#!/usr/bin/env python
# encoding: utf-8

from __future__ import print_function
from functions import conv2d_forward, conv2d_backward, avgpool2d_forward, avgpool2d_backward
import numpy as np


def get_fake_data():
    inp = np.array([[[[1, 8, 2, 8, 6, 0],
                     [4, 1, 3, 1, 1, 1],
                     [3, 2, 0, 5, 4, 7],
                     [7, 6, 7, 2, 4, 4],
                     [3, 8, 6, 4, 7, 9],
                     [9, 2, 8, 4, 3, 4]],

                    [[8, 5, 3, 4, 0, 6],
                     [2, 9, 6, 0, 9, 9],
                     [4, 5, 0, 1, 7, 3],
                     [8, 5, 7, 1, 8, 6],
                     [9, 6, 2, 7, 7, 5],
                     [1, 3, 5, 5, 7, 3]],

                    [[1, 3, 3, 5, 0, 8],
                     [1, 7, 9, 0, 9, 9],
                     [7, 5, 2, 3, 5, 3],
                     [8, 1, 8, 8, 0, 2],
                     [9, 4, 2, 7, 7, 3],
                     [3, 3, 4, 9, 1, 7]]],


                   [[[1, 7, 4, 4, 3, 2],
                     [5, 5, 1, 2, 6, 1],
                     [3, 8, 4, 2, 0, 6],
                     [7, 3, 4, 8, 1, 9],
                     [6, 6, 9, 1, 9, 7],
                     [6, 7, 3, 9, 2, 3]],

                    [[9, 6, 8, 0, 2, 8],
                     [9, 7, 5, 4, 1, 4],
                     [6, 6, 8, 4, 5, 7],
                     [6, 9, 2, 5, 4, 9],
                     [7, 6, 0, 4, 9, 4],
                     [1, 4, 1, 0, 4, 2]],

                    [[1, 9, 3, 3, 5, 6],
                     [8, 0, 5, 9, 5, 7],
                     [8, 2, 5, 2, 1, 1],
                     [5, 3, 6, 3, 2, 8],
                     [4, 7, 0, 7, 1, 9],
                     [7, 4, 5, 4, 2, 6]]],


                   [[[3, 7, 6, 1, 9, 8],
                     [9, 3, 7, 1, 4, 6],
                     [4, 4, 0, 0, 6, 3],
                     [5, 7, 2, 3, 0, 3],
                     [8, 4, 3, 8, 5, 3],
                     [8, 5, 7, 7, 2, 2]],

                    [[5, 9, 5, 2, 3, 7],
                     [3, 1, 9, 6, 4, 2],
                     [1, 9, 7, 9, 6, 2],
                     [3, 9, 9, 8, 7, 8],
                     [4, 0, 8, 1, 6, 7],
                     [2, 2, 8, 9, 4, 7]],

                    [[0, 1, 6, 9, 5, 2],
                     [5, 4, 7, 9, 8, 9],
                     [0, 5, 6, 8, 5, 8],
                     [4, 0, 0, 3, 6, 8],
                     [8, 7, 3, 2, 8, 6],
                     [7, 3, 0, 0, 5, 2]]],


                   [[[9, 7, 5, 8, 8, 9],
                     [0, 2, 0, 2, 2, 5],
                     [6, 2, 3, 6, 0, 3],
                     [6, 4, 4, 7, 6, 4],
                     [8, 6, 5, 1, 4, 4],
                     [0, 0, 9, 1, 8, 8]],

                    [[8, 5, 9, 4, 0, 5],
                     [2, 0, 6, 6, 9, 5],
                     [9, 6, 0, 7, 4, 0],
                     [5, 6, 5, 4, 3, 7],
                     [2, 2, 4, 0, 6, 4],
                     [1, 9, 1, 1, 7, 9]],

                    [[4, 2, 0, 3, 3, 9],
                     [8, 4, 8, 4, 7, 2],
                     [8, 3, 4, 6, 3, 1],
                     [7, 1, 0, 2, 4, 6],
                     [1, 1, 3, 9, 9, 1],
                     [8, 2, 6, 3, 5, 4]]]])

    w = np.array([[[[7, 4],
                 [0, 9]],

                [[4, 6],
                 [6, 6]],

                [[3, 5],
                 [9, 1]]],


               [[[2, 7],
                 [7, 5]],

                [[3, 7],
                 [9, 3]],

                [[2, 2],
                 [1, 3]]],


               [[[6, 3],
                 [7, 5]],

                [[7, 2],
                 [2, 2]],

                [[6, 3],
                 [5, 2]]],


               [[[0, 7],
                 [3, 3]],

                [[1, 4],
                 [2, 3]],

                [[0, 8],
                 [9, 1]]]])

    b = np.array([9, 5, 5, 6])

    grad_out = np.array([[[[9, 6, 3, 2, 0, 0, 4],
                         [3, 1, 0, 2, 2, 5, 6],
                         [8, 1, 5, 7, 6, 7, 5],
                         [0, 9, 5, 1, 4, 8, 1],
                         [7, 3, 9, 7, 0, 7, 3],
                         [0, 0, 0, 3, 7, 8, 1],
                         [7, 1, 4, 9, 6, 8, 6]],

                        [[8, 8, 7, 0, 7, 6, 7],
                         [4, 2, 2, 3, 5, 2, 1],
                         [3, 9, 3, 3, 9, 4, 5],
                         [6, 8, 3, 7, 3, 8, 2],
                         [9, 3, 8, 6, 4, 3, 4],
                         [6, 8, 5, 1, 0, 3, 1],
                         [4, 2, 8, 5, 4, 5, 4]],

                        [[2, 6, 6, 1, 1, 6, 6],
                         [0, 2, 6, 5, 4, 0, 4],
                         [4, 1, 4, 4, 1, 7, 6],
                         [8, 4, 4, 4, 7, 6, 5],
                         [0, 1, 4, 1, 6, 5, 6],
                         [9, 4, 6, 5, 7, 8, 2],
                         [9, 1, 9, 5, 0, 8, 3]],

