AI03-Topic01, Deep learning

# coding: utf-8
import numpy as np


def identity_function(x):
    return x


def step_function(x):
    return np.array(x > 0, dtype=np.int)


def sigmoid(x):
    return 1 / (1 + np.exp(-x))    


def sigmoid_grad(x):
    return (1.0 - sigmoid(x)) * sigmoid(x)
    

def relu(x):
    return np.maximum(0, x)


def relu_grad(x):
    grad = np.zeros(x)
    grad[x>=0] = 1
    return grad
    

def softmax(x):
    if x.ndim == 2:
        x = x.T
        x = x - np.max(x, axis=0)
        y = np.exp(x) / np.sum(np.exp(x), axis=0)
        return y.T 

    x = x - np.max(x) # オーバーフロー対策
    return np.exp(x) / np.sum(np.exp(x))


def mean_squared_error(y, t):
    return 0.5 * np.sum((y-t)**2)


def cross_entropy_error(y, t):
    if y.ndim == 1:
        t = t.reshape(1, t.size)
        y = y.reshape(1, y.size)
        
    # 教師データがone-hot-vectorの場合、正解ラベルのインデックスに変換
    if t.size == y.size:
        t = t.argmax(axis=1)
             
    batch_size = y.shape[0]
    return -np.sum(np.log(y[np.arange(batch_size), t] + 1e-7)) / batch_size


def softmax_loss(X, t):
    y = softmax(X)
    return cross_entropy_error(y, t)

# coding: utf-8
import numpy as np

def _numerical_gradient_1d(f, x):
    h = 1e-4 # 0.0001
    grad = np.zeros_like(x)
    
    for idx in range(x.size):
        tmp_val = x[idx]
        x[idx] = float(tmp_val) + h
        fxh1 = f(x) # f(x+h)
        
        x[idx] = tmp_val - h 
        fxh2 = f(x) # f(x-h)
        grad[idx] = (fxh1 - fxh2) / (2*h)
        
        x[idx] = tmp_val # 値を元に戻す
        
    return grad


def numerical_gradient_2d(f, X):
    if X.ndim == 1:
        return _numerical_gradient_1d(f, X)
    else:
        grad = np.zeros_like(X)
        
        for idx, x in enumerate(X):
            grad[idx] = _numerical_gradient_1d(f, x)
        
        return grad


def numerical_gradient(f, x):
    h = 1e-4 # 0.0001
    grad = np.zeros_like(x)
    
    it = np.nditer(x, flags=['multi_index'], op_flags=['readwrite'])
    while not it.finished:
        idx = it.multi_index
        tmp_val = x[idx]
        x[idx] = float(tmp_val) + h
        fxh1 = f(x) # f(x+h)
        
        x[idx] = tmp_val - h 
        fxh2 = f(x) # f(x-h)
        grad[idx] = (fxh1 - fxh2) / (2*h)
        
        x[idx] = tmp_val # 値を元に戻す
        it.iternext()   
        
    return grad

# coding: utf-8
import numpy as np
from common.functions import *
from common.util import im2col, col2im


class Relu:
    def __init__(self):
        self.mask = None

    def forward(self, x):
        self.mask = (x <= 0)
        out = x.copy()
        out[self.mask] = 0

        return out

    def backward(self, dout):
        dout[self.mask] = 0
        dx = dout

        return dx


class Sigmoid:
    def __init__(self):
        self.out = None

    def forward(self, x):
        out = sigmoid(x)
        self.out = out
        return out

    def backward(self, dout):
        dx = dout * (1.0 - self.out) * self.out

        return dx


class Affine:
    def __init__(self, W, b):
        self.W =W
        self.b = b
        
        self.x = None
        self.original_x_shape = None
        # 重み・バイアスパラメータの微分
        self.dW = None
        self.db = None

    def forward(self, x):
        # テンソル対応
        self.original_x_shape = x.shape
        x = x.reshape(x.shape[0], -1)
        self.x = x

