xmodar

import torch

def _indexer_into(x, dim=0, keepdim=False):
    '''indexes into x along dim.'''
    def indexer(i):
        # (e.g., x[:, 2, :] is indexer(2) if dim == 1)
        out = x[[slice(None, None)] * dim + [i, ...]]
        return out.unsqueeze(dim) if keepdim and x.dim() != out.dim() else out
    return indexer

xmodar

import torch
import tensorflow as tf


def histogram_summary(name, array):
    if not hasattr(histogram_summary, 'session'):
        histogram_summary.placeholder = tf.placeholder(tf.float32)
        histogram_summary.session = tf.Session()
        histogram_summary.histograms = {}
    if name not in histogram_summary.histograms:

xmodar

# sfbvc stands for single file branch version control.
#
# By Modar Alfadly <https://modar.me> on the 24th Jan 2019
#
# sfbvc is a convention to create an orphan branch for each file in a repository
# and the master branch will be the merge of all the other branches.
# This is a niche convention which is trying to simulate file history
# in applications similar to cloud storages like Google Drive and Dropbox.
# We are using git under the hood and assuming that it is installed and in PATH.
#

xmodar

#Python Cheat Sheet

#Any thing preceded by a '#' is a comment and won't be executed like this line here

#Variables are names defined by the programmer that hold values
WonderfulVariableByMe = 5
#There are some reserved words like: for, if, def, while, break, ... that cannot be used to name a variable
#A variable name must not contain spaces and must never start with a number
#Variable names are case-sensitive: modar does not equal Modar

xmodar

xmodar

from torch.nn import functional as F
from torchvision.transforms.functional import normalize


def denormalize_conv2d(weight, bias, mean, std):
    weight, bias = weight.data, bias.data
    std = torch.as_tensor(std).data.view(1, -1, 1, 1)
    mean = torch.as_tensor(mean).data.view(1, -1, 1, 1)
    w = weight / std
    b = bias - (w * mean).flatten(1).sum(1) 

xmodar

import torch

def polynomial(coefficients, x):
    """Evaluate polynomials using Horner method.

    The coefficients are from highest to lowest order.

    Args:
        coefficients: Tensor of size (N, *K).
            K is any broadcastable size to `x.size()`.

xmodar

from collections import namedtuple
from types import MethodType, FunctionType


# using neither typing.NamedTuple nor dataclasses.dataclass
def named_tuple(function, field_names, *args, name=None, **kwargs):
    """Memoize namedtuple types for function outputs."""
    if isinstance(function, MethodType):
        function = function.__func__
    assert isinstance(function, FunctionType)

xmodar

from collections import namedtuple

import numpy as np


class PCA:
    def __init__(self, features, variance=None):
        if variance is None:
            pca = self.fit(features).pca
            features = pca.projection_matrix

xmodar