Update.

[culture.git] / world.py

diff --git a/world.py b/world.py
index 839f4ff..36aa1e9 100755 (executable)
--- a/world.py
+++ b/world.py
@@ -41,16 +41,15 @@ token2char = "_" + "".join([chr(ord("A") + n) for n in range(len(colors) - 1)])
 
 
 def generate_seq(
 
 
 def generate_seq(

-    nb,
-    height,
-    width,
-    nb_birds=3,
-    nb_iterations=2,
+    nb, height, width, nb_birds=3, nb_iterations=2, return_iterations=False

 ):
     pairs = []
 ):
     pairs = []

+    kept_iterations = []

 
     for _ in tqdm.tqdm(range(nb), dynamic_ncols=True, desc="world generation"):
         while True:
 
     for _ in tqdm.tqdm(range(nb), dynamic_ncols=True, desc="world generation"):
         while True:

+            iterations = []
+

             f_start = torch.zeros(height, width, dtype=torch.int64)
 
             i, j, vi, vj = (
             f_start = torch.zeros(height, width, dtype=torch.int64)
 
             i, j, vi, vj = (


@@ -90,6 +89,7 @@ def generate_seq(
             f_end = f_start.clone()
 
             for l in range(nb_iterations):
             f_end = f_start.clone()
 
             for l in range(nb_iterations):

+                iterations.append(f_end.clone())

                 f_end[...] = 0
                 nb_collisions = 0
                 for n in range(nb_birds):
                 f_end[...] = 0
                 nb_collisions = 0
                 for n in range(nb_birds):


@@ -125,9 +125,12 @@ def generate_seq(
                     f_end[i[n] - vi[n], j[n]] = c
                     f_end[i[n], j[n] - vj[n]] = c
 
                     f_end[i[n] - vi[n], j[n]] = c
                     f_end[i[n], j[n] - vj[n]] = c
 

+            iterations.append(f_end.clone())
+

             if nb_collisions == 0:
                 break
 
             if nb_collisions == 0:
                 break
 

+        kept_iterations.append(iterations)

         pairs.append((f_start, f_end))
 
     result = []
         pairs.append((f_start, f_end))
 
     result = []


@@ -147,7 +150,11 @@ def generate_seq(
                 )[None, :]
             )
 
                 )[None, :]
             )
 

-    return torch.cat(result, dim=0)
+    if return_iterations:
+        # iterations = torch.cat([ torch.cat([ x[None, None] for x in l], dim = 1) for l in kept_iterations ], dim=0)
+        return torch.cat(result, dim=0), kept_iterations
+    else:
+        return torch.cat(result, dim=0)

 
 
 ######################################################################
 
 
 ######################################################################


@@ -219,32 +226,33 @@ def generate_seq_old(
     return torch.cat(result, dim=0)
 
 
     return torch.cat(result, dim=0)
 
 

-def sample2img(seq, height, width, upscale=15):
-    f_first = seq[:, : height * width].reshape(-1, height, width)
-    f_second = seq[:, height * width + 1 :].reshape(-1, height, width)
-    direction = seq[:, height * width]
+def frame2img(x, height, width, upscale=15):
+    x = x.reshape(-1, height, width)
+    m = torch.logical_and(x >= 0, x < first_bird_token + nb_bird_tokens).long()
+    x = colors[x * m].permute(0, 3, 1, 2)
+    s = x.shape
+    x = x[:, :, :, None, :, None].expand(-1, -1, -1, upscale, -1, upscale)
+    x = x.reshape(s[0], s[1], s[2] * upscale, s[3] * upscale)

 
 

-    def mosaic(x, upscale):
-        x = x.reshape(-1, height, width)
-        m = torch.logical_and(x >= 0, x < first_bird_token + nb_bird_tokens).long()
-        x = colors[x * m].permute(0, 3, 1, 2)
-        s = x.shape
-        x = x[:, :, :, None, :, None].expand(-1, -1, -1, upscale, -1, upscale)
-        x = x.reshape(s[0], s[1], s[2] * upscale, s[3] * upscale)
+    x[:, :, :, torch.arange(0, x.size(3), upscale)] = 0
+    x[:, :, torch.arange(0, x.size(2), upscale), :] = 0
+    x = x[:, :, 1:, 1:]