        out = np.dot(self.x, self.W) + self.b

        return out

    def backward(self, dout):
        dx = np.dot(dout, self.W.T)
        self.dW = np.dot(self.x.T, dout)
        self.db = np.sum(dout, axis=0)
        
        dx = dx.reshape(*self.original_x_shape)  # 入力データの形状に戻す（テンソル対応）
        return dx


class SoftmaxWithLoss:
    def __init__(self):
        self.loss = None
        self.y = None # softmaxの出力
        self.t = None # 教師データ

    def forward(self, x, t):
        self.t = t
        self.y = softmax(x)
        self.loss = cross_entropy_error(self.y, self.t)
        
        return self.loss

# coding: utf-8
import sys, os
sys.path.append(os.pardir)  # 親ディレクトリのファイルをインポートするための設定
import numpy as np
from collections import OrderedDict
from common.layers import *
from common.gradient import numerical_gradient


class MultiLayerNet:
    """全結合による多層ニューラルネットワーク

    Parameters
    ----------
    input_size : 入力サイズ（MNISTの場合は784）
    hidden_size_list : 隠れ層のニューロンの数のリスト（e.g. [100, 100, 100]）
    output_size : 出力サイズ（MNISTの場合は10）
    activation : 'relu' or 'sigmoid'
    weight_init_std : 重みの標準偏差を指定（e.g. 0.01）
        'relu'または'he'を指定した場合は「Heの初期値」を設定
        'sigmoid'または'xavier'を指定した場合は「Xavierの初期値」を設定
    weight_decay_lambda : Weight Decay（L2ノルム）の強さ
    """
    def __init__(self, input_size, hidden_size_list, output_size,
                 activation='relu', weight_init_std='relu', weight_decay_lambda=0):
        self.input_size = input_size
        self.output_size = output_size
        self.hidden_size_list = hidden_size_list
        self.hidden_layer_num = len(hidden_size_list)
        self.weight_decay_lambda = weight_decay_lambda
        self.params = {}

        # 重みの初期化
        self.__init_weight(weight_init_std)

        # レイヤの生成
        activation_layer = {'sigmoid': Sigmoid, 'relu': Relu}
        self.layers = OrderedDict()
        for idx in range(1, self.hidden_layer_num+1):
            self.layers['Affine' + str(idx)] = Affine(self.params['W' + str(idx)],
                                                      self.params['b' + str(idx)])
            self.layers['Activation_function' + str(idx)] = activation_layer[activation]()

        idx = self.hidden_layer_num + 1
        self.layers['Affine' + str(idx)] = Affine(self.params['W' + str(idx)],
            self.params['b' + str(idx)])

        self.last_layer = SoftmaxWithLoss()

    def __init_weight(self, weight_init_std):
        """重みの初期値設定

        Parameters
        ----------
        weight_init_std : 重みの標準偏差を指定（e.g. 0.01）
            'relu'または'he'を指定した場合は「Heの初期値」を設定
            'sigmoid'または'xavier'を指定した場合は「Xavierの初期値」を設定
        """
        all_size_list = [self.input_size] + self.hidden_size_list + [self.output_size]
        for idx in range(1, len(all_size_list)):
            scale = weight_init_std
            if str(weight_init_std).lower() in ('relu', 'he'):
                scale = np.sqrt(2.0 / all_size_list[idx - 1])  # ReLUを使う場合に推奨される初期値
            elif str(weight_init_std).lower() in ('sigmoid', 'xavier'):
                scale = np.sqrt(1.0 / all_size_list[idx - 1])  # sigmoidを使う場合に推奨される初期値

            self.params['W' + str(idx)] = scale * np.random.randn(all_size_list[idx-1], all_size_list[idx])
            self.params['b' + str(idx)] = np.zeros(all_size_list[idx])

    def predict(self, x):
        for layer in self.layers.values():
            x = layer.forward(x)

