AI03-Topic01, Training skills

Back to the previous page
List of posts to read before reading this article

Parameter update
Initial value of weight
Batch normalization
For the right training
Find appropriate hyperparameter values
Reference Codes

Parameter update

Initial value of weight

Batch normalization

For the right training

Find appropriate hyperparameter values

Reference Codes

Pre-define

functions.py

# 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)

gradient.py

# 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

layers.py

# 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

multi_layer_net.py

# 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

multi_layer_net_extend.py

# 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

optimizer.py

# 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)

trainer.py

# 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))

util.py

# 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]

batch_norm_gradient_check.py

# 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 dataset.mnist import load_mnist
from common.multi_layer_net_extend import MultiLayerNetExtend

# データの読み込み
(x_train, t_train), (x_test, t_test) = load_mnist(normalize=True, one_hot_label=True)

network = MultiLayerNetExtend(input_size=784, hidden_size_list=[100, 100], output_size=10,
                              use_batchnorm=True)

x_batch = x_train[:1]
t_batch = t_train[:1]

grad_backprop = network.gradient(x_batch, t_batch)
grad_numerical = network.numerical_gradient(x_batch, t_batch)


for key in grad_numerical.keys():
    diff = np.average( np.abs(grad_backprop[key] - grad_numerical[key]) )
    print(key + ":" + str(diff))

OUTPUT

batch_norm_test.py

# 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
import matplotlib.pyplot as plt
from dataset.mnist import load_mnist
from common.multi_layer_net_extend import MultiLayerNetExtend
from common.optimizer import SGD, Adam

(x_train, t_train), (x_test, t_test) = load_mnist(normalize=True)

# 学習データを削減
x_train = x_train[:1000]
t_train = t_train[:1000]

max_epochs = 20
train_size = x_train.shape[0]
batch_size = 100
learning_rate = 0.01


def __train(weight_init_std):
    bn_network = MultiLayerNetExtend(input_size=784, hidden_size_list=[100, 100, 100, 100, 100], output_size=10, 
                                    weight_init_std=weight_init_std, use_batchnorm=True)
    network = MultiLayerNetExtend(input_size=784, hidden_size_list=[100, 100, 100, 100, 100], output_size=10,
                                weight_init_std=weight_init_std)
    optimizer = SGD(lr=learning_rate)
    
    train_acc_list = []
    bn_train_acc_list = []
    
    iter_per_epoch = max(train_size / batch_size, 1)
    epoch_cnt = 0
    
    for i in range(1000000000):
        batch_mask = np.random.choice(train_size, batch_size)
        x_batch = x_train[batch_mask]
        t_batch = t_train[batch_mask]
    
        for _network in (bn_network, network):
            grads = _network.gradient(x_batch, t_batch)
            optimizer.update(_network.params, grads)
    
        if i % iter_per_epoch == 0:
            train_acc = network.accuracy(x_train, t_train)
            bn_train_acc = bn_network.accuracy(x_train, t_train)
            train_acc_list.append(train_acc)
            bn_train_acc_list.append(bn_train_acc)
    
            print("epoch:" + str(epoch_cnt) + " | " + str(train_acc) + " - " + str(bn_train_acc))
    
            epoch_cnt += 1
            if epoch_cnt >= max_epochs:
                break
                
    return train_acc_list, bn_train_acc_list


# 3.グラフの描画==========
weight_scale_list = np.logspace(0, -4, num=16)
x = np.arange(max_epochs)

for i, w in enumerate(weight_scale_list):
    print( "============== " + str(i+1) + "/16" + " ==============")
    train_acc_list, bn_train_acc_list = __train(w)
    
    plt.subplot(4,4,i+1)
    plt.title("W:" + str(w))
    if i == 15:
        plt.plot(x, bn_train_acc_list, label='Batch Normalization', markevery=2)
        plt.plot(x, train_acc_list, linestyle = "--", label='Normal(without BatchNorm)', markevery=2)
    else:
        plt.plot(x, bn_train_acc_list, markevery=2)
        plt.plot(x, train_acc_list, linestyle="--", markevery=2)

    plt.ylim(0, 1.0)
    if i % 4:
        plt.yticks([])
    else:
        plt.ylabel("accuracy")
    if i < 12:
        plt.xticks([])
    else:
        plt.xlabel("epochs")
    plt.legend(loc='lower right')
    
plt.show()

