 2) * (2 * (vm % 2) - 1), (1 - vm // 2) * (2 * (vm % 2) - 1)
             vm = torch.randint(4, (1,))[0]
             vi, vj = (vm // 2) * (2 * (vm % 2) - 1), (1 - vm // 2) * (2 * (vm % 2) - 1)

-            for l in range(obj_length):
-                intact[n, i, j] = c
+
+            f_start[n, i, j] = c + 2
+            f_start[n, i - vi, j - vj] = c + 2
+            f_start[n, i + vj, j - vi] = c + 2
+            f_start[n, i - vj, j + vi] = c + 2
+
+            for l in range(nb_iterations):

                 i += vi
                 j += vj
                 i += vi
                 j += vj

-                if i < 0 or i >= height or j < 0 or j >= width or intact[n, i, j] != 0:
+                if i < 0 or i >= height or j < 0 or j >= width:

                     i -= vi
                     j -= vj
                     i -= vi
                     j -= vj

-                    vi, vj = -vj, vi
+                    vi, vj = -vi, -vj

                     i += vi
                     j += vj
                     i += vi
                     j += vj

-                    if (
-                        i < 0
-                        or i >= height
-                        or j < 0
-                        or j >= width
-                        or intact[n, i, j] != 0
-                    ):
-                        break
-
-    masked = intact.clone()
-
-    for n in range(nb):
-        i = torch.randint(height - mask_height + 1, (1,))[0]
-        j = torch.randint(width - mask_width + 1, (1,))[0]
-        masked[n, i : i + mask_height, j : j + mask_width] = 1
+
+            f_end[n, i, j] = c + 2
+            f_end[n, i - vi, j - vj] = c + 2
+            f_end[n, i + vj, j - vi] = c + 2
+            f_end[n, i - vj, j + vi] = c + 2

 
     return torch.cat(
         [
 
     return torch.cat(
         [

-            masked.flatten(1),
-            torch.full((masked.size(0), 1), len(colors)),
-            intact.flatten(1),
+            f_end.flatten(1),
+            torch.full((f_end.size(0), 1), len(colors)),
+            f_start.flatten(1),

         ],
         dim=1,
     )
 
 
 def sample2img(seq, height, width):
         ],
         dim=1,
     )
 
 
 def sample2img(seq, height, width):

-    intact = seq[:, : height * width].reshape(-1, height, width)
-    masked = seq[:, height * width + 1 :].reshape(-1, height, width)
-    img_intact, img_masked = colors[intact], colors[masked]
+    f_start = seq[:, : height * width].reshape(-1, height, width)
+    f_start = (f_start >= len(colors)).long() + (f_start < len(colors)).long() * f_start
+    f_end = seq[:, height * width + 1 :].reshape(-1, height, width)
+    f_end = (f_end >= len(colors)).long() + (f_end < len(colors)).long() * f_end
+
+    img_f_start, img_f_end = colors[f_start], colors[f_end]

 
     img = torch.cat(
         [
 
     img = torch.cat(
         [

-            img_intact,
+            img_f_start,

             torch.full(
             torch.full(

-                (img_intact.size(0), img_intact.size(1), 1, img_intact.size(3)), 1
+                (img_f_start.size(0), img_f_start.size(1), 1, img_f_start.size(3)), 1

             ),
             ),

-            img_masked,
+            img_f_end,

         ],
         dim=2,
     )
         ],
         dim=2,
     )


@@ -118,7 +117,7 @@ if __name__ == "__main__":
 
     height, width = 6, 8
     start_time = time.perf_counter()
 
     height, width = 6, 8
     start_time = time.perf_counter()

-    seq = generate(nb=64, height=height, width=width)
+    seq = generate(nb=64, height=height, width=width, max_nb_obj=3)

     delay = time.perf_counter() - start_time
     print(f"{seq.size(0)/delay:02f} samples/s")
 
     delay = time.perf_counter() - start_time
     print(f"{seq.size(0)/delay:02f} samples/s")