                        [[5, 7, 7, 2, 6, 7, 0],
                         [2, 9, 4, 0, 5, 7, 4],
                         [4, 9, 9, 9, 6, 3, 5],
                         [8, 4, 2, 0, 6, 3, 6],
                         [5, 7, 0, 3, 1, 7, 3],
                         [9, 7, 5, 1, 7, 9, 0],
                         [9, 6, 9, 3, 4, 4, 8]]],


                       [[[6, 8, 3, 3, 8, 8, 1],
                         [2, 9, 1, 0, 1, 8, 9],
                         [7, 2, 2, 3, 5, 5, 7],
                         [4, 6, 4, 2, 4, 5, 0],
                         [1, 5, 6, 8, 6, 5, 8],
                         [6, 1, 7, 4, 6, 4, 4],
                         [1, 2, 6, 8, 2, 8, 7]],

                        [[1, 6, 7, 4, 4, 3, 0],
                         [0, 2, 4, 4, 5, 5, 3],
                         [0, 7, 3, 1, 7, 0, 9],
                         [5, 2, 3, 1, 6, 2, 9],
                         [5, 0, 2, 4, 3, 0, 7],
                         [3, 7, 7, 2, 4, 3, 2],
                         [4, 8, 0, 2, 6, 1, 3]],

                        [[4, 3, 0, 2, 9, 9, 1],
                         [7, 7, 2, 9, 7, 2, 1],
                         [1, 3, 4, 4, 1, 4, 6],
                         [0, 5, 0, 9, 3, 7, 8],
                         [7, 1, 7, 8, 1, 6, 4],
                         [5, 3, 4, 5, 3, 7, 4],
                         [5, 4, 8, 7, 3, 3, 3]],

                        [[6, 3, 5, 0, 2, 4, 5],
                         [9, 4, 0, 5, 9, 3, 4],
                         [8, 5, 3, 5, 8, 1, 9],
                         [0, 0, 2, 1, 4, 9, 3],
                         [2, 8, 0, 7, 0, 8, 2],
                         [4, 9, 9, 1, 0, 9, 7],
                         [2, 0, 3, 9, 2, 1, 4]]],


                       [[[5, 3, 1, 7, 9, 5, 5],
                         [0, 3, 4, 2, 9, 3, 5],
                         [2, 2, 4, 5, 5, 6, 5],
                         [0, 9, 6, 3, 2, 3, 5],
                         [6, 6, 9, 3, 8, 5, 1],
                         [7, 4, 0, 6, 8, 5, 2],
                         [7, 3, 8, 8, 2, 6, 8]],

                        [[7, 2, 6, 0, 6, 1, 1],
                         [4, 6, 6, 1, 3, 4, 1],
                         [9, 2, 1, 9, 9, 5, 6],
                         [4, 5, 3, 2, 3, 0, 4],
                         [1, 2, 4, 9, 8, 9, 5],
                         [0, 2, 6, 2, 3, 1, 8],
                         [9, 6, 5, 0, 8, 8, 7]],

                        [[7, 8, 6, 8, 0, 0, 2],
                         [6, 0, 3, 6, 3, 7, 7],
                         [4, 3, 4, 6, 4, 3, 4],
                         [3, 4, 2, 8, 4, 4, 4],
                         [7, 0, 5, 3, 9, 6, 3],
                         [5, 3, 4, 5, 6, 1, 1],
                         [3, 7, 2, 2, 5, 2, 9]],

                        [[3, 4, 1, 2, 3, 3, 9],
                         [1, 9, 2, 0, 2, 2, 2],
                         [8, 4, 9, 8, 9, 5, 0],
                         [8, 2, 8, 1, 7, 0, 2],
                         [6, 3, 7, 4, 6, 4, 2],
                         [9, 6, 7, 8, 0, 5, 7],
                         [6, 1, 6, 3, 4, 7, 7]]],


                       [[[2, 1, 9, 1, 1, 4, 3],
                         [2, 5, 9, 2, 5, 2, 2],
                         [5, 5, 3, 7, 0, 8, 5],
                         [7, 7, 5, 9, 7, 2, 9],
                         [3, 6, 8, 3, 0, 4, 0],
                         [0, 3, 4, 9, 9, 7, 1],
                         [1, 1, 2, 9, 6, 9, 0]],

                        [[8, 2, 9, 8, 4, 1, 8],
                         [2, 2, 5, 6, 7, 0, 9],
                         [7, 4, 3, 8, 7, 4, 2],
                         [6, 5, 6, 1, 6, 2, 6],
                         [2, 9, 4, 6, 1, 4, 0],
                         [7, 2, 6, 3, 9, 6, 6],
                         [9, 7, 0, 7, 6, 7, 1]],

                        [[0, 4, 6, 8, 1, 3, 5],
                         [8, 5, 9, 9, 2, 2, 6],
                         [4, 6, 3, 5, 0, 9, 2],
                         [1, 8, 5, 9, 3, 4, 4],
                         [6, 0, 7, 8, 6, 7, 5],
                         [0, 1, 0, 7, 3, 5, 2],
                         [9, 2, 8, 3, 1, 0, 4]],

                        [[9, 5, 8, 5, 6, 8, 4],
                         [8, 4, 4, 0, 4, 4, 1],
                         [0, 7, 2, 5, 7, 6, 9],
                         [5, 4, 2, 7, 3, 8, 8],
                         [7, 4, 5, 7, 7, 5, 5],
                         [6, 3, 9, 3, 8, 1, 4],
                         [3, 6, 0, 5, 9, 4, 6]]]])

    return inp, w, b, grad_out


def get_conv_answer():
    out = np.array([[[[  67.,  171.,  105.,  155.,  132.,   53.,  117.],
                     [ 115.,  219.,  324.,  251.,  192.,  334.,  192.],
                     [ 100.,  281.,  243.,  157.,  235.,  353.,  124.],
                     [ 199.,  335.,  220.,  202.,  302.,  263.,  133.],
                     [ 215.,  420.,  324.,  279.,  332.,  350.,  124.],
                     [ 210.,  253.,  298.,  299.,  372.,  300.,  182.],
                     [  66.,  126.,  126.,  188.,  143.,  130.,   70.]],