        return x

    def loss(self, x, t):
        """損失関数を求める

        Parameters
        ----------
        x : 入力データ
        t : 教師ラベル

        Returns
        -------
        損失関数の値
        """
        y = self.predict(x)

        weight_decay = 0
        for idx in range(1, self.hidden_layer_num + 2):
            W = self.params['W' + str(idx)]
            weight_decay += 0.5 * self.weight_decay_lambda * np.sum(W ** 2)

        return self.last_layer.forward(y, t) + weight_decay

    def accuracy(self, x, t):
        y = self.predict(x)
        y = np.argmax(y, axis=1)
        if t.ndim != 1 : t = np.argmax(t, axis=1)

        accuracy = np.sum(y == t) / float(x.shape[0])
        return accuracy

    def numerical_gradient(self, x, t):
        """勾配を求める（数値微分）

        Parameters
        ----------
        x : 入力データ
        t : 教師ラベル

        Returns
        -------
        各層の勾配を持ったディクショナリ変数
            grads['W1']、grads['W2']、...は各層の重み
            grads['b1']、grads['b2']、...は各層のバイアス
        """
        loss_W = lambda W: self.loss(x, t)

        grads = {}
        for idx in range(1, self.hidden_layer_num+2):
            grads['W' + str(idx)] = numerical_gradient(loss_W, self.params['W' + str(idx)])
            grads['b' + str(idx)] = numerical_gradient(loss_W, self.params['b' + str(idx)])

        return grads

    def gradient(self, x, t):
        """勾配を求める（誤差逆伝搬法）

        Parameters
        ----------
        x : 入力データ
        t : 教師ラベル

        Returns
        -------
        各層の勾配を持ったディクショナリ変数
            grads['W1']、grads['W2']、...は各層の重み
            grads['b1']、grads['b2']、...は各層のバイアス
        """
        # forward
        self.loss(x, t)

        # backward
        dout = 1
        dout = self.last_layer.backward(dout)

        layers = list(self.layers.values())
        layers.reverse()
        for layer in layers:
            dout = layer.backward(dout)

        # 設定
        grads = {}
        for idx in range(1, self.hidden_layer_num+2):
            grads['W' + str(idx)] = self.layers['Affine' + str(idx)].dW + self.weight_decay_lambda * self.layers['Affine' + str(idx)].W
            grads['b' + str(idx)] = self.layers['Affine' + str(idx)].db

        return grads

# coding: utf-8
import sys, os
sys.path.append(os.pardir) # 親ディレクトリのファイルをインポートするための設定
import numpy as np
from collections import OrderedDict
from common.layers import *
from common.gradient import numerical_gradient

class MultiLayerNetExtend:
    """拡張版の全結合による多層ニューラルネットワーク
    
    Weiht Decay、Dropout、Batch Normalizationの機能を持つ

    Parameters
    ----------
    input_size : 入力サイズ（MNISTの場合は784）
    hidden_size_list : 隠れ層のニューロンの数のリスト（e.g. [100, 100, 100]）
    output_size : 出力サイズ（MNISTの場合は10）
    activation : 'relu' or 'sigmoid'
    weight_init_std : 重みの標準偏差を指定（e.g. 0.01）
        'relu'または'he'を指定した場合は「Heの初期値」を設定
        'sigmoid'または'xavier'を指定した場合は「Xavierの初期値」を設定
    weight_decay_lambda : Weight Decay（L2ノルム）の強さ
    use_dropout: Dropoutを使用するかどうか
    dropout_ration : Dropoutの割り合い
    use_batchNorm: Batch Normalizationを使用するかどうか
    """
    def __init__(self, input_size, hidden_size_list, output_size,
                 activation='relu', weight_init_std='relu', weight_decay_lambda=0, 
                 use_dropout = False, dropout_ration = 0.5, use_batchnorm=False):
        self.input_size = input_size
        self.output_size = output_size
        self.hidden_size_list = hidden_size_list
        self.hidden_layer_num = len(hidden_size_list)
        self.use_dropout = use_dropout
        self.weight_decay_lambda = weight_decay_lambda
        self.use_batchnorm = use_batchnorm
        self.params = {}

