{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# MNIST-Neural Network-Batch Normalization"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "# coding: utf-8\n",
    "import sys, os\n",
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "import math\n",
    "\n",
    "sys.path.append(os.pardir)\n",
    "from deeplink.mnist import *\n",
    "from deeplink.networks import *"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Multilayer Neural Network Model (Two Hidden Layers) and Learing/Validation"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Initializers "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "# coding: utf-8\n",
    "import numpy as np\n",
    "\n",
    "class Initializer:\n",
    "    def __init__(self, params, params_size_list, use_batch_normalization=False):\n",
    "        self.params = params\n",
    "        self.params_size_list = params_size_list\n",
    "        self.use_batch_normalization = use_batch_normalization\n",
    "\n",
    "    def initialize_params(self):\n",
    "        pass\n",
    "\n",
    "    def get_params(self):\n",
    "        return self.params\n",
    "\n",
    "\n",
    "class Zero_Initializer(Initializer):\n",
    "    def initialize_params(self, use_batch_normalization):\n",
    "        for idx in range(1, len(self.params_size_list)):\n",
    "            self.params['W' + str(idx)] = np.zeros(self.params_size_list[idx - 1], self.params_size_list[idx])\n",
    "            self.params['b' + str(idx)] = np.zeros(self.params_size_list[idx])\n",
    "            if self.use_batch_normalization and idx < len(self.params_size_list) - 1:\n",
    "                self.params['gamma' + str(idx)] = np.zeros(self.params_size_list[idx])\n",
    "                self.params['beta' + str(idx)] = np.zeros(self.params_size_list[idx])\n",
    "\n",
    "class N1_Initializer(Initializer):\n",
    "    def initialize_params(self):\n",
    "        for idx in range(1, len(self.params_size_list)):\n",
    "            self.params['W' + str(idx)] = np.random.randn(self.params_size_list[idx - 1], self.params_size_list[idx])\n",
    "            self.params['b' + str(idx)] = np.random.randn(self.params_size_list[idx])\n",
    "            if self.use_batch_normalization and idx < len(self.params_size_list) - 1:\n",
    "                self.params['gamma' + str(idx)] = np.random.randn(self.params_size_list[idx])\n",
    "                self.params['beta' + str(idx)] = np.random.randn(self.params_size_list[idx])\n",
    "\n",
    "class N2_Initializer(Initializer):\n",
    "    def initialize_params(self):\n",
    "        for idx in range(1, len(self.params_size_list)):\n",
    "            self.params['W' + str(idx)] = np.random.randn(self.params_size_list[idx - 1], self.params_size_list[idx]) * 0.01\n",
    "            self.params['b' + str(idx)] = np.random.randn(self.params_size_list[idx]) * 0.01\n",
    "            if self.use_batch_normalization and idx < len(self.params_size_list) - 1:\n",
    "                self.params['gamma' + str(idx)] = np.random.randn(self.params_size_list[idx]) * 0.01\n",
    "                self.params['beta' + str(idx)] = np.random.randn(self.params_size_list[idx]) * 0.01\n",
    "\n",
    "class Xavier_Initializer(Initializer):\n",
    "    def initialize_params(self):\n",
    "        for idx in range(1, len(self.params_size_list)):\n",
    "            self.params['W' + str(idx)] = np.random.randn(self.params_size_list[idx - 1], self.params_size_list[idx]) / np.sqrt(self.params_size_list[idx - 1])\n",
    "            self.params['b' + str(idx)] = np.random.randn(self.params_size_list[idx]) / np.sqrt(self.params_size_list[idx - 1])\n",
    "            if self.use_batch_normalization and idx < len(self.params_size_list) - 1:\n",
    "                self.params['gamma' + str(idx)] = np.random.randn(self.params_size_list[idx]) / np.sqrt(self.params_size_list[idx - 1])\n",
    "                self.params['beta' + str(idx)] = np.random.randn(self.params_size_list[idx]) / np.sqrt(self.params_size_list[idx - 1])\n",
    "\n",
    "\n",
    "class He_Initializer(Initializer):\n",
    "    def initialize_params(self):\n",
    "        for idx in range(1, len(self.params_size_list)):\n",
    "            self.params['W' + str(idx)] = np.random.randn(self.params_size_list[idx - 1], self.params_size_list[idx]) * np.sqrt(2) / np.sqrt(self.params_size_list[idx - 1])\n",
    "            self.params['b' + str(idx)] = np.random.randn(self.params_size_list[idx]) * np.sqrt(2) / np.sqrt(self.params_size_list[idx - 1])\n",
    "            if self.use_batch_normalization and idx < len(self.params_size_list) - 1:\n",
    "                self.params['gamma' + str(idx)] = np.random.randn(self.params_size_list[idx]) * np.sqrt(2) / np.sqrt(self.params_size_list[idx - 1])\n",
    "                self.params['beta' + str(idx)] = np.random.randn(self.params_size_list[idx]) * np.sqrt(2) / np.sqrt(self.params_size_list[idx - 1])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### New Layer - Batch Normalization"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "class BatchNormalization:\n",
    "    def __init__(self, gamma, beta, momentum=0.9, running_mean=None, running_var=None):\n",
    "        self.gamma = gamma\n",
    "        self.beta = beta\n",
    "        self.momentum = momentum\n",
    "        self.input_shape = None\n",
    "\n",
    "        self.running_mean = running_mean\n",
    "        self.running_var = running_var  \n",
    "        \n",
    "        self.batch_size = None\n",
    "        self.xc = None\n",
    "        self.std = None\n",
    "        self.dgamma = None\n",
    "        self.dbeta = None\n",
    "\n",
    "    def forward(self, x, is_train=True):\n",
    "        self.input_shape = x.shape\n",
    "        if x.ndim != 2:\n",
    "            N, C, H, W = x.shape\n",
    "            x = x.reshape(N, -1)\n",
    "\n",
    "        out = self.__forward(x, is_train)\n",
    "        \n",
    "        return out.reshape(*self.input_shape)\n",
    "            \n",
    "    def __forward(self, x, is_train):\n",
    "        if self.running_mean is None:\n",
    "            N, D = x.shape\n",
    "            self.running_mean = np.zeros(D)\n",
    "            self.running_var = np.zeros(D)\n",
    "                        \n",
    "        if is_train:\n",
    "            mu = x.mean(axis=0)\n",
    "            xc = x - mu\n",
    "            var = np.mean(xc**2, axis=0)\n",
    "            std = np.sqrt(var + 10e-7)\n",
    "            xn = xc / std\n",
    "            \n",
    "            self.batch_size = x.shape[0]\n",
    "            self.xc = xc\n",
    "            self.xn = xn\n",
    "            self.std = std\n",
    "            self.running_mean = self.momentum * self.running_mean + (1-self.momentum) * mu\n",
    "            self.running_var = self.momentum * self.running_var + (1-self.momentum) * var            \n",
    "        else:\n",
    "            xc = x - self.running_mean\n",
    "            xn = xc / ((np.sqrt(self.running_var + 10e-7)))\n",
    "            \n",
    "        out = self.gamma * xn + self.beta \n",
    "        return out\n",
    "\n",
    "    def backward(self, dout):\n",
    "        if dout.ndim != 2:\n",
    "            N, C, H, W = dout.shape\n",
    "            dout = dout.reshape(N, -1)\n",
    "\n",
    "        dx = self.__backward(dout)\n",
    "\n",
    "        dx = dx.reshape(*self.input_shape)\n",
    "        return dx\n",
    "\n",
    "    def __backward(self, dout):\n",
    "        dbeta = dout.sum(axis=0)\n",
    "        dgamma = np.sum(self.xn * dout, axis=0)\n",
    "        dxn = self.gamma * dout\n",
    "        dxc = dxn / self.std\n",
    "        dstd = -np.sum((dxn * self.xc) / (self.std * self.std), axis=0)\n",
    "        dvar = 0.5 * dstd / self.std\n",
    "        dxc += (2.0 / self.batch_size) * self.xc * dvar\n",
    "        dmu = np.sum(dxc, axis=0)\n",