OUTPUT

hyperparameter_optimization.py

# 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
import matplotlib.pyplot as plt
from dataset.mnist import load_mnist
from common.multi_layer_net import MultiLayerNet
from common.util import shuffle_dataset
from common.trainer import Trainer

(x_train, t_train), (x_test, t_test) = load_mnist(normalize=True)

# 高速化のため訓練データの削減
x_train = x_train[:500]
t_train = t_train[:500]

# 検証データの分離
validation_rate = 0.20
validation_num = int(x_train.shape[0] * validation_rate)
x_train, t_train = shuffle_dataset(x_train, t_train)
x_val = x_train[:validation_num]
t_val = t_train[:validation_num]
x_train = x_train[validation_num:]
t_train = t_train[validation_num:]


def __train(lr, weight_decay, epocs=50):
    network = MultiLayerNet(input_size=784, hidden_size_list=[100, 100, 100, 100, 100, 100],
                            output_size=10, weight_decay_lambda=weight_decay)
    trainer = Trainer(network, x_train, t_train, x_val, t_val,
                      epochs=epocs, mini_batch_size=100,
                      optimizer='sgd', optimizer_param={'lr': lr}, verbose=False)
    trainer.train()

    return trainer.test_acc_list, trainer.train_acc_list


# ハイパーパラメータのランダム探索======================================
optimization_trial = 100
results_val = {}
results_train = {}
for _ in range(optimization_trial):
    # 探索したハイパーパラメータの範囲を指定===============
    weight_decay = 10 ** np.random.uniform(-8, -4)
    lr = 10 ** np.random.uniform(-6, -2)
    # ================================================

    val_acc_list, train_acc_list = __train(lr, weight_decay)
    print("val acc:" + str(val_acc_list[-1]) + " | lr:" + str(lr) + ", weight decay:" + str(weight_decay))
    key = "lr:" + str(lr) + ", weight decay:" + str(weight_decay)
    results_val[key] = val_acc_list
    results_train[key] = train_acc_list

# グラフの描画========================================================
print("=========== Hyper-Parameter Optimization Result ===========")
graph_draw_num = 20
col_num = 5
row_num = int(np.ceil(graph_draw_num / col_num))
i = 0

for key, val_acc_list in sorted(results_val.items(), key=lambda x:x[1][-1], reverse=True):
    print("Best-" + str(i+1) + "(val acc:" + str(val_acc_list[-1]) + ") | " + key)

    plt.subplot(row_num, col_num, i+1)
    plt.title("Best-" + str(i+1))
    plt.ylim(0.0, 1.0)
    if i % 5: plt.yticks([])
    plt.xticks([])
    x = np.arange(len(val_acc_list))
    plt.plot(x, val_acc_list)
    plt.plot(x, results_train[key], "--")
    i += 1

    if i >= graph_draw_num:
        break

plt.show()

OUTPUT

optimizer_compare_mnist.py

# coding: utf-8
import os
import sys
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 matplotlib.pyplot as plt
from dataset.mnist import load_mnist
from common.util import smooth_curve
from common.multi_layer_net import MultiLayerNet
from common.optimizer import *