                    [[  37.,  149.,  137.,  116.,  132.,   89.,   67.],
                     [  99.,  230.,  238.,  207.,  151.,  231.,  136.],
                     [  97.,  209.,  199.,   93.,  198.,  289.,  131.],
                     [ 151.,  273.,  206.,  214.,  186.,  264.,  118.],
                     [ 195.,  319.,  304.,  217.,  287.,  299.,  146.],
                     [ 164.,  265.,  218.,  285.,  281.,  293.,  106.],
                     [  81.,   73.,  123.,  125.,  118.,   97.,   36.]],

                    [[  28.,   89.,  108.,   98.,  124.,   75.,   57.],
                     [  53.,  190.,  232.,  186.,  177.,  188.,  165.],
                     [  61.,  185.,  217.,  165.,  155.,  290.,  198.],
                     [ 110.,  271.,  210.,  174.,  193.,  224.,  136.],
                     [ 117.,  326.,  267.,  280.,  240.,  274.,  171.],
                     [ 112.,  290.,  240.,  248.,  290.,  264.,  181.],
                     [  43.,  105.,  102.,  161.,  144.,  117.,   92.]],

                    [[  34.,   76.,   85.,   86.,  101.,   50.,   90.],
                     [  72.,  176.,  181.,  226.,   94.,  235.,  114.],
                     [  78.,  213.,  195.,   58.,  203.,  234.,   69.],
                     [ 152.,  227.,  114.,  193.,  219.,  158.,   51.],
                     [ 196.,  238.,  250.,  175.,  205.,  225.,   76.],
                     [ 168.,  201.,  160.,  226.,  280.,  180.,   92.],
                     [  97.,   57.,  117.,  131.,   68.,  109.,    9.]]],


                   [[[  73.,  180.,  213.,  123.,   80.,  138.,  111.],
                     [ 179.,  377.,  274.,  235.,  265.,  230.,  160.],
                     [ 194.,  384.,  274.,  265.,  194.,  269.,  104.],
                     [ 201.,  321.,  319.,  297.,  172.,  288.,  208.],
                     [ 198.,  353.,  313.,  180.,  355.,  327.,  237.],
                     [ 162.,  346.,  230.,  271.,  228.,  295.,  167.],
                     [  74.,  148.,  129.,  105.,  126.,   99.,   56.]],

                    [[  40.,  174.,  170.,  137.,   72.,  101.,   97.],
                     [ 153.,  315.,  278.,  183.,  171.,  203.,   95.],
                     [ 176.,  289.,  259.,  225.,  168.,  179.,  139.],
                     [ 152.,  306.,  286.,  209.,  189.,  256.,  192.],
                     [ 169.,  315.,  246.,  229.,  206.,  384.,  160.],
                     [ 158.,  261.,  234.,  164.,  256.,  238.,   94.],
                     [  68.,  119.,   77.,   95.,   77.,   72.,   29.]],

                    [[  30.,  100.,  153.,   90.,   77.,   93.,   65.],
                     [  88.,  272.,  254.,  202.,  184.,  203.,  159.],
                     [ 105.,  304.,  236.,  208.,  178.,  171.,  142.],
                     [ 107.,  280.,  240.,  253.,  168.,  185.,  217.],
                     [ 105.,  287.,  272.,  212.,  238.,  267.,  272.],
                     [  95.,  295.,  256.,  192.,  234.,  247.,  184.],
                     [  46.,  131.,  125.,   99.,  103.,   88.,   73.]],

                    [[  37.,   84.,  159.,   76.,   65.,  100.,   82.],
                     [ 107.,  301.,  148.,  151.,  196.,  189.,   88.],
                     [ 176.,  215.,  175.,  206.,  144.,  145.,   51.],
                     [ 159.,  225.,  190.,  172.,  116.,  180.,  130.],
                     [ 162.,  204.,  219.,  157.,  179.,  269.,  125.],
                     [ 136.,  255.,  157.,  172.,  200.,  205.,   77.],
                     [ 108.,  104.,   75.,  102.,   52.,   87.,    8.]]],


                   [[[  66.,  157.,  162.,  123.,  206.,  188.,   69.],
                     [ 155.,  237.,  347.,  321.,  315.,  354.,  192.],
                     [ 130.,  238.,  310.,  358.,  368.,  286.,  170.],
                     [  98.,  307.,  286.,  281.,  277.,  333.,  182.],
                     [ 171.,  289.,  297.,  289.,  256.,  338.,  182.],
                     [ 196.,  291.,  283.,  284.,  272.,  307.,  136.],
                     [  88.,  141.,  137.,  172.,  151.,  114.,   57.]],

                    [[  35.,  136.,  199.,  136.,  108.,  167.,  126.],
                     [ 130.,  265.,  254.,  270.,  251.,  286.,  115.],
                     [ 122.,  177.,  301.,  247.,  267.,  261.,   88.],
                     [  86.,  245.,  278.,  260.,  277.,  228.,  134.],
                     [ 145.,  285.,  206.,  264.,  236.,  282.,  141.],
                     [ 172.,  212.,  225.,  291.,  288.,  223.,  123.],
                     [  89.,   96.,  132.,  155.,   98.,   98.,   34.]],

                    [[  30.,   91.,  129.,  114.,  122.,  157.,   85.],
                     [  85.,  219.,  272.,  283.,  235.,  282.,  205.],
                     [  75.,  211.,  211.,  272.,  261.,  268.,  174.],
                     [  58.,  195.,  249.,  201.,  239.,  241.,  162.],
                     [ 102.,  257.,  234.,  212.,  250.,  267.,  192.],
                     [ 119.,  292.,  210.,  247.,  218.,  241.,  146.],
                     [  54.,  137.,  104.,  142.,  139.,  101.,   78.]],