    "        dx = dxc - dmu / self.batch_size\n",
    "        \n",
    "        self.dgamma = dgamma\n",
    "        self.dbeta = dbeta\n",
    "        \n",
    "        return dx"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "activation_layers = {\n",
    "    'Sigmoid': Sigmoid,\n",
    "    'ReLU': ReLU\n",
    "}\n",
    "\n",
    "optimizers = {\n",
    "    \"SGD\": SGD,\n",
    "    \"Momentum\": Momentum,\n",
    "    \"Nesterov\": Nesterov,\n",
    "    \"AdaGrad\": AdaGrad,\n",
    "    \"RMSprop\": RMSprop,\n",
    "    \"Adam\": Adam\n",
    "}\n",
    "\n",
    "initializers = {\n",
    "    'Zero': Zero_Initializer,\n",
    "    'N1': N1_Initializer,\n",
    "    'N2': N2_Initializer, # We will use this as a new initializer for supporting Batch Normalization\n",
    "    'Xavier': Xavier_Initializer,\n",
    "    'He': He_Initializer\n",
    "}"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Multi Layer Model Class"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "class MultiLayerNetExtended(MultiLayerNet):\n",
    "    def __init__(self, input_size, hidden_size_list, output_size, activation='ReLU', initializer='N2', \n",
    "                 optimizer='AdaGrad', learning_rate=0.01, use_batch_normalization=False):\n",
    "        self.input_size = input_size\n",
    "        self.output_size = output_size\n",
    "        self.hidden_size_list = hidden_size_list\n",
    "        self.hidden_layer_num = len(hidden_size_list)\n",
    "        \n",
    "        self.use_batch_normalization = use_batch_normalization\n",
    "        \n",
    "        # Weight Initialization\n",
    "        self.params = {}\n",
    "        self.weight_initialization(initializer)\n",
    "        \n",
    "        # Layering\n",
    "        self.layers = OrderedDict()\n",
    "        self.last_layer = None\n",
    "        self.layering(activation)\n",
    "\n",
    "        # Optimization Method\n",
    "        self.optimizer = optimizers[optimizer](lr=learning_rate)\n",
    "    \n",
    "    def weight_initialization(self, initializer):\n",
    "        params_size_list = [self.input_size] + self.hidden_size_list + [self.output_size]\n",
    "        initializer_obj = initializers[initializer](self.params, \n",
    "                                                    params_size_list, \n",
    "                                                    self.use_batch_normalization)\n",
    "        initializer_obj.initialize_params();\n",
    "        \n",
    "    def layering(self, activation):\n",
    "        for idx in range(1, self.hidden_layer_num + 1):\n",
    "            self.layers['Affine' + str(idx)] = Affine(self.params['W' + str(idx)], self.params['b' + str(idx)])\n",
    "            if self.use_batch_normalization:\n",
    "                self.layers['Batch_Normalization' + str(idx)] = BatchNormalization(self.params['gamma' + str(idx)], \n",
    "                                                                                   self.params['beta' + str(idx)])\n",
    "            self.layers['Activation' + str(idx)] = activation_layers[activation]()\n",
    "\n",
    "        idx = self.hidden_layer_num + 1\n",
    "        self.layers['Affine' + str(idx)] = Affine(self.params['W' + str(idx)], self.params['b' + str(idx)])\n",
    "\n",
    "        self.last_layer = SoftmaxWithCrossEntropyLoss()  \n",
    "\n",
    "    def predict(self, x, is_train=False):\n",
    "        for key, layer in self.layers.items():\n",
    "            if \"BatchNorm\" in key:\n",
    "                x = layer.forward(x, is_train)\n",
    "            else:\n",
    "                x = layer.forward(x)\n",
    "        return x\n",
    "\n",
    "    def loss(self, x, t, is_train=False):\n",
    "        y = self.predict(x, is_train)\n",
    "        return self.last_layer.forward(y, t)\n",
    "\n",
    "    def accuracy(self, x, t):\n",
    "        y = self.predict(x, is_train=False)\n",
    "        y = np.argmax(y, axis=1)\n",
    "        if t.ndim != 1 : t = np.argmax(t, axis=1)\n",
    "\n",
    "        accuracy = np.sum(y == t) / float(x.shape[0])\n",
    "        return accuracy        \n",
    "\n",
    "    def backpropagation_gradient(self, x, t):\n",
    "        # forward\n",
    "        self.loss(x, t, is_train=True)\n",
    "\n",
    "        # backward\n",
    "        din = 1\n",
    "        din = self.last_layer.backward(din)\n",
    "\n",
    "        layers = list(self.layers.values())\n",
    "        layers.reverse()\n",
    "        for layer in layers:\n",
    "            din = layer.backward(din)\n",
    "\n",
    "        grads = {}\n",
    "        for idx in range(1, self.hidden_layer_num + 2):\n",
    "            grads['W' + str(idx)] = self.layers['Affine' + str(idx)].dW\n",
    "            grads['b' + str(idx)] = self.layers['Affine' + str(idx)].db\n",
    "\n",
    "            if self.use_batch_normalization and idx <= self.hidden_layer_num:\n",
    "                grads['gamma' + str(idx)] = self.layers['Batch_Normalization' + str(idx)].dgamma\n",
    "                grads['beta' + str(idx)] = self.layers['Batch_Normalization' + str(idx)].dbeta\n",
    "                \n",
    "        return grads\n",
    "\n",
    "    def learning(self, x_batch, t_batch):\n",
    "        grads = self.backpropagation_gradient(x_batch, t_batch)\n",
    "        self.optimizer.update(self.params, grads)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Training and Evaluation"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "data = mnist_data(\"/Users/yhhan/git/aiclass/0.Professor/data/MNIST_data/.\")\n",
    "(img_train, label_train), (img_validation, label_validation), (img_test, label_test) = data.load_mnist(flatten=True, normalize=True, one_hot_label=True)\n",
    "\n",
    "input_size=784\n",
    "hidden_layer1_size=128\n",
    "hidden_layer2_size=128\n",
    "output_size=10\n",
    "\n",
    "num_epochs = 50\n",
    "train_size = img_train.shape[0]\n",
    "batch_size = 1000\n",
    "learning_rate = 0.1\n",
    "\n",
    "markers = {\"N2, SGD, No_Batch_Norm\": \"x\", \"N2, SGD, Batch_Norm\": \"o\", \n",
    "           \"N2, AdaGrad, No_Batch_Norm\": \"+\", \"N2, AdaGrad, Batch_Norm\": \"*\",\n",
    "           \"He, AdaGrad, No_Batch_Norm\": \"h\", \"He, AdaGrad, Batch_Norm\": \"H\"}\n",
    "\n",
    "networks = {}\n",
    "train_errors = {}\n",
    "validation_errors = {}\n",
    "test_accuracy_values = {}\n",
    "max_test_accuracy_epoch = {}\n",
    "max_test_accuracy_value = {}\n",
    "\n",
    "for key in markers.keys():\n",
    "    if key == \"N2, SGD, No_Batch_Norm\":\n",
    "        networks[key] = MultiLayerNetExtended(input_size, [hidden_layer1_size, hidden_layer2_size], output_size, \n",
    "                                activation='ReLU', \n",
    "                                initializer='N2',\n",
    "                                optimizer='SGD', learning_rate=learning_rate,\n",
    "                                use_batch_normalization=False)\n",
    "    elif key == \"N2, SGD, Batch_Norm\":\n",
    "        networks[key] = MultiLayerNetExtended(input_size, [hidden_layer1_size, hidden_layer2_size], output_size, \n",
    "                                activation='ReLU', \n",
    "                                initializer='N2',\n",
    "                                optimizer='SGD', learning_rate=learning_rate,\n",
    "                                use_batch_normalization=True)\n",
    "    elif key == \"N2, AdaGrad, No_Batch_Norm\":\n",
    "        networks[key] = MultiLayerNetExtended(input_size, [hidden_layer1_size, hidden_layer2_size], output_size, \n",
    "                                activation='ReLU', \n",
    "                                initializer='N2',\n",
    "                                optimizer='AdaGrad', learning_rate=learning_rate,\n",
    "                                use_batch_normalization=False)\n",
    "    elif key == \"N2, AdaGrad, Batch_Norm\":\n",