# 0:MNISTデータの読み込み==========
(x_train, t_train), (x_test, t_test) = load_mnist(normalize=True)

train_size = x_train.shape[0]
batch_size = 128
max_iterations = 2000


# 1:実験の設定==========
optimizers = {}
optimizers['SGD'] = SGD()
optimizers['Momentum'] = Momentum()
optimizers['AdaGrad'] = AdaGrad()
optimizers['Adam'] = Adam()
#optimizers['RMSprop'] = RMSprop()

networks = {}
train_loss = {}
for key in optimizers.keys():
    networks[key] = MultiLayerNet(
        input_size=784, hidden_size_list=[100, 100, 100, 100],
        output_size=10)
    train_loss[key] = []    


# 2:訓練の開始==========
for i in range(max_iterations):
    batch_mask = np.random.choice(train_size, batch_size)
    x_batch = x_train[batch_mask]
    t_batch = t_train[batch_mask]
    
    for key in optimizers.keys():
        grads = networks[key].gradient(x_batch, t_batch)
        optimizers[key].update(networks[key].params, grads)
    
        loss = networks[key].loss(x_batch, t_batch)
        train_loss[key].append(loss)
    
    if i % 100 == 0:
        print( "===========" + "iteration:" + str(i) + "===========")
        for key in optimizers.keys():
            loss = networks[key].loss(x_batch, t_batch)
            print(key + ":" + str(loss))


# 3.グラフの描画==========
markers = {"SGD": "o", "Momentum": "x", "AdaGrad": "s", "Adam": "D"}
x = np.arange(max_iterations)
for key in optimizers.keys():
    plt.plot(x, smooth_curve(train_loss[key]), marker=markers[key], markevery=100, label=key)
plt.xlabel("iterations")
plt.ylabel("loss")
plt.ylim(0, 1)
plt.legend()
plt.show()

OUTPUT

optimizer_compare_naive.py

# 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
import matplotlib.pyplot as plt
from collections import OrderedDict
from common.optimizer import *


def f(x, y):
    return x**2 / 20.0 + y**2


def df(x, y):
    return x / 10.0, 2.0*y

init_pos = (-7.0, 2.0)
params = {}
params['x'], params['y'] = init_pos[0], init_pos[1]
grads = {}
grads['x'], grads['y'] = 0, 0


optimizers = OrderedDict()
optimizers["SGD"] = SGD(lr=0.95)
optimizers["Momentum"] = Momentum(lr=0.1)
optimizers["AdaGrad"] = AdaGrad(lr=1.5)
optimizers["Adam"] = Adam(lr=0.3)

idx = 1

for key in optimizers:
    optimizer = optimizers[key]
    x_history = []
    y_history = []
    params['x'], params['y'] = init_pos[0], init_pos[1]
    
    for i in range(30):
        x_history.append(params['x'])
        y_history.append(params['y'])
        
        grads['x'], grads['y'] = df(params['x'], params['y'])
        optimizer.update(params, grads)
    

    x = np.arange(-10, 10, 0.01)
    y = np.arange(-5, 5, 0.01)
    
    X, Y = np.meshgrid(x, y) 
    Z = f(X, Y)
    
    # for simple contour line  
    mask = Z > 7
    Z[mask] = 0
    
    # plot 
    plt.subplot(2, 2, idx)
    idx += 1
    plt.plot(x_history, y_history, 'o-', color="red")
    plt.contour(X, Y, Z)
    plt.ylim(-10, 10)
    plt.xlim(-10, 10)
    plt.plot(0, 0, '+')
    #colorbar()
    #spring()
    plt.title(key)
    plt.xlabel("x")
    plt.ylabel("y")
    
plt.show()

OUTPUT

overfit_dropout.py

# coding: utf-8
import os
import sys
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
import matplotlib.pyplot as plt
from dataset.mnist import load_mnist
from common.multi_layer_net_extend import MultiLayerNetExtend
from common.trainer import Trainer

(x_train, t_train), (x_test, t_test) = load_mnist(normalize=True)