                    [[  30.,   74.,   93.,  106.,  135.,  131.,   62.],
                     [  88.,  198.,  227.,  230.,  251.,  234.,  116.],
                     [ 136.,  124.,  250.,  221.,  251.,  230.,   93.],
                     [  66.,  216.,  163.,  173.,  200.,  214.,  105.],
                     [ 129.,  217.,  176.,  173.,  175.,  265.,   91.],
                     [ 179.,  209.,  174.,  175.,  192.,  197.,   51.],
                     [ 126.,   75.,   89.,   99.,   85.,   68.,   13.]]],


                   [[[ 142.,  188.,  156.,  162.,  135.,  156.,  120.],
                     [ 133.,  290.,  238.,  317.,  288.,  379.,  167.],
                     [ 177.,  252.,  205.,  259.,  279.,  219.,   79.],
                     [ 218.,  336.,  199.,  257.,  254.,  189.,  129.],
                     [ 183.,  237.,  203.,  188.,  304.,  341.,  116.],
                     [  72.,  251.,  286.,  196.,  292.,  350.,  146.],
                     [  55.,  101.,  123.,  119.,  128.,  214.,  113.]],

                    [[  86.,  200.,  153.,  182.,  149.,  151.,  122.],
                     [ 162.,  191.,  196.,  234.,  231.,  291.,  138.],
                     [ 116.,  217.,  173.,  197.,  258.,  181.,   56.],
                     [ 192.,  257.,  180.,  248.,  222.,  178.,  110.],
                     [ 145.,  232.,  203.,  215.,  187.,  249.,  111.],
                     [ 104.,  137.,  243.,  153.,  208.,  310.,  168.],
                     [  28.,   91.,  118.,   58.,  131.,  179.,   56.]],

                    [[  74.,  153.,  117.,  112.,  130.,  149.,  123.],
                     [  80.,  238.,  189.,  221.,  220.,  241.,  203.],
                     [  97.,  213.,  141.,  222.,  228.,  193.,  108.],
                     [ 119.,  300.,  173.,  182.,  254.,  177.,  101.],
                     [ 100.,  246.,  189.,  180.,  225.,  245.,  155.],
                     [  54.,  162.,  180.,  219.,  204.,  309.,  157.],
                     [  31.,   84.,  127.,  116.,   89.,  186.,  140.]],

                    [[  61.,  123.,   97.,   78.,   92.,  108.,  124.],
                     [ 147.,  185.,  150.,  223.,  184.,  280.,   54.],
                     [ 131.,  189.,  152.,  172.,  219.,  131.,   29.],
                     [ 188.,  199.,  125.,  181.,  131.,  138.,   86.],
                     [ 155.,  133.,  121.,  154.,  219.,  243.,   42.],
                     [  89.,  169.,  155.,  181.,  212.,  202.,   88.],
                     [  74.,   59.,  130.,   42.,  131.,  137.,   15.]]]])

    grad_inp = np.array([[[[ 342.,  384.,  236.,  195.,  292.,  323.],
                         [ 232.,  322.,  303.,  326.,  344.,  302.],
                         [ 441.,  359.,  295.,  354.,  416.,  387.],
                         [ 349.,  396.,  334.,  290.,  349.,  396.],
                         [ 344.,  315.,  340.,  312.,  338.,  364.],
                         [ 370.,  334.,  380.,  287.,  417.,  362.]],

                        [[ 318.,  312.,  184.,  196.,  229.,  281.],
                         [ 222.,  254.,  248.,  277.,  329.,  296.],
                         [ 366.,  338.,  289.,  360.,  365.,  353.],
                         [ 360.,  324.,  304.,  265.,  326.,  309.],
                         [ 300.,  338.,  308.,  244.,  310.,  296.],
                         [ 304.,  278.,  304.,  255.,  373.,  299.]],

                        [[ 255.,  303.,  180.,  143.,  219.,  239.],
                         [ 236.,  231.,  234.,  276.,  310.,  278.],
                         [ 300.,  338.,  298.,  246.,  341.,  296.],
                         [ 301.,  278.,  172.,  276.,  261.,  302.],
                         [ 288.,  260.,  251.,  176.,  369.,  280.],
                         [ 291.,  261.,  296.,  298.,  376.,  212.]]],


                       [[[ 370.,  316.,  219.,  303.,  440.,  335.],
                         [ 288.,  325.,  254.,  312.,  341.,  298.],
                         [ 304.,  228.,  233.,  254.,  316.,  384.],
                         [ 225.,  283.,  301.,  333.,  302.,  433.],
                         [ 233.,  349.,  418.,  301.,  277.,  359.],
                         [ 318.,  356.,  368.,  297.,  335.,  304.]],

                        [[ 336.,  300.,  230.,  283.,  340.,  260.],
                         [ 278.,  267.,  187.,  237.,  327.,  315.],
                         [ 283.,  194.,  211.,  255.,  289.,  374.],
                         [ 201.,  250.,  251.,  288.,  269.,  337.],
                         [ 227.,  307.,  363.,  271.,  258.,  341.],
                         [ 272.,  350.,  312.,  282.,  262.,  265.]],

                        [[ 319.,  239.,  151.,  288.,  350.,  217.],
                         [ 319.,  165.,  198.,  269.,  298.,  275.],
                         [ 184.,  169.,  219.,  237.,  244.,  385.],
                         [ 173.,  235.,  223.,  275.,  285.,  279.],
                         [ 272.,  265.,  384.,  196.,  271.,  301.],
                         [ 231.,  312.,  265.,  267.,  270.,  261.]]],


                       [[[ 292.,  351.,  267.,  280.,  287.,  261.],
                         [ 297.,  266.,  323.,  335.,  428.,  324.],
                         [ 344.,  274.,  397.,  363.,  343.,  270.],
                         [ 268.,  351.,  361.,  388.,  348.,  273.],
                         [ 291.,  274.,  422.,  443.,  406.,  295.],
                         [ 385.,  330.,  327.,  295.,  323.,  413.]],