    "        networks[key] = MultiLayerNetExtended(input_size, [hidden_layer1_size, hidden_layer2_size], output_size, \n",
    "                                activation='ReLU', \n",
    "                                initializer='N2',\n",
    "                                optimizer='AdaGrad', learning_rate=learning_rate,\n",
    "                                use_batch_normalization=True)\n",
    "    elif key == \"He, AdaGrad, No_Batch_Norm\":\n",
    "        networks[key] = MultiLayerNetExtended(input_size, [hidden_layer1_size, hidden_layer2_size], output_size, \n",
    "                                activation='ReLU', \n",
    "                                initializer='He',\n",
    "                                optimizer='AdaGrad', learning_rate=learning_rate,\n",
    "                                use_batch_normalization=False)\n",
    "    elif key == \"He, AdaGrad, Batch_Norm\":\n",
    "        networks[key] = MultiLayerNetExtended(input_size, [hidden_layer1_size, hidden_layer2_size], output_size, \n",
    "                                activation='ReLU', \n",
    "                                initializer='He',\n",
    "                                optimizer='AdaGrad', learning_rate=learning_rate,\n",
    "                                use_batch_normalization=True)\n",
    "        \n",
    "    train_errors[key] = [] \n",
    "    validation_errors[key] = []\n",
    "    test_accuracy_values[key] = []\n",
    "    max_test_accuracy_epoch[key] = 0\n",
    "    max_test_accuracy_value[key] = 0.0"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "N2, SGD, No_Batch_Norm    -Epoch:  0, Train Err.:2.30142, Validation Err.:2.30115, Test Accuracy:0.11350, Max Test Accuracy:0.11350\n",
      "N2, SGD, Batch_Norm       -Epoch:  0, Train Err.:2.30076, Validation Err.:2.30081, Test Accuracy:0.11350, Max Test Accuracy:0.11350\n",
      "N2, AdaGrad, No_Batch_Norm-Epoch:  0, Train Err.:0.28646, Validation Err.:0.27083, Test Accuracy:0.89810, Max Test Accuracy:0.89810\n",
      "N2, AdaGrad, Batch_Norm   -Epoch:  0, Train Err.:0.08490, Validation Err.:0.12210, Test Accuracy:0.95600, Max Test Accuracy:0.95600\n",
      "He, AdaGrad, No_Batch_Norm-Epoch:  0, Train Err.:0.27105, Validation Err.:0.23288, Test Accuracy:0.91000, Max Test Accuracy:0.91000\n",
      "He, AdaGrad, Batch_Norm   -Epoch:  0, Train Err.:0.08500, Validation Err.:0.11982, Test Accuracy:0.95650, Max Test Accuracy:0.95650\n",
      "\n",
      "N2, SGD, No_Batch_Norm    -Epoch:  1, Train Err.:2.29994, Validation Err.:2.29949, Test Accuracy:0.11350, Max Test Accuracy:0.11350\n",
      "N2, SGD, Batch_Norm       -Epoch:  1, Train Err.:2.29402, Validation Err.:2.29373, Test Accuracy:0.11350, Max Test Accuracy:0.11350\n",
      "N2, AdaGrad, No_Batch_Norm-Epoch:  1, Train Err.:0.17610, Validation Err.:0.17474, Test Accuracy:0.93160, Max Test Accuracy:0.93160\n",
      "N2, AdaGrad, Batch_Norm   -Epoch:  1, Train Err.:0.04542, Validation Err.:0.09554, Test Accuracy:0.96700, Max Test Accuracy:0.96700\n",
      "He, AdaGrad, No_Batch_Norm-Epoch:  1, Train Err.:0.18877, Validation Err.:0.17099, Test Accuracy:0.93500, Max Test Accuracy:0.93500\n",
      "He, AdaGrad, Batch_Norm   -Epoch:  1, Train Err.:0.04356, Validation Err.:0.09434, Test Accuracy:0.96700, Max Test Accuracy:0.96700\n",
      "\n",
      "N2, SGD, No_Batch_Norm    -Epoch:  2, Train Err.:2.29598, Validation Err.:2.29525, Test Accuracy:0.11350, Max Test Accuracy:0.11350\n",
      "N2, SGD, Batch_Norm       -Epoch:  2, Train Err.:2.21592, Validation Err.:2.21335, Test Accuracy:0.20590, Max Test Accuracy:0.20590\n",
      "N2, AdaGrad, No_Batch_Norm-Epoch:  2, Train Err.:0.12487, Validation Err.:0.14111, Test Accuracy:0.94520, Max Test Accuracy:0.94520\n",
      "N2, AdaGrad, Batch_Norm   -Epoch:  2, Train Err.:0.02827, Validation Err.:0.08908, Test Accuracy:0.97040, Max Test Accuracy:0.97040\n",
      "He, AdaGrad, No_Batch_Norm-Epoch:  2, Train Err.:0.14593, Validation Err.:0.15055, Test Accuracy:0.94480, Max Test Accuracy:0.94480\n",
      "He, AdaGrad, Batch_Norm   -Epoch:  2, Train Err.:0.03047, Validation Err.:0.08662, Test Accuracy:0.97020, Max Test Accuracy:0.97020\n",
      "\n",
      "N2, SGD, No_Batch_Norm    -Epoch:  3, Train Err.:2.27636, Validation Err.:2.27430, Test Accuracy:0.18860, Max Test Accuracy:0.18860\n",
      "N2, SGD, Batch_Norm       -Epoch:  3, Train Err.:1.87459, Validation Err.:1.86765, Test Accuracy:0.51140, Max Test Accuracy:0.51140\n",
      "N2, AdaGrad, No_Batch_Norm-Epoch:  3, Train Err.:0.09501, Validation Err.:0.12811, Test Accuracy:0.95270, Max Test Accuracy:0.95270\n",
      "N2, AdaGrad, Batch_Norm   -Epoch:  3, Train Err.:0.01708, Validation Err.:0.08797, Test Accuracy:0.97150, Max Test Accuracy:0.97150\n",
      "He, AdaGrad, No_Batch_Norm-Epoch:  3, Train Err.:0.12191, Validation Err.:0.13801, Test Accuracy:0.94970, Max Test Accuracy:0.94970\n",
      "He, AdaGrad, Batch_Norm   -Epoch:  3, Train Err.:0.02223, Validation Err.:0.08496, Test Accuracy:0.97220, Max Test Accuracy:0.97220\n",
      "\n",
      "N2, SGD, No_Batch_Norm    -Epoch:  4, Train Err.:2.03846, Validation Err.:2.02219, Test Accuracy:0.34520, Max Test Accuracy:0.34520\n",
      "N2, SGD, Batch_Norm       -Epoch:  4, Train Err.:1.31604, Validation Err.:1.31001, Test Accuracy:0.62020, Max Test Accuracy:0.62020\n",
      "N2, AdaGrad, No_Batch_Norm-Epoch:  4, Train Err.:0.07719, Validation Err.:0.12186, Test Accuracy:0.95640, Max Test Accuracy:0.95640\n",
      "N2, AdaGrad, Batch_Norm   -Epoch:  4, Train Err.:0.01082, Validation Err.:0.08955, Test Accuracy:0.97380, Max Test Accuracy:0.97380\n",
      "He, AdaGrad, No_Batch_Norm-Epoch:  4, Train Err.:0.10159, Validation Err.:0.13027, Test Accuracy:0.95340, Max Test Accuracy:0.95340\n",
      "He, AdaGrad, Batch_Norm   -Epoch:  4, Train Err.:0.01767, Validation Err.:0.08480, Test Accuracy:0.97360, Max Test Accuracy:0.97360\n",
      "\n",
      "N2, SGD, No_Batch_Norm    -Epoch:  5, Train Err.:1.32011, Validation Err.:1.28427, Test Accuracy:0.58910, Max Test Accuracy:0.58910\n",
      "N2, SGD, Batch_Norm       -Epoch:  5, Train Err.:0.64360, Validation Err.:0.64611, Test Accuracy:0.85730, Max Test Accuracy:0.85730\n",
      "N2, AdaGrad, No_Batch_Norm-Epoch:  5, Train Err.:0.06636, Validation Err.:0.11686, Test Accuracy:0.95740, Max Test Accuracy:0.95740\n",
      "N2, AdaGrad, Batch_Norm   -Epoch:  5, Train Err.:0.00727, Validation Err.:0.09021, Test Accuracy:0.97430, Max Test Accuracy:0.97430\n",
      "He, AdaGrad, No_Batch_Norm-Epoch:  5, Train Err.:0.08680, Validation Err.:0.12379, Test Accuracy:0.95610, Max Test Accuracy:0.95610\n",
      "He, AdaGrad, Batch_Norm   -Epoch:  5, Train Err.:0.01242, Validation Err.:0.08559, Test Accuracy:0.97340, Max Test Accuracy:0.97360\n",
      "\n",
      "N2, SGD, No_Batch_Norm    -Epoch:  6, Train Err.:0.79624, Validation Err.:0.73915, Test Accuracy:0.74060, Max Test Accuracy:0.74060\n",
      "N2, SGD, Batch_Norm       -Epoch:  6, Train Err.:0.30023, Validation Err.:0.31701, Test Accuracy:0.93570, Max Test Accuracy:0.93570\n",
      "N2, AdaGrad, No_Batch_Norm-Epoch:  6, Train Err.:0.05990, Validation Err.:0.11310, Test Accuracy:0.95900, Max Test Accuracy:0.95900\n",
      "N2, AdaGrad, Batch_Norm   -Epoch:  6, Train Err.:0.00510, Validation Err.:0.09130, Test Accuracy:0.97610, Max Test Accuracy:0.97610\n",
      "He, AdaGrad, No_Batch_Norm-Epoch:  6, Train Err.:0.07553, Validation Err.:0.12046, Test Accuracy:0.95790, Max Test Accuracy:0.95790\n",
      "He, AdaGrad, Batch_Norm   -Epoch:  6, Train Err.:0.00794, Validation Err.:0.08634, Test Accuracy:0.97520, Max Test Accuracy:0.97520\n",
      "\n",
      "N2, SGD, No_Batch_Norm    -Epoch:  7, Train Err.:0.65980, Validation Err.:0.59393, Test Accuracy:0.79580, Max Test Accuracy:0.79580\n",
      "N2, SGD, Batch_Norm       -Epoch:  7, Train Err.:0.16340, Validation Err.:0.19568, Test Accuracy:0.95150, Max Test Accuracy:0.95150\n",
