dodox/PriorConditionedAnnealing
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Added Rayleigh Perlin

Browse Source
This commit is contained in:
Dominik Moritz Roth 2024-04-18 14:29:07 +02:00
parent 446eee5fa1
commit e66dbfe52d
2 changed files with 51 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

48
priorConditionedAnnealing/noise.py
View File

@ -126,6 +126,30 @@ class Perlin_Noise():
self.index = 0
self.noise = PerlinNoise(octaves=self.octave)
class P_Perlin_Noise():
def __init__(self, known_shape=None, scale=0.1, octave=1):
self.known_shape = known_shape
self.scale = scale
self.octave = octave
self.magic = PI # Axis offset, should be (kinda) irrational
# We want to genrate samples, that approx ~N(0,1)
self.normal_factor = PI/20
self.clear_cache_every = 128
self.reset()
def __call__(self, shape=None):
if shape == None:
shape = self.known_shape
self.index += 1
noise = [self.noise([self.index*self.scale, self.magic+(2*a)]) / self.normal_factor
for a in range(np.prod(shape))]
if self.index % self.clear_cache_every == 0:
self.noise.cache = {}
return th.Tensor(noise).view(shape)
def reset(self):
self.index = 0
self.noise = PerlinNoise(octaves=self.octave)
class Harmonic_Perlin_Noise():
def __init__(self, known_shape=None, scale=0.1, octaves=8):
@ -173,3 +197,27 @@ class Dirty_Perlin_Noise():
def reset(self):
self.perlin = Perlin_Noise(known_shape=self.known_shape, scale=self.scale, octave=1)
self.white = White_Noise(known_shape=self.known_shape)
class Rayleigh_Perlin_Noise():
def __init__(self, known_shape=None, sigma=0.1):
self.known_shape = known_shape
self.sigma = sigma
self.magic = PI # Axis offset, should be (kinda) irrational
# We want to genrate samples, that approx ~N(0,1)
self.normal_factor = PI/20
self.clear_cache_every = 128
self.reset()
def __call__(self, shape=None):
assert shape == self.known_shape or (shape[1:] == self.known_shape[1:] and shape[0] <= self.known_shape[0])
self.index += 1
noise = [self.noise([self.index*self.scales[a%np.prod(self.known_shape[:-1])], self.magic+(2*a)]) / self.normal_factor
for a in range(np.prod(shape))]
if self.index % self.clear_cache_every == 0:
self.noise.cache = {}
return th.Tensor(noise).view(shape)
def reset(self):
self.index = 0
self.scales = np.random.rayleigh(scale=self.sigma, size=np.prod(self.known_shape[:-1]))
self.noise = PerlinNoise(octaves=1)

4
priorConditionedAnnealing/pca.py
View File

@ -55,10 +55,12 @@ class Avaible_Noise_Funcs(Enum):
DIRTYPERLIN = 5
SDE = 6
SHORTPINK = 7
P_PERLIN = 8
RAYLEIGH_PERLIN = 9
def get_func(self):
# stil aaaaaaaa
return [noise.White_Noise, noise.Pink_Noise, noise.Colored_Noise, noise.Perlin_Noise, noise.Harmonic_Perlin_Noise, noise.Dirty_Perlin_Noise, noise.SDE_Noise, noise.shortPink_Noise][self.value]
return [noise.White_Noise, noise.Pink_Noise, noise.Colored_Noise, noise.Perlin_Noise, noise.Harmonic_Perlin_Noise, noise.Dirty_Perlin_Noise, noise.SDE_Noise, noise.shortPink_Noise, noise.P_Perlin_Noise, noise.Rayleigh_Perlin_Noise][self.value]
def cast_to_enum(inp, Class):