ferrine

import numpy as np
import itertools

def Amat(kernel, size):
    assert kernel.shape[0] == kernel.shape[1]
    ksize = kernel.shape[0]
    assert ksize % 2
    osize = (size + 1 - ksize)
    A = np.zeros((osize ** 2, size ** 2))
    pos = lambda _1, _2, s: _1 * s + _2

ferrine

ferrine

ferrine

import itertools
import torch


def svd(x):
    # https://discuss.pytorch.org/t/multidimensional-svd/4366/2
    batches = x.shape[:-2]
    if batches:
        n, m = x.shape[-2:]
        k = min(n, m)

ferrine

ferrine

ferrine

import torch
def map_nested(fn, structure, cond=lambda obj: isinstance(obj, torch.Tensor)):
    r"""
    Applies fn to an object in a possibly nested data structure and returns same
    structure with every element changed if condition satisfied.
    """

    def inner_map(obj):
        if cond(obj):
            return fn(obj)

ferrine

import torch.nn
import collections

class Builder(object):
    def __init__(self, *namespaces):
        self._namespace = collections.ChainMap(*namespaces)

    def __call__(self, name, *args, **kwargs):
        try:
            return self._namespace[name](*args, **kwargs)

ferrine

import sacred.observers
import tensorboardX
import os


class TensorboardObserver(sacred.observers.FileStorageObserver, tensorboardX.SummaryWriter):
    VERSION = "TensorboardObserver-0.0.1"

    def __init__(self, basedir, resource_dir=None, source_dir=None,
                 template=None, priority=sacred.observers.file_storage.DEFAULT_FILE_STORAGE_PRIORITY,

ferrine