      "N2, AdaGrad, No_Batch_Norm-Epoch:  7, Train Err.:0.05385, Validation Err.:0.11145, Test Accuracy:0.96110, Max Test Accuracy:0.96110\n",
      "N2, AdaGrad, Batch_Norm   -Epoch:  7, Train Err.:0.00390, Validation Err.:0.09530, Test Accuracy:0.97630, Max Test Accuracy:0.97630\n",
      "He, AdaGrad, No_Batch_Norm-Epoch:  7, Train Err.:0.06787, Validation Err.:0.11779, Test Accuracy:0.96050, Max Test Accuracy:0.96050\n",
      "He, AdaGrad, Batch_Norm   -Epoch:  7, Train Err.:0.00552, Validation Err.:0.08728, Test Accuracy:0.97390, Max Test Accuracy:0.97520\n",
      "\n",
      "N2, SGD, No_Batch_Norm    -Epoch:  8, Train Err.:0.58878, Validation Err.:0.52060, Test Accuracy:0.82420, Max Test Accuracy:0.82420\n",
      "N2, SGD, Batch_Norm       -Epoch:  8, Train Err.:0.10522, Validation Err.:0.14610, Test Accuracy:0.96080, Max Test Accuracy:0.96080\n",
      "N2, AdaGrad, No_Batch_Norm-Epoch:  8, Train Err.:0.04869, Validation Err.:0.11205, Test Accuracy:0.96180, Max Test Accuracy:0.96180\n",
      "N2, AdaGrad, Batch_Norm   -Epoch:  8, Train Err.:0.00304, Validation Err.:0.09796, Test Accuracy:0.97650, Max Test Accuracy:0.97650\n",
      "He, AdaGrad, No_Batch_Norm-Epoch:  8, Train Err.:0.06219, Validation Err.:0.11598, Test Accuracy:0.96170, Max Test Accuracy:0.96170\n",
      "He, AdaGrad, Batch_Norm   -Epoch:  8, Train Err.:0.00421, Validation Err.:0.09080, Test Accuracy:0.97420, Max Test Accuracy:0.97520\n",
      "\n",
      "N2, SGD, No_Batch_Norm    -Epoch:  9, Train Err.:0.52825, Validation Err.:0.45882, Test Accuracy:0.84660, Max Test Accuracy:0.84660\n",
      "N2, SGD, Batch_Norm       -Epoch:  9, Train Err.:0.07354, Validation Err.:0.11918, Test Accuracy:0.96720, Max Test Accuracy:0.96720\n",
      "N2, AdaGrad, No_Batch_Norm-Epoch:  9, Train Err.:0.04488, Validation Err.:0.11235, Test Accuracy:0.96220, Max Test Accuracy:0.96220\n",
      "N2, AdaGrad, Batch_Norm   -Epoch:  9, Train Err.:0.00243, Validation Err.:0.10307, Test Accuracy:0.97700, Max Test Accuracy:0.97700\n",
      "He, AdaGrad, No_Batch_Norm-Epoch:  9, Train Err.:0.05715, Validation Err.:0.11423, Test Accuracy:0.96310, Max Test Accuracy:0.96310\n",
      "He, AdaGrad, Batch_Norm   -Epoch:  9, Train Err.:0.00329, Validation Err.:0.09269, Test Accuracy:0.97360, Max Test Accuracy:0.97520\n",
      "\n",
      "N2, SGD, No_Batch_Norm    -Epoch: 10, Train Err.:0.48160, Validation Err.:0.40801, Test Accuracy:0.86270, Max Test Accuracy:0.86270\n",
      "N2, SGD, Batch_Norm       -Epoch: 10, Train Err.:0.05488, Validation Err.:0.10457, Test Accuracy:0.97090, Max Test Accuracy:0.97090\n",
      "N2, AdaGrad, No_Batch_Norm-Epoch: 10, Train Err.:0.04085, Validation Err.:0.11234, Test Accuracy:0.96230, Max Test Accuracy:0.96230\n",
      "N2, AdaGrad, Batch_Norm   -Epoch: 10, Train Err.:0.00194, Validation Err.:0.10662, Test Accuracy:0.97630, Max Test Accuracy:0.97700\n",
      "He, AdaGrad, No_Batch_Norm-Epoch: 10, Train Err.:0.05259, Validation Err.:0.11215, Test Accuracy:0.96380, Max Test Accuracy:0.96380\n",
      "He, AdaGrad, Batch_Norm   -Epoch: 10, Train Err.:0.00259, Validation Err.:0.09566, Test Accuracy:0.97320, Max Test Accuracy:0.97520\n",
      "\n",
      "N2, SGD, No_Batch_Norm    -Epoch: 11, Train Err.:0.45130, Validation Err.:0.37351, Test Accuracy:0.87320, Max Test Accuracy:0.87320\n",
      "N2, SGD, Batch_Norm       -Epoch: 11, Train Err.:0.04303, Validation Err.:0.09581, Test Accuracy:0.97340, Max Test Accuracy:0.97340\n",
      "N2, AdaGrad, No_Batch_Norm-Epoch: 11, Train Err.:0.03811, Validation Err.:0.11280, Test Accuracy:0.96310, Max Test Accuracy:0.96310\n",
      "N2, AdaGrad, Batch_Norm   -Epoch: 11, Train Err.:0.00160, Validation Err.:0.11009, Test Accuracy:0.97640, Max Test Accuracy:0.97700\n",
      "He, AdaGrad, No_Batch_Norm-Epoch: 11, Train Err.:0.04696, Validation Err.:0.11148, Test Accuracy:0.96440, Max Test Accuracy:0.96440\n",
      "He, AdaGrad, Batch_Norm   -Epoch: 11, Train Err.:0.00219, Validation Err.:0.09775, Test Accuracy:0.97370, Max Test Accuracy:0.97520\n",
      "\n",
      "N2, SGD, No_Batch_Norm    -Epoch: 12, Train Err.:0.42699, Validation Err.:0.34824, Test Accuracy:0.88190, Max Test Accuracy:0.88190\n",
      "N2, SGD, Batch_Norm       -Epoch: 12, Train Err.:0.03519, Validation Err.:0.09106, Test Accuracy:0.97490, Max Test Accuracy:0.97490\n",
      "N2, AdaGrad, No_Batch_Norm-Epoch: 12, Train Err.:0.03566, Validation Err.:0.11386, Test Accuracy:0.96370, Max Test Accuracy:0.96370\n",
      "N2, AdaGrad, Batch_Norm   -Epoch: 12, Train Err.:0.00138, Validation Err.:0.11260, Test Accuracy:0.97650, Max Test Accuracy:0.97700\n",
      "He, AdaGrad, No_Batch_Norm-Epoch: 12, Train Err.:0.04388, Validation Err.:0.11102, Test Accuracy:0.96450, Max Test Accuracy:0.96450\n",
      "He, AdaGrad, Batch_Norm   -Epoch: 12, Train Err.:0.00181, Validation Err.:0.09970, Test Accuracy:0.97310, Max Test Accuracy:0.97520\n",
      "\n",
      "N2, SGD, No_Batch_Norm    -Epoch: 13, Train Err.:0.40504, Validation Err.:0.32743, Test Accuracy:0.88800, Max Test Accuracy:0.88800\n",
      "N2, SGD, Batch_Norm       -Epoch: 13, Train Err.:0.02928, Validation Err.:0.08753, Test Accuracy:0.97480, Max Test Accuracy:0.97490\n",
      "N2, AdaGrad, No_Batch_Norm-Epoch: 13, Train Err.:0.03294, Validation Err.:0.11450, Test Accuracy:0.96330, Max Test Accuracy:0.96370\n",
      "N2, AdaGrad, Batch_Norm   -Epoch: 13, Train Err.:0.00116, Validation Err.:0.11458, Test Accuracy:0.97650, Max Test Accuracy:0.97700\n",
      "He, AdaGrad, No_Batch_Norm-Epoch: 13, Train Err.:0.04062, Validation Err.:0.11041, Test Accuracy:0.96520, Max Test Accuracy:0.96520\n",
      "He, AdaGrad, Batch_Norm   -Epoch: 13, Train Err.:0.00156, Validation Err.:0.10114, Test Accuracy:0.97330, Max Test Accuracy:0.97520\n",
      "\n",
      "N2, SGD, No_Batch_Norm    -Epoch: 14, Train Err.:0.38497, Validation Err.:0.30956, Test Accuracy:0.89390, Max Test Accuracy:0.89390\n",
      "N2, SGD, Batch_Norm       -Epoch: 14, Train Err.:0.02486, Validation Err.:0.08599, Test Accuracy:0.97410, Max Test Accuracy:0.97490\n",
      "N2, AdaGrad, No_Batch_Norm-Epoch: 14, Train Err.:0.03046, Validation Err.:0.11549, Test Accuracy:0.96350, Max Test Accuracy:0.96370\n",
      "N2, AdaGrad, Batch_Norm   -Epoch: 14, Train Err.:0.00101, Validation Err.:0.11607, Test Accuracy:0.97650, Max Test Accuracy:0.97700\n",
      "He, AdaGrad, No_Batch_Norm-Epoch: 14, Train Err.:0.03738, Validation Err.:0.11023, Test Accuracy:0.96510, Max Test Accuracy:0.96520\n",
      "He, AdaGrad, Batch_Norm   -Epoch: 14, Train Err.:0.00133, Validation Err.:0.10274, Test Accuracy:0.97350, Max Test Accuracy:0.97520\n",
      "\n",
      "N2, SGD, No_Batch_Norm    -Epoch: 15, Train Err.:0.36626, Validation Err.:0.29415, Test Accuracy:0.89830, Max Test Accuracy:0.89830\n",
      "N2, SGD, Batch_Norm       -Epoch: 15, Train Err.:0.02116, Validation Err.:0.08525, Test Accuracy:0.97500, Max Test Accuracy:0.97500\n",
      "N2, AdaGrad, No_Batch_Norm-Epoch: 15, Train Err.:0.02821, Validation Err.:0.11692, Test Accuracy:0.96360, Max Test Accuracy:0.96370\n",
      "N2, AdaGrad, Batch_Norm   -Epoch: 15, Train Err.:0.00088, Validation Err.:0.11764, Test Accuracy:0.97650, Max Test Accuracy:0.97700\n",
      "He, AdaGrad, No_Batch_Norm-Epoch: 15, Train Err.:0.03517, Validation Err.:0.11059, Test Accuracy:0.96570, Max Test Accuracy:0.96570\n",
      "He, AdaGrad, Batch_Norm   -Epoch: 15, Train Err.:0.00119, Validation Err.:0.10467, Test Accuracy:0.97360, Max Test Accuracy:0.97520\n",
      "\n",
      "N2, SGD, No_Batch_Norm    -Epoch: 16, Train Err.:0.34959, Validation Err.:0.28041, Test Accuracy:0.90390, Max Test Accuracy:0.90390\n",
      "N2, SGD, Batch_Norm       -Epoch: 16, Train Err.:0.01766, Validation Err.:0.08557, Test Accuracy:0.97530, Max Test Accuracy:0.97530\n",
      "N2, AdaGrad, No_Batch_Norm-Epoch: 16, Train Err.:0.02642, Validation Err.:0.11830, Test Accuracy:0.96330, Max Test Accuracy:0.96370\n",
      "N2, AdaGrad, Batch_Norm   -Epoch: 16, Train Err.:0.00079, Validation Err.:0.11851, Test Accuracy:0.97680, Max Test Accuracy:0.97700\n",
