{
"cells": [
{
"cell_type": "markdown",
"metadata": {
"id": "_xGwQdv44OkO"
},
"source": [
"# 머신 러닝 교과서 3판"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "ZDRcmK8K4OkU"
},
"source": [
"# 12장 - 다층 인공 신경망을 밑바닥부터 구현"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "5zzcJG584OkV"
},
"source": [
"**아래 링크를 통해 이 노트북을 주피터 노트북 뷰어(nbviewer.jupyter.org)로 보거나 구글 코랩(colab.research.google.com)에서 실행할 수 있습니다.**\n",
"\n",
""
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "Rh7AAS9i4OkV"
},
"source": [
"### 목차"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "zIfT2P-D4OkV"
},
"source": [
"- 인공 신경망으로 복잡한 함수 모델링\n",
" - 단일층 신경망 요약\n",
" - 다층 신경망 구조\n",
" - 정방향 계산으로 신경망 활성화 출력 계산\n",
"- 손글씨 숫자 분류\n",
" - MNIST 데이터셋 구하기\n",
" - 다층 퍼셉트론 구현\n",
"- 인공 신경망 훈련\n",
" - 로지스틱 비용 함수 계산\n",
" - 역전파 알고리즘 이해\n",
" - 역전파 알고리즘으로 신경망 훈련\n",
"- 신경망의 수렴\n",
"- 신경망 구현에 관한 몇 가지 첨언\n",
"- 요약"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "v0ItJ7A04OkW"
},
"source": [
"
\n",
"
"
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {
"id": "zvyRuFKr4OkW"
},
"outputs": [],
"source": [
"from IPython.display import Image"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "ORtCZtmt4OkW"
},
"source": [
"# 인공 신경망으로 복잡한 함수 모델링"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "zZ1axgpt4OkX"
},
"source": [
"..."
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "agpO4o5J4OkX"
},
"source": [
"## 단일층 신경망 요약"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 304
},
"id": "1k-XISPU4OkX",
"outputId": "8a8b7dd1-8f62-470c-a336-d0885f431643",
"scrolled": true
},
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/html": [
"![](\"https://git.io/JLdrS\")
"
],
"text/plain": [
""
]
},
"metadata": {},
"execution_count": 2
}
],
"source": [
"Image(url='https://git.io/JLdrS', width=600)"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "OWCJE5nw4OkY"
},
"source": [
"
\n",
"
"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "fhENAYu74OkY"
},
"source": [
"## 다층 신경망 구조"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 367
},
"id": "umM0VuIx4OkZ",
"outputId": "7fb6f6ba-df3e-4914-8534-01f09fb8e3b8"
},
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/html": [
"![](\"https://git.io/JLdrx\")
"
],
"text/plain": [
""
]
},
"metadata": {},
"execution_count": 3
}
],
"source": [
"Image(url='https://git.io/JLdrx', width=600)"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 366
},
"id": "HoN06CDB4OkZ",
"outputId": "1bc9308e-8af8-4814-cd19-67967d8d9aed"
},
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/html": [
"![](\"https://git.io/JLdrp\")
"
],
"text/plain": [
""
]
},
"metadata": {},
"execution_count": 4
}
],
"source": [
"Image(url='https://git.io/JLdrp', width=500)"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "o7Tzuk9m4OkZ"
},
"source": [
"
\n",
"
"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "xDU-ewSp4Oka"
},
"source": [
"## 정방향 계산으로 신경망 활성화 출력 계산"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 355
},
"id": "REJ94FgH4Oka",
"outputId": "1dee1da1-59b9-4282-ac3c-348930d4cc91"
},
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/html": [
"![](\"https://git.io/JLdoe\")
"
],
"text/plain": [
""
]
},
"metadata": {},
"execution_count": 5
}
],
"source": [
"Image(url='https://git.io/JLdoe', width=500)"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "qMOAw-WC4Okb"
},
"source": [
"사이킷런을 사용해 MNIST 데이터를 적재하려면 다음 코드의 주석을 해제하고 실행하세요."
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 74
},
"id": "Conf1Omr4Okb",
"outputId": "f2f82986-5e15-49b8-c44e-4c53752c0313"
},
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"\"\\nfrom sklearn.datasets import fetch_openml\\nfrom sklearn.model_selection import train_test_split\\n\\n\\nX, y = fetch_openml('mnist_784', version=1, return_X_y=True)\\ny = y.astype(int)\\nX = ((X / 255.) - .5) * 2\\nX_train, X_test, y_train, y_test = train_test_split(\\n X, y, test_size=10000, random_state=123, stratify=y)\\n\""
],
"application/vnd.google.colaboratory.intrinsic+json": {
"type": "string"
}
},
"metadata": {},
"execution_count": 6
}
],
"source": [
"\"\"\"\n",
"from sklearn.datasets import fetch_openml\n",
"from sklearn.model_selection import train_test_split\n",
"\n",
"\n",
"X, y = fetch_openml('mnist_784', version=1, return_X_y=True)\n",
"y = y.astype(int)\n",
"X = ((X / 255.) - .5) * 2\n",
"X_train, X_test, y_train, y_test = train_test_split(\n",
" X, y, test_size=10000, random_state=123, stratify=y)\n",
"\"\"\""
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "j3zsvP8b4Okb"
},
"source": [
"
\n",
"
"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "srqaPOBL4Okb"
},
"source": [
"# 손글씨 숫자 분류"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "fQ9VEg904Okc"
},
"source": [
"..."
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "dZQsVb2G4Okc"
},
"source": [
"## MNIST 데이터셋 구하기"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "vm_CQgZY4Okc"
},
"source": [
"MNIST 데이터셋은 http://yann.lecun.com/exdb/mnist/에 공개되어 있으며 다음 네 부분으로 구성되어 있습니다.\n",
"\n",
"- 훈련 세트 이미지: train-images-idx3-ubyte.gz(9.9MB, 압축 해제 후 47MB, 60,000개 샘플)\n",
"- 훈련 세트 레이블: train-labels-idx1-ubyte.gz(29KB, 압축 해제 후 60KB, 60,000개 레이블)\n",
"- 테스트 세트 이미지: t10k-images-idx3-ubyte.gz(1.6MB, 압축 해제 후 7.8MB, 10,000개 샘플)\n",
"- 테스트 세트 레이블: t10k-labels-idx1-ubyte.gz(5KB, 압축 해제 후 10KB, 10,000개 레이블)\n",
"\n",
"이 절에서는 MNIST 데이터 중 일부만 사용합니다. 따라서 훈련 데이터셋의 이미지와 레이블만 다운로드합니다.\n",
"\n",
"파일을 다운로드한 후에 다음 코드 셀을 실행하면 파일 압축을 풀 수 있습니다."
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "953BW0QA4Okd",
"outputId": "38ebe4fe-de10-432a-b976-89f518af4714"
},
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"--2025-09-02 07:48:10-- https://github.com/rickiepark/python-machine-learning-book-3rd-edition/raw/master/ch12/train-images-idx3-ubyte.gz\n",
"Resolving github.com (github.com)... 140.82.113.4\n",
"Connecting to github.com (github.com)|140.82.113.4|:443... connected.\n",
"HTTP request sent, awaiting response... 302 Found\n",
"Location: https://raw.githubusercontent.com/rickiepark/python-machine-learning-book-3rd-edition/master/ch12/train-images-idx3-ubyte.gz [following]\n",
"--2025-09-02 07:48:11-- https://raw.githubusercontent.com/rickiepark/python-machine-learning-book-3rd-edition/master/ch12/train-images-idx3-ubyte.gz\n",
"Resolving raw.githubusercontent.com (raw.githubusercontent.com)... 185.199.108.133, 185.199.109.133, 185.199.110.133, ...\n",
"Connecting to raw.githubusercontent.com (raw.githubusercontent.com)|185.199.108.133|:443... connected.\n",
"HTTP request sent, awaiting response... 200 OK\n",
"Length: 9912422 (9.5M) [application/octet-stream]\n",
"Saving to: ‘train-images-idx3-ubyte.gz’\n",
"\n",
"train-images-idx3-u 100%[===================>] 9.45M --.-KB/s in 0.1s \n",
"\n",
"2025-09-02 07:48:11 (83.2 MB/s) - ‘train-images-idx3-ubyte.gz’ saved [9912422/9912422]\n",
"\n",
"--2025-09-02 07:48:11-- https://github.com/rickiepark/python-machine-learning-book-3rd-edition/raw/master/ch12/train-labels-idx1-ubyte.gz\n",
"Resolving github.com (github.com)... 140.82.112.4\n",
"Connecting to github.com (github.com)|140.82.112.4|:443... connected.\n",
"HTTP request sent, awaiting response... 302 Found\n",
"Location: https://raw.githubusercontent.com/rickiepark/python-machine-learning-book-3rd-edition/master/ch12/train-labels-idx1-ubyte.gz [following]\n",
"--2025-09-02 07:48:11-- https://raw.githubusercontent.com/rickiepark/python-machine-learning-book-3rd-edition/master/ch12/train-labels-idx1-ubyte.gz\n",
