Skip to content

Instantly share code, notes, and snippets.

View yoyololicon's full-sized avatar
🐎
うまぴょい~

Chin-Yun Yu yoyololicon

🐎
うまぴょい~
View GitHub Profile
🌞 Morning 98 commits ███▏░░░░░░░░░░░░░░░░░ 15.3%
🌆 Daytime 158 commits █████▏░░░░░░░░░░░░░░░ 24.7%
🌃 Evening 282 commits █████████▎░░░░░░░░░░░ 44.1%
🌙 Night 102 commits ███▎░░░░░░░░░░░░░░░░░ 15.9%
@yoyololicon
yoyololicon / differentiable_lfilter.py
Last active August 25, 2022 12:59
This lfilter can propogate gradient to filter coefficients.
import torch
import torch.nn as nn
import torch.nn.functional as F
from torchaudio.functional import lfilter as torch_lfilter
from torch.autograd import Function, gradcheck
class lfilter(Function):
@staticmethod
import numpy as np
import networkx as nx
from scipy.spatial import Delaunay
def W(x):
return (x + np.pi) % (2 * np.pi) - np.pi
def mcf_sparse(x, y, psi, capacity=None):
points = np.vstack((x, y)).T
num_points = points.shape[0]
import numpy as np
import networkx as nx
def W(x):
return (x + np.pi) % (2 * np.pi) - np.pi
def mcf(x: np.ndarray, capacity=None):
assert x.ndim == 2, "Input x should be a 2d array!"
# construct index for each node