                        [[ 217.,  279.,  234.,  277.,  290.,  245.],
                         [ 271.,  255.,  259.,  339.,  349.,  270.],
                         [ 262.,  255.,  369.,  334.,  298.,  252.],
                         [ 267.,  318.,  311.,  332.,  315.,  267.],
                         [ 268.,  286.,  361.,  388.,  355.,  247.],
                         [ 354.,  275.,  287.,  298.,  283.,  397.]],

                        [[ 203.,  224.,  254.,  220.,  238.,  267.],
                         [ 271.,  198.,  254.,  316.,  283.,  270.],
                         [ 258.,  275.,  347.,  294.,  285.,  177.],
                         [ 273.,  296.,  274.,  298.,  273.,  222.],
                         [ 268.,  305.,  257.,  398.,  263.,  193.],
                         [ 306.,  213.,  326.,  257.,  244.,  309.]]],


                       [[[ 313.,  387.,  513.,  295.,  233.,  293.],
                         [ 313.,  362.,  419.,  316.,  344.,  328.],
                         [ 406.,  356.,  379.,  411.,  307.,  399.],
                         [ 369.,  444.,  394.,  389.,  335.,  296.],
                         [ 285.,  293.,  493.,  386.,  403.,  279.],
                         [ 231.,  283.,  299.,  437.,  454.,  328.]],

                        [[ 244.,  386.,  433.,  248.,  218.,  275.],
                         [ 292.,  325.,  328.,  309.,  281.,  302.],
                         [ 360.,  314.,  372.,  345.,  308.,  322.],
                         [ 315.,  396.,  362.,  360.,  258.,  308.],
                         [ 283.,  272.,  390.,  301.,  357.,  223.],
                         [ 227.,  278.,  281.,  430.,  396.,  301.]],

                        [[ 262.,  379.,  344.,  208.,  240.,  225.],
                         [ 250.,  332.,  228.,  256.,  254.,  230.],
                         [ 345.,  257.,  312.,  297.,  317.,  335.],
                         [ 305.,  290.,  403.,  293.,  284.,  322.],
                         [ 208.,  263.,  354.,  297.,  341.,  202.],
                         [ 191.,  264.,  270.,  356.,  311.,  214.]]]])

    grad_w = np.array([[[[ 2885.,  3012.],
                         [ 2873.,  2852.]],

                        [[ 3303.,  3335.],
                         [ 2992.,  3215.]],

                        [[ 3111.,  3070.],
                         [ 2846.,  2771.]]],


                       [[[ 2635.,  2698.],
                         [ 2862.,  2756.]],

                        [[ 3032.,  3084.],
                         [ 2990.,  2990.]],

                        [[ 2916.,  2794.],
                         [ 2710.,  2650.]]],


                       [[[ 2703.,  2921.],
                         [ 2794.,  2798.]],

                        [[ 3271.,  2913.],
                         [ 3044.,  3044.]],

                        [[ 2748.,  2933.],
                         [ 2769.,  2881.]]],


                       [[[ 2728.,  3257.],
                         [ 2907.,  3043.]],

                        [[ 3260.,  3458.],
                         [ 3125.,  3379.]],

                        [[ 2980.,  3065.],
                         [ 2763.,  3173.]]]])

    grad_b = np.array([876, 857, 852, 922])

    return out, grad_inp, grad_w, grad_b

def get_pool_data_answer():
    pool_inp = np.array([[[[1, 8, 2, 8, 6, 0],
                         [4, 1, 3, 1, 1, 1],
                         [3, 2, 0, 5, 4, 7],
                         [7, 6, 7, 2, 4, 4],
                         [3, 8, 6, 4, 7, 9],
                         [9, 2, 8, 4, 3, 4]],

                        [[8, 5, 3, 4, 0, 6],
                         [2, 9, 6, 0, 9, 9],
                         [4, 5, 0, 1, 7, 3],
                         [8, 5, 7, 1, 8, 6],
                         [9, 6, 2, 7, 7, 5],
                         [1, 3, 5, 5, 7, 3]],

                        [[1, 3, 3, 5, 0, 8],
                         [1, 7, 9, 0, 9, 9],
                         [7, 5, 2, 3, 5, 3],
                         [8, 1, 8, 8, 0, 2],
                         [9, 4, 2, 7, 7, 3],
                         [3, 3, 4, 9, 1, 7]]],


                       [[[1, 7, 4, 4, 3, 2],
                         [5, 5, 1, 2, 6, 1],
                         [3, 8, 4, 2, 0, 6],
                         [7, 3, 4, 8, 1, 9],
                         [6, 6, 9, 1, 9, 7],
                         [6, 7, 3, 9, 2, 3]],

                        [[9, 6, 8, 0, 2, 8],
                         [9, 7, 5, 4, 1, 4],
                         [6, 6, 8, 4, 5, 7],
                         [6, 9, 2, 5, 4, 9],
                         [7, 6, 0, 4, 9, 4],
                         [1, 4, 1, 0, 4, 2]],

                        [[1, 9, 3, 3, 5, 6],
                         [8, 0, 5, 9, 5, 7],
                         [8, 2, 5, 2, 1, 1],
                         [5, 3, 6, 3, 2, 8],
                         [4, 7, 0, 7, 1, 9],
                         [7, 4, 5, 4, 2, 6]]],


                       [[[3, 7, 6, 1, 9, 8],
                         [9, 3, 7, 1, 4, 6],
                         [4, 4, 0, 0, 6, 3],
                         [5, 7, 2, 3, 0, 3],
                         [8, 4, 3, 8, 5, 3],
                         [8, 5, 7, 7, 2, 2]],