        # 重みの初期化
        self.__init_weight(weight_init_std)

        # レイヤの生成
        activation_layer = {'sigmoid': Sigmoid, 'relu': Relu}
        self.layers = OrderedDict()
        for idx in range(1, self.hidden_layer_num+1):
            self.layers['Affine' + str(idx)] = Affine(self.params['W' + str(idx)],
                                                      self.params['b' + str(idx)])
            if self.use_batchnorm:
                self.params['gamma' + str(idx)] = np.ones(hidden_size_list[idx-1])
                self.params['beta' + str(idx)] = np.zeros(hidden_size_list[idx-1])
                self.layers['BatchNorm' + str(idx)] = BatchNormalization(self.params['gamma' + str(idx)], self.params['beta' + str(idx)])
                
            self.layers['Activation_function' + str(idx)] = activation_layer[activation]()
            
            if self.use_dropout:
                self.layers['Dropout' + str(idx)] = Dropout(dropout_ration)

        idx = self.hidden_layer_num + 1
        self.layers['Affine' + str(idx)] = Affine(self.params['W' + str(idx)], self.params['b' + str(idx)])

        self.last_layer = SoftmaxWithLoss()

    def __init_weight(self, weight_init_std):
        """重みの初期値設定

        Parameters
        ----------
        weight_init_std : 重みの標準偏差を指定（e.g. 0.01）
            'relu'または'he'を指定した場合は「Heの初期値」を設定
            'sigmoid'または'xavier'を指定した場合は「Xavierの初期値」を設定
        """
        all_size_list = [self.input_size] + self.hidden_size_list + [self.output_size]
        for idx in range(1, len(all_size_list)):
            scale = weight_init_std
            if str(weight_init_std).lower() in ('relu', 'he'):
                scale = np.sqrt(2.0 / all_size_list[idx - 1])  # ReLUを使う場合に推奨される初期値
            elif str(weight_init_std).lower() in ('sigmoid', 'xavier'):
                scale = np.sqrt(1.0 / all_size_list[idx - 1])  # sigmoidを使う場合に推奨される初期値
            self.params['W' + str(idx)] = scale * np.random.randn(all_size_list[idx-1], all_size_list[idx])
            self.params['b' + str(idx)] = np.zeros(all_size_list[idx])

    def predict(self, x, train_flg=False):
        for key, layer in self.layers.items():
            if "Dropout" in key or "BatchNorm" in key:
                x = layer.forward(x, train_flg)
            else:
                x = layer.forward(x)

        return x

    def loss(self, x, t, train_flg=False):
        """損失関数を求める
        引数のxは入力データ、tは教師ラベル
        """
        y = self.predict(x, train_flg)

        weight_decay = 0
        for idx in range(1, self.hidden_layer_num + 2):
            W = self.params['W' + str(idx)]
            weight_decay += 0.5 * self.weight_decay_lambda * np.sum(W**2)

        return self.last_layer.forward(y, t) + weight_decay

    def accuracy(self, X, T):
        Y = self.predict(X, train_flg=False)
        Y = np.argmax(Y, axis=1)
        if T.ndim != 1 : T = np.argmax(T, axis=1)

        accuracy = np.sum(Y == T) / float(X.shape[0])
        return accuracy

    def numerical_gradient(self, X, T):
        """勾配を求める（数値微分）

        Parameters
        ----------
        X : 入力データ
        T : 教師ラベル

        Returns
        -------
        各層の勾配を持ったディクショナリ変数
            grads['W1']、grads['W2']、...は各層の重み
            grads['b1']、grads['b2']、...は各層のバイアス
        """
        loss_W = lambda W: self.loss(X, T, train_flg=True)

