xmodar

import gc
import math
import time
import datetime
from contextlib import contextmanager

import torch


class Monitor:

xmodar

import ssl
import urllib
from pathlib import Path

import torch
from torch.utils.data import Dataset
from torchvision.datasets.utils import extract_archive, check_integrity

import h5py
import pandas as pd

xmodar

import math


def chunk_dim(tensor, chunks, dim=0):
    """Split a dimension of a tensor into two dimensions"""
    shape = list(tensor.shape)
    shape[dim] //= chunks
    shape.insert(dim, chunks)
    return tensor.view(shape)

xmodar

"""Frechet's distance between two multi-variate Gaussians"""
import torch
import torch.nn as nn


class FrechetDistance:
    """Frechet's distance between two multi-variate Gaussians
    https://www.sciencedirect.com/science/article/pii/0047259X8290077X
    """
    def __init__(self, double=True, num_iterations=20, eps=1e-12):

xmodar

from typing import Tuple, Optional, Union, List

import torch
import torch.nn as nn

__all__ = [
    'dot', 'get_neighbors', 'gather_features', 'point_sparsity',
    'weighted_sampling'
]

xmodar

import itertools
from typing import Tuple, Optional
from contextlib import contextmanager

import torch
from torch.utils import benchmark


# @torch.jit.script
def nearest_neighbors(

xmodar

"""Utilities for argparse arguments."""
import os
import sys
from argparse import Namespace
from collections import OrderedDict
from itertools import product, chain
from typing import Union, Dict

__all__ = ['parse_grid']

xmodar

#!/usr/bin/env python3
"""Ego4D video box blur."""
import gc
import json
from pathlib import Path
from argparse import ArgumentParser

# conda install av pillow tqdm -c conda-forge -c anaconda
import av  # used versions: av=8.0.3 and ffmpeg=4.3.1
from tqdm import tqdm  # used versions: tqdm=4.59.0

xmodar

"""YOLOv3 object detector."""
import math
from pathlib import Path
from urllib.request import urlopen

from PIL import Image
from PIL import ImageColor, ImageOps

import matplotlib.pyplot as plt
import matplotlib.patches as patches

xmodar

from functools import partial

import torch
from torch import nn
from torch.autograd import grad
from torch.autograd.functional import jacobian, jvp


def rand_cov(vector):
    """Create a covariance matrix from the specs of a given vector."""