                        [[5, 9, 5, 2, 3, 7],
                         [3, 1, 9, 6, 4, 2],
                         [1, 9, 7, 9, 6, 2],
                         [3, 9, 9, 8, 7, 8],
                         [4, 0, 8, 1, 6, 7],
                         [2, 2, 8, 9, 4, 7]],

                        [[0, 1, 6, 9, 5, 2],
                         [5, 4, 7, 9, 8, 9],
                         [0, 5, 6, 8, 5, 8],
                         [4, 0, 0, 3, 6, 8],
                         [8, 7, 3, 2, 8, 6],
                         [7, 3, 0, 0, 5, 2]]],


                       [[[9, 7, 5, 8, 8, 9],
                         [0, 2, 0, 2, 2, 5],
                         [6, 2, 3, 6, 0, 3],
                         [6, 4, 4, 7, 6, 4],
                         [8, 6, 5, 1, 4, 4],
                         [0, 0, 9, 1, 8, 8]],

                        [[8, 5, 9, 4, 0, 5],
                         [2, 0, 6, 6, 9, 5],
                         [9, 6, 0, 7, 4, 0],
                         [5, 6, 5, 4, 3, 7],
                         [2, 2, 4, 0, 6, 4],
                         [1, 9, 1, 1, 7, 9]],

                        [[4, 2, 0, 3, 3, 9],
                         [8, 4, 8, 4, 7, 2],
                         [8, 3, 4, 6, 3, 1],
                         [7, 1, 0, 2, 4, 6],
                         [1, 1, 3, 9, 9, 1],
                         [8, 2, 6, 3, 5, 4]]]])

    pool_out = np.array([[[[ 0.25,  2.5 ,  3.5 ,  0.  ],
                         [ 1.75,  1.5 ,  2.75,  2.  ],
                         [ 2.5 ,  6.75,  4.25,  3.25],
                         [ 2.25,  2.5 ,  1.75,  1.  ]],

                        [[ 2.  ,  2.  ,  1.  ,  1.5 ],
                         [ 1.5 ,  5.  ,  4.25,  3.  ],
                         [ 4.25,  5.  ,  5.75,  2.75],
                         [ 0.25,  2.  ,  3.  ,  0.75]],

                        [[ 0.25,  1.5 ,  1.25,  2.  ],
                         [ 2.  ,  5.75,  4.25,  3.  ],
                         [ 4.25,  3.75,  5.5 ,  1.25],
                         [ 0.75,  1.75,  2.5 ,  1.75]]],


                       [[[ 0.25,  2.75,  1.75,  0.5 ],
                         [ 2.  ,  4.5 ,  2.5 ,  1.75],
                         [ 3.25,  5.5 ,  4.75,  4.  ],
                         [ 1.5 ,  2.5 ,  2.75,  0.75]],

                        [[ 2.25,  3.5 ,  0.5 ,  2.  ],
                         [ 3.75,  6.5 ,  3.5 ,  2.75],
                         [ 3.25,  4.25,  5.5 ,  3.25],
                         [ 0.25,  1.25,  1.  ,  0.5 ]],

                        [[ 0.25,  3.  ,  2.  ,  1.5 ],
                         [ 4.  ,  3.  ,  4.25,  2.  ],
                         [ 2.25,  4.  ,  3.25,  4.25],
                         [ 1.75,  2.25,  1.5 ,  1.5 ]]],


                       [[[ 0.75,  3.25,  2.5 ,  2.  ],
                         [ 3.25,  3.5 ,  2.75,  2.25],
                         [ 3.25,  4.  ,  4.  ,  1.5 ],
                         [ 2.  ,  3.  ,  2.25,  0.5 ]],

                        [[ 1.25,  3.5 ,  1.25,  1.75],
                         [ 1.  ,  6.5 ,  6.25,  1.  ],
                         [ 1.75,  6.5 ,  5.5 ,  3.75],
                         [ 0.5 ,  2.5 ,  3.25,  1.75]],

                        [[ 0.  ,  1.75,  3.5 ,  0.5 ],
                         [ 1.25,  5.5 ,  7.5 ,  4.25],
                         [ 3.  ,  2.5 ,  4.75,  3.5 ],
                         [ 1.75,  0.75,  1.25,  0.5 ]]],


                       [[[ 2.25,  3.  ,  4.  ,  2.25],
                         [ 1.5 ,  1.75,  2.5 ,  2.  ],
                         [ 3.5 ,  4.75,  4.5 ,  2.  ],
                         [ 0.  ,  2.25,  2.25,  2.  ]],

                        [[ 2.  ,  3.5 ,  1.  ,  1.25],
                         [ 2.75,  3.  ,  6.5 ,  1.25],
                         [ 1.75,  4.25,  3.25,  2.75],
                         [ 0.25,  2.5 ,  2.  ,  2.25]],

                        [[ 1.  ,  0.5 ,  1.5 ,  2.25],
                         [ 4.  ,  4.75,  5.  ,  0.75],
                         [ 2.  ,  1.25,  6.  ,  1.75],
                         [ 2.  ,  2.  ,  2.  ,  1.  ]]]])

    grad_pool_out = np.array([[[[1, 5, 0, 1],
                                 [2, 4, 8, 8],
                                 [6, 8, 1, 4],
                                 [7, 4, 2, 3]],

                                [[6, 1, 1, 6],
                                 [7, 8, 8, 0],
                                 [4, 3, 7, 6],
                                 [2, 6, 2, 2]],

                                [[5, 3, 3, 9],
                                 [4, 4, 6, 0],
                                 [4, 5, 1, 4],
                                 [7, 4, 9, 2]]],


                               [[[1, 3, 0, 3],
                                 [1, 8, 1, 7],
                                 [9, 3, 4, 5],
                                 [0, 1, 5, 3]],

                                [[7, 6, 8, 8],
                                 [4, 8, 3, 9],
                                 [4, 0, 7, 8],
                                 [1, 9, 8, 6]],

                                [[5, 2, 1, 6],
                                 [4, 4, 9, 6],
                                 [8, 7, 4, 3],
                                 [4, 1, 4, 6]]],