        grads = {}
        for idx in range(1, self.hidden_layer_num+2):
            grads['W' + str(idx)] = numerical_gradient(loss_W, self.params['W' + str(idx)])
            grads['b' + str(idx)] = numerical_gradient(loss_W, self.params['b' + str(idx)])
            
            if self.use_batchnorm and idx != self.hidden_layer_num+1:
                grads['gamma' + str(idx)] = numerical_gradient(loss_W, self.params['gamma' + str(idx)])
                grads['beta' + str(idx)] = numerical_gradient(loss_W, self.params['beta' + str(idx)])

        return grads
        
    def gradient(self, x, t):
        # forward
        self.loss(x, t, train_flg=True)

        # backward
        dout = 1
        dout = self.last_layer.backward(dout)

        layers = list(self.layers.values())
        layers.reverse()
        for layer in layers:
            dout = layer.backward(dout)

        # 設定
        grads = {}
        for idx in range(1, self.hidden_layer_num+2):
            grads['W' + str(idx)] = self.layers['Affine' + str(idx)].dW + self.weight_decay_lambda * self.params['W' + str(idx)]
            grads['b' + str(idx)] = self.layers['Affine' + str(idx)].db

            if self.use_batchnorm and idx != self.hidden_layer_num+1:
                grads['gamma' + str(idx)] = self.layers['BatchNorm' + str(idx)].dgamma
                grads['beta' + str(idx)] = self.layers['BatchNorm' + str(idx)].dbeta

        return grads

# coding: utf-8
import numpy as np

class SGD:

    """確率的勾配降下法（Stochastic Gradient Descent）"""

    def __init__(self, lr=0.01):
        self.lr = lr
        
    def update(self, params, grads):
        for key in params.keys():
            params[key] -= self.lr * grads[key] 


class Momentum:

    """Momentum SGD"""

    def __init__(self, lr=0.01, momentum=0.9):
        self.lr = lr
        self.momentum = momentum
        self.v = None
        
    def update(self, params, grads):
        if self.v is None:
            self.v = {}
            for key, val in params.items():                                
                self.v[key] = np.zeros_like(val)
                
        for key in params.keys():
            self.v[key] = self.momentum*self.v[key] - self.lr*grads[key] 
            params[key] += self.v[key]


class Nesterov:

    """Nesterov's Accelerated Gradient (http://arxiv.org/abs/1212.0901)"""

    def __init__(self, lr=0.01, momentum=0.9):
        self.lr = lr
        self.momentum = momentum
        self.v = None
        
    def update(self, params, grads):
        if self.v is None:
            self.v = {}
            for key, val in params.items():
                self.v[key] = np.zeros_like(val)
            
        for key in params.keys():
            self.v[key] *= self.momentum
            self.v[key] -= self.lr * grads[key]
            params[key] += self.momentum * self.momentum * self.v[key]
            params[key] -= (1 + self.momentum) * self.lr * grads[key]


class AdaGrad:

    """AdaGrad"""

    def __init__(self, lr=0.01):
        self.lr = lr
        self.h = None
        
    def update(self, params, grads):
        if self.h is None:
            self.h = {}
            for key, val in params.items():
                self.h[key] = np.zeros_like(val)
            
        for key in params.keys():
            self.h[key] += grads[key] * grads[key]
            params[key] -= self.lr * grads[key] / (np.sqrt(self.h[key]) + 1e-7)


class RMSprop:

    """RMSprop"""

    def __init__(self, lr=0.01, decay_rate = 0.99):
        self.lr = lr
        self.decay_rate = decay_rate
        self.h = None
        
    def update(self, params, grads):
        if self.h is None:
            self.h = {}
            for key, val in params.items():
                self.h[key] = np.zeros_like(val)
            
        for key in params.keys():
            self.h[key] *= self.decay_rate
            self.h[key] += (1 - self.decay_rate) * grads[key] * grads[key]
            params[key] -= self.lr * grads[key] / (np.sqrt(self.h[key]) + 1e-7)


class Adam:

    """Adam (http://arxiv.org/abs/1412.6980v8)"""

    def __init__(self, lr=0.001, beta1=0.9, beta2=0.999):
        self.lr = lr
        self.beta1 = beta1
        self.beta2 = beta2
        self.iter = 0
        self.m = None
        self.v = None
        
    def update(self, params, grads):
        if self.m is None:
            self.m, self.v = {}, {}
            for key, val in params.items():
                self.m[key] = np.zeros_like(val)
                self.v[key] = np.zeros_like(val)
        
        self.iter += 1
        lr_t  = self.lr * np.sqrt(1.0 - self.beta2**self.iter) / (1.0 - self.beta1**self.iter)         
        
        for key in params.keys():
            #self.m[key] = self.beta1*self.m[key] + (1-self.beta1)*grads[key]
            #self.v[key] = self.beta2*self.v[key] + (1-self.beta2)*(grads[key]**2)
            self.m[key] += (1 - self.beta1) * (grads[key] - self.m[key])
            self.v[key] += (1 - self.beta2) * (grads[key]**2 - self.v[key])
            
            params[key] -= lr_t * self.m[key] / (np.sqrt(self.v[key]) + 1e-7)
            
            #unbias_m += (1 - self.beta1) * (grads[key] - self.m[key]) # correct bias
            #unbisa_b += (1 - self.beta2) * (grads[key]*grads[key] - self.v[key]) # correct bias
            #params[key] += self.lr * unbias_m / (np.sqrt(unbisa_b) + 1e-7)

# coding: utf-8
import sys, os
sys.path.append(os.pardir)  # 親ディレクトリのファイルをインポートするための設定
import numpy as np
from common.optimizer import *

class Trainer:
    """ニューラルネットの訓練を行うクラス
    """
    def __init__(self, network, x_train, t_train, x_test, t_test,
                 epochs=20, mini_batch_size=100,
                 optimizer='SGD', optimizer_param={'lr':0.01}, 
                 evaluate_sample_num_per_epoch=None, verbose=True):
        self.network = network
        self.verbose = verbose
        self.x_train = x_train
        self.t_train = t_train
        self.x_test = x_test
        self.t_test = t_test
        self.epochs = epochs
        self.batch_size = mini_batch_size
        self.evaluate_sample_num_per_epoch = evaluate_sample_num_per_epoch

        # optimizer
        optimizer_class_dict = {'sgd':SGD, 'momentum':Momentum, 'nesterov':Nesterov,
                                'adagrad':AdaGrad, 'rmsprpo':RMSprop, 'adam':Adam}
        self.optimizer = optimizer_class_dict[optimizer.lower()](**optimizer_param)
        
        self.train_size = x_train.shape[0]
        self.iter_per_epoch = max(self.train_size / mini_batch_size, 1)
        self.max_iter = int(epochs * self.iter_per_epoch)
        self.current_iter = 0
        self.current_epoch = 0
        
        self.train_loss_list = []
        self.train_acc_list = []
        self.test_acc_list = []

    def train_step(self):
        batch_mask = np.random.choice(self.train_size, self.batch_size)
        x_batch = self.x_train[batch_mask]
        t_batch = self.t_train[batch_mask]
        
        grads = self.network.gradient(x_batch, t_batch)
        self.optimizer.update(self.network.params, grads)
        
        loss = self.network.loss(x_batch, t_batch)
        self.train_loss_list.append(loss)
        if self.verbose: print("train loss:" + str(loss))
        
        if self.current_iter % self.iter_per_epoch == 0:
            self.current_epoch += 1
            
            x_train_sample, t_train_sample = self.x_train, self.t_train
            x_test_sample, t_test_sample = self.x_test, self.t_test
            if not self.evaluate_sample_num_per_epoch is None:
                t = self.evaluate_sample_num_per_epoch
                x_train_sample, t_train_sample = self.x_train[:t], self.t_train[:t]
                x_test_sample, t_test_sample = self.x_test[:t], self.t_test[:t]
                
