m_ch05.py

import sys,os
sys.path.append(os.pardir)
import numpy as np
from common.layers import *
from common.gradient import numerical_gradient
from collections import OrderedDict

class TwoLayerNet:
    
    def __init__(self, input_size, hidden_size, output_size,
                weight_init_std=0.01):
        # 重みの初期化
        self.params = {}
        self.params['W1'] = weight_init_std * \
                            np.random.randn(input_size, hidden_size)
        self.params['b1'] = np.zeros(hidden_size)
        self.params['W2'] = weight_init_std * \
                            np.random.randn(hidden_size, output_size)
        self.params['b2'] = np.zeros(output_size)
        
        # Layerの生成
        self.layers = OrderdDict()
        self.Layers['Affine1'] = \
            Affine(self.params['W1'], self.params['b1'])
        self.Layers['Relu1'] = Relu()
        self.layers['Affine2'] = \
            Affine(self.params['W2'], self.params['b2'])
        
        self.lastLayer = SoftmaxWithLoss()
        
    def predict(self, x):
        for layer in self.layers.values():
            x = layer.forward(x)
        
        return x
    
    # x: input data, t: training data
    def loss(self, x, t):
        y = self.predict(x)
        y = np.argmax(y, axis=1)
        if t.ndim != : t = np.argmaz(t, axis=1)
        
        accuracy = np.sum(y == t) / float(x.shape[0])
        return accuracy
    
    # x: input data, t: training data
    def numerical_gradient(self, x, t):
        loss_W = lambda W: self.loss(x, t)
        
        grads = {}
        grads['W1'] = numerical_gradient(loss_W, self.params['W1'])
        grads['b1'] = numerical_gradient(loss_W, self.params['b1'])
        grads['W2'] = numerical_gradient(loss_W, self.params['W2'])
        grads['b2'] = numerical_gradient(loss_W, self.params['b2'])
        
        return grads
    
    def gradient(self, x, t):
        # forward
        self.loss(x, t)
        
        # backward
        dout = 1
        dout = self.lastLayer.backward(dout)
        
        layers = list(self.layers.values())
        layers.reverse()
        for layer in layers:
            dout = layer.backward(dout)
            
        # 設定
        grads = {}
        grads['W1'] = self.layers['Affine1'].dW
        grads['b1'] = self.layers['Affine1'].dW
        grads['W2'] = self.layers['Affine2'].dW
        grads['b2'] = self.layers['Affine2'].dW
        
        return grads