読者です 読者をやめる 読者になる 読者になる

Djangoroidの奮闘記

python,django,angularJS1~三十路過ぎたプログラマーの奮闘記

Python DeepLearningに再挑戦 16 誤差逆伝播法 誤差逆伝播法を使った学習

概要

Python DeepLearningに再挑戦 16 誤差逆伝播誤差逆伝播法を使った学習

参考書籍

誤差逆伝播法を使った学習

import sys, os
sys.path.append(os.pardir)
import numpy as np
from dataset.mnist import load_mnist
from two_layer_net import TwoLayerNet

#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 = TwoLayerNet(input_size=784, hidden_size=50, output_size=10)

iters_num = 10000
train_size = x_train.shape[0]
batch_size = 100
learning_rate = 0.1
train_loss_list = []
train_acc_list = []
test_acc_list = []

iter_per_epoch = max(train_size / batch_size, 1)

for i in range(iters_num):
    batch_mask = np.random.choice(train_size, batch_size)
    x_batch = x_train[batch_mask]
    t_batch = t_train[batch_mask]
    
    #  誤差逆伝播法によって勾配を求める
    grad = network.gradient(x_batch, t_batch)
    
    # 更新
    for key in ('W1', 'b1', 'W2', 'b2'):
        network.params[key] -= learning_rate * grad[key]
        
    loss = network.loss(x_batch, t_batch)
    train_loss_list.append(loss)
    
    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(train_acc, test_acc)

すごい!誤差がどんどんなくなっていく〜!

それにしても難しいなぁ〜。