# 過学習を再現するために、学習データを削減
x_train = x_train[:300]
t_train = t_train[:300]

# Dropuoutの有無、割り合いの設定 ========================
use_dropout = True  # Dropoutなしのときの場合はFalseに
dropout_ratio = 0.2
# ====================================================

network = MultiLayerNetExtend(input_size=784, hidden_size_list=[100, 100, 100, 100, 100, 100],
                              output_size=10, use_dropout=use_dropout, dropout_ration=dropout_ratio)
trainer = Trainer(network, x_train, t_train, x_test, t_test,
                  epochs=301, mini_batch_size=100,
                  optimizer='sgd', optimizer_param={'lr': 0.01}, verbose=True)
trainer.train()

train_acc_list, test_acc_list = trainer.train_acc_list, trainer.test_acc_list

# グラフの描画==========
markers = {'train': 'o', 'test': 's'}
x = np.arange(len(train_acc_list))
plt.plot(x, train_acc_list, marker='o', label='train', markevery=10)
plt.plot(x, test_acc_list, marker='s', label='test', markevery=10)
plt.xlabel("epochs")
plt.ylabel("accuracy")
plt.ylim(0, 1.0)
plt.legend(loc='lower right')
plt.show()

OUTPUT

overfit_weight_decay.py

# coding: utf-8
import os
import sys

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
import matplotlib.pyplot as plt
from dataset.mnist import load_mnist
from common.multi_layer_net import MultiLayerNet
from common.optimizer import SGD

(x_train, t_train), (x_test, t_test) = load_mnist(normalize=True)

# 過学習を再現するために、学習データを削減
x_train = x_train[:300]
t_train = t_train[:300]

# weight decay（荷重減衰）の設定 =======================
#weight_decay_lambda = 0 # weight decayを使用しない場合
weight_decay_lambda = 0.1
# ====================================================

network = MultiLayerNet(input_size=784, hidden_size_list=[100, 100, 100, 100, 100, 100], output_size=10,
                        weight_decay_lambda=weight_decay_lambda)
optimizer = SGD(lr=0.01)

max_epochs = 201
train_size = x_train.shape[0]
batch_size = 100

train_loss_list = []
train_acc_list = []
test_acc_list = []

iter_per_epoch = max(train_size / batch_size, 1)
epoch_cnt = 0

for i in range(1000000000):
    batch_mask = np.random.choice(train_size, batch_size)
    x_batch = x_train[batch_mask]
    t_batch = t_train[batch_mask]

    grads = network.gradient(x_batch, t_batch)
    optimizer.update(network.params, grads)

    if i % iter_per_epoch == 0:
        train_acc = network.accuracy(x_train, t_train)
        test_acc = network.accuracy(x_test, t_test)
        train_acc_list.append(train_acc)
        test_acc_list.append(test_acc)

        print("epoch:" + str(epoch_cnt) + ", train acc:" + str(train_acc) + ", test acc:" + str(test_acc))

        epoch_cnt += 1
        if epoch_cnt >= max_epochs:
            break


# 3.グラフの描画==========
markers = {'train': 'o', 'test': 's'}
x = np.arange(max_epochs)
plt.plot(x, train_acc_list, marker='o', label='train', markevery=10)
plt.plot(x, test_acc_list, marker='s', label='test', markevery=10)
plt.xlabel("epochs")
plt.ylabel("accuracy")
plt.ylim(0, 1.0)
plt.legend(loc='lower right')
plt.show()

OUTPUT

weight_init_activation_histogram.py

# coding: utf-8
import numpy as np
import matplotlib.pyplot as plt


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


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


def tanh(x):
    return np.tanh(x)
    
input_data = np.random.randn(1000, 100)  # 1000個のデータ
node_num = 100  # 各隠れ層のノード（ニューロン）の数
hidden_layer_size = 5  # 隠れ層が5層
activations = {}  # ここにアクティベーションの結果を格納する

x = input_data

for i in range(hidden_layer_size):
    if i != 0:
        x = activations[i-1]