      "He, AdaGrad, No_Batch_Norm-Epoch: 16, Train Err.:0.03254, Validation Err.:0.11065, Test Accuracy:0.96600, Max Test Accuracy:0.96600\n",
      "He, AdaGrad, Batch_Norm   -Epoch: 16, Train Err.:0.00106, Validation Err.:0.10594, Test Accuracy:0.97400, Max Test Accuracy:0.97520\n",
      "\n",
      "N2, SGD, No_Batch_Norm    -Epoch: 17, Train Err.:0.33412, Validation Err.:0.26818, Test Accuracy:0.90800, Max Test Accuracy:0.90800\n",
      "N2, SGD, Batch_Norm       -Epoch: 17, Train Err.:0.01482, Validation Err.:0.08499, Test Accuracy:0.97570, Max Test Accuracy:0.97570\n",
      "N2, AdaGrad, No_Batch_Norm-Epoch: 17, Train Err.:0.02445, Validation Err.:0.12019, Test Accuracy:0.96290, Max Test Accuracy:0.96370\n",
      "N2, AdaGrad, Batch_Norm   -Epoch: 17, Train Err.:0.00071, Validation Err.:0.11948, Test Accuracy:0.97670, Max Test Accuracy:0.97700\n",
      "He, AdaGrad, No_Batch_Norm-Epoch: 17, Train Err.:0.03080, Validation Err.:0.11160, Test Accuracy:0.96690, Max Test Accuracy:0.96690\n",
      "He, AdaGrad, Batch_Norm   -Epoch: 17, Train Err.:0.00095, Validation Err.:0.10721, Test Accuracy:0.97420, Max Test Accuracy:0.97520\n",
      "\n",
      "N2, SGD, No_Batch_Norm    -Epoch: 18, Train Err.:0.31952, Validation Err.:0.25706, Test Accuracy:0.91130, Max Test Accuracy:0.91130\n",
      "N2, SGD, Batch_Norm       -Epoch: 18, Train Err.:0.01276, Validation Err.:0.08456, Test Accuracy:0.97540, Max Test Accuracy:0.97570\n",
      "N2, AdaGrad, No_Batch_Norm-Epoch: 18, Train Err.:0.02259, Validation Err.:0.12186, Test Accuracy:0.96410, Max Test Accuracy:0.96410\n",
      "N2, AdaGrad, Batch_Norm   -Epoch: 18, Train Err.:0.00064, Validation Err.:0.12058, Test Accuracy:0.97690, Max Test Accuracy:0.97700\n",
      "He, AdaGrad, No_Batch_Norm-Epoch: 18, Train Err.:0.02863, Validation Err.:0.11167, Test Accuracy:0.96660, Max Test Accuracy:0.96690\n",
      "He, AdaGrad, Batch_Norm   -Epoch: 18, Train Err.:0.00086, Validation Err.:0.10881, Test Accuracy:0.97430, Max Test Accuracy:0.97520\n",
      "\n",
      "N2, SGD, No_Batch_Norm    -Epoch: 19, Train Err.:0.30613, Validation Err.:0.24693, Test Accuracy:0.91380, Max Test Accuracy:0.91380\n",
      "N2, SGD, Batch_Norm       -Epoch: 19, Train Err.:0.01115, Validation Err.:0.08410, Test Accuracy:0.97510, Max Test Accuracy:0.97570\n",
      "N2, AdaGrad, No_Batch_Norm-Epoch: 19, Train Err.:0.02127, Validation Err.:0.12316, Test Accuracy:0.96420, Max Test Accuracy:0.96420\n",
      "N2, AdaGrad, Batch_Norm   -Epoch: 19, Train Err.:0.00059, Validation Err.:0.12152, Test Accuracy:0.97690, Max Test Accuracy:0.97700\n",
      "He, AdaGrad, No_Batch_Norm-Epoch: 19, Train Err.:0.02658, Validation Err.:0.11335, Test Accuracy:0.96670, Max Test Accuracy:0.96690\n",
      "He, AdaGrad, Batch_Norm   -Epoch: 19, Train Err.:0.00078, Validation Err.:0.11002, Test Accuracy:0.97430, Max Test Accuracy:0.97520\n",
      "\n",
      "N2, SGD, No_Batch_Norm    -Epoch: 20, Train Err.:0.29372, Validation Err.:0.23764, Test Accuracy:0.91650, Max Test Accuracy:0.91650\n",
      "N2, SGD, Batch_Norm       -Epoch: 20, Train Err.:0.00985, Validation Err.:0.08445, Test Accuracy:0.97440, Max Test Accuracy:0.97570\n",
      "N2, AdaGrad, No_Batch_Norm-Epoch: 20, Train Err.:0.01970, Validation Err.:0.12503, Test Accuracy:0.96420, Max Test Accuracy:0.96420\n",
      "N2, AdaGrad, Batch_Norm   -Epoch: 20, Train Err.:0.00054, Validation Err.:0.12274, Test Accuracy:0.97710, Max Test Accuracy:0.97710\n",
      "He, AdaGrad, No_Batch_Norm-Epoch: 20, Train Err.:0.02503, Validation Err.:0.11407, Test Accuracy:0.96750, Max Test Accuracy:0.96750\n",
      "He, AdaGrad, Batch_Norm   -Epoch: 20, Train Err.:0.00072, Validation Err.:0.11122, Test Accuracy:0.97440, Max Test Accuracy:0.97520\n",
      "\n",
      "N2, SGD, No_Batch_Norm    -Epoch: 21, Train Err.:0.28205, Validation Err.:0.22896, Test Accuracy:0.91890, Max Test Accuracy:0.91890\n",
      "N2, SGD, Batch_Norm       -Epoch: 21, Train Err.:0.00871, Validation Err.:0.08360, Test Accuracy:0.97460, Max Test Accuracy:0.97570\n",
      "N2, AdaGrad, No_Batch_Norm-Epoch: 21, Train Err.:0.01834, Validation Err.:0.12802, Test Accuracy:0.96420, Max Test Accuracy:0.96420\n",
      "N2, AdaGrad, Batch_Norm   -Epoch: 21, Train Err.:0.00050, Validation Err.:0.12379, Test Accuracy:0.97710, Max Test Accuracy:0.97710\n",
      "He, AdaGrad, No_Batch_Norm-Epoch: 21, Train Err.:0.02354, Validation Err.:0.11514, Test Accuracy:0.96730, Max Test Accuracy:0.96750\n",
      "He, AdaGrad, Batch_Norm   -Epoch: 21, Train Err.:0.00067, Validation Err.:0.11254, Test Accuracy:0.97450, Max Test Accuracy:0.97520\n",
      "\n",
      "N2, SGD, No_Batch_Norm    -Epoch: 22, Train Err.:0.27117, Validation Err.:0.22087, Test Accuracy:0.92180, Max Test Accuracy:0.92180\n",
      "N2, SGD, Batch_Norm       -Epoch: 22, Train Err.:0.00777, Validation Err.:0.08401, Test Accuracy:0.97420, Max Test Accuracy:0.97570\n",
      "N2, AdaGrad, No_Batch_Norm-Epoch: 22, Train Err.:0.01741, Validation Err.:0.12887, Test Accuracy:0.96420, Max Test Accuracy:0.96420\n",
      "N2, AdaGrad, Batch_Norm   -Epoch: 22, Train Err.:0.00047, Validation Err.:0.12481, Test Accuracy:0.97710, Max Test Accuracy:0.97710\n",
      "He, AdaGrad, No_Batch_Norm-Epoch: 22, Train Err.:0.02249, Validation Err.:0.11574, Test Accuracy:0.96690, Max Test Accuracy:0.96750\n",
      "He, AdaGrad, Batch_Norm   -Epoch: 22, Train Err.:0.00062, Validation Err.:0.11362, Test Accuracy:0.97440, Max Test Accuracy:0.97520\n",
      "\n",
      "N2, SGD, No_Batch_Norm    -Epoch: 23, Train Err.:0.26075, Validation Err.:0.21323, Test Accuracy:0.92460, Max Test Accuracy:0.92460\n",
      "N2, SGD, Batch_Norm       -Epoch: 23, Train Err.:0.00715, Validation Err.:0.08335, Test Accuracy:0.97360, Max Test Accuracy:0.97570\n",
      "N2, AdaGrad, No_Batch_Norm-Epoch: 23, Train Err.:0.01611, Validation Err.:0.13067, Test Accuracy:0.96370, Max Test Accuracy:0.96420\n",
      "N2, AdaGrad, Batch_Norm   -Epoch: 23, Train Err.:0.00044, Validation Err.:0.12586, Test Accuracy:0.97720, Max Test Accuracy:0.97720\n",
      "He, AdaGrad, No_Batch_Norm-Epoch: 23, Train Err.:0.02146, Validation Err.:0.11648, Test Accuracy:0.96660, Max Test Accuracy:0.96750\n",
      "He, AdaGrad, Batch_Norm   -Epoch: 23, Train Err.:0.00058, Validation Err.:0.11470, Test Accuracy:0.97430, Max Test Accuracy:0.97520\n",
      "\n",
      "N2, SGD, No_Batch_Norm    -Epoch: 24, Train Err.:0.25069, Validation Err.:0.20605, Test Accuracy:0.92760, Max Test Accuracy:0.92760\n",
      "N2, SGD, Batch_Norm       -Epoch: 24, Train Err.:0.00650, Validation Err.:0.08365, Test Accuracy:0.97350, Max Test Accuracy:0.97570\n",
      "N2, AdaGrad, No_Batch_Norm-Epoch: 24, Train Err.:0.01508, Validation Err.:0.13254, Test Accuracy:0.96400, Max Test Accuracy:0.96420\n",
      "N2, AdaGrad, Batch_Norm   -Epoch: 24, Train Err.:0.00041, Validation Err.:0.12683, Test Accuracy:0.97750, Max Test Accuracy:0.97750\n",
      "He, AdaGrad, No_Batch_Norm-Epoch: 24, Train Err.:0.02042, Validation Err.:0.11790, Test Accuracy:0.96750, Max Test Accuracy:0.96750\n",
      "He, AdaGrad, Batch_Norm   -Epoch: 24, Train Err.:0.00054, Validation Err.:0.11563, Test Accuracy:0.97440, Max Test Accuracy:0.97520\n",
      "\n",
      "N2, SGD, No_Batch_Norm    -Epoch: 25, Train Err.:0.24084, Validation Err.:0.19927, Test Accuracy:0.93030, Max Test Accuracy:0.93030\n",
      "N2, SGD, Batch_Norm       -Epoch: 25, Train Err.:0.00607, Validation Err.:0.08327, Test Accuracy:0.97410, Max Test Accuracy:0.97570\n",
      "N2, AdaGrad, No_Batch_Norm-Epoch: 25, Train Err.:0.01414, Validation Err.:0.13492, Test Accuracy:0.96410, Max Test Accuracy:0.96420\n",
      "N2, AdaGrad, Batch_Norm   -Epoch: 25, Train Err.:0.00038, Validation Err.:0.12764, Test Accuracy:0.97770, Max Test Accuracy:0.97770\n",
      "He, AdaGrad, No_Batch_Norm-Epoch: 25, Train Err.:0.01964, Validation Err.:0.11808, Test Accuracy:0.96710, Max Test Accuracy:0.96750\n",
