colors = torch.tensor(
[
[255, 255, 255],
- [255, 0, 0],
- [0, 128, 0],
+ [255, 20, 147],
[0, 0, 255],
- [255, 200, 0],
+ [0, 192, 0],
+ [0, 255, 255],
[192, 192, 192],
+ [106, 90, 205],
+ [255, 0, 0],
+ [220, 20, 60],
+ [65, 105, 225],
+ [255, 200, 0],
+ # [255, 182, 193],
+ # [75, 0, 130],
+ # [128, 0, 128],
+ # [30, 144, 255],
+ # [135, 206, 235],
+ # [0, 255, 0],
+ # [64, 224, 208],
+ # [250, 128, 114],
+ # [255, 165, 0],
+ # [0, 255, 255],
]
)
token_background = 0
first_bird_token = 1
-nb_bird_tokens = len(colors) - 1
+nb_bird_tokens = colors.size(0) - 1
token_forward = first_bird_token + nb_bird_tokens
token_backward = token_forward + 1
-token2char = "_" + "".join([str(n) for n in range(len(colors) - 1)]) + "><"
+token2char = "_" + "".join([chr(ord("A") + n) for n in range(len(colors) - 1)]) + "><"
def generate(
nb,
height,
width,
- max_nb_obj=2,
+ nb_birds=3,
+ nb_iterations=1,
+):
+ pairs = []
+
+ for _ in tqdm.tqdm(range(nb), dynamic_ncols=True, desc="world generation"):
+ f_start = torch.zeros(height, width, dtype=torch.int64)
+
+ i, j, vi, vj = (
+ torch.empty(nb_birds, dtype=torch.int64),
+ torch.empty(nb_birds, dtype=torch.int64),
+ torch.empty(nb_birds, dtype=torch.int64),
+ torch.empty(nb_birds, dtype=torch.int64),
+ )
+
+ col = torch.randperm(colors.size(0) - 1)[:nb_birds].sort().values + 1
+
+ for n in range(nb_birds):
+ c = col[n]
+
+ while True:
+ i[n], j[n] = (
+ torch.randint(height, (1,))[0],
+ torch.randint(width, (1,))[0],
+ )
+ vm = torch.randint(4, (1,))[0]
+ vi[n], vj[n] = (vm % 2) * 2 - 1, (vm // 2) * 2 - 1
+ if (
+ i[n] - vi[n] >= 0
+ and i[n] - vi[n] < height
+ and j[n] - vj[n] >= 0
+ and j[n] - vj[n] < width
+ and f_start[i[n], j[n]] == 0
+ and f_start[i[n] - vi[n], j[n]] == 0
+ and f_start[i[n], j[n] - vj[n]] == 0
+ ):
+ break
+
+ f_start[i[n], j[n]] = c
+ f_start[i[n] - vi[n], j[n]] = c
+ f_start[i[n], j[n] - vj[n]] = c
+
+ f_end = f_start.clone()
+
+ for l in range(nb_iterations):
+ for n in range(nb_birds):
+ c = col[n]
+ f_end[i[n], j[n]] = 0
+ f_end[i[n] - vi[n], j[n]] = 0
+ f_end[i[n], j[n] - vj[n]] = 0
+
+ pi, pj, pvi, pvj = i[n].item(), j[n].item(), vi[n].item(), vj[n].item()
+
+ assert (
+ f_end[i[n], j[n]] == 0
+ and f_end[i[n] - vi[n], j[n]] == 0
+ and f_end[i[n], j[n] - vj[n]] == 0
+ )
+
+ if (i[n] == 0 and vi[n] == -1) or (i[n] == height - 1 and vi[n] == 1):
+ vi[n] = -vi[n]
+ if (j[n] == 0 and vj[n] == -1) or (j[n] == width - 1 and vj[n] == 1):
+ vj[n] = -vj[n]
+
+ i[n] += vi[n]
+ j[n] += vj[n]
+
+ if not (
+ f_end[i[n], j[n]] == 0
+ and f_end[i[n] - vi[n], j[n]] == 0
+ and f_end[i[n], j[n] - vj[n]] == 0
+ ):
+ i[n], j[n], vi[n], vj[n] = pi, pj, pvi, pvj
+
+ f_end[i[n], j[n]] = c
+ f_end[i[n] - vi[n], j[n]] = c
+ f_end[i[n], j[n] - vj[n]] = c
+
+ pairs.append((f_start, f_end))
+
+ result = []
+ for p in pairs:
+ if torch.rand(1) < 0.5:
+ result.append(
+ torch.cat(
+ [p[0].flatten(), torch.tensor([token_forward]), p[1].flatten()],
+ dim=0,
+ )[None, :]
+ )
+ else:
+ result.append(
+ torch.cat(
+ [p[1].flatten(), torch.tensor([token_backward]), p[0].flatten()],
+ dim=0,
+ )[None, :]
+ )
+
+ return torch.cat(result, dim=0)
+
+
+def generate_(
+ nb,
+ height,
+ width,
+ nb_birds=3,
nb_iterations=2,
):
pairs = []
f_end = torch.zeros(height, width, dtype=torch.int64)
n = torch.arange(f_start.size(0))
- nb_birds = torch.randint(max_nb_obj, (1,)).item() + 1
for c in (
(torch.randperm(nb_bird_tokens) + first_bird_token)[:nb_birds].sort().values
):
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:]
+
for n in range(m.size(0)):
for i in range(m.size(1)):
for j in range(m.size(2)):
return x
- direction_symbol = torch.full((direction.size(0), height * upscale, upscale), 0)
+ direction_symbol = torch.full((direction.size(0), height * upscale - 1, upscale), 0)
direction_symbol = colors[direction_symbol].permute(0, 3, 1, 2)
- separator = torch.full((direction.size(0), 3, height * upscale, 1), 0)
+ separator = torch.full((direction.size(0), 3, height * upscale - 1, 1), 0)
for n in range(direction_symbol.size(0)):
if direction[n] == token_forward:
n,
:,
(height * upscale) // 2 - upscale // 2 + k,
- 3 + abs(k - upscale // 2),
+ 3 + upscale // 2 - abs(k - upscale // 2),
] = 0
elif direction[n] == token_backward:
for k in range(upscale):
n,
:,
(height * upscale) // 2 - upscale // 2 + k,
- 3 + upscale // 2 - abs(k - upscale // 2),
+ 3 + abs(k - upscale // 2),
] = 0
else:
for k in range(2, upscale - 2):
height, width = 6, 8
start_time = time.perf_counter()
- seq = generate(nb=90, height=height, width=width, max_nb_obj=3)
+ seq = generate(nb=90, height=height, width=width)
delay = time.perf_counter() - start_time
print(f"{seq.size(0)/delay:02f} samples/s")
print(img.size())
torchvision.utils.save_image(
- img.float() / 255.0, "/tmp/world.png", nrow=6, padding=4
+ img.float() / 255.0, "/tmp/world.png", nrow=6, padding=6, pad_value=0
)
projects / culture.git / blobdiff