)
token_background = 0
-first_fish_token = 1
-nb_fish_tokens = len(colors) - 1
-token_forward = first_fish_token + nb_fish_tokens
+first_bird_token = 1
+nb_bird_tokens = len(colors) - 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)]) + "><"
f_end = torch.zeros(height, width, dtype=torch.int64)
n = torch.arange(f_start.size(0))
- nb_fish = torch.randint(max_nb_obj, (1,)).item() + 1
+ nb_birds = torch.randint(max_nb_obj, (1,)).item() + 1
for c in (
- (torch.randperm(nb_fish_tokens) + first_fish_token)[:nb_fish].sort().values
+ (torch.randperm(nb_bird_tokens) + first_bird_token)[:nb_birds].sort().values
):
i, j = (
torch.randint(height - 2, (1,))[0] + 1,
def sample2img(seq, height, width, upscale=15):
- f_start = seq[:, : height * width].reshape(-1, height, width)
- f_end = seq[:, height * width + 1 :].reshape(-1, height, width)
+ f_first = seq[:, : height * width].reshape(-1, height, width)
+ f_second = seq[:, height * width + 1 :].reshape(-1, height, width)
+ direction = seq[:, height * width]
def mosaic(x, upscale):
x = x.reshape(-1, height, width)
- m = torch.logical_and(x >= 0, x < first_fish_token + nb_fish_tokens).long()
+ 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)
return x
- return torch.cat([mosaic(f_start, upscale), mosaic(f_end, upscale)], dim=3)
+ direction_symbol = torch.full((direction.size(0), height * upscale, upscale), 0)
+ direction_symbol = colors[direction_symbol].permute(0, 3, 1, 2)
+ separator = torch.full((direction.size(0), 3, height * upscale, 1), 0)
+
+ for n in range(direction_symbol.size(0)):
+ if direction[n] == token_forward:
+ for k in range(upscale):
+ direction_symbol[
+ n,
+ :,
+ (height * upscale) // 2 - upscale // 2 + k,
+ 3 + abs(k - upscale // 2),
+ ] = 0
+ elif direction[n] == token_backward:
+ for k in range(upscale):
+ direction_symbol[
+ n,
+ :,
+ (height * upscale) // 2 - upscale // 2 + k,
+ 3 + upscale // 2 - abs(k - upscale // 2),
+ ] = 0
+ else:
+ for k in range(2, upscale - 2):
+ direction_symbol[
+ n, :, (height * upscale) // 2 - upscale // 2 + k, k
+ ] = 0
+ direction_symbol[
+ n, :, (height * upscale) // 2 - upscale // 2 + k, upscale - 1 - k
+ ] = 0
+
+ return torch.cat(
+ [
+ mosaic(f_first, upscale),
+ separator,
+ direction_symbol,
+ separator,
+ mosaic(f_second, upscale),
+ ],
+ dim=3,
+ )
def seq2str(seq):
height, width = 6, 8
start_time = time.perf_counter()
- seq = generate(nb=64, height=height, width=width, max_nb_obj=3)
+ seq = generate(nb=90, height=height, width=width, max_nb_obj=3)
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=8, padding=2
+ img.float() / 255.0, "/tmp/world.png", nrow=6, padding=4
)