      "He, AdaGrad, Batch_Norm   -Epoch: 25, Train Err.:0.00050, Validation Err.:0.11657, Test Accuracy:0.97440, Max Test Accuracy:0.97520\n",
      "\n",
      "N2, SGD, No_Batch_Norm    -Epoch: 26, Train Err.:0.23130, Validation Err.:0.19266, Test Accuracy:0.93240, Max Test Accuracy:0.93240\n",
      "N2, SGD, Batch_Norm       -Epoch: 26, Train Err.:0.00560, Validation Err.:0.08301, Test Accuracy:0.97380, Max Test Accuracy:0.97570\n",
      "N2, AdaGrad, No_Batch_Norm-Epoch: 26, Train Err.:0.01322, Validation Err.:0.13632, Test Accuracy:0.96400, Max Test Accuracy:0.96420\n",
      "N2, AdaGrad, Batch_Norm   -Epoch: 26, Train Err.:0.00036, Validation Err.:0.12859, Test Accuracy:0.97780, Max Test Accuracy:0.97780\n",
      "He, AdaGrad, No_Batch_Norm-Epoch: 26, Train Err.:0.01873, Validation Err.:0.11930, Test Accuracy:0.96710, Max Test Accuracy:0.96750\n",
      "He, AdaGrad, Batch_Norm   -Epoch: 26, Train Err.:0.00047, Validation Err.:0.11756, Test Accuracy:0.97430, Max Test Accuracy:0.97520\n",
      "\n",
      "N2, SGD, No_Batch_Norm    -Epoch: 27, Train Err.:0.22194, Validation Err.:0.18645, Test Accuracy:0.93430, Max Test Accuracy:0.93430\n",
      "N2, SGD, Batch_Norm       -Epoch: 27, Train Err.:0.00517, Validation Err.:0.08312, Test Accuracy:0.97460, Max Test Accuracy:0.97570\n",
      "N2, AdaGrad, No_Batch_Norm-Epoch: 27, Train Err.:0.01216, Validation Err.:0.13738, Test Accuracy:0.96360, Max Test Accuracy:0.96420\n",
      "N2, AdaGrad, Batch_Norm   -Epoch: 27, Train Err.:0.00034, Validation Err.:0.12942, Test Accuracy:0.97770, Max Test Accuracy:0.97780\n",
      "He, AdaGrad, No_Batch_Norm-Epoch: 27, Train Err.:0.01786, Validation Err.:0.11987, Test Accuracy:0.96740, Max Test Accuracy:0.96750\n",
      "He, AdaGrad, Batch_Norm   -Epoch: 27, Train Err.:0.00045, Validation Err.:0.11840, Test Accuracy:0.97430, Max Test Accuracy:0.97520\n",
      "\n",
      "N2, SGD, No_Batch_Norm    -Epoch: 28, Train Err.:0.21302, Validation Err.:0.18058, Test Accuracy:0.93670, Max Test Accuracy:0.93670\n",
      "N2, SGD, Batch_Norm       -Epoch: 28, Train Err.:0.00480, Validation Err.:0.08302, Test Accuracy:0.97460, Max Test Accuracy:0.97570\n",
      "N2, AdaGrad, No_Batch_Norm-Epoch: 28, Train Err.:0.01178, Validation Err.:0.13984, Test Accuracy:0.96370, Max Test Accuracy:0.96420\n",
      "N2, AdaGrad, Batch_Norm   -Epoch: 28, Train Err.:0.00033, Validation Err.:0.13013, Test Accuracy:0.97770, Max Test Accuracy:0.97780\n",
      "He, AdaGrad, No_Batch_Norm-Epoch: 28, Train Err.:0.01713, Validation Err.:0.12092, Test Accuracy:0.96730, Max Test Accuracy:0.96750\n",
      "He, AdaGrad, Batch_Norm   -Epoch: 28, Train Err.:0.00042, Validation Err.:0.11916, Test Accuracy:0.97430, Max Test Accuracy:0.97520\n",
      "\n",
      "N2, SGD, No_Batch_Norm    -Epoch: 29, Train Err.:0.20453, Validation Err.:0.17506, Test Accuracy:0.93910, Max Test Accuracy:0.93910\n",
      "N2, SGD, Batch_Norm       -Epoch: 29, Train Err.:0.00449, Validation Err.:0.08289, Test Accuracy:0.97490, Max Test Accuracy:0.97570\n",
      "N2, AdaGrad, No_Batch_Norm-Epoch: 29, Train Err.:0.01116, Validation Err.:0.14196, Test Accuracy:0.96370, Max Test Accuracy:0.96420\n",
      "N2, AdaGrad, Batch_Norm   -Epoch: 29, Train Err.:0.00031, Validation Err.:0.13093, Test Accuracy:0.97770, Max Test Accuracy:0.97780\n",
      "He, AdaGrad, No_Batch_Norm-Epoch: 29, Train Err.:0.01650, Validation Err.:0.12167, Test Accuracy:0.96760, Max Test Accuracy:0.96760\n",
      "He, AdaGrad, Batch_Norm   -Epoch: 29, Train Err.:0.00040, Validation Err.:0.12010, Test Accuracy:0.97410, Max Test Accuracy:0.97520\n",
      "\n",
      "N2, SGD, No_Batch_Norm    -Epoch: 30, Train Err.:0.19651, Validation Err.:0.16975, Test Accuracy:0.94060, Max Test Accuracy:0.94060\n",
      "N2, SGD, Batch_Norm       -Epoch: 30, Train Err.:0.00422, Validation Err.:0.08285, Test Accuracy:0.97410, Max Test Accuracy:0.97570\n",
      "N2, AdaGrad, No_Batch_Norm-Epoch: 30, Train Err.:0.01041, Validation Err.:0.14353, Test Accuracy:0.96360, Max Test Accuracy:0.96420\n",
      "N2, AdaGrad, Batch_Norm   -Epoch: 30, Train Err.:0.00029, Validation Err.:0.13171, Test Accuracy:0.97760, Max Test Accuracy:0.97780\n",
      "He, AdaGrad, No_Batch_Norm-Epoch: 30, Train Err.:0.01577, Validation Err.:0.12294, Test Accuracy:0.96740, Max Test Accuracy:0.96760\n",
      "He, AdaGrad, Batch_Norm   -Epoch: 30, Train Err.:0.00038, Validation Err.:0.12076, Test Accuracy:0.97410, Max Test Accuracy:0.97520\n",
      "\n",
      "N2, SGD, No_Batch_Norm    -Epoch: 31, Train Err.:0.18891, Validation Err.:0.16480, Test Accuracy:0.94220, Max Test Accuracy:0.94220\n",
      "N2, SGD, Batch_Norm       -Epoch: 31, Train Err.:0.00395, Validation Err.:0.08283, Test Accuracy:0.97450, Max Test Accuracy:0.97570\n",
      "N2, AdaGrad, No_Batch_Norm-Epoch: 31, Train Err.:0.00996, Validation Err.:0.14605, Test Accuracy:0.96310, Max Test Accuracy:0.96420\n",
      "N2, AdaGrad, Batch_Norm   -Epoch: 31, Train Err.:0.00028, Validation Err.:0.13242, Test Accuracy:0.97740, Max Test Accuracy:0.97780\n",
      "He, AdaGrad, No_Batch_Norm-Epoch: 31, Train Err.:0.01522, Validation Err.:0.12392, Test Accuracy:0.96800, Max Test Accuracy:0.96800\n",
      "He, AdaGrad, Batch_Norm   -Epoch: 31, Train Err.:0.00036, Validation Err.:0.12149, Test Accuracy:0.97420, Max Test Accuracy:0.97520\n",
      "\n",
      "N2, SGD, No_Batch_Norm    -Epoch: 32, Train Err.:0.18163, Validation Err.:0.16016, Test Accuracy:0.94330, Max Test Accuracy:0.94330\n",
      "N2, SGD, Batch_Norm       -Epoch: 32, Train Err.:0.00372, Validation Err.:0.08270, Test Accuracy:0.97410, Max Test Accuracy:0.97570\n",
      "N2, AdaGrad, No_Batch_Norm-Epoch: 32, Train Err.:0.00953, Validation Err.:0.14784, Test Accuracy:0.96320, Max Test Accuracy:0.96420\n",
      "N2, AdaGrad, Batch_Norm   -Epoch: 32, Train Err.:0.00027, Validation Err.:0.13304, Test Accuracy:0.97740, Max Test Accuracy:0.97780\n",
      "He, AdaGrad, No_Batch_Norm-Epoch: 32, Train Err.:0.01442, Validation Err.:0.12540, Test Accuracy:0.96790, Max Test Accuracy:0.96800\n",
      "He, AdaGrad, Batch_Norm   -Epoch: 32, Train Err.:0.00034, Validation Err.:0.12223, Test Accuracy:0.97420, Max Test Accuracy:0.97520\n",
      "\n",
      "N2, SGD, No_Batch_Norm    -Epoch: 33, Train Err.:0.17469, Validation Err.:0.15575, Test Accuracy:0.94530, Max Test Accuracy:0.94530\n",
      "N2, SGD, Batch_Norm       -Epoch: 33, Train Err.:0.00353, Validation Err.:0.08281, Test Accuracy:0.97470, Max Test Accuracy:0.97570\n",
      "N2, AdaGrad, No_Batch_Norm-Epoch: 33, Train Err.:0.00903, Validation Err.:0.14978, Test Accuracy:0.96350, Max Test Accuracy:0.96420\n",
      "N2, AdaGrad, Batch_Norm   -Epoch: 33, Train Err.:0.00026, Validation Err.:0.13374, Test Accuracy:0.97740, Max Test Accuracy:0.97780\n",
      "He, AdaGrad, No_Batch_Norm-Epoch: 33, Train Err.:0.01374, Validation Err.:0.12632, Test Accuracy:0.96790, Max Test Accuracy:0.96800\n",
      "He, AdaGrad, Batch_Norm   -Epoch: 33, Train Err.:0.00033, Validation Err.:0.12285, Test Accuracy:0.97410, Max Test Accuracy:0.97520\n",
      "\n",
      "N2, SGD, No_Batch_Norm    -Epoch: 34, Train Err.:0.16821, Validation Err.:0.15166, Test Accuracy:0.94630, Max Test Accuracy:0.94630\n",
      "N2, SGD, Batch_Norm       -Epoch: 34, Train Err.:0.00333, Validation Err.:0.08228, Test Accuracy:0.97450, Max Test Accuracy:0.97570\n",
      "N2, AdaGrad, No_Batch_Norm-Epoch: 34, Train Err.:0.00887, Validation Err.:0.15215, Test Accuracy:0.96290, Max Test Accuracy:0.96420\n",
      "N2, AdaGrad, Batch_Norm   -Epoch: 34, Train Err.:0.00025, Validation Err.:0.13437, Test Accuracy:0.97740, Max Test Accuracy:0.97780\n",
      "He, AdaGrad, No_Batch_Norm-Epoch: 34, Train Err.:0.01326, Validation Err.:0.12789, Test Accuracy:0.96780, Max Test Accuracy:0.96800\n",
      "He, AdaGrad, Batch_Norm   -Epoch: 34, Train Err.:0.00031, Validation Err.:0.12351, Test Accuracy:0.97390, Max Test Accuracy:0.97520\n",
      "\n",
      "N2, SGD, No_Batch_Norm    -Epoch: 35, Train Err.:0.16203, Validation Err.:0.14782, Test Accuracy:0.94840, Max Test Accuracy:0.94840\n",
