lromor

# Copyright (C) 2022 Leonardo Romor
#
# This program is free software: you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation, either version 3 of the License, or
# (at your option) any later version.
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the

daydreamt

import jax
import jax.numpy as np
from jax.experimental import stax
from jax.experimental import optimizers
from jax.experimental.stax import Dense, Relu, Tanh, Softmax, LogSoftmax
from jax import jit, grad, random

import time
import itertools

z-a-f

import imageio
import numpy as np
import os

from collections import defaultdict
from torch.utils.data import Dataset

from tqdm.autonotebook import tqdm

dir_structure_help = r"""

lgeiger

from __future__ import absolute_import
from __future__ import division
from __future__ import print_function

from tensorflow.python.eager import context
from tensorflow.python.ops import control_flow_ops
from tensorflow.python.ops import math_ops
from tensorflow.python.ops import state_ops
from tensorflow.python.framework import ops
from tensorflow.python.training import optimizer

dpressel

import torch
import torch.nn as nn

class Highway(nn.Module):

    def __init__(self, input_size):
        super(Highway, self).__init__()
        self.proj = nn.Linear(input_size, input_size)
        self.transform = nn.Linear(input_size, input_size)
        self.transform.bias.data.fill_(-2.0)

vvanirudh

# Drawn from https://gist.github.com/rocknrollnerd/c5af642cf217971d93f499e8f70fcb72 (in Theano)
# This is implemented in PyTorch
# Author : Anirudh Vemula

import torch
import torch.nn as nn
from torch.autograd import Variable
import numpy as np

from sklearn.datasets import fetch_mldata

dpressel

# This is a stack of res conns
def skip_conns(inputs, wsz_all, n):
    for i in range(n):
        with tf.variable_scope("skip-%d" % i):
            W_p = tf.get_variable("W_p", [wsz_all, wsz_all])
            b_p = tf.get_variable("B_p", [1, wsz_all], initializer=tf.constant_initializer(0.0))
            proj = tf.nn.relu(tf.matmul(inputs, W_p) + b_p, "relu")

        inputs = inputs + proj

GaelVaroquaux

'''
Non-parametric computation of entropy and mutual-information

Adapted by G Varoquaux for code created by R Brette, itself
from several papers (see in the code).

This code is maintained at https://github.com/mutualinfo/mutual_info 
Please download the latest code there, to have improvements and 
bug fixes.