"Resolving raw.githubusercontent.com (raw.githubusercontent.com)... 185.199.108.133, 185.199.109.133, 185.199.110.133, ...\n",
"Connecting to raw.githubusercontent.com (raw.githubusercontent.com)|185.199.108.133|:443... connected.\n",
"HTTP request sent, awaiting response... 200 OK\n",
"Length: 28881 (28K) [application/octet-stream]\n",
"Saving to: ‘train-labels-idx1-ubyte.gz’\n",
"\n",
"train-labels-idx1-u 100%[===================>] 28.20K --.-KB/s in 0.003s \n",
"\n",
"2025-09-02 07:48:12 (8.73 MB/s) - ‘train-labels-idx1-ubyte.gz’ saved [28881/28881]\n",
"\n",
"--2025-09-02 07:48:12-- https://github.com/rickiepark/python-machine-learning-book-3rd-edition/raw/master/ch12/t10k-images-idx3-ubyte.gz\n",
"Resolving github.com (github.com)... 140.82.114.3\n",
"Connecting to github.com (github.com)|140.82.114.3|:443... connected.\n",
"HTTP request sent, awaiting response... 302 Found\n",
"Location: https://raw.githubusercontent.com/rickiepark/python-machine-learning-book-3rd-edition/master/ch12/t10k-images-idx3-ubyte.gz [following]\n",
"--2025-09-02 07:48:12-- https://raw.githubusercontent.com/rickiepark/python-machine-learning-book-3rd-edition/master/ch12/t10k-images-idx3-ubyte.gz\n",
"Resolving raw.githubusercontent.com (raw.githubusercontent.com)... 185.199.110.133, 185.199.109.133, 185.199.111.133, ...\n",
"Connecting to raw.githubusercontent.com (raw.githubusercontent.com)|185.199.110.133|:443... connected.\n",
"HTTP request sent, awaiting response... 200 OK\n",
"Length: 1648877 (1.6M) [application/octet-stream]\n",
"Saving to: ‘t10k-images-idx3-ubyte.gz’\n",
"\n",
"t10k-images-idx3-ub 100%[===================>] 1.57M --.-KB/s in 0.07s \n",
"\n",
"2025-09-02 07:48:12 (23.5 MB/s) - ‘t10k-images-idx3-ubyte.gz’ saved [1648877/1648877]\n",
"\n",
"--2025-09-02 07:48:12-- https://github.com/rickiepark/python-machine-learning-book-3rd-edition/raw/master/ch12/t10k-labels-idx1-ubyte.gz\n",
"Resolving github.com (github.com)... 140.82.112.4\n",
"Connecting to github.com (github.com)|140.82.112.4|:443... connected.\n",
"HTTP request sent, awaiting response... 302 Found\n",
"Location: https://raw.githubusercontent.com/rickiepark/python-machine-learning-book-3rd-edition/master/ch12/t10k-labels-idx1-ubyte.gz [following]\n",
"--2025-09-02 07:48:12-- https://raw.githubusercontent.com/rickiepark/python-machine-learning-book-3rd-edition/master/ch12/t10k-labels-idx1-ubyte.gz\n",
"Resolving raw.githubusercontent.com (raw.githubusercontent.com)... 185.199.110.133, 185.199.109.133, 185.199.111.133, ...\n",
"Connecting to raw.githubusercontent.com (raw.githubusercontent.com)|185.199.110.133|:443... connected.\n",
"HTTP request sent, awaiting response... 200 OK\n",
"Length: 4542 (4.4K) [application/octet-stream]\n",
"Saving to: ‘t10k-labels-idx1-ubyte.gz’\n",
"\n",
"t10k-labels-idx1-ub 100%[===================>] 4.44K --.-KB/s in 0s \n",
"\n",
"2025-09-02 07:48:13 (47.1 MB/s) - ‘t10k-labels-idx1-ubyte.gz’ saved [4542/4542]\n",
"\n"
]
}
],
"source": [
"# 코랩을 사용할 때는 다음 코드를 실행하세요.\n",
"!wget https://github.com/rickiepark/python-machine-learning-book-3rd-edition/raw/master/ch12/train-images-idx3-ubyte.gz\n",
"!wget https://github.com/rickiepark/python-machine-learning-book-3rd-edition/raw/master/ch12/train-labels-idx1-ubyte.gz\n",
"!wget https://github.com/rickiepark/python-machine-learning-book-3rd-edition/raw/master/ch12/t10k-images-idx3-ubyte.gz\n",
"!wget https://github.com/rickiepark/python-machine-learning-book-3rd-edition/raw/master/ch12/t10k-labels-idx1-ubyte.gz"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {
"id": "gAOPi8444Okd"
},
"outputs": [],
"source": [
"# MNIST 데이터 압축을 푸는 코드\n",
"\n",
"import sys\n",
"import gzip\n",
"import shutil\n",
"import os\n",
"\n",
"if (sys.version_info > (3, 0)):\n",
" writemode = 'wb'\n",
"else:\n",
" writemode = 'w'\n",
"\n",
"zipped_mnist = [f for f in os.listdir() if f.endswith('ubyte.gz')]\n",
"for z in zipped_mnist:\n",
" with gzip.GzipFile(z, mode='rb') as decompressed, open(z[:-3], writemode) as outfile:\n",
" outfile.write(decompressed.read())"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "ocRxdefS4Okd"
},
"source": [
"----\n",
"\n",
"위 코드 셀을 실행할 때 에러가 발생할 경우:\n",
"\n",
"위 코드 셀을 실행할 때 문제가 있다면 터미널에서 Unix/Linux gzip 명령을 사용해 파일의 압축을 푸는 것이 좋습니다. 예를 들어 MNIST 다운로드 디렉토리에서 다음 명령을 실행합니다.\n",
"\n",
" gzip *ubyte.gz -d\n",
"\n",
"또는 마이크로소프트 윈도우를 사용한다면 선호하는 압축 프로그램을 사용할 수 있습니다. 이미지는 바이트 형태로 저장되어 있으므로 다음에 나오는 함수를 사용해 넘파이 배열로 읽어 MLP 모델을 훈련합니다.\n",
"\n",
"gzip을 사용하지 않는다면 만들어진 파일 이름이 다음과 같은지 확인하세요.\n",
"\n",
"- train-images-idx3-ubyte\n",
"- train-labels-idx1-ubyte\n",
"- t10k-images-idx3-ubyte\n",
"- t10k-labels-idx1-ubyte\n",
"\n",
"만약 압축 해제 후에 (파일 확장자를 예측하는 일부 도구들 때문에) 파일 이름이 `train-images.idx3-ubyte`처럼 된다면 다음 코드를 진행하기 전에 `train-images-idx3-ubyte`로 이름을 바꾸어 주세요.\n",
"\n",
"----"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {
"id": "2pFzNdM24Okd"
},
"outputs": [],
"source": [
"import os\n",
"import struct\n",
"import numpy as np\n",
"\n",
"def load_mnist(path, kind='train'):\n",
" \"\"\"`path`에서 MNIST 데이터 불러오기\"\"\"\n",
" labels_path = os.path.join(path,\n",
" '%s-labels-idx1-ubyte' % kind)\n",
" images_path = os.path.join(path,\n",
" '%s-images-idx3-ubyte' % kind)\n",
"\n",
" with open(labels_path, 'rb') as lbpath:\n",
" magic, n = struct.unpack('>II',\n",
" lbpath.read(8))\n",
" labels = np.fromfile(lbpath,\n",
" dtype=np.uint8)\n",
"\n",
" with open(images_path, 'rb') as imgpath:\n",
" magic, num, rows, cols = struct.unpack(\">IIII\",\n",
" imgpath.read(16))\n",
" images = np.fromfile(imgpath,\n",
" dtype=np.uint8).reshape(len(labels), 784)\n",
" images = ((images / 255.) - .5) * 2\n",
"\n",
" return images, labels"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "hIdJUukR4Okd",
"outputId": "ee9eec9e-f3a4-4a54-f87b-675b1aa8b1d0"
},
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"sample_data\t\t train-images-idx3-ubyte\n",
"t10k-images-idx3-ubyte\t train-images-idx3-ubyte.gz\n",
"t10k-images-idx3-ubyte.gz train-labels-idx1-ubyte\n",
"t10k-labels-idx1-ubyte\t train-labels-idx1-ubyte.gz\n",
"t10k-labels-idx1-ubyte.gz\n"
]
}
],
"source": [
"!ls"
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "CG3DAEF_4Oke",
"outputId": "73531368-5ec9-4c06-d90a-cea370345856"
},
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"행: 60000, 열: 784\n"
]
}
],
"source": [
"X_train, y_train = load_mnist('', kind='train')\n",
"print('행: %d, 열: %d' % (X_train.shape[0], X_train.shape[1]))"
]
},
{
"cell_type": "code",
"execution_count": 12,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "0onTIGXH4Oke",
"outputId": "07bbc43e-808b-4f02-e33a-59888b811576"
},
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"행: 10000, 열: 784\n"
]
}
],
"source": [
"X_test, y_test = load_mnist('', kind='t10k')\n",
"print('행: %d, 열: %d' % (X_test.shape[0], X_test.shape[1]))"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "2VSBU6TT4Okf"
},
"source": [
"각 클래스의 첫 번째 이미지를 그립니다:"
]
},
{
"cell_type": "code",
"execution_count": 13,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 338
},
"id": "FbAKUDJG4Okg",
"outputId": "66f56699-965f-4009-9e26-f687f4bbb428"
},
"outputs": [
{
"output_type": "display_data",
"data": {
"text/plain": [
""
],
"image/png": "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\n"
},
"metadata": {}
}
],
"source": [
"import matplotlib.pyplot as plt\n",
"\n",
"fig, ax = plt.subplots(nrows=2, ncols=5, sharex=True, sharey=True)\n",
"ax = ax.flatten()\n",