    # 初期値の値をいろいろ変えて実験しよう！
    w = np.random.randn(node_num, node_num) * 1
    # w = np.random.randn(node_num, node_num) * 0.01
    # w = np.random.randn(node_num, node_num) * np.sqrt(1.0 / node_num)
    # w = np.random.randn(node_num, node_num) * np.sqrt(2.0 / node_num)


    a = np.dot(x, w)


    # 活性化関数の種類も変えて実験しよう！
    z = sigmoid(a)
    # z = ReLU(a)
    # z = tanh(a)

    activations[i] = z

# ヒストグラムを描画
for i, a in activations.items():
    plt.subplot(1, len(activations), i+1)
    plt.title(str(i+1) + "-layer")
    if i != 0: plt.yticks([], [])
    # plt.xlim(0.1, 1)
    # plt.ylim(0, 7000)
    plt.hist(a.flatten(), 30, range=(0,1))
plt.show()

OUTPUT

weight_init_compare.py

# coding: utf-8
import os
import sys

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
import matplotlib.pyplot as plt
from dataset.mnist import load_mnist
from common.util import smooth_curve
from common.multi_layer_net import MultiLayerNet
from common.optimizer import SGD


# 0:MNISTデータの読み込み==========
(x_train, t_train), (x_test, t_test) = load_mnist(normalize=True)

train_size = x_train.shape[0]
batch_size = 128
max_iterations = 2000


# 1:実験の設定==========
weight_init_types = {'std=0.01': 0.01, 'Xavier': 'sigmoid', 'He': 'relu'}
optimizer = SGD(lr=0.01)

networks = {}
train_loss = {}
for key, weight_type in weight_init_types.items():
    networks[key] = MultiLayerNet(input_size=784, hidden_size_list=[100, 100, 100, 100],
                                  output_size=10, weight_init_std=weight_type)
    train_loss[key] = []


# 2:訓練の開始==========
for i in range(max_iterations):
    batch_mask = np.random.choice(train_size, batch_size)
    x_batch = x_train[batch_mask]
    t_batch = t_train[batch_mask]
    
    for key in weight_init_types.keys():
        grads = networks[key].gradient(x_batch, t_batch)
        optimizer.update(networks[key].params, grads)
    
        loss = networks[key].loss(x_batch, t_batch)
        train_loss[key].append(loss)
    
    if i % 100 == 0:
        print("===========" + "iteration:" + str(i) + "===========")
        for key in weight_init_types.keys():
            loss = networks[key].loss(x_batch, t_batch)
            print(key + ":" + str(loss))


# 3.グラフの描画==========
markers = {'std=0.01': 'o', 'Xavier': 's', 'He': 'D'}
x = np.arange(max_iterations)
for key in weight_init_types.keys():
    plt.plot(x, smooth_curve(train_loss[key]), marker=markers[key], markevery=100, label=key)
plt.xlabel("iterations")
plt.ylabel("loss")
plt.ylim(0, 2.5)
plt.legend()
plt.show()

OUTPUT

List of posts followed by this article

Reference

6626070
2997924

AI03-Topic01, Training skills

Contents

Parameter update

Initial value of weight

Batch normalization

For the right training

Find appropriate hyperparameter values

Reference Codes

batch_norm_gradient_check.py

batch_norm_test.py

hyperparameter_optimization.py

optimizer_compare_mnist.py

optimizer_compare_naive.py

overfit_dropout.py

overfit_weight_decay.py

weight_init_activation_histogram.py

weight_init_compare.py

6626070 2997924

AI03-Topic01, Training skills

Contents

Parameter update

Initial value of weight

Batch normalization

For the right training

Find appropriate hyperparameter values

Reference Codes

batch_norm_gradient_check.py

batch_norm_test.py

hyperparameter_optimization.py

optimizer_compare_mnist.py

optimizer_compare_naive.py

overfit_dropout.py

overfit_weight_decay.py

weight_init_activation_histogram.py

weight_init_compare.py

6626070
2997924