      "N2, SGD, Batch_Norm       -Epoch: 35, Train Err.:0.00318, Validation Err.:0.08267, Test Accuracy:0.97410, Max Test Accuracy:0.97570\n",
      "N2, AdaGrad, No_Batch_Norm-Epoch: 35, Train Err.:0.00842, Validation Err.:0.15306, Test Accuracy:0.96310, Max Test Accuracy:0.96420\n",
      "N2, AdaGrad, Batch_Norm   -Epoch: 35, Train Err.:0.00024, Validation Err.:0.13498, Test Accuracy:0.97740, Max Test Accuracy:0.97780\n",
      "He, AdaGrad, No_Batch_Norm-Epoch: 35, Train Err.:0.01279, Validation Err.:0.12788, Test Accuracy:0.96810, Max Test Accuracy:0.96810\n",
      "He, AdaGrad, Batch_Norm   -Epoch: 35, Train Err.:0.00030, Validation Err.:0.12411, Test Accuracy:0.97400, Max Test Accuracy:0.97520\n",
      "\n",
      "N2, SGD, No_Batch_Norm    -Epoch: 36, Train Err.:0.15635, Validation Err.:0.14423, Test Accuracy:0.94980, Max Test Accuracy:0.94980\n",
      "N2, SGD, Batch_Norm       -Epoch: 36, Train Err.:0.00302, Validation Err.:0.08239, Test Accuracy:0.97430, Max Test Accuracy:0.97570\n",
      "N2, AdaGrad, No_Batch_Norm-Epoch: 36, Train Err.:0.00799, Validation Err.:0.15626, Test Accuracy:0.96290, Max Test Accuracy:0.96420\n",
      "N2, AdaGrad, Batch_Norm   -Epoch: 36, Train Err.:0.00023, Validation Err.:0.13557, Test Accuracy:0.97740, Max Test Accuracy:0.97780\n",
      "He, AdaGrad, No_Batch_Norm-Epoch: 36, Train Err.:0.01226, Validation Err.:0.12988, Test Accuracy:0.96810, Max Test Accuracy:0.96810\n",
      "He, AdaGrad, Batch_Norm   -Epoch: 36, Train Err.:0.00029, Validation Err.:0.12464, Test Accuracy:0.97400, Max Test Accuracy:0.97520\n",
      "\n",
      "N2, SGD, No_Batch_Norm    -Epoch: 37, Train Err.:0.15101, Validation Err.:0.14092, Test Accuracy:0.95040, Max Test Accuracy:0.95040\n",
      "N2, SGD, Batch_Norm       -Epoch: 37, Train Err.:0.00289, Validation Err.:0.08262, Test Accuracy:0.97420, Max Test Accuracy:0.97570\n",
      "N2, AdaGrad, No_Batch_Norm-Epoch: 37, Train Err.:0.00743, Validation Err.:0.15788, Test Accuracy:0.96260, Max Test Accuracy:0.96420\n",
      "N2, AdaGrad, Batch_Norm   -Epoch: 37, Train Err.:0.00022, Validation Err.:0.13611, Test Accuracy:0.97750, Max Test Accuracy:0.97780\n",
      "He, AdaGrad, No_Batch_Norm-Epoch: 37, Train Err.:0.01169, Validation Err.:0.13048, Test Accuracy:0.96840, Max Test Accuracy:0.96840\n",
      "He, AdaGrad, Batch_Norm   -Epoch: 37, Train Err.:0.00028, Validation Err.:0.12523, Test Accuracy:0.97390, Max Test Accuracy:0.97520\n",
      "\n",
      "N2, SGD, No_Batch_Norm    -Epoch: 38, Train Err.:0.14598, Validation Err.:0.13778, Test Accuracy:0.95150, Max Test Accuracy:0.95150\n",
      "N2, SGD, Batch_Norm       -Epoch: 38, Train Err.:0.00277, Validation Err.:0.08238, Test Accuracy:0.97370, Max Test Accuracy:0.97570\n",
      "N2, AdaGrad, No_Batch_Norm-Epoch: 38, Train Err.:0.00720, Validation Err.:0.15925, Test Accuracy:0.96270, Max Test Accuracy:0.96420\n",
      "N2, AdaGrad, Batch_Norm   -Epoch: 38, Train Err.:0.00021, Validation Err.:0.13673, Test Accuracy:0.97750, Max Test Accuracy:0.97780\n",
      "He, AdaGrad, No_Batch_Norm-Epoch: 38, Train Err.:0.01135, Validation Err.:0.13158, Test Accuracy:0.96840, Max Test Accuracy:0.96840\n",
      "He, AdaGrad, Batch_Norm   -Epoch: 38, Train Err.:0.00027, Validation Err.:0.12585, Test Accuracy:0.97370, Max Test Accuracy:0.97520\n",
      "\n",
      "N2, SGD, No_Batch_Norm    -Epoch: 39, Train Err.:0.14118, Validation Err.:0.13490, Test Accuracy:0.95270, Max Test Accuracy:0.95270\n",
      "N2, SGD, Batch_Norm       -Epoch: 39, Train Err.:0.00265, Validation Err.:0.08244, Test Accuracy:0.97370, Max Test Accuracy:0.97570\n",
      "N2, AdaGrad, No_Batch_Norm-Epoch: 39, Train Err.:0.00693, Validation Err.:0.16186, Test Accuracy:0.96280, Max Test Accuracy:0.96420\n",
      "N2, AdaGrad, Batch_Norm   -Epoch: 39, Train Err.:0.00020, Validation Err.:0.13723, Test Accuracy:0.97750, Max Test Accuracy:0.97780\n",
      "He, AdaGrad, No_Batch_Norm-Epoch: 39, Train Err.:0.01104, Validation Err.:0.13206, Test Accuracy:0.96860, Max Test Accuracy:0.96860\n",
      "He, AdaGrad, Batch_Norm   -Epoch: 39, Train Err.:0.00026, Validation Err.:0.12636, Test Accuracy:0.97370, Max Test Accuracy:0.97520\n",
      "\n",
      "N2, SGD, No_Batch_Norm    -Epoch: 40, Train Err.:0.13669, Validation Err.:0.13224, Test Accuracy:0.95330, Max Test Accuracy:0.95330\n",
      "N2, SGD, Batch_Norm       -Epoch: 40, Train Err.:0.00255, Validation Err.:0.08238, Test Accuracy:0.97390, Max Test Accuracy:0.97570\n",
      "N2, AdaGrad, No_Batch_Norm-Epoch: 40, Train Err.:0.00658, Validation Err.:0.16311, Test Accuracy:0.96210, Max Test Accuracy:0.96420\n",
      "N2, AdaGrad, Batch_Norm   -Epoch: 40, Train Err.:0.00020, Validation Err.:0.13771, Test Accuracy:0.97740, Max Test Accuracy:0.97780\n",
      "He, AdaGrad, No_Batch_Norm-Epoch: 40, Train Err.:0.01053, Validation Err.:0.13296, Test Accuracy:0.96850, Max Test Accuracy:0.96860\n",
      "He, AdaGrad, Batch_Norm   -Epoch: 40, Train Err.:0.00025, Validation Err.:0.12694, Test Accuracy:0.97380, Max Test Accuracy:0.97520\n",
      "\n",
      "N2, SGD, No_Batch_Norm    -Epoch: 41, Train Err.:0.13246, Validation Err.:0.12978, Test Accuracy:0.95420, Max Test Accuracy:0.95420\n",
      "N2, SGD, Batch_Norm       -Epoch: 41, Train Err.:0.00244, Validation Err.:0.08242, Test Accuracy:0.97380, Max Test Accuracy:0.97570\n",
      "N2, AdaGrad, No_Batch_Norm-Epoch: 41, Train Err.:0.00622, Validation Err.:0.16490, Test Accuracy:0.96220, Max Test Accuracy:0.96420\n",
      "N2, AdaGrad, Batch_Norm   -Epoch: 41, Train Err.:0.00019, Validation Err.:0.13821, Test Accuracy:0.97730, Max Test Accuracy:0.97780\n",
      "He, AdaGrad, No_Batch_Norm-Epoch: 41, Train Err.:0.01007, Validation Err.:0.13419, Test Accuracy:0.96850, Max Test Accuracy:0.96860\n",
      "He, AdaGrad, Batch_Norm   -Epoch: 41, Train Err.:0.00024, Validation Err.:0.12742, Test Accuracy:0.97380, Max Test Accuracy:0.97520\n",
      "\n",
      "N2, SGD, No_Batch_Norm    -Epoch: 42, Train Err.:0.12850, Validation Err.:0.12750, Test Accuracy:0.95460, Max Test Accuracy:0.95460\n",
      "N2, SGD, Batch_Norm       -Epoch: 42, Train Err.:0.00235, Validation Err.:0.08221, Test Accuracy:0.97360, Max Test Accuracy:0.97570\n",
      "N2, AdaGrad, No_Batch_Norm-Epoch: 42, Train Err.:0.00600, Validation Err.:0.16643, Test Accuracy:0.96220, Max Test Accuracy:0.96420\n",
      "N2, AdaGrad, Batch_Norm   -Epoch: 42, Train Err.:0.00018, Validation Err.:0.13869, Test Accuracy:0.97720, Max Test Accuracy:0.97780\n",
      "He, AdaGrad, No_Batch_Norm-Epoch: 42, Train Err.:0.00978, Validation Err.:0.13493, Test Accuracy:0.96780, Max Test Accuracy:0.96860\n",
      "He, AdaGrad, Batch_Norm   -Epoch: 42, Train Err.:0.00023, Validation Err.:0.12790, Test Accuracy:0.97370, Max Test Accuracy:0.97520\n",
      "\n",
      "N2, SGD, No_Batch_Norm    -Epoch: 43, Train Err.:0.12470, Validation Err.:0.12529, Test Accuracy:0.95600, Max Test Accuracy:0.95600\n",
      "N2, SGD, Batch_Norm       -Epoch: 43, Train Err.:0.00226, Validation Err.:0.08232, Test Accuracy:0.97420, Max Test Accuracy:0.97570\n",
      "N2, AdaGrad, No_Batch_Norm-Epoch: 43, Train Err.:0.00578, Validation Err.:0.16789, Test Accuracy:0.96210, Max Test Accuracy:0.96420\n",
      "N2, AdaGrad, Batch_Norm   -Epoch: 43, Train Err.:0.00018, Validation Err.:0.13918, Test Accuracy:0.97720, Max Test Accuracy:0.97780\n",
      "He, AdaGrad, No_Batch_Norm-Epoch: 43, Train Err.:0.00951, Validation Err.:0.13580, Test Accuracy:0.96780, Max Test Accuracy:0.96860\n",
      "He, AdaGrad, Batch_Norm   -Epoch: 43, Train Err.:0.00022, Validation Err.:0.12843, Test Accuracy:0.97380, Max Test Accuracy:0.97520\n",
      "\n",
      "N2, SGD, No_Batch_Norm    -Epoch: 44, Train Err.:0.12109, Validation Err.:0.12324, Test Accuracy:0.95690, Max Test Accuracy:0.95690\n",
      "N2, SGD, Batch_Norm       -Epoch: 44, Train Err.:0.00218, Validation Err.:0.08235, Test Accuracy:0.97380, Max Test Accuracy:0.97570\n",