"for i in range(10):\n",
" img = X_train[y_train == i][0].reshape(28, 28)\n",
" ax[i].imshow(img, cmap='Greys')\n",
"\n",
"ax[0].set_xticks([])\n",
"ax[0].set_yticks([])\n",
"plt.tight_layout()\n",
"# plt.savefig('images/12_5.png', dpi=300)\n",
"plt.show()"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "HUnoHgFM4Okg"
},
"source": [
"숫자 7 샘플 25개를 그립니다:"
]
},
{
"cell_type": "code",
"execution_count": 14,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 486
},
"id": "BavCchb_4Okh",
"outputId": "4a111438-52f1-4452-9b74-c25b1edaf6bd",
"scrolled": true
},
"outputs": [
{
"output_type": "display_data",
"data": {
"text/plain": [
""
],
"image/png": "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\n"
},
"metadata": {}
}
],
"source": [
"fig, ax = plt.subplots(nrows=5, ncols=5, sharex=True, sharey=True,)\n",
"ax = ax.flatten()\n",
"for i in range(25):\n",
" img = X_train[y_train == 7][i].reshape(28, 28)\n",
" ax[i].imshow(img, cmap='Greys')\n",
"\n",
"ax[0].set_xticks([])\n",
"ax[0].set_yticks([])\n",
"plt.tight_layout()\n",
"# plt.savefig('images/12_6.png', dpi=300)\n",
"plt.show()"
]
},
{
"cell_type": "code",
"execution_count": 15,
"metadata": {
"id": "Ia7lqEr64Okh"
},
"outputs": [],
"source": [
"import numpy as np\n",
"\n",
"np.savez_compressed('mnist_scaled.npz',\n",
" X_train=X_train,\n",
" y_train=y_train,\n",
" X_test=X_test,\n",
" y_test=y_test)"
]
},
{
"cell_type": "code",
"execution_count": 16,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "l0lcuihY4Oki",
"outputId": "d61781aa-13aa-4149-862a-ac605646075c"
},
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"['X_train', 'y_train', 'X_test', 'y_test']"
]
},
"metadata": {},
"execution_count": 16
}
],
"source": [
"mnist = np.load('mnist_scaled.npz')\n",
"mnist.files"
]
},
{
"cell_type": "code",
"execution_count": 17,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "kL_pNeYW4Oki",
"outputId": "d9a9866b-6ae0-436c-d32b-d951ddd39fa0"
},
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"(60000, 784)"
]
},
"metadata": {},
"execution_count": 17
}
],
"source": [
"X_train, y_train, X_test, y_test = [mnist[f] for f in ['X_train', 'y_train',\n",
" 'X_test', 'y_test']]\n",
"\n",
"del mnist\n",
"\n",
"X_train.shape"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "yo4f_UJ64Oki"
},
"source": [
"
\n",
"
"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "wvMEd6qy4Oki"
},
"source": [
"## 다층 퍼셉트론 구현"
]
},
{
"cell_type": "code",
"execution_count": 18,
"metadata": {
"id": "ps0ZyJjU4Oki"
},
"outputs": [],
"source": [
"import numpy as np\n",
"import sys\n",
"\n",
"\n",
"class NeuralNetMLP(object):\n",
" \"\"\"피드포워드 신경망 / 다층 퍼셉트론 분류기\n",
"\n",
" 매개변수\n",
"\n",
" ------------\n",
" n_hidden : int (기본값: 30)\n",
" 은닉 유닛 개수\n",
" l2 : float (기본값: 0.)\n",
" L2 규제의 람다 값\n",
" l2=0이면 규제 없음. (기본값)\n",
" epochs : int (기본값: 100)\n",
" 훈련 세트를 반복할 횟수\n",
" eta : float (기본값: 0.001)\n",
" 학습률\n",
" shuffle : bool (기본값: True)\n",
" 에포크마다 훈련 세트를 섞을지 여부\n",
" True이면 데이터를 섞어 순서를 바꿉니다\n",
" minibatch_size : int (기본값: 1)\n",
" 미니 배치의 훈련 샘플 개수\n",
" seed : int (기본값: None)\n",
" 가중치와 데이터 셔플링을 위한 난수 초깃값\n",
"\n",
" 속성\n",
" -----------\n",
" eval_ : dict\n",
" 훈련 에포크마다 비용, 훈련 정확도, 검증 정확도를 수집하기 위한 딕셔너리\n",
"\n",
" \"\"\"\n",
" def __init__(self, n_hidden=30,\n",
" l2=0., epochs=100, eta=0.001,\n",
" shuffle=True, minibatch_size=1, seed=None):\n",
"\n",
" self.random = np.random.RandomState(seed)\n",
" self.n_hidden = n_hidden\n",
" self.l2 = l2\n",
" self.epochs = epochs\n",
" self.eta = eta\n",
" self.shuffle = shuffle\n",
" self.minibatch_size = minibatch_size\n",
"\n",
" def _onehot(self, y, n_classes):\n",
" \"\"\"레이블을 원-핫 방식으로 인코딩합니다\n",
"\n",
" 매개변수\n",
" ------------\n",
" y : 배열, 크기 = [n_samples]\n",
" 타깃 값.\n",
" n_classes : int\n",
" 클래스 개수\n",
"\n",
" 반환값\n",
" -----------\n",
" onehot : 배열, 크기 = (n_samples, n_labels)\n",
"\n",
" \"\"\"\n",
" onehot = np.zeros((n_classes, y.shape[0]))\n",
" for idx, val in enumerate(y.astype(int)):\n",
" onehot[val, idx] = 1.\n",
" return onehot.T\n",
"\n",
" def _sigmoid(self, z):\n",
" \"\"\"로지스틱 함수(시그모이드)를 계산합니다\"\"\"\n",
" return 1. / (1. + np.exp(-np.clip(z, -250, 250)))\n",
"\n",
" def _forward(self, X):\n",
" \"\"\"정방향 계산을 수행합니다\"\"\"\n",
"\n",
" # 단계 1: 은닉층의 최종 입력\n",
" # [n_samples, n_features] dot [n_features, n_hidden]\n",
" # -> [n_samples, n_hidden]\n",
" z_h = np.dot(X, self.w_h) + self.b_h\n",
"\n",
" # 단계 2: 은닉층의 활성화 출력\n",
" a_h = self._sigmoid(z_h)\n",
"\n",
" # 단계 3: 출력층의 최종 입력\n",
" # [n_samples, n_hidden] dot [n_hidden, n_classlabels]\n",
" # -> [n_samples, n_classlabels]\n",
" z_out = np.dot(a_h, self.w_out) + self.b_out\n",
"\n",
" # 단계 4: 출력층의 활성화 출력\n",
" a_out = self._sigmoid(z_out)\n",
"\n",
" return z_h, a_h, z_out, a_out\n",
"\n",
" def _compute_cost(self, y_enc, output):\n",
" \"\"\"비용 함수를 계산합니다\n",
"\n",
" 매개변수\n",
" ----------\n",
" y_enc : 배열, 크기 = (n_samples, n_labels)\n",
" 원-핫 인코딩된 클래스 레이블\n",
" output : 배열, 크기 = [n_samples, n_output_units]\n",
" 출력층의 활성화 출력 (정방향 계산)\n",
"\n",
" 반환값\n",
" ---------\n",
" cost : float\n",
" 규제가 포함된 비용\n",
"\n",
" \"\"\"\n",
" L2_term = (self.l2 *\n",
" (np.sum(self.w_h ** 2.) +\n",
" np.sum(self.w_out ** 2.)))\n",
"\n",
" term1 = -y_enc * (np.log(output))\n",
" term2 = (1. - y_enc) * np.log(1. - output)\n",
" cost = np.sum(term1 - term2) + L2_term\n",
"\n",
" # 다른 데이터셋에서는 극단적인 (0 또는 1에 가까운) 활성화 값이 나올 수 있습니다.\n",
" # 파이썬과 넘파이의 수치 연산이 불안정하기 때문에 \"ZeroDivisionError\"가 발생할 수 있습니다.\n",
" # 즉, log(0)을 평가하는 경우입니다.\n",
" # 이 문제를 해결하기 위해 로그 함수에 전달되는 활성화 값에 작은 상수를 더합니다.\n",
" #\n",
" # 예를 들어:\n",
" #\n",
" # term1 = -y_enc * (np.log(output + 1e-5))\n",
" # term2 = (1. - y_enc) * np.log(1. - output + 1e-5)\n",
"\n",
" return cost\n",
"\n",
" def predict(self, X):\n",
" \"\"\"클래스 레이블을 예측합니다\n",
"\n",
" 매개변수\n",
" -----------\n",
" X : 배열, 크기 = [n_samples, n_features]\n",
" 원본 특성의 입력층\n",
"\n",
" 반환값:\n",
" ----------\n",
" y_pred : 배열, 크기 = [n_samples]\n",
" 예측된 클래스 레이블\n",
"\n",
" \"\"\"\n",
" z_h, a_h, z_out, a_out = self._forward(X)\n",
" y_pred = np.argmax(z_out, axis=1)\n",
" return y_pred\n",
"\n",
" def fit(self, X_train, y_train, X_valid, y_valid):\n",
" \"\"\"훈련 데이터에서 가중치를 학습합니다\n",
"\n",
" 매개변수\n",
" -----------\n",
" X_train : 배열, 크기 = [n_samples, n_features]\n",
" 원본 특성의 입력층\n",
" y_train : 배열, 크기 = [n_samples]\n",
" 타깃 클래스 레이블\n",
" X_valid : 배열, 크기 = [n_samples, n_features]\n",
" 훈련하는 동안 검증에 사용할 샘플 특성\n",
" y_valid : 배열, 크기 = [n_samples]\n",
" 훈련하는 동안 검증에 사용할 샘플 레이블\n",
"\n",
" 반환값:\n",
" ----------\n",
" self\n",
"\n",
" \"\"\"\n",
" n_output = np.unique(y_train).shape[0] # number of class labels\n",
" n_features = X_train.shape[1]\n",
"\n",
" ########################\n",
" # 가중치 초기화\n",
" ########################\n",
"\n",
" # 입력층 -> 은닉층 사이의 가중치\n",
" self.b_h = np.zeros(self.n_hidden)\n",
" self.w_h = self.random.normal(loc=0.0, scale=0.1,\n",
" size=(n_features, self.n_hidden))\n",
"\n",
" # 은닉층 -> 출력층 사이의 가중치\n",
" self.b_out = np.zeros(n_output)\n",
" self.w_out = self.random.normal(loc=0.0, scale=0.1,\n",
" size=(self.n_hidden, n_output))\n",
"\n",
" epoch_strlen = len(str(self.epochs)) # 출력 포맷을 위해\n",
" self.eval_ = {'cost': [], 'train_acc': [], 'valid_acc': []}\n",
"\n",
" y_train_enc = self._onehot(y_train, n_output)\n",
"\n",
" # 훈련 에포크를 반복합니다\n",
" for i in range(self.epochs):\n",
"\n",
" # 미니 배치로 반복합니다\n",
" indices = np.arange(X_train.shape[0])\n",
"\n",
" if self.shuffle:\n",
" self.random.shuffle(indices)\n",
"\n",