                               [[[4, 5, 3, 9],
                                 [0, 7, 4, 8],
                                 [0, 5, 7, 7],
                                 [5, 9, 8, 6]],

                                [[1, 8, 7, 1],
                                 [6, 6, 4, 7],
                                 [6, 1, 9, 5],
                                 [3, 6, 5, 4]],

                                [[8, 3, 8, 7],
                                 [0, 6, 8, 8],
                                 [5, 4, 8, 0],
                                 [5, 7, 5, 6]]],


                               [[[6, 9, 2, 8],
                                 [6, 7, 3, 8],
                                 [3, 0, 5, 1],
                                 [0, 9, 3, 1]],

                                [[8, 8, 2, 6],
                                 [0, 6, 5, 2],
                                 [6, 0, 2, 8],
                                 [4, 4, 5, 3]],

                                [[6, 2, 0, 8],
                                 [5, 1, 4, 9],
                                 [4, 7, 0, 7],
                                 [9, 5, 3, 0]]]])

    grad_pool_inp = np.array([[[[ 0.25,  1.25,  1.25,  0.  ,  0.  ,  0.25],
                             [ 0.5 ,  1.  ,  1.  ,  2.  ,  2.  ,  2.  ],
                             [ 0.5 ,  1.  ,  1.  ,  2.  ,  2.  ,  2.  ],
                             [ 1.5 ,  2.  ,  2.  ,  0.25,  0.25,  1.  ],
                             [ 1.5 ,  2.  ,  2.  ,  0.25,  0.25,  1.  ],
                             [ 1.75,  1.  ,  1.  ,  0.5 ,  0.5 ,  0.75]],

                            [[ 1.5 ,  0.25,  0.25,  0.25,  0.25,  1.5 ],
                             [ 1.75,  2.  ,  2.  ,  2.  ,  2.  ,  0.  ],
                             [ 1.75,  2.  ,  2.  ,  2.  ,  2.  ,  0.  ],
                             [ 1.  ,  0.75,  0.75,  1.75,  1.75,  1.5 ],
                             [ 1.  ,  0.75,  0.75,  1.75,  1.75,  1.5 ],
                             [ 0.5 ,  1.5 ,  1.5 ,  0.5 ,  0.5 ,  0.5 ]],

                            [[ 1.25,  0.75,  0.75,  0.75,  0.75,  2.25],
                             [ 1.  ,  1.  ,  1.  ,  1.5 ,  1.5 ,  0.  ],
                             [ 1.  ,  1.  ,  1.  ,  1.5 ,  1.5 ,  0.  ],
                             [ 1.  ,  1.25,  1.25,  0.25,  0.25,  1.  ],
                             [ 1.  ,  1.25,  1.25,  0.25,  0.25,  1.  ],
                             [ 1.75,  1.  ,  1.  ,  2.25,  2.25,  0.5 ]]],


                           [[[ 0.25,  0.75,  0.75,  0.  ,  0.  ,  0.75],
                             [ 0.25,  2.  ,  2.  ,  0.25,  0.25,  1.75],
                             [ 0.25,  2.  ,  2.  ,  0.25,  0.25,  1.75],
                             [ 2.25,  0.75,  0.75,  1.  ,  1.  ,  1.25],
                             [ 2.25,  0.75,  0.75,  1.  ,  1.  ,  1.25],
                             [ 0.  ,  0.25,  0.25,  1.25,  1.25,  0.75]],

                            [[ 1.75,  1.5 ,  1.5 ,  2.  ,  2.  ,  2.  ],
                             [ 1.  ,  2.  ,  2.  ,  0.75,  0.75,  2.25],
                             [ 1.  ,  2.  ,  2.  ,  0.75,  0.75,  2.25],
                             [ 1.  ,  0.  ,  0.  ,  1.75,  1.75,  2.  ],
                             [ 1.  ,  0.  ,  0.  ,  1.75,  1.75,  2.  ],
                             [ 0.25,  2.25,  2.25,  2.  ,  2.  ,  1.5 ]],

                            [[ 1.25,  0.5 ,  0.5 ,  0.25,  0.25,  1.5 ],
                             [ 1.  ,  1.  ,  1.  ,  2.25,  2.25,  1.5 ],
                             [ 1.  ,  1.  ,  1.  ,  2.25,  2.25,  1.5 ],
                             [ 2.  ,  1.75,  1.75,  1.  ,  1.  ,  0.75],
                             [ 2.  ,  1.75,  1.75,  1.  ,  1.  ,  0.75],
                             [ 1.  ,  0.25,  0.25,  1.  ,  1.  ,  1.5 ]]],


                           [[[ 1.  ,  1.25,  1.25,  0.75,  0.75,  2.25],
                             [ 0.  ,  1.75,  1.75,  1.  ,  1.  ,  2.  ],
                             [ 0.  ,  1.75,  1.75,  1.  ,  1.  ,  2.  ],
                             [ 0.  ,  1.25,  1.25,  1.75,  1.75,  1.75],
                             [ 0.  ,  1.25,  1.25,  1.75,  1.75,  1.75],
                             [ 1.25,  2.25,  2.25,  2.  ,  2.  ,  1.5 ]],

                            [[ 0.25,  2.  ,  2.  ,  1.75,  1.75,  0.25],
                             [ 1.5 ,  1.5 ,  1.5 ,  1.  ,  1.  ,  1.75],
                             [ 1.5 ,  1.5 ,  1.5 ,  1.  ,  1.  ,  1.75],
                             [ 1.5 ,  0.25,  0.25,  2.25,  2.25,  1.25],
                             [ 1.5 ,  0.25,  0.25,  2.25,  2.25,  1.25],
                             [ 0.75,  1.5 ,  1.5 ,  1.25,  1.25,  1.  ]],

