grey-area

grey-area

from functools import reduce
from copy import deepcopy
from itertools import product


def get_key_paths(d, key_paths=[], param_lists=[], acc=[]):
    for k, v in d.items():
        if isinstance(v, dict):
            get_key_paths(v, key_paths, param_lists, acc=acc + [k])
        elif isinstance(v, list):

grey-area

import numpy as np
import matplotlib.pyplot as plt

# make_cmap function is from: http://schubert.atmos.colostate.edu/~cslocum/custom_cmap.html

def make_cmap(colors, position=None, bit=False):
    '''
    make_cmap takes a list of tuples which contain RGB values. The RGB
    values may either be in 8-bit [0 to 255] (in which bit must be set to
    True when called) or arithmetic [0 to 1] (default). make_cmap returns

grey-area

import numpy as np

# Base class
class Base:
    # 'Constructor' class methods to make instances with common values for data attribute
    @classmethod
    def create_common_instance_1(cls):
        value = np.eye(3)
        return cls(value)

grey-area

\documentclass{article}

\usepackage[utf8]{inputenc}
\usepackage{tikz}
\usepackage{pgfplots}

\begin{document}

\begin{figure}[ht]
  \centering

grey-area

import numpy as np
import matplotlib.pyplot as plt
from scipy.special import gamma

trials = 200
steps = 1000
xs = np.arange(steps)
ds = [1, 10, 100]

fig, axes = plt.subplots(1, 3, sharey=True)

grey-area

import numpy as np
from PIL import Image
from tqdm import tqdm


# Image resolution will be this divided by 2
# due to downsampling
resolution = 4000

# Points in the complex plane

grey-area

import numpy as np
from PIL import Image
from matplotlib.colors import hsv_to_rgb

# Parameters
lim = 50
sub_pixel_resolution = 1

xs_min, xs_max = (-lim, lim)
ys_min, ys_max = (-lim * 0.5625, lim * 0.5625)

grey-area

import torch
import torch.nn as nn


class MirroredConv1d(nn.Module):
    def __init__(self, **kwargs):
        super(MirroredConv1d, self).__init__()

        if kwargs['out_channels'] % 2 == 1:
            raise ValueError('Number of output channels must be even')

grey-area

import torch
from pathlib import Path
import platform
from datetime import datetime
import git
from pip._internal.operations import freeze


def save_checkpoint(checkpoint_path, model, optimizer, config_dict):
    run_info = {