" for start_idx in range(0, indices.shape[0] - self.minibatch_size +\n",
" 1, self.minibatch_size):\n",
" batch_idx = indices[start_idx:start_idx + self.minibatch_size]\n",
"\n",
" # 정방향 계산\n",
" z_h, a_h, z_out, a_out = self._forward(X_train[batch_idx])\n",
"\n",
" ##################\n",
" # 역전파\n",
" ##################\n",
"\n",
" # [n_examples, n_classlabels]\n",
" delta_out = a_out - y_train_enc[batch_idx]\n",
"\n",
" # [n_examples, n_hidden]\n",
" sigmoid_derivative_h = a_h * (1. - a_h)\n",
"\n",
" # [n_examples, n_classlabels] dot [n_classlabels, n_hidden]\n",
" # -> [n_examples, n_hidden]\n",
" delta_h = (np.dot(delta_out, self.w_out.T) *\n",
" sigmoid_derivative_h)\n",
"\n",
" # [n_features, n_examples] dot [n_examples, n_hidden]\n",
" # -> [n_features, n_hidden]\n",
" grad_w_h = np.dot(X_train[batch_idx].T, delta_h)\n",
" grad_b_h = np.sum(delta_h, axis=0)\n",
"\n",
" # [n_hidden, n_examples] dot [n_examples, n_classlabels]\n",
" # -> [n_hidden, n_classlabels]\n",
" grad_w_out = np.dot(a_h.T, delta_out)\n",
" grad_b_out = np.sum(delta_out, axis=0)\n",
"\n",
" # 규제와 가중치 업데이트\n",
" delta_w_h = (grad_w_h + self.l2*self.w_h)\n",
" delta_b_h = grad_b_h # 편향은 규제하지 않습니다\n",
" self.w_h -= self.eta * delta_w_h\n",
" self.b_h -= self.eta * delta_b_h\n",
"\n",
" delta_w_out = (grad_w_out + self.l2*self.w_out)\n",
" delta_b_out = grad_b_out # 편향은 규제하지 않습니다\n",
" self.w_out -= self.eta * delta_w_out\n",
" self.b_out -= self.eta * delta_b_out\n",
"\n",
" #############\n",
" # 평가\n",
" #############\n",
"\n",
" # 훈련하는 동안 에포크마다 평가합니다\n",
" z_h, a_h, z_out, a_out = self._forward(X_train)\n",
"\n",
" cost = self._compute_cost(y_enc=y_train_enc,\n",
" output=a_out)\n",
"\n",
" y_train_pred = self.predict(X_train)\n",
" y_valid_pred = self.predict(X_valid)\n",
"\n",
" # 넘파이 1.20에서 `np.float`가 deprecated되므로 대신 `float`를 사용합니다.\n",
" train_acc = ((np.sum(y_train == y_train_pred)).astype(float) /\n",
" X_train.shape[0])\n",
" valid_acc = ((np.sum(y_valid == y_valid_pred)).astype(float) /\n",
" X_valid.shape[0])\n",
"\n",
" sys.stderr.write('\\r%0*d/%d | 비용: %.2f '\n",
" '| 훈련/검증 정확도: %.2f%%/%.2f%% ' %\n",
" (epoch_strlen, i+1, self.epochs, cost,\n",
" train_acc*100, valid_acc*100))\n",
" sys.stderr.flush()\n",
"\n",
" self.eval_['cost'].append(cost)\n",
" self.eval_['train_acc'].append(train_acc)\n",
" self.eval_['valid_acc'].append(valid_acc)\n",
"\n",
" return self"
]
},
{
"cell_type": "code",
"execution_count": 19,
"metadata": {
"id": "-vdALhZX4Okj"
},
"outputs": [],
"source": [
"n_epochs = 200"
]
},
{
"cell_type": "code",
"execution_count": 20,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "hNzZGfqF4Okk",
"outputId": "a5b50f5e-6816-4a7b-ace5-719419a103b4"
},
"outputs": [
{
"output_type": "stream",
"name": "stderr",
"text": [
"200/200 | 비용: 5065.78 | 훈련/검증 정확도: 99.28%/97.98% "
]
},
{
"output_type": "execute_result",
"data": {
"text/plain": [
"<__main__.NeuralNetMLP at 0x7e5c9c41f0e0>"
]
},
"metadata": {},
"execution_count": 20
}
],
"source": [
"nn = NeuralNetMLP(n_hidden=100,\n",
" l2=0.01,\n",
" epochs=n_epochs,\n",
" eta=0.0005,\n",
" minibatch_size=100,\n",
" shuffle=True,\n",
" seed=1)\n",
"\n",
"nn.fit(X_train=X_train[:55000],\n",
" y_train=y_train[:55000],\n",
" X_valid=X_train[55000:],\n",
" y_valid=y_train[55000:])"
]
},
{
"cell_type": "code",
"execution_count": 21,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 449
},
"id": "8YRZV-vn4Okk",
"outputId": "cca5790c-ae97-4270-c1e2-3b8a88140d9f"
},
"outputs": [
{
"output_type": "display_data",
"data": {
"text/plain": [
""
],
"image/png": "iVBORw0KGgoAAAANSUhEUgAAAk0AAAGwCAYAAAC0HlECAAAAOnRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjEwLjAsIGh0dHBzOi8vbWF0cGxvdGxpYi5vcmcvlHJYcgAAAAlwSFlzAAAPYQAAD2EBqD+naQAAUNNJREFUeJzt3Xl4FFW+P/539Z6tO/sGgYSdsApIjLgMEgkYHRHuiA5XUVAGJjACKgyjgnrnioN3RB0Rx3E0fMdRNDOugPALIKAStiA7RJZAgKSzkKQ7a3e6+/z+CKmhTYBOTFLdyfv1PP08dNXp6k+lTOptnVOnJCGEABERERFdk0rpAoiIiIh8AUMTERERkQcYmoiIiIg8wNBERERE5AGGJiIiIiIPMDQREREReYChiYiIiMgDGqUL6CxcLhcKCgoQFBQESZKULoeIiIg8IIRAZWUlYmNjoVJd+1oSQ1MbKSgoQFxcnNJlEBERUSucP38e3bt3v2YbhqY2EhQUBKDhh240GhWuhoiIiDxhtVoRFxcnn8evhaGpjTR2yRmNRoYmIiIiH+PJ0BoOBCciIiLyAEMTERERkQcYmoiIiIg8wNBERERE5AGGJiIiIiIPMDQREREReYChiYiIiMgDDE1EREREHmBoIiIiIvIAQxMRERGRBxiaiIiIiDzA0ERERETkAT6w18vV2p0oq7FDq5IQaTQoXQ4REVGXxStNXm7TUTPGvLwVT2YeVLoUIiKiLo2hyctp1BIAwO5wKVwJERFR18bQ5OW06oZDVO9kaCIiIlISQ5OX010OTQ6XULgSIiKiro2hycuxe46IiMg7MDR5OS2vNBEREXkFhiYvp718pYljmoiIiJTF0OTl5IHg7J4jIiJSFEOTl5NDE7vniIiIFMXQ5OXYPUdEROQdGJq8HLvniIiIvANDk5dj9xwREZF3YGjycporuueEYHAiIiJSCkOTl2ucEVwIwMmrTURERIphaPJyjd1zACe4JCIiUhJDk5dr7J4DADvvoCMiIlIMQ5OX06quuNLk5JUmIiIipTA0eTmVSoJaxbmaiIiIlMbQ5AMaJ7i0c64mIiIixTA0+YDGweAcCE5ERKQchiYfIE9wye45IiIixTA0+QB2zxERESmPockHsHuOiIhIeQxNPoDdc0RERMpjaPIBWjWnHCAiIlIaQ5MP0KgarzSxe46IiEgpDE0+QKu5HJo4EJyIiEgxDE0+QHe5e87hYmgiIiJSCkOTD2jsnrOze46IiEgxDE0+gN1zREREymNo8gHsniMiIlIeQ5MPYPccERGR8hiafAC754iIiJTH0OQDtCp2zxERESlN8dB08eJF/Pd//zfCwsLg5+eHIUOGYN++ffJ6IQSWLl2KmJgY+Pn5ISUlBSdPnnTbRllZGaZNmwaj0Yjg4GDMnDkTVVVVbm0OHTqEW2+9FQaDAXFxcVixYkWTWjIzMzFgwAAYDAYMGTIEGzZsaJ+dbqH/PEaF3XNERERKUTQ0lZeXY8yYMdBqtfj6669x7Ngx/PnPf0ZISIjcZsWKFXjjjTfw9ttvY/fu3QgICEBqairq6urkNtOmTcPRo0eRlZWFdevWYceOHZg1a5a83mq1Yvz48ejZsydycnLwyiuv4Pnnn8c777wjt9m5cycefPBBzJw5Ez/88AMmTZqESZMm4ciRIx3zw7gGrYaPUSEiIlKcUNDixYvFLbfcctX1LpdLREdHi1deeUVeVlFRIfR6vfjoo4+EEEIcO3ZMABB79+6V23z99ddCkiRx8eJFIYQQb731lggJCRE2m83tu/v37y+/v//++0VaWprb9yclJYnf/OY3Hu2LxWIRAITFYvGofUss++KI6Ll4nVix8Xibb5uIiKgra8n5W9ErTV9++SVGjRqFX/3qV4iMjMQNN9yAv/3tb/L6vLw8mM1mpKSkyMtMJhOSkpKQnZ0NAMjOzkZwcDBGjRolt0lJSYFKpcLu3bvlNrfddht0Op3cJjU1Fbm5uSgvL5fbXPk9jW0av+enbDYbrFar26u96DTsniMiIlKaoqHpzJkzWL16Nfr27YtNmzZhzpw5+N3vfoc1a9YAAMxmMwAgKirK7XNRUVHyOrPZjMjISLf1Go0GoaGhbm2a28aV33G1No3rf2r58uUwmUzyKy4ursX77ymtmt1zRERESlM0NLlcLowYMQIvvfQSbrjhBsyaNQuPP/443n77bSXL8siSJUtgsVjk1/nz59vtuxrnaWJoIiIiUo6ioSkmJgaJiYluywYOHIj8/HwAQHR0NACgqKjIrU1RUZG8Ljo6GsXFxW7rHQ4HysrK3No0t40rv+NqbRrX/5Rer4fRaHR7tRe5e87B7jkiIiKlKBqaxowZg9zcXLdlP/74I3r27AkASEhIQHR0NLZs2SKvt1qt2L17N5KTkwEAycnJqKioQE5Ojtxm69atcLlcSEpKktvs2LED9fX1cpusrCz0799fvlMvOTnZ7Xsa2zR+j5Lk7jnO00RERKQYRUPTggULsGvXLrz00ks4deoUPvzwQ7zzzjtIT08HAEiShPnz5+OPf/wjvvzySxw+fBgPP/wwYmNjMWnSJAANV6YmTJiAxx9/HHv27MH333+PuXPn4oEHHkBsbCwA4Ne//jV0Oh1mzpyJo0eP4uOPP8brr7+OhQsXyrU88cQT2LhxI/785z/jxIkTeP7557Fv3z7MnTu3w38uP/Wf7jleaSIiIlJMB9zNd01fffWVGDx4sNDr9WLAgAHinXfecVvvcrnEc889J6KiooRerxfjxo0Tubm5bm0uXbokHnzwQREYGCiMRqN49NFHRWVlpVubgwcPiltuuUXo9XrRrVs38fLLLzep5ZNPPhH9+vUTOp1ODBo0SKxfv97j/WjPKQf+X/ZZ0XPxOjH7H/vafNtERERdWUvO35IQgpcv2oDVaoXJZILFYmnz8U1r9+Tj958eRsrASLw7/cY23TYREVFX1pLzt+KPUaHra3yMip3dc0RERIphaPIB2st3zzk45QAREZFiGJp8gFbFyS2JiIiUxtDkA9g9R0REpDyGJh/A7jkiIiLlMTT5AHbPERERKY+hyQc0Xmni5JZERETKYWjyARpeaSIiIlIcQ5MPaBwIztBERESkHIYmH6CTB4Kze46IiEgpDE0+oLF7zs4rTURERIphaPIB7J4jIiJSHkOTD2D3HBERkfIYmnxAY/ecwyXgcjE4ERERKYGhyQc0ztMEAPUudtEREREpgaHJB+jU/zlM7KIjIiJSBkOTD2jsngM4GJyIiEgpDE0+QK2SIF3OTZx2gIiISBkMTT5AkiRoVbyDjoiISEkMTT5Cq+bz54iIiJTE0OQjGu+gq+eVJiIiIkUwNPkIjYqzghMRESmJoclH6Ng9R0REpCiGJh/B7jkiIiJlMTT5iMa5mniliYiISBkMTT5Cq+aYJiIiIiUxNPmIxtDEeZqIiIiUwdDkIxrnaeKM4ERERMpgaPIRvNJERESkLIYmH8ExTURERMpiaPIR7J4jIiJSFkOTj2D3HBERkbIYmnwEu+eIiIiUxdDkI7R8jAoREZGiGJp8hEbNx6gQEREpiaHJR7B7joiISFkMTT5Cx+45IiIiRTE0+Qh2zxERESmLoclHsHuOiIhIWQxNPqKxe87B0ERERKQIhiYf0dg9Z2f3HBERkSIYmnwEu+eIiIiUxdDkI7TsniMiIlKUoqHp+eefhyRJbq8BAwbI6+vq6pCeno6wsDAEBgZiypQpKCoqcttGfn4+0tLS4O/vj8jISDz99NNwOBxubbZt24YRI0ZAr9ejT58+yMjIaFLLqlWrEB8fD4PBgKSkJOzZs6dd9rm1tLx7joiISFGKX2kaNGgQCgsL5dd3330nr1uwYAG++uorZGZmYvv27SgoKMDkyZPl9U6nE2lpabDb7di5cyfWrFmDjIwMLF26VG6Tl5eHtLQ0jB07FgcOHMD8+fPx2GOPYdOmTXKbjz/+GAsXLsSyZcuwf/9+DBs2DKmpqSguLu6YH4IHtPKYJl5pIiIiUoRQ0LJly8SwYcOaXVdRUSG0Wq3IzMyUlx0/flwAENnZ2UIIITZs2CBUKpUwm81ym9WrVwuj0ShsNpsQQohFixaJQYMGuW176tSpIjU1VX4/evRokZ6eLr93Op0iNjZWLF++3ON9sVgsAoCwWCwef6YlPt6bL3ouXiceeW93u2yfiIioK2rJ+VvxK00nT55EbGwsevXqhWnTpiE/Px8AkJOTg/r6eqSkpMhtBwwYgB49eiA7OxsAkJ2djSFDhiAqKkpuk5qaCqvViqNHj8ptrtxGY5vGbdjtduTk5Li1UalUSElJkds0x2azwWq1ur3ak47dc0RERIpSNDQlJSUhIyMDGzduxOrVq5GXl4dbb70VlZWVMJvN0Ol0CA4OdvtMVFQUzGYzAMBsNrsFpsb1jeuu1cZqtaK2thalpaVwOp3NtmncRnOWL18Ok8kkv+Li4lr1M/AU754jIiJSlkbJL584caL876FDhyIpKQk9e/bEJ598Aj8/PwUru74lS5Zg4cKF8nur1dquwUnDZ88REREpSvHuuSsFBwejX79+OHXqFKKjo2G321FRUeHWpqioCNHR0QCA6OjoJnfTNb6/Xhuj0Qg/Pz+Eh4dDrVY326ZxG83R6/UwGo1ur/bE7jkiIiJleVVoqqqqwunTpxETE4ORI0dCq9Viy5Yt8vrc3Fzk5+cjOTkZAJCcnIzDhw+73eWWlZUFo9GIxMREuc2V22hs07gNnU6HkSNHurVxuVzYsmWL3MYbsHuOiIhIWYqGpqeeegrbt2/H2bNnsXPnTtx3331Qq9V48MEHYTKZMHPmTCxcuBDffPMNcnJy8OijjyI5ORk33XQTAGD8+PFITEzEQw89hIMHD2LTpk149tlnkZ6eDr1eDwCYPXs2zpw5g0WLFuHEiRN466238Mknn2DBggVyHQsXLsTf/vY3rFmzBsePH8ecOXNQXV2NRx99VJGfS3PYPUdERKQsRcc0XbhwAQ8++CAuXbqEiIgI3HLLLdi1axciIiIAACtXroRKpcKUKVNgs9mQmpqKt956S/68Wq3GunXrMGfOHCQnJyMgIADTp0/Hiy++KLdJSEjA+vXrsWDBArz++uvo3r073n33XaSmpsptpk6dipKSEixduhRmsxnDhw/Hxo0bmwwOVxIntyQiIlKWJITgWbgNWK1WmEwmWCyWdhnfdOhCBX755veINRmwc8m4Nt8+ERFRV9SS87dXjWmiq/vPjODMuEREREpgaPIRHAhORESkLIYmH6G9PBDcwdBERESkCIYmH8GB4ERERMpiaPIR/xnT5ALH7hMREXU8hiYf4adTy/+2OdhFR0RE1NEYmnyEv1YNqWFYEyrrHMoWQ0RE1AUxNPkIlUpCoK5hLtLKunqFqyEiIup6GJp8SKChITRV2XiliYiIqKMxNPmQoMbQxO45IiKiDsfQ5EMC9Ze753iliYiIqMMxNPmQQIMWAK80ERERKYGhyYcE6TkQnIiISCkMTT4kiAPBiYiIFMPQ5EM4pomIiEg5DE0+JJB3zxERESmGocmHyFeaGJqIiIg6HEOTD+GYJiIiIuUwNPmQIE45QEREpBiGJh/CgeBERETKYWjyIf959hznaSIiIupoDE0+JIgDwYmIiBTD0ORDrpxyQAihcDVERERdC0OTD2kcCO5wCdgcLoWrISIi6loYmnyIv1YNSWr4N7voiIiIOhZDkw9RqSQE6vjQXiIiIiUwNPmYQE5wSUREpAiGJh8TxOfPERERKYKhycdwgksiIiJlMDT5mEA+SoWIiEgRDE0+5j8TXHIgOBERUUdiaPIxjd1zHAhORETUsRiafEzjQHCOaSIiIupYDE0+JpB3zxERESmCocnHBPKhvURERIpgaPIxQZzckoiISBEMTT4mUM8pB4iIiJTA0ORjOBCciIhIGQxNPuY/z57jPE1EREQdiaHJxwRxIDgREZEiGJp8zJVTDgghFK6GiIio62Bo8jFBl58953AJ2BwuhashIiLqOhiafIy/Vg1Javg3u+iIiIg6DkOTj1GpJATq+NBeIiKijuY1oenll1+GJEmYP3++vKyurg7p6ekICwtDYGAgpkyZgqKiIrfP5efnIy0tDf7+/oiMjMTTTz8Nh8P9Csy2bdswYsQI6PV69OnTBxkZGU2+f9WqVYiPj4fBYEBSUhL27NnTHrvZJgI5wSUREVGH84rQtHfvXvz1r3/F0KFD3ZYvWLAAX331FTIzM7F9+3YUFBRg8uTJ8nqn04m0tDTY7Xbs3LkTa9asQUZGBpYuXSq3ycvLQ1paGsaOHYsDBw5g/vz5eOyxx7Bp0ya5zccff4yFCxdi2bJl2L9/P4YNG4bU1FQUFxe3/863Ah+lQkREpAChsMrKStG3b1+RlZUlbr/9dvHEE08IIYSoqKgQWq1WZGZmym2PHz8uAIjs7GwhhBAbNmwQKpVKmM1muc3q1auF0WgUNptNCCHEokWLxKBBg9y+c+rUqSI1NVV+P3r0aJGeni6/dzqdIjY2Vixfvtzj/bBYLAKAsFgsnu98K93/9k7Rc/E68fkPF9r9u4iIiDqzlpy/Fb/SlJ6ejrS0NKSkpLgtz8nJQX19vdvyAQMGoEePHsjOzgYAZGdnY8iQIYiKipLbpKamwmq14ujRo3Kbn247NTVV3obdbkdOTo5bG5VKhZSUFLlNc2w2G6xWq9uro0QaDQCAkkpbh30nERFRV6dR8svXrl2L/fv3Y+/evU3Wmc1m6HQ6BAcHuy2PioqC2WyW21wZmBrXN667Vhur1Yra2lqUl5fD6XQ22+bEiRNXrX358uV44YUXPNvRNhYZpAcAFDM0ERERdRjFrjSdP38eTzzxBP75z3/CYDAoVUarLVmyBBaLRX6dP3++w75bDk3Wug77TiIioq5OsdCUk5OD4uJijBgxAhqNBhqNBtu3b8cbb7wBjUaDqKgo2O12VFRUuH2uqKgI0dHRAIDo6Ogmd9M1vr9eG6PRCD8/P4SHh0OtVjfbpnEbzdHr9TAajW6vjhJp5JUmIiKijqZYaBo3bhwOHz6MAwcOyK9Ro0Zh2rRp8r+1Wi22bNkifyY3Nxf5+flITk4GACQnJ+Pw4cNud7llZWXBaDQiMTFRbnPlNhrbNG5Dp9Nh5MiRbm1cLhe2bNkit/E2kUENV+YYmoiIiDqOYmOagoKCMHjwYLdlAQEBCAsLk5fPnDkTCxcuRGhoKIxGI+bNm4fk5GTcdNNNAIDx48cjMTERDz30EFasWAGz2Yxnn30W6enp0OsbrsbMnj0bb775JhYtWoQZM2Zg69at+OSTT7B+/Xr5excuXIjp06dj1KhRGD16NF577TVUV1fj0Ucf7aCfRsuwe46IiKjjKToQ/HpWrlwJlUqFKVOmwGazITU1FW+99Za8Xq1WY926dZgzZw6Sk5MREBCA6dOn48UXX5TbJCQkYP369ViwYAFef/11dO/eHe+++y5SU1PlNlOnTkVJSQmWLl0Ks9mM4cOHY+PGjU0Gh3uLxitN1joH6uqdMGjVCldERETU+UlCCKF0EZ2B1WqFyWSCxWJp9/FNQgj0f24j7A4Xvl00FnGh/u36fURERJ1VS87fis/TRC0nSdIV0w6wi46IiKgjMDT5qAh5XBMHgxMREXWEVoWmF198ETU1NU2W19bWuo0novbDCS6JiIg6VqtC0wsvvICqqqomy2tqahSbJbur+c+0A+yeIyIi6gitCk1CCEiS1GT5wYMHERoa+rOLouuLZPccERFRh2rRlAMhISGQJAmSJKFfv35uwcnpdKKqqgqzZ89u8yKpqcZZwUuqGJqIiIg6QotC02uvvQYhBGbMmIEXXngBJpNJXqfT6RAfH++1s2h3NnL3HK80ERERdYgWhabp06cDaJgwcsyYMdBovHpuzE4tggPBiYiIOlSrxjQFBQXh+PHj8vsvvvgCkyZNwh/+8AfY7fY2K46urrF77lK1DQ6nS+FqiIiIOr9Whabf/OY3+PHHHwEAZ86cwdSpU+Hv74/MzEwsWrSoTQuk5oUF6KGSACGAS9UMqkRERO2tVaHpxx9/xPDhwwEAmZmZuP322/Hhhx8iIyMD//73v9uyProKtUpCeCDvoCMiIuoorZ5ywOVq6BLavHkz7rrrLgBAXFwcSktL2646uqbGLjrO1URERNT+WhWaRo0ahT/+8Y/4xz/+ge3btyMtLQ0AkJeXh6ioqDYtkK7uPxNc8koTERFRe2tVaHrttdewf/9+zJ07F8888wz69OkDAPjXv/6Fm2++uU0LpKuLYPccERFRh2nVnAFDhw7F4cOHmyx/5ZVXoFarf3ZR5JluIX4AgPyyps8BJCIiorb1syZaysnJkaceSExMxIgRI9qkKPJM74hAAMDpkqbPASQiIqK21arQVFxcjKlTp2L79u0IDg4GAFRUVGDs2LFYu3YtIiIi2rJGuoo+kZdDU3HVVZ8HSERERG2jVWOa5s2bh6qqKhw9ehRlZWUoKyvDkSNHYLVa8bvf/a6ta6SriA/3h0oCKm0OlHAwOBERUbtq1ZWmjRs3YvPmzRg4cKC8LDExEatWrcL48ePbrDi6Nr1GjR6h/jh7qQaniqsQaTQoXRIREVGn1aorTS6XC1qttslyrVYrz99EHYPjmoiIiDpGq0LTHXfcgSeeeAIFBQXysosXL2LBggUYN25cmxVH19e7cVxTSbXClRAREXVurQpNb775JqxWK+Lj49G7d2/07t0bCQkJsFqt+Mtf/tLWNdI19Ll8pelUMa80ERERtadWjWmKi4vD/v37sXnzZpw4cQIAMHDgQKSkpLRpcXR9vSMDALB7joiIqL216ErT1q1bkZiYCKvVCkmScOedd2LevHmYN28ebrzxRgwaNAjffvtte9VKzWgc01RoqUOVzaFwNURERJ1Xi0LTa6+9hscffxxGo7HJOpPJhN/85jd49dVX26w4ur5gfx3CA3UAgDO82kRERNRuWhSaDh48iAkTJlx1/fjx45GTk/Ozi6KW4R10RERE7a9FoamoqKjZqQYaaTQalJSU/OyiqGUa76DjYHAiIqL206LQ1K1bNxw5cuSq6w8dOoSYmJifXRS1jHylqZjTDhAREbWXFoWmu+66C8899xzq6uqarKutrcWyZctw9913t1lx5Jm+l680/VhcqXAlREREnVeLphx49tln8emnn6Jfv36YO3cu+vfvDwA4ceIEVq1aBafTiWeeeaZdCqWrGxATBADIK61Gjd0Bf12rZpIgIiKia2jR2TUqKgo7d+7EnDlzsGTJEgghAACSJCE1NRWrVq1CVFRUuxRKVxcZZEB4oB6lVTbkmitxQ48QpUsiIiLqdFp8SaJnz57YsGEDysvLcerUKQgh0LdvX4SE8EStpMRYI3b8WIJjhVaGJiIionbQ6n6ckJAQ3HjjjW1ZC/0MA2OCsOPHEhwvtCpdChERUafUqmfPkfdJjGmYcPRYAUMTERFRe2Bo6iQGxTaEphPmSrhcQuFqiIiIOh+Gpk4iPiwAeo0KNXYnzpXVKF0OERFRp8PQ1Elo1CoMiG6YeoBddERERG2PoakTSbzcRXes0KJwJURERJ0PQ1MnMvDyYPDjhZwZnIiIqK0xNHUivIOOiIio/TA0dSIDYoyQJMBsrUORtenzAYmIiKj1GJo6kUC9BkO7mQAA238sUbgaIiKizoWhqZO5vX8kAGB7LkMTERFRW1I0NK1evRpDhw6F0WiE0WhEcnIyvv76a3l9XV0d0tPTERYWhsDAQEyZMgVFRUVu28jPz0daWhr8/f0RGRmJp59+Gg6Hw63Ntm3bMGLECOj1evTp0wcZGRlNalm1ahXi4+NhMBiQlJSEPXv2tMs+t7df9I8AAHx7sgQOp0vhaoiIiDoPRUNT9+7d8fLLLyMnJwf79u3DHXfcgXvvvRdHjx4FACxYsABfffUVMjMzsX37dhQUFGDy5Mny551OJ9LS0mC327Fz506sWbMGGRkZWLp0qdwmLy8PaWlpGDt2LA4cOID58+fjsccew6ZNm+Q2H3/8MRYuXIhly5Zh//79GDZsGFJTU1FcXNxxP4w2Mqx7MIL9tbDWOfDD+QqlyyEiIuo8hJcJCQkR7777rqioqBBarVZkZmbK644fPy4AiOzsbCGEEBs2bBAqlUqYzWa5zerVq4XRaBQ2m00IIcSiRYvEoEGD3L5j6tSpIjU1VX4/evRokZ6eLr93Op0iNjZWLF++3OO6LRaLACAsFkvLdrgdzP1wv+i5eJ14ZeMJpUshIiLyai05f3vNmCan04m1a9eiuroaycnJyMnJQX19PVJSUuQ2AwYMQI8ePZCdnQ0AyM7OxpAhQxAVFSW3SU1NhdVqla9WZWdnu22jsU3jNux2O3JyctzaqFQqpKSkyG2aY7PZYLVa3V7e4hf9Grrotv3oe1fKiIiIvJXioenw4cMIDAyEXq/H7Nmz8dlnnyExMRFmsxk6nQ7BwcFu7aOiomA2mwEAZrPZLTA1rm9cd602VqsVtbW1KC0thdPpbLZN4zaas3z5cphMJvkVFxfXqv1vD7ddDk1HLlpRXMmpB4iIiNqC4qGpf//+OHDgAHbv3o05c+Zg+vTpOHbsmNJlXdeSJUtgsVjk1/nz55UuSRYRpMeQy1MPfPtjqcLVEBERdQ6KhyadToc+ffpg5MiRWL58OYYNG4bXX38d0dHRsNvtqKiocGtfVFSE6OhoAEB0dHSTu+ka31+vjdFohJ+fH8LDw6FWq5tt07iN5uj1evmuv8aXN7m1bzgA4LtTDE1ERERtQfHQ9FMulws2mw0jR46EVqvFli1b5HW5ubnIz89HcnIyACA5ORmHDx92u8stKysLRqMRiYmJcpsrt9HYpnEbOp0OI0eOdGvjcrmwZcsWuY0vuuVyaPr2ZCmEEApXQ0RE5Ps0Sn75kiVLMHHiRPTo0QOVlZX48MMPsW3bNmzatAkmkwkzZ87EwoULERoaCqPRiHnz5iE5ORk33XQTAGD8+PFITEzEQw89hBUrVsBsNuPZZ59Feno69Ho9AGD27Nl48803sWjRIsyYMQNbt27FJ598gvXr18t1LFy4ENOnT8eoUaMwevRovPbaa6iursajjz6qyM+lLYzsGQI/rRqlVTacMFfKD/MlIiKi1lE0NBUXF+Phhx9GYWEhTCYThg4dik2bNuHOO+8EAKxcuRIqlQpTpkyBzWZDamoq3nrrLfnzarUa69atw5w5c5CcnIyAgABMnz4dL774otwmISEB69evx4IFC/D666+je/fuePfdd5Gamiq3mTp1KkpKSrB06VKYzWYMHz4cGzdubDI43JfoNWok9QrFttwSfHeylKGJiIjoZ5IE+27ahNVqhclkgsVi8ZrxTe9+ewZ/XH8ct/WLwP+bMVrpcoiIiLxOS87fXjemidrOrX0bph7Yk3cJdfVOhashIiLybQxNnVi/qEBEBulRV+/C/nPlSpdDRETk0xiaOjFJknBLn4a76LafLFG4GiIiIt/G0NTJ3TEwEgDw9WEzpx4gIiL6GRiaOrk7BkTCX6dGflkNDl6wKF0OERGRz2Jo6uT8dRqkDGyYOuGrgwUKV0NEROS7GJq6gHuGxQIA1h0qgMvFLjoiIqLWYGjqAm7rFw6jQYMiqw17z5YpXQ4REZFPYmjqAvQaNSYMbnj48JfsoiMiImoVhqYuorGLbv3hQk50SURE1AoMTV3Ezb3DEWsyoKKmHpuOmpUuh4iIyOcwNHURapWE+2+MAwB8tCdf4WqIiIh8D0NTF3L/qDioJGDXmTKcKalSuhwiIiKfwtDUhcQG++EX/RtmCP9473mFqyEiIvItDE1dzAOXu+gycy5wQDgREVELMDR1MXcMiESsyYCyajve//6s0uUQERH5DIamLkajVuGp1P4AgFXfnEJxZZ3CFREREfkGhqYuaNLwbhgWF4wqmwN/3vSj0uUQERH5BIamLkilkrD07kQAwCc553G0wKJwRURERN6PoamLGtkzBGlDYyAE8O63eUqXQ0RE5PUYmrqwWbf2AgCsO1SAkkqbwtUQERF5N4amLmxYXDCGxwWj3ik4SzgREdF1MDR1cY/cHA8A+GDXOdQ7XcoWQ0RE5MUYmrq4u4bEICJIj+JKG74+wgf5EhERXQ1DUxen06jw69E9AADv7DgNIYTCFREREXknhibCw8k94adV48hFK7aeKFa6HCIiIq/E0EQIC9Tj4eSeAIA3tpzk1SYiIqJmMDQRAODx23rBT6vGwQsWbPuxROlyiIiIvA5DEwEAwgP1+O+bGsY2vbIxF7V2p8IVEREReReGJpLNuq03jAYNjhVaMffD/XBwCgIiIiIZQxPJIoL0eHf6jdBrVNhyohhLPj3M8U1ERESXMTSRm9EJoXjz1yOgVknIzLmAzH0XlC6JiIjIKzA0URN3Jkbh6dT+AID/WXcMhZZahSsiIiJSHkMTNevxW3theFwwKm0O/P7f7KYjIiJiaKJmqVUS/u9XQ6HTqLD9xxJ8caBA6ZKIiIgUxdBEV9UnMgi/u6MPAODPWbmwO3g3HRERdV0MTXRNM25JQESQHufLavHxvvNKl0NERKQYhia6Jn+dBnPHNlxt+suWk6ir56SXRETUNTE00XU9MDoO3YL9UFxpw1+3n1G6HCIiIkUwNNF16TVqLLizHwBg5eYf8c6O0wpXRERE1PEYmsgjU0Z0w+zbewMAXtpwAq9t/lHhioiIiDoWQxN5RJIk/H7iACya0DDp5WubTyLnXLnCVREREXUchiZqkd/+og/uH9UdAPD8l0fhcnHSSyIi6hoYmqjFnk4dgCC9BocvWpCZw2kIiIioa1A0NC1fvhw33ngjgoKCEBkZiUmTJiE3N9etTV1dHdLT0xEWFobAwEBMmTIFRUVFbm3y8/ORlpYGf39/REZG4umnn4bD4XBrs23bNowYMQJ6vR59+vRBRkZGk3pWrVqF+Ph4GAwGJCUlYc+ePW2+z51BRJAeT6T0BQCs2JiL82U1CldERETU/hQNTdu3b0d6ejp27dqFrKws1NfXY/z48aiurpbbLFiwAF999RUyMzOxfft2FBQUYPLkyfJ6p9OJtLQ02O127Ny5E2vWrEFGRgaWLl0qt8nLy0NaWhrGjh2LAwcOYP78+XjsscewadMmuc3HH3+MhQsXYtmyZdi/fz+GDRuG1NRUFBcXd8wPw8dMvzkefSMDcanajl+++R2+P1WqdElERETtS3iR4uJiAUBs375dCCFERUWF0Gq1IjMzU25z/PhxAUBkZ2cLIYTYsGGDUKlUwmw2y21Wr14tjEajsNlsQgghFi1aJAYNGuT2XVOnThWpqany+9GjR4v09HT5vdPpFLGxsWL58uUe1W6xWAQAYbFYWrjXvutCeY24+41vRc/F60TC79eJf+07r3RJRERELdKS87dXjWmyWCwAgNDQUABATk4O6uvrkZKSIrcZMGAAevTogezsbABAdnY2hgwZgqioKLlNamoqrFYrjh49Kre5chuNbRq3YbfbkZOT49ZGpVIhJSVFbvNTNpsNVqvV7dXVdAv2Q+bsZEy+oRtcAlj070PIOlZ0/Q8SERH5IK8JTS6XC/Pnz8eYMWMwePBgAIDZbIZOp0NwcLBb26ioKJjNZrnNlYGpcX3jumu1sVqtqK2tRWlpKZxOZ7NtGrfxU8uXL4fJZJJfcXFxrdtxH2fQqvHn+4dhyojucLoE0j/cj11nLildFhERUZvzmtCUnp6OI0eOYO3atUqX4pElS5bAYrHIr/Pnu+5dZJIk4U9ThiBlYCTsDhdmZuzF3rNlSpdFRETUprwiNM2dOxfr1q3DN998g+7du8vLo6OjYbfbUVFR4da+qKgI0dHRcpuf3k3X+P56bYxGI/z8/BAeHg61Wt1sm8Zt/JRer4fRaHR7dWUatQpv/noExvQJQ7XdiUfe28PgREREnYqioUkIgblz5+Kzzz7D1q1bkZCQ4LZ+5MiR0Gq12LJli7wsNzcX+fn5SE5OBgAkJyfj8OHDbne5ZWVlwWg0IjExUW5z5TYa2zRuQ6fTYeTIkW5tXC4XtmzZIreh6zNo1Xj34Rvl4DTj/b2cjoCIiDqP9h+XfnVz5swRJpNJbNu2TRQWFsqvmpoauc3s2bNFjx49xNatW8W+fftEcnKySE5Oltc7HA4xePBgMX78eHHgwAGxceNGERERIZYsWSK3OXPmjPD39xdPP/20OH78uFi1apVQq9Vi48aNcpu1a9cKvV4vMjIyxLFjx8SsWbNEcHCw211519IV7567mhqbQ9y36jvRc/E6cd+q70S9w6l0SURERM1qyflb0dAEoNnX+++/L7epra0Vv/3tb0VISIjw9/cX9913nygsLHTbztmzZ8XEiROFn5+fCA8PF08++aSor693a/PNN9+I4cOHC51OJ3r16uX2HY3+8pe/iB49egidTidGjx4tdu3a5fG+MDS5y79ULQYv3Sh6Ll4nVmblKl0OERFRs1py/paEEHx4WBuwWq0wmUywWCxdfnxToy8OXMQTaw9AJQHLJw/B1Bt7KF0SERGRm5acv71iIDh1TvcO74apo+LgEsDifx/G05kHUWt3Kl0WERFRqzA0UbtaPnkInk7tD5UEZOZcwOTVO3G2tPr6HyQiIvIyDE3UrlQqCelj++CDmUkID9TheKEV9/zlO2w62vykoURERN6KoYk6xM19wrFu3q0Y1TMElTYHfvOPHLy04TgcTpfSpREREXmEoYk6TLTJgI9m3YTHbmmYj+udHWcw7d3dKK+2K1wZERHR9TE0UYfSqlV49u5EvDVtBAL1GuzOK8OUt3dyEkwiIvJ6DE2kiLuGxODT396MWJMBZ0qqcd9b32PriaLrf5CIiEghDE2kmH5RQfgsfQwSY4worbJjRsY+pP9zP4or65QujYiIqAmGJlJUlNGAf81JxqzbekGtkrD+cCFSV+7AxiO8u46IiLwLQxMpzl+nwR/uGogv0sdgYIwR5TX1mP1BDp79/DBcLk5YT0RE3oGhibzG4G4mfJ5+M2bf3huSBHywKx9LPmVwIiIi78DQRF5Fr1Hj9xMH4I0HboBKAj7edx5/+Oww6ur5+BUiIlIWQxN5pXuGxWLl1OFQScDavecxfuUO/H9HzeDzpYmISCkMTeS17h3eDW//90hEGw3IL6vBrH/kYN5HP8BSU690aURE1AUxNJFXGz8oGluevB2//UVvqFUS1h0qxMTXd2D7jyVKl0ZERF0MQxN5vQC9BosmDMC/59yMnmH+KLDUYfp7ezAzYy/OlFQpXR4REXURDE3kM4bHBWPD727FjDEJ0KgkbDlRjPErd+B/1h2DpZZddkRE1L4kwZG1bcJqtcJkMsFiscBoNCpdTqd3qrgK/7v+GL7JbeimCwvQ4aXJQ5A6KFrhyoiIyJe05PzN0NRGGJqUsS23GH9cfxynihu66X41sjv+a2R39I8OQrC/TuHqiIjI2zE0KYChSTk2hxOvZv2Id3acwZX/NU8YFI0/TRkKk79WueKIiMirteT8zTFN5PP0GjWWTByItY/fhJSBkegW7AcA2HjUjLvf/Ba7z1yCk7OKExHRz8QrTW2EV5q8y5GLFsz5Zw7Ol9UCAAL1GtzUKxS/nzgQfSIDFa6OiIi8Ba80UZc3uJsJ6+beivtu6IZAvQZVNgc2Hy/G3X/5Fv/YdY4zixMRUYvxSlMb4ZUm7+V0CRwvtOJPG0/g25OlAICkhFD8z6TB6BcVpHB1RESkJA4EVwBDk/dzuQQydp7Fik0nUFfvglol4Z6hMUhJjMJt/SJgNHDAOBFRV8PQpACGJt9xobwG/7PuGDYdLZKXBeo1mHdHHzwyJh56jVrB6oiIqCMxNCmAocn35Jwrx6ajZmQdK0JeaTUAoGeYP565ayDuTIyCJEkKV0hERO2NoUkBDE2+y+US+Pf+C1ixKRcllTYAwJg+YZh9e28k9wqDRs37JYiIOiuGJgUwNPm+KpsDb31zCu9+lwe7wwWg4fEs9w7vhoeSeyIhPEDhComIqK0xNCmAoanzOF9Wg7e3n8bXR8woq7bLy0cnhGJQrBEDY4y4a0gMAvUaBaskIqK2wNCkAIamzqfe6cJ3J0vxj13n8E1usdsjWkx+Wjxyczym3xyP0AA+446IyFcxNCmAoalzO3epGrvOXMLJoipsPVGMM5cHjmvVEsYPisaDN/bAzb3DoFJx8DgRkS9haFIAQ1PX4XQJfH2kEO/sOINDFyzy8rhQP0wdFYdfjYpDlNGgYIVEROQphiYFMDR1TUcuWvDx3vP4/MBFVNY5AABqlYSx/SNwe78IjIoPRf+oIF6BIiLyUgxNCmBo6tpq7U5sOFyItXvzsfdsudu6IIMGo3qG4LZ+EZg8ojtMfpx5nIjIWzA0KYChiRqdKq7E+kNm7DtXhv3nylFtd8rr/HVq3DUkBoNijegdEYibeoVBp+E8UERESmFoUgBDEzXH4XThhLkSu85cQua+C8gtqnRbHxfqhyfv7I9fDotlFx4RkQIYmhTA0ETXI4TArjNl2P5jCc6WVmPfuTKUVjXMA9Uj1B//NbI7Jo/ohu4h/gpXSkTUdTA0KYChiVqqxu7A+9+fxV+3n4b18iByABgYY8SdAyMxbmAUhnQz8QoUEVE7YmhSAEMTtVat3YmNRwvxyd4L2J13Ca4rfiMjgvRIGRiJcQOikNw7DAGchZyIqE0xNCmAoYnaQlm1Hd+cKMaWE0XYnlviNohckoDeEYHoGxmIkAAdoo0G3D8qDtEmzglFRNRaDE0KYGiitmZzOLH7TBk2Hy/C1hPFuFBe26SNXqPCI2Picc/QWCSEB/BKFBFRCzE0KYChidpbSaUNhy9W4NylGlTU1OP7U6XYd859TqiE8ADcGB+C0QlhGB0firhQP0gSx0QREV1NS87fik4Qs2PHDtxzzz2IjY2FJEn4/PPP3dYLIbB06VLExMTAz88PKSkpOHnypFubsrIyTJs2DUajEcHBwZg5cyaqqqrc2hw6dAi33norDAYD4uLisGLFiia1ZGZmYsCAATAYDBgyZAg2bNjQ5vtL9HNEBOlxx4AoPDomAQvu7IfM2cl475FRGNMnDGGXHxqcV1qNT/ZdwFOZB3HbK9/gpuVbMO+jH/CP7LM4X1aj8B4QEfk2Ra/lV1dXY9iwYZgxYwYmT57cZP2KFSvwxhtvYM2aNUhISMBzzz2H1NRUHDt2DAZDwziOadOmobCwEFlZWaivr8ejjz6KWbNm4cMPPwTQkCDHjx+PlJQUvP322zh8+DBmzJiB4OBgzJo1CwCwc+dOPPjgg1i+fDnuvvtufPjhh5g0aRL279+PwYMHd9wPhKgFJEnCHQOicMeAKABAebUdB85XYM/ZMuzJK8OhCxUostrw1cECfHWwAMBR3NAjGHf0j0S/6CD0iwpCj1B/qHl3HhGRR7yme06SJHz22WeYNGkSgIarTLGxsXjyySfx1FNPAQAsFguioqKQkZGBBx54AMePH0diYiL27t2LUaNGAQA2btyIu+66CxcuXEBsbCxWr16NZ555BmazGTpdw/+N//73v8fnn3+OEydOAACmTp2K6upqrFu3Tq7npptuwvDhw/H22297VD+758jb1NU78UN+BfaeLcP3p0qx52wZfvrbrteo0DcqEKmJ0fivUd0RY/JTplgiIoW05PzttaNG8/LyYDabkZKSIi8zmUxISkpCdnY2HnjgAWRnZyM4OFgOTACQkpIClUqF3bt347777kN2djZuu+02OTABQGpqKv70pz+hvLwcISEhyM7OxsKFC92+PzU1tUl34ZVsNhtsNpv83mq1tsFeE7Udg1aN5N5hSO4dht+N64tiax2+PmLGgfMV+LGoEqeKq2BzuHDkohVHLlqxcvOP6B7ij5AAHUL8tQjx1yHSqMeonqEYHR8Kkz+fmUdEXZvXhiaz2QwAiIqKclseFRUlrzObzYiMjHRbr9FoEBoa6tYmISGhyTYa14WEhMBsNl/ze5qzfPlyvPDCC63YMyJlRBoNmH5zPKZffu90CVwor8Hes+X4ZN957MkrQ35ZDfJ/MvbprzgDAAjQqWH00+LG+FDM+UVvDIzhFVUi6lq8NjR5uyVLlrhdnbJarYiLi1OwIqKWUask9AwLQM+wAPzXyO4oqKhFQUUtymvqUV5jR3m1HefKarD7zCWcLqlGtd2JarsTXx4swJcHC5DcKwxD40zoGxmE8EAdwgL06B0ZAH8d/6wQUefktX/doqOjAQBFRUWIiYmRlxcVFWH48OFym+LiYrfPORwOlJWVyZ+Pjo5GUVGRW5vG99dr07i+OXq9Hnq9vhV7RuSdYoP9EBvc/JgmS209yqvtMFvr8I9d57DhcCGyz1xC9plLbu3UKgmJMUaM7BmCkT1DMCo+xG2cVEWNHYF6DTRqRW/cJSJqFa8NTQkJCYiOjsaWLVvkkGS1WrF7927MmTMHAJCcnIyKigrk5ORg5MiRAICtW7fC5XIhKSlJbvPMM8+gvr4eWm3DmIysrCz0798fISEhcpstW7Zg/vz58vdnZWUhOTm5g/aWyLuZ/LQw+WkRHx6Am3qFIa+0Gt+fKkWuuRJ5pdUoq7ajuLIOpVV2HL5oweGLFmTsPAsAiDUZ0DsyECeLqmC21sFo0CC5dxgmDI7G3UNjoWWAIiIfoejdc1VVVTh16hQA4IYbbsCrr76KsWPHIjQ0FD169MCf/vQnvPzyy25TDhw6dMhtyoGJEyeiqKgIb7/9tjzlwKhRo+QpBywWC/r374