 
 

-        x[:, :, :, torch.arange(0, x.size(3), upscale)] = 0
-        x[:, :, torch.arange(0, x.size(2), upscale), :] = 0
-        x = x[:, :, 1:, 1:]
+    for n in range(m.size(0)):
+        for i in range(m.size(1)):
+            for j in range(m.size(2)):
+                if m[n, i, j] == 0:
+                    for k in range(2, upscale - 2):
+                        x[n, :, i * upscale + k, j * upscale + k] = 0
+                        x[n, :, i * upscale + upscale - 1 - k, j * upscale + k] = 0

 
 

-        for n in range(m.size(0)):
-            for i in range(m.size(1)):
-                for j in range(m.size(2)):
-                    if m[n, i, j] == 0:
-                        for k in range(2, upscale - 2):
-                            x[n, :, i * upscale + k, j * upscale + k] = 0
-                            x[n, :, i * upscale + upscale - 1 - k, j * upscale + k] = 0
+    return x

 
 

-        return x
+
+def seq2img(seq, height, width, upscale=15):
+    f_first = seq[:, : height * width].reshape(-1, height, width)
+    f_second = seq[:, height * width + 1 :].reshape(-1, height, width)
+    direction = seq[:, height * width]

 
     direction_symbol = torch.full((direction.size(0), height * upscale - 1, upscale), 0)
     direction_symbol = colors[direction_symbol].permute(0, 3, 1, 2)
 
     direction_symbol = torch.full((direction.size(0), height * upscale - 1, upscale), 0)
     direction_symbol = colors[direction_symbol].permute(0, 3, 1, 2)


@@ -278,11 +286,11 @@ def sample2img(seq, height, width, upscale=15):
 
     return torch.cat(
         [
 
     return torch.cat(
         [

-            mosaic(f_first, upscale),
+            frame2img(f_first, height, width, upscale),

             separator,
             direction_symbol,
             separator,
             separator,
             direction_symbol,
             separator,

-            mosaic(f_second, upscale),
+            frame2img(f_second, height, width, upscale),

         ],
         dim=3,
     )
         ],
         dim=3,
     )


@@ -302,16 +310,28 @@ if __name__ == "__main__":
 
     height, width = 6, 8
     start_time = time.perf_counter()
 
     height, width = 6, 8
     start_time = time.perf_counter()

-    seq = generate_seq(nb=90, height=height, width=width)
+    seq, it = generate_seq(
+        nb=64, height=height, width=width, nb_iterations=100, return_iterations=True
+    )

     delay = time.perf_counter() - start_time
     print(f"{seq.size(0)/delay:02f} samples/s")
 
     print(seq2str(seq[:4]))
 
     delay = time.perf_counter() - start_time
     print(f"{seq.size(0)/delay:02f} samples/s")
 
     print(seq2str(seq[:4]))
 

+    for t in range(len(it[0])):
+        img = torch.cat([frame2img(f[t], height, width) for f in it], dim=0)
+        torchvision.utils.save_image(
+            img.float() / 255.0,
+            f"/tmp/frame_{t:03d}.png",
+            nrow=8,
+            padding=6,
+            pad_value=0,
+        )
+

     # m = (torch.rand(seq.size()) < 0.05).long()
     # seq = (1 - m) * seq + m * 23
 
     # m = (torch.rand(seq.size()) < 0.05).long()
     # seq = (1 - m) * seq + m * 23
 

-    img = sample2img(seq, height, width)
+    img = seq2img(seq, height, width)

     print(img.size())
 
     torchvision.utils.save_image(
     print(img.size())
 
     torchvision.utils.save_image(