            train_acc = self.network.accuracy(x_train_sample, t_train_sample)
            test_acc = self.network.accuracy(x_test_sample, t_test_sample)
            self.train_acc_list.append(train_acc)
            self.test_acc_list.append(test_acc)

            if self.verbose: print("=== epoch:" + str(self.current_epoch) + ", train acc:" + str(train_acc) + ", test acc:" + str(test_acc) + " ===")
        self.current_iter += 1

    def train(self):
        for i in range(self.max_iter):
            self.train_step()

        test_acc = self.network.accuracy(self.x_test, self.t_test)

        if self.verbose:
            print("=============== Final Test Accuracy ===============")
            print("test acc:" + str(test_acc))

# coding: utf-8
import numpy as np


def smooth_curve(x):
    """損失関数のグラフを滑らかにするために用いる

    参考：http://glowingpython.blogspot.jp/2012/02/convolution-with-numpy.html
    """
    window_len = 11
    s = np.r_[x[window_len-1:0:-1], x, x[-1:-window_len:-1]]
    w = np.kaiser(window_len, 2)
    y = np.convolve(w/w.sum(), s, mode='valid')
    return y[5:len(y)-5]


def shuffle_dataset(x, t):
    """データセットのシャッフルを行う

    Parameters
    ----------
    x : 訓練データ
    t : 教師データ

    Returns
    -------
    x, t : シャッフルを行った訓練データと教師データ
    """
    permutation = np.random.permutation(x.shape[0])
    x = x[permutation,:] if x.ndim == 2 else x[permutation,:,:,:]
    t = t[permutation]

    return x, t

def conv_output_size(input_size, filter_size, stride=1, pad=0):
    return (input_size + 2*pad - filter_size) / stride + 1


def im2col(input_data, filter_h, filter_w, stride=1, pad=0):
    """

    Parameters
    ----------
    input_data : (データ数, チャンネル, 高さ, 幅)の4次元配列からなる入力データ
    filter_h : フィルターの高さ
    filter_w : フィルターの幅
    stride : ストライド
    pad : パディング

    Returns
    -------
    col : 2次元配列
    """
    N, C, H, W = input_data.shape
    out_h = (H + 2*pad - filter_h)//stride + 1
    out_w = (W + 2*pad - filter_w)//stride + 1

    img = np.pad(input_data, [(0,0), (0,0), (pad, pad), (pad, pad)], 'constant')
    col = np.zeros((N, C, filter_h, filter_w, out_h, out_w))

    for y in range(filter_h):
        y_max = y + stride*out_h
        for x in range(filter_w):
            x_max = x + stride*out_w
            col[:, :, y, x, :, :] = img[:, :, y:y_max:stride, x:x_max:stride]

    col = col.transpose(0, 4, 5, 1, 2, 3).reshape(N*out_h*out_w, -1)
    return col


def col2im(col, input_shape, filter_h, filter_w, stride=1, pad=0):
    """

    Parameters
    ----------
    col :
    input_shape : 入力データの形状（例：(10, 1, 28, 28)）
    filter_h :
    filter_w
    stride
    pad

    Returns
    -------

    """
    N, C, H, W = input_shape
    out_h = (H + 2*pad - filter_h)//stride + 1
    out_w = (W + 2*pad - filter_w)//stride + 1
    col = col.reshape(N, out_h, out_w, C, filter_h, filter_w).transpose(0, 3, 4, 5, 1, 2)

    img = np.zeros((N, C, H + 2*pad + stride - 1, W + 2*pad + stride - 1))
    for y in range(filter_h):
        y_max = y + stride*out_h
        for x in range(filter_w):
            x_max = x + stride*out_w
            img[:, :, y:y_max:stride, x:x_max:stride] += col[:, :, y, x, :, :]

    return img[:, :, pad:H + pad, pad:W + pad]