/x48dj8eLFOHLkCGbMmIGVK1e6TTlw++234+WXX0ZaWhrWrl2Ll156qUVTDvDuOerqhBAosNQh51w5cs6WISe/HMcLK+F0Xf1PTFyoH+4ZGouLFbUwW+pwx4BIPDC6B0x+HHRORB3DZ2YE37ZtG8aOHdtk+fTp05GRkQEhBJYtW4Z33nkHFRUVuOWWW/DWW2+hX79+ctuysjLMnTsXX331FVQqFaZMmYI33ngDgYGBcptDhw4hPT0de/fuRXh4OObNm4fFixe7fWdmZiaeffZZnD17Fn379sWKFStw1113ebwvDE1ETVXbHDh4vgJnSqvRNzIQibFGnC6pxjcnivHP3edQWmVv8hl/nRopAxseUDy0uwndgv1g8tOirt4Fm8MJk5+Ws5wTUZvxmdDUmTA0EbVMrd2Jj/fm42iBFQkRAQjQafDh7nzkFlVe83O9wgNw56Ao3BAXgkijHnEh/ogI4vhCImodhiYFMDQR/XxCCOw9W47vTpVi1+lLOFVShbLqplejfioiSI9BscbLLxMGxRrRI9SfV6SI6LoYmhTA0ETUPurqnbDW1iNAr4FTCGzPLcGW40U4e6kGxdY6FFrrmsx0DgBBBg2ijAZoVBLUKgkalQSDVo0beoQguXcYDBoVrHUOhAboMLS7iQPSiboohiYFMDQRKaPG7sDxwkocK7DgaIEVRwusyDVXwu50ebwNf50aN8aHIrl3GG6MD4XJTwO1SoXYYAP0GnU7Vk9ESmNoUgBDE5H3qHe6cLqkChU19XC6BBwuAafLhUtVduw6U4acc2VQSRKCDBrkl9WgvKa+2e3oNCoM7WbC4G4m9AzzR3xYAAbGGBFl1EOSJNQ7XdCoJHYDEvkwhiYFMDQR+SaXSyC3qBLZpxsm6zx8wQKbwwmbw4Uau7PZzxgNGjhcAjV2J4L9tRjSzYT4sADoNCoE6NToExWExJggxIcFcCJPIi/H0KQAhiaizkUIgbOXarDvbBlOFVchv6wGp4qrcKa0+ppzT11Jr1GhX1QQQgN0cAkBnVqFKJMBsSYDok1+iAzSo6zajvNlNYgN9sPdw2LYHUjUwRiaFMDQRNQ11NU7ce5SDQxaFYIMWlwsr8WhixUostTB7hSoqLEjt6gSuebKq16pupooox6TbugGjUqCwyVgNGhh9NMi2E+LYH8too0G9Lx8RYuI2gZDkwIYmojoSi6XQH5ZDU6Yrai2OaFWSaixO2G21sFsqUWhpQ7FVhuC/bXoFuyH70+Xoshqu+521SoJPUP90SsiEAnh/tCoVXC5BIx+WkQZDYg2GhBt0iPKaECQgTOrE11PS87fXvvsOSIiX6ZSSYgPD0B8eIBH7W0OJ748UIAfzldAp1ZBrZJQVedARa0dFTX1qKipx8WKWlTZHDhTWo0zpdXX3WaATo0oowE6TcP2eob549a+ERjSzQSVJEGrlhAX6g+Dll2CRJ7glaY2witNRNTehBAostpwuqQKp0uqcO5SDYQAVBJQUVuPImsdzJY6mK11qKxzeLRNSQK6h/ihd0QgekcEIi7EDxFBBhj9NKh3umB3CNidLjicLkQGGdA7MgDRRgPvGKROg91zCmBoIiJvUmN3oMhqQ7G1DvVOgXqnC4cuWLDjZAnOXaqBJAF1dicqbZ6FqyuZ/LQYHheMATFB0KlVqHcKnCpuCHJhATqMjA/BgOggBOq1CDJoEGMyINrEOa/IOzE0KYChiYh8jRACl6rtOF1chdMl1ThVXIVCSy1KKm2osjmg06igVavk7sICSy3yL9XA4eHdg1eSJCAuxB/9o4PQLdgPRoMGRj8tjAYtDDo1qm0OVNsciA32w4DoIIT461DvdEGlkhDqr4NKxStb1D44pomIiK5LkiSEB+oRHqhHUq8wjz5jd7iQa67ED+fLkVdaLT/CJj7MH30ig1BoqcW+s+Xy+CtLbT0KKmphc7iQX1aD/LKaFtepUUmIDNJjYIwRg7uZEGTQwCUE9Bo1QgJ0CNI3nMpcQkAIQACINhrQJzIQfjpe3aK2wytNbYRXmoiImieEQGmVHSeLK/GjuRIlVTZYax2w1tXDWluPGrsTQQYN/HQNM7Tnmq2oq3dBJTUEoNaepSQJCNRpYHO6oJYkDIgJwuBYE6KMehj9tNCpVVBJEvRaFSKC9IgM0iMisGE8l0sA1XYH/LVqTlDaybF7TgEMTUREbcPlEhBomF6h3tnw+JsL5TU4crHh+YL2yyGozuFEWbUdVTYHJEhQSWhISkLgQnktLlXbW/X9jfNkAQ0TlA6KNSIiSI9zl2pwqdqOG+KCcWu/CGhUEgotdYAQMPnrEBmkR2KsEQlhAQ1jxupd0GtU7Fr0cgxNCmBoIiLyLpeqbLDU1sOgVaPG7sTRAguOF1aiosYOS2096p2uhitKNgdKq2woqbTB6uFdh9eiU6vgcDVsW6uWEGU0IMZkQJTRgBB/HerqGx7TE6BXw+SnQ4zJgITwAATo1fL8XTV2B+rqXQgP1KFHmD96hAage4gfp4doBwxNCmBoIiLyfXX1TpTX2KFVqxCg06DAUotDFypQUVOP+LAABBk02HXmEnadKYNOo0KU0QCtWkJ5TT0ultfgeGElautbNhN8S4QF6GD00yJAr4YQgNMl4BICTpdAaIAO/aKC0DsiENEmA8ICdAAAh0vAWluP8pp6+OlUGBxrQq+IQKivcgWsrt6J/fnluFBei5t7h6F7iH+77Y83YGhSAEMTERE5XQIFFbXQa1Tw06lhrXM0zJ1lqUOhpVa+8qXXqFBjbwhoF8prkVdajbp6J2JMBkQaDQjSa6DTqFBkrUN+WS3Ol9WgqhXTQ1yNTq1CsL8WJj8tVJLUMIgeDYPpL5Y3DNxvNKy7CUO6m9Aj1B/hgXoE6DXw16kb7qzUNNxdqVWr4K9TI1Cvgepyt6pKkhDsp/X67kmGJgUwNBERUXsRQqC8pmEC08q6hukZIAFqSYJaJUGSgJJKG06YK3G2tBrFlTaUVdshSYBWpUKgQYMQfy0qaupxtMB63athEUF6dA/xw8HzFWjFDBMytUpCeKAOEUENd2lKAGwO1+WXE2pJQq+IQMSF+qOksg7nLtXAaNCif3SQ3B3pr2u4SzIsQCeHtrbE0KQAhiYiIvIFTpdAoaUWFTUNdy8CACRAJUmQAIQF6tA7IhCSJKGk0oZtucU4e6ka58tqUV7TMPC+1u5EvdOFeqeA3eGC3emSx2G1pzsTo/C3h0e16TY5TxMRERE1S62S0D3EH91Drt82IkiPX42K83jb9U4XxOUB8A6XwKUqO0oqbSipqkNpZcPdjHqtCnqNGnqtCrZ6F06XVOF8WQ0ijQb0DPVHeY0dueZKFFXaYHc4UWN34lKVHZeqbQgP1LV2t9sEQxMRERG1Ce0Vc1pp1RKiLz9CBzC1yfYdzva9knU9nLGLiIiIfILSE40yNBERERF5gKGJiIiIyAMMTUREREQeYGgiIiIi8gBDExEREZEHGJqIiIiIPMDQREREROQBhiYiIiIiDzA0EREREXmAoYmIiIjIAwxNRERERB5gaCIiIiLyAEMTERERkQc0ShfQWQghAABWq1XhSoiIiMhTjeftxvP4tTA0tZHKykoAQFxcnMKVEBERUUtVVlbCZDJds40kPIlWdF0ulwsFBQUICgqCJEltum2r1Yq4uDicP38eRqOxTbftDTr7/gHcx86gs+8fwH3sDDr7/gFtv49CCFRWViI2NhYq1bVHLfFKUxtRqVTo3r17u36H0WjstL8EQOffP4D72Bl09v0DuI+dQWffP6Bt9/F6V5gacSA4ERERkQcYmoiIiIg8wNDkA/R6PZYtWwa9Xq90Ke2is+8fwH3sDDr7/gHcx86gs+8foOw+ciA4ERERkQd4pYmIiIjIAwxNRERERB5gaCIiIiLyAEMTERERkQcYmrzcqlWrEB8fD4PBgKSkJOzZs0fpklpt+fLluPHGGxEUFITIyEhMmjQJubm5bm1+8YtfQJIkt9fs2bMVqrhlnn/++Sa1DxgwQF5fV1eH9PR0hIWFITAwEFOmTEFRUZGCFbdcfHx8k32UJAnp6ekAfPP47dixA/fccw9iY2MhSRI+//xzt/VCCCxduhQxMTHw8/NDSkoKTp486damrKwM06ZNg9FoRHBwMGbOnImqqqoO3Iuru9b+1dfXY/HixRgyZAgCAgIQGxuLhx9+GAUFBW7baO64v/zyyx28J1d3vWP4yCOPNKl/woQJbm28+RgC19/H5n4vJUnCK6+8Irfx5uPoyfnBk7+h+fn5SEtLg7+/PyIjI/H000/D4XC0WZ0MTV7s448/xsKFC7Fs2TLs378fw4YNQ2pqKoqLi5UurVW2b9+O9PR07Nq1C1lZWaivr8f48eNRXV3t1u7xxx9HYWGh/FqxYoVCFbfcoEGD3Gr/7rvv5HULFizAV199hczMTGzfvh0FBQWYPHmygtW23N69e932LysrCwDwq1/9Sm7ja8evuroaw4YNw6pVq5pdv2LFCrzxxht4++23sXv3bgQEBCA1NRV1dXVym2nTpuHo0aPIysrCunXrsGPHDsyaNaujduGarrV/NTU12L9/P5577jns378fn376KXJzc/HLX/6ySdsXX3zR7bjOmzevI8r3yPWOIQBMmDDBrf6PPvrIbb03H0Pg+vt45b4VFhbivffegyRJmDJlils7bz2Onpwfrvc31Ol0Ii0tDXa7HTt37sSaNWuQkZGBpUuXtl2hgrzW6NGjRXp6uvze6XSK2NhYsXz5cgWrajvFxcUCgNi+fbu87PbbbxdPPPGEckX9DMuWLRPDhg1rdl1FRYXQarUiMzNTXnb8+HEBQGRnZ3dQhW3viSeeEL179xYul0sI4dvHTwghAIjPPvtMfu9yuUR0dLR45ZVX5GUVFRVCr9eLjz76SAghxLFjxwQAsXfvXrnN119/LSRJEhcvXuyw2j3x0/1rzp49ewQAce7cOXlZz549xcqVK9u3uDbS3D5Onz5d3HvvvVf9jC8dQyE8O4733nuvuOOOO9yW+dJx/On5wZO/oRs2bBAqlUqYzWa5zerVq4XRaBQ2m61N6uKVJi9lt9uRk5ODlJQUeZlKpUJKSgqys7MVrKztWCwWAEBoaKjb8n/+858IDw/H4MGDsWTJEtTU1ChRXqucPHkSsbGx6NWrF6ZNm4b8/HwAQE5ODurr692O54ABA9CjRw+fPZ52ux0ffPABZsyY4faQal8+fj+Vl5cHs9nsdtxMJhOSkpLk45adnY3g4GCMGjVKbpOSkgKVSoXdu3d3eM0/l8VigSRJCA4Odlv+8ssvIywsDDfccANeeeWVNu3y6Ajbtm1DZGQk+vfvjzlz5uDSpUvyus52DIuKirB+/XrMnDmzyTpfOY4/PT948jc0OzsbQ4YMQVRUlNwmNTUVVqsVR48ebZO6+MBeL1VaWgqn0+l28AEgKioKJ06cUKiqtuNyuTB//nyMGTMGgwcPlpf/+te/Rs+ePREbG4tDhw5h8eLFyM3NxaeffqpgtZ5JSkpCRkYG+vfvj8LCQrzwwgu49dZbceTIEZjNZuh0uiYnoqioKJjNZmUK/pk+//xzVFRU4JFHHpGX+fLxa07jsWnu97BxndlsRmRkpNt6jUaD0NBQnzu2dXV1WLx4MR588EG3B6H+7ne/w4gRIxAaGoqdO3diyZIlKCwsxKuvvqpgtZ6bMGECJk+ejISEBJw+fRp/+MMfMHHiRGRnZ0OtVneqYwgAa9asQVBQUJPuf185js2dHzz5G2o2m5v9XW1c1xYYmkgR6enpOHLkiNuYHwBuYwiGDBmCmJgYjBs3DqdPn0bv3r07uswWmThxovzvoUOHIikpCT179sQnn3wCPz8/BStrH3//+98xceJExMbGyst8+fh1dfX19bj//vshhMDq1avd1i1cuFD+99ChQ6HT6fCb3/wGy5cv94nHdTzwwAPyv4cMGYKhQ4eid+/e2LZtG8aNG6dgZe3jvffew7Rp02AwGNyW+8pxvNr5wRuwe85LhYeHQ61WN7kzoKioCNHR0QpV1Tbmzp2LdevW4ZtvvkH37t2v2TYpKQkAcOrUqY4orU0FBwejX79+OHXqFKKjo2G321FRUeHWxleP57lz57B582Y89thj12zny8cPgHxsrvV7GB0d3eTmDIfDgbKyMp85to2B6dy5c8jKynK7ytScpKQkOBwOnD17tmMKbGO9evVCeHi4/N9lZziGjb799lvk5uZe93cT8M7jeLXzgyd/Q6Ojo5v9XW1c1xYYmryUTqfDyJEjsWXLFnmZy+XCli1bkJycrGBlrSeEwNy5c/HZZ59h69atSEhIuO5nDhw4AACIiYlp5+raXlVVFU6fPo2YmBiMHDkSWq3W7Xjm5uYiPz/fJ4/n+++/j8jISKSlpV2znS8fPwBISEhAdHS023GzWq3YvXu3fNySk5NRUVGBnJwcuc3WrVvhcrnk0OjNGgPTyZMnsXnzZoSFhV33MwcOHIBKpWrSpeUrLly4gEuXLsn/Xfr6MbzS3//+d4wcORLDhg27bltvOo7XOz948jc0OTkZhw8fdgvAjf8TkJiY2GaFkpdau3at0Ov1IiMjQxw7dkzMmjVLBAcHu90Z4EvmzJkjTCaT2LZtmygsLJRfNTU1QgghTp06JV588UWxb98+kZeXJ7744gvRq1cvcdtttylcuWeefPJJsW3bNpGXlye+//57kZKSIsLDw0VxcbEQQojZs2eLHj16iK1bt4p9+/aJ5ORkkZycrHDVLed0OkWPHj3E4sWL3Zb76vGrrKwUP/zwg/jhhx8EAPHqq6+KH374Qb577OWXXxbBwcHiiy++EIcOHRL33nuvSEhIELW1tfI2JkyYIG644Qaxe/du8d1334m+ffuKBx98UKldcnOt/bPb7eKXv/yl6N69uzhw4IDb72Xj3UY7d+4UK1euFAcOHBCnT58WH3zwgYiIiBAPP/ywwnv2H9fax8rKSvHUU0+J7OxskZeXJzZv3ixGjBgh+vbtK+rq6uRtePMxFOL6/50KIYTFYhH+/v5i9erVTT7v7cfxeucHIa7/N9ThcIjBgweL8ePHiwMHDoiNGzeKiIgIsWTJkjark6HJy/3lL38RPXr0EDqdTowePVrs2rVL6ZJaDUCzr/fff18IIUR+fr647bbbRGhoqNDr9aJPnz7i6aefFhaLRdnCPTR16lQRExMjdDqd6Natm5g6dao4deqUvL62tlb89re/FSEhIcLf31/cd999orCwUMGKW2fTpk0CgMjNzXVb7qvH75tvvmn2v8vp06cLIRqmHXjuuedEVFSU0Ov1Yty4cU32/dKlS+LBBx8UgYGBwmg0ikcffVRUVlYqsDdNXWv/8vLyrvp7+c033wghhMjJyRFJSUnCZDIJg8EgBg4cKF566SW3wKG0a+1jTU2NGD9+vIiIiBBarVb07NlTPP74403+59Obj6EQ1//vVAgh/vrXvwo/Pz9RUVHR5PPefhyvd34QwrO/oWfPnhUTJ04Ufn5+Ijw8XDz55JOivr6+zeqULhdLRERERNfAMU1EREREHmBoIiIiIvIAQxMRERGRBxiaiIiIiDzA0ERERETkAYYmIiIiIg8wNBERERF5gKGJiIiIyAMMTUREbUiSJHz++edKl0FE7YChiYg6jUceeQSSJDV5TZgwQenSiKgT0ChdABFRW5owYQLef/99t2V6vV6haoioM+GVJiLqVPR6PaKjo91eISEhABq6zlavXo2JEyfCz88PvXr1wr/+9S+3zx8+fBh33HEH/Pz8EBYWhlmzZqGqqsqtzXvvvYdBgwZBr9cjJiYGc+fOdVtfWlqK++67D/7+/ujbty++/PJLeV15eTmmTZuGiIgI+Pn5oW/fvk1CHhF5J4YmIupSnnvuOUyZMgUHDx7EtGnT8MADD+D48eMAgOrqaqSmpiIkJAR79+5FZmYmNm/e7BaKVq9ejfT0dMyaNQuHDx/Gl19+iT59+rh9xwsvvID7778fhw4dwl133YVp06ahrKxM/v5jx47h66+/xvHjx7F69WqEh4d33A+AiFpPEBF1EtOnTxdqtVoEBAS4vf73f/9XCCEEADF79my3zyQlJYk5c+YIIYR45513REhIiKiqqpLXr1+/XqhUKmE2m4UQQsTGxopnnnnmqjUAEM8++6z8vqqqSgAQX3/9tRBCiHvuuUc8+uijbbPDRNShOKaJiDqVsWPHYvXq1W7LQkND5X8nJye7rUtOTsaBAwcAAMePH8ewYcMQEBAgrx8zZgxcLhdyc3MhSRIKCgowbty4a9YwdOhQ+d8BAQEwGo0oLi4GAMyZMwdTpkzB/v37MX78eEyaNAk333xzq/aViDoWQxMRdSoBAQFNusvaip+fn0fttFqt23tJkuByuQAAEydOxLlz57BhwwZkZWVh3LhxSE9Px//93/+1eb1E1LY4pomIupRdu3Y1eT9w4EAAwMCBA3Hw4EFUV1fL67///nuoVCr0798fQUFBiI+Px5YtW35WDREREZg+fTo++OADvPbaa3jnnXd+1vaIqGPwShMRdSo2mw1ms9ltmUajkQdbZ2ZmYtSoUbjlllvwz3/+E3v27MHf//53AMC0adOwbNkyTJ8+Hc8//zxKSkowb948PPTQQ4iKigIAPP/885g9ezYiIyMxceJEVFZW4vvvv8e8efM8qm/p0qUYOXIkBg0aBJvNhnXr1smhjYi8G0MTEXUqGzduRExMjNuy/v3748SJEwAa7mxbu3Ytfvvb3yImJgYfffQREhMTAQD+/v7YtGkTnnjiCdx4443w9/fHlClT8Oqrr8rbmj59Ourq6rBy5Uo89dRTCA8Px3/91395XJ9Op8OSJUtw9uxZ+Pn54dZbb8XatWvbYM+JqL1JQgihdBFERB1BkiR89tlnmDRpktKlEJEP4pgmIiIiIg8wNBERERF5gGOaiKjL4GgEIvo5eKWJiIiIyAMMTUREREQeYGgiIiIi8gBDExEREZEHGJqIiIiIPMDQREREROQBhiYiIiIiDzA0EREREXng/wfWqu9aagnwqgAAAABJRU5ErkJggg==\n"
},
"metadata": {}
}
],
"source": [
"import matplotlib.pyplot as plt\n",
"\n",
"plt.plot(range(nn.epochs), nn.eval_['cost'])\n",
"plt.ylabel('Cost')\n",
"plt.xlabel('Epochs')\n",
"# plt.savefig('images/12_07.png', dpi=300)\n",
"plt.show()"
]
},
{
"cell_type": "code",
"execution_count": 22,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 454
},
"id": "z4O1gYie4Okl",
"outputId": "ed8730b4-e2ba-4fbf-ec65-b7b6324b3e77"
},
"outputs": [
{
"output_type": "display_data",
"data": {
"text/plain": [
""
],
"image/png": "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\n"
},
"metadata": {}
}
],
"source": [
"plt.plot(range(nn.epochs), nn.eval_['train_acc'],\n",
" label='Training')\n",
"plt.plot(range(nn.epochs), nn.eval_['valid_acc'],\n",
" label='Validation', linestyle='--')\n",
"plt.ylabel('Accuracy')\n",
"plt.xlabel('Epochs')\n",
"plt.legend(loc='lower right')\n",
"# plt.savefig('images/12_08.png', dpi=300)\n",
"plt.show()"
]
},
{
"cell_type": "code",
"execution_count": 23,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "zscbDz7F4Okl",
"outputId": "68c7f2c6-9a1b-4955-bd84-f994de5c5be2"
},
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"테스트 정확도: 97.54%\n"
]
}
],
"source": [
"y_test_pred = nn.predict(X_test)\n",
"# 넘파이 1.20에서 `np.float`가 deprecated되므로 대신 `float`를 사용합니다.\n",
"acc = (np.sum(y_test == y_test_pred)\n",
" .astype(float) / X_test.shape[0])\n",
"\n",
"print('테스트 정확도: %.2f%%' % (acc * 100))"
]
},
{
"cell_type": "code",
"execution_count": 24,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 486
},
"id": "bOSkex4s4Okl",
"outputId": "cee2a081-ca94-484d-f0d5-2b6a330261b6"
},
"outputs": [
{
"output_type": "display_data",
"data": {
"text/plain": [
""
],
"image/png": "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\n"
},
"metadata": {}
}
],
"source": [
"miscl_img = X_test[y_test != y_test_pred][:25]\n",
"correct_lab = y_test[y_test != y_test_pred][:25]\n",
"miscl_lab = y_test_pred[y_test != y_test_pred][:25]\n",
"\n",
"fig, ax = plt.subplots(nrows=5, ncols=5, sharex=True, sharey=True)\n",
"ax = ax.flatten()\n",
"for i in range(25):\n",
" img = miscl_img[i].reshape(28, 28)\n",
" ax[i].imshow(img, cmap='Greys', interpolation='nearest')\n",
" ax[i].set_title('%d) t: %d p: %d' % (i+1, correct_lab[i], miscl_lab[i]))\n",
"\n",
"ax[0].set_xticks([])\n",
"ax[0].set_yticks([])\n",
"plt.tight_layout()\n",
"# plt.savefig('images/12_09.png', dpi=300)\n",
"plt.show()"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "j3Wd15HC4Okl"
},
"source": [
"
\n",
"
"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "h8bE0O6b4Okl"
},
"source": [
"# 인공 신경망 훈련"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "2k-FpEok4Okl"
},
"source": [
"..."
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "R4si-7664Okl"
},
"source": [
"## 로지스틱 비용 함수 계산"
]
},
{
"cell_type": "code",
"execution_count": 25,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 312
},
"id": "GAakQltn4Okl",
"outputId": "add615db-a2a3-416a-effd-88f96e77d5dd"
},
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/html": [
"![](\"https://git.io/JLdov\")
"
],
"text/plain": [
""
]
},
"metadata": {},
"execution_count": 25
}
],
"source": [
"Image(url='https://git.io/JLdov', width=300)"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "LN03rNNR4Okm"
},
"source": [
"
\n",
"
"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "ETGepTEw4Okm"
},
"source": [
"## 역전파 알고리즘 이해"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "pFPsW5UE4Okm"
},
"source": [
"..."
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "iovHPtie4Okm"
},
"source": [
"## 역전파 알고리즘으로 신경망 훈련"
]
},
{
"cell_type": "code",
"execution_count": 26,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 237
},
"id": "kkqR0QCI4Okm",
"outputId": "134c1a20-4b2f-4df0-efe9-443511857c63"
},
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/html": [
"![](\"https://git.io/JLdoa\")
"
],
"text/plain": [
""
]
},
"metadata": {},
"execution_count": 26
}
],
"source": [
"Image(url='https://git.io/JLdoa', width=400)"
]
},
{
"cell_type": "code",
"execution_count": 27,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 405
},
"id": "Bj3Colmn4Okm",
"outputId": "79b55b5b-608a-49ed-a80a-13c0989cdcc9"
},
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/html": [
"![](\"https://git.io/JLdoz\")
"
],
"text/plain": [
""
]
},
"metadata": {},
"execution_count": 27
}
],
"source": [
"Image(url='https://git.io/JLdoz', width=500)"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "yCWIr16M4Okm"
},
"source": [
"
\n",
"
"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "_t9nD_3j4Okn"
},
"source": [
"# 신경망의 수렴"
]
},
{
"cell_type": "code",
"execution_count": 28,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 336
},
"id": "X5M8ZRzm4Okn",
"outputId": "8c039384-5b63-4586-b8fb-74c451913aa4"
},
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/html": [
"![](\"https://git.io/JLdoK\")
"
],
"text/plain": [
""
]
},
"metadata": {},
"execution_count": 28
}
],
"source": [
"Image(url='https://git.io/JLdoK', width=500)"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "hwvf3FQX4Okn"
},
"source": [
"
\n",
"
"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "8dwCxPtm4Okn"
},
"source": [
"..."
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "zKoOueKo4Okn"
},
"source": [
"# 요약"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "o2TWIlZV4Okn"
},
"source": [
"..."
]
}
],
"metadata": {
"anaconda-cloud": {},
"colab": {
"name": "ch12.ipynb",
"provenance": []
},
"kernelspec": {
"display_name": "Python 3",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.7.3"
},
"gpuClass": "standard"
},
"nbformat": 4,
"nbformat_minor": 0
} ![](\"https://jupyter.org/assets/share.png\")
주피터 노트북 뷰어로 보기\n",
" ![](\"https://www.tensorflow.org/images/colab_logo_32px.png\"){kind=logo}
구글 코랩(Colab)에서 실행하기\n",
"