                            [[ 2.  ,  0.75,  0.75,  2.  ,  2.  ,  1.75],
                             [ 0.  ,  1.5 ,  1.5 ,  2.  ,  2.  ,  2.  ],
                             [ 0.  ,  1.5 ,  1.5 ,  2.  ,  2.  ,  2.  ],
                             [ 1.25,  1.  ,  1.  ,  2.  ,  2.  ,  0.  ],
                             [ 1.25,  1.  ,  1.  ,  2.  ,  2.  ,  0.  ],
                             [ 1.25,  1.75,  1.75,  1.25,  1.25,  1.5 ]]],


                           [[[ 1.5 ,  2.25,  2.25,  0.5 ,  0.5 ,  2.  ],
                             [ 1.5 ,  1.75,  1.75,  0.75,  0.75,  2.  ],
                             [ 1.5 ,  1.75,  1.75,  0.75,  0.75,  2.  ],
                             [ 0.75,  0.  ,  0.  ,  1.25,  1.25,  0.25],
                             [ 0.75,  0.  ,  0.  ,  1.25,  1.25,  0.25],
                             [ 0.  ,  2.25,  2.25,  0.75,  0.75,  0.25]],

                            [[ 2.  ,  2.  ,  2.  ,  0.5 ,  0.5 ,  1.5 ],
                             [ 0.  ,  1.5 ,  1.5 ,  1.25,  1.25,  0.5 ],
                             [ 0.  ,  1.5 ,  1.5 ,  1.25,  1.25,  0.5 ],
                             [ 1.5 ,  0.  ,  0.  ,  0.5 ,  0.5 ,  2.  ],
                             [ 1.5 ,  0.  ,  0.  ,  0.5 ,  0.5 ,  2.  ],
                             [ 1.  ,  1.  ,  1.  ,  1.25,  1.25,  0.75]],

                            [[ 1.5 ,  0.5 ,  0.5 ,  0.  ,  0.  ,  2.  ],
                             [ 1.25,  0.25,  0.25,  1.  ,  1.  ,  2.25],
                             [ 1.25,  0.25,  0.25,  1.  ,  1.  ,  2.25],
                             [ 1.  ,  1.75,  1.75,  0.  ,  0.  ,  1.75],
                             [ 1.  ,  1.75,  1.75,  0.  ,  0.  ,  1.75],
                             [ 2.25,  1.25,  1.25,  0.75,  0.75,  0.  ]]]])

    return pool_inp, pool_out, grad_pool_out, grad_pool_inp

inp, w, b, grad_out = get_fake_data()
out, grad_inp, grad_w, grad_b = get_conv_answer()

pool_inp, pool_out, grad_pool_out, grad_pool_inp = get_pool_data_answer()

try:
    test_conv_out = conv2d_forward(inp, w, b, 2, 1)
except:
    print('[FAILED] conv2d_forward: bug in codes, can not run for inp.shape = (4, 3, 6, 6), w.shape = (4, 3, 2, 2), ker_size = 2, pad = 1')
else:
    if test_conv_out.shape != out.shape:
        print('[ERROR] conv2d_forward: output shape is not correct')
    else:
        diff = test_conv_out - out
        if abs(diff).max() > 1e-5:
            print('[ERROR] conv2d_forward: output value is not correct')
        else:
            print('[PASS] conv2d_forward: all correct')

flag = 1

try:
    test_grad_inp, test_grad_w, test_grad_b = conv2d_backward(inp, grad_out, w, b, 2, 1)
except:
    print('[FAILED] conv2d_backward: bug in codes, can not run for inp.shape = (4, 3, 6, 6), grad.shape = (4, 4, 7, 7), w.shape = (4, 3, 2, 2), ker_size = 2, pad = 1')
    flag = 0
else:
    if test_grad_inp.shape != grad_inp.shape:
        print('[ERROR] conv2d_backward: grad_input shape is not correct')
        flag = 0
    else:
        diff = test_grad_inp - grad_inp
        if abs(diff).max() > 1e-5:
            print('[ERROR] conv2d_backward: grad_input value is not correct')
            flag = 0

    if test_grad_w.shape != grad_w.shape:
        print('[ERROR] conv2d_backward: grad_w shape is not correct')
        flag = 0
    else:
        diff = test_grad_w - grad_w
        if abs(diff).max() > 1e-5:
            print('[ERROR] conv2d_backward: grad_w value is not correct')
            flag = 0

    if test_grad_b.shape != grad_b.shape:
        print('[ERROR] conv2d_backward: grad_b shape is not correct')
        flag = 0
    else:
        diff = test_grad_b - grad_b
        if abs(diff).max() > 1e-5:
            print('[ERROR] conv2d_backward: grad_b value is not correct')
            flag = 0
finally:
    if flag:
        print('[PASS] conv2d_backward: all correct')

try:
    test_pool_out = avgpool2d_forward(pool_inp, 2, 1)
except:
    print('[FAILED] avgpool2d_forward: bug in codes, can not run for inp.shape = (4, 3, 6, 6), ker_size = 2, pad = 1')
else:
    if test_pool_out.shape != pool_out.shape:
        print('[ERROR] avgpool2d_forward: output shape is not correct')
    else:
        diff = test_pool_out - pool_out
        if abs(diff).max() > 1e-5:
            print('[ERROR] avgpool2d_forward: output value is not correct')
        else:
            print('[PASS] avgpool2d_forward: all correct')

try:
    test_grad_pool_inp = avgpool2d_backward(pool_inp, grad_pool_out, 2, 1)
except:
    print('[FAILED] avgpool2d_backward: bug in codes, can not run for inp.shape = (4, 3, 6, 6), grad.shape = (4, 3, 4, 4), ker_size = 2, pad = 1')
else:
    if test_grad_pool_inp.shape != grad_pool_inp.shape:
        print('[ERROR] avgpool2d_backward: grad input shape is not correct')
    else:
        diff = test_grad_pool_inp - grad_pool_inp
        if abs(diff).max() > 1e-5:
            print('[ERROR] avgpool2d_backward: grad input value is not correct')
        else:
            print('[PASS] avgpool2d_backward: all correct')