      "N2, AdaGrad, No_Batch_Norm-Epoch: 44, Train Err.:0.00543, Validation Err.:0.16925, Test Accuracy:0.96200, Max Test Accuracy:0.96420\n",
      "N2, AdaGrad, Batch_Norm   -Epoch: 44, Train Err.:0.00017, Validation Err.:0.13959, Test Accuracy:0.97720, Max Test Accuracy:0.97780\n",
      "He, AdaGrad, No_Batch_Norm-Epoch: 44, Train Err.:0.00915, Validation Err.:0.13653, Test Accuracy:0.96810, Max Test Accuracy:0.96860\n",
      "He, AdaGrad, Batch_Norm   -Epoch: 44, Train Err.:0.00022, Validation Err.:0.12888, Test Accuracy:0.97370, Max Test Accuracy:0.97520\n",
      "\n",
      "N2, SGD, No_Batch_Norm    -Epoch: 45, Train Err.:0.11773, Validation Err.:0.12128, Test Accuracy:0.95760, Max Test Accuracy:0.95760\n",
      "N2, SGD, Batch_Norm       -Epoch: 45, Train Err.:0.00210, Validation Err.:0.08241, Test Accuracy:0.97420, Max Test Accuracy:0.97570\n",
      "N2, AdaGrad, No_Batch_Norm-Epoch: 45, Train Err.:0.00521, Validation Err.:0.17106, Test Accuracy:0.96210, Max Test Accuracy:0.96420\n",
      "N2, AdaGrad, Batch_Norm   -Epoch: 45, Train Err.:0.00017, Validation Err.:0.14005, Test Accuracy:0.97720, Max Test Accuracy:0.97780\n",
      "He, AdaGrad, No_Batch_Norm-Epoch: 45, Train Err.:0.00883, Validation Err.:0.13793, Test Accuracy:0.96800, Max Test Accuracy:0.96860\n",
      "He, AdaGrad, Batch_Norm   -Epoch: 45, Train Err.:0.00021, Validation Err.:0.12942, Test Accuracy:0.97370, Max Test Accuracy:0.97520\n",
      "\n",
      "N2, SGD, No_Batch_Norm    -Epoch: 46, Train Err.:0.11454, Validation Err.:0.11936, Test Accuracy:0.95780, Max Test Accuracy:0.95780\n",
      "N2, SGD, Batch_Norm       -Epoch: 46, Train Err.:0.00203, Validation Err.:0.08213, Test Accuracy:0.97390, Max Test Accuracy:0.97570\n",
      "N2, AdaGrad, No_Batch_Norm-Epoch: 46, Train Err.:0.00501, Validation Err.:0.17291, Test Accuracy:0.96200, Max Test Accuracy:0.96420\n",
      "N2, AdaGrad, Batch_Norm   -Epoch: 46, Train Err.:0.00016, Validation Err.:0.14048, Test Accuracy:0.97720, Max Test Accuracy:0.97780\n",
      "He, AdaGrad, No_Batch_Norm-Epoch: 46, Train Err.:0.00837, Validation Err.:0.13798, Test Accuracy:0.96770, Max Test Accuracy:0.96860\n",
      "He, AdaGrad, Batch_Norm   -Epoch: 46, Train Err.:0.00020, Validation Err.:0.12979, Test Accuracy:0.97390, Max Test Accuracy:0.97520\n",
      "\n",
      "N2, SGD, No_Batch_Norm    -Epoch: 47, Train Err.:0.11148, Validation Err.:0.11759, Test Accuracy:0.95860, Max Test Accuracy:0.95860\n",
      "N2, SGD, Batch_Norm       -Epoch: 47, Train Err.:0.00198, Validation Err.:0.08242, Test Accuracy:0.97420, Max Test Accuracy:0.97570\n",
      "N2, AdaGrad, No_Batch_Norm-Epoch: 47, Train Err.:0.00488, Validation Err.:0.17379, Test Accuracy:0.96250, Max Test Accuracy:0.96420\n",
      "N2, AdaGrad, Batch_Norm   -Epoch: 47, Train Err.:0.00016, Validation Err.:0.14091, Test Accuracy:0.97730, Max Test Accuracy:0.97780\n",
      "He, AdaGrad, No_Batch_Norm-Epoch: 47, Train Err.:0.00815, Validation Err.:0.13917, Test Accuracy:0.96810, Max Test Accuracy:0.96860\n",
      "He, AdaGrad, Batch_Norm   -Epoch: 47, Train Err.:0.00020, Validation Err.:0.13024, Test Accuracy:0.97380, Max Test Accuracy:0.97520\n",
      "\n",
      "N2, SGD, No_Batch_Norm    -Epoch: 48, Train Err.:0.10846, Validation Err.:0.11591, Test Accuracy:0.95970, Max Test Accuracy:0.95970\n",
      "N2, SGD, Batch_Norm       -Epoch: 48, Train Err.:0.00190, Validation Err.:0.08237, Test Accuracy:0.97400, Max Test Accuracy:0.97570\n",
      "N2, AdaGrad, No_Batch_Norm-Epoch: 48, Train Err.:0.00465, Validation Err.:0.17527, Test Accuracy:0.96200, Max Test Accuracy:0.96420\n",
      "N2, AdaGrad, Batch_Norm   -Epoch: 48, Train Err.:0.00015, Validation Err.:0.14129, Test Accuracy:0.97740, Max Test Accuracy:0.97780\n",
      "He, AdaGrad, No_Batch_Norm-Epoch: 48, Train Err.:0.00782, Validation Err.:0.14013, Test Accuracy:0.96790, Max Test Accuracy:0.96860\n",
      "He, AdaGrad, Batch_Norm   -Epoch: 48, Train Err.:0.00019, Validation Err.:0.13071, Test Accuracy:0.97390, Max Test Accuracy:0.97520\n",
      "\n",
      "N2, SGD, No_Batch_Norm    -Epoch: 49, Train Err.:0.10557, Validation Err.:0.11436, Test Accuracy:0.96020, Max Test Accuracy:0.96020\n",
      "N2, SGD, Batch_Norm       -Epoch: 49, Train Err.:0.00185, Validation Err.:0.08243, Test Accuracy:0.97410, Max Test Accuracy:0.97570\n",
      "N2, AdaGrad, No_Batch_Norm-Epoch: 49, Train Err.:0.00454, Validation Err.:0.17855, Test Accuracy:0.96170, Max Test Accuracy:0.96420\n",
      "N2, AdaGrad, Batch_Norm   -Epoch: 49, Train Err.:0.00015, Validation Err.:0.14174, Test Accuracy:0.97740, Max Test Accuracy:0.97780\n",
      "He, AdaGrad, No_Batch_Norm-Epoch: 49, Train Err.:0.00757, Validation Err.:0.14114, Test Accuracy:0.96780, Max Test Accuracy:0.96860\n",
      "He, AdaGrad, Batch_Norm   -Epoch: 49, Train Err.:0.00019, Validation Err.:0.13112, Test Accuracy:0.97380, Max Test Accuracy:0.97520\n",
      "\n"
     ]
    }
   ],
   "source": [
    "epoch_list = []\n",
    "\n",
    "num_batch = math.ceil(train_size / batch_size)\n",
    "\n",
    "for i in range(num_epochs):\n",
    "    epoch_list.append(i)\n",
    "    for key in markers.keys():\n",
    "        for k in range(num_batch):\n",
    "            x_batch = img_train[k * batch_size : k * batch_size + batch_size]\n",
    "            t_batch = label_train[k * batch_size : k * batch_size + batch_size]\n",
    "            networks[key].learning(x_batch, t_batch)\n",
    "\n",
    "        train_loss = networks[key].loss(x_batch, t_batch, is_train=True)\n",
    "        train_errors[key].append(train_loss)\n",
    "\n",
    "        validation_loss = networks[key].loss(img_validation, label_validation, is_train=False)\n",
    "        validation_errors[key].append(validation_loss)    \n",
    "\n",
    "        test_accuracy = networks[key].accuracy(img_test, label_test)\n",
    "        test_accuracy_values[key].append(test_accuracy)\n",
    "        if test_accuracy > max_test_accuracy_value[key]:\n",
    "            max_test_accuracy_epoch[key] = i            \n",
    "            max_test_accuracy_value[key] = test_accuracy\n",
    "        print(\"{0:26s}-Epoch:{1:3d}, Train Err.:{2:7.5f}, Validation Err.:{3:7.5f}, Test Accuracy:{4:7.5f}, Max Test Accuracy:{5:7.5f}\".format(\n",
    "            key,\n",
    "            i,\n",
    "            train_loss,\n",
    "            validation_loss,\n",
    "            test_accuracy,\n",
    "            max_test_accuracy_value[key]\n",
    "        ))\n",
    "    print()    "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAABJ8AAALJCAYAAAAaioKhAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nAAAAKAyDTwAAAAAAACjM/wFxpKXBDtcrmgAAAABJRU5ErkJggg==\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x108b8a470>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "f, axarr = plt.subplots(2, 2, figsize=(20, 12))\n",
    "for key in markers.keys():\n",
    "    axarr[0, 0].plot(epoch_list[1:], train_errors[key][1:], marker=markers[key], markevery=2, label=key)\n",
    "axarr[0, 0].set_ylabel('Train - Total Error')\n",
    "axarr[0, 0].set_xlabel('Epochs')\n",
    "axarr[0, 0].grid(True)\n",
    "axarr[0, 0].set_title('Train Error')\n",
    "axarr[0, 0].legend(loc='upper right')\n",
    "\n",
    "for key in markers.keys():\n",
    "    axarr[0, 1].plot(epoch_list[1:], validation_errors[key][1:], marker=markers[key], markevery=2, label=key)\n",
    "axarr[0, 1].set_ylabel('Validation - Total Error')\n",
    "axarr[0, 1].set_xlabel('Epochs')\n",
    "axarr[0, 1].grid(True)\n",
    "axarr[0, 1].set_title('Validation Error')\n",
    "axarr[0, 1].legend(loc='upper right')\n",
    "\n",
    "for key in markers.keys():\n",
    "    axarr[1, 0].plot(epoch_list[1:], train_errors[key][1:], marker=markers[key], markevery=2, label=key)\n",
    "axarr[1, 0].set_ylabel('Train - Total Error')\n",
    "axarr[1, 0].set_xlabel('Epochs')\n",
    "axarr[1, 0].grid(True)\n",
    "axarr[1, 0].set_ylim(0, 0.2)\n",
    "axarr[1, 0].set_title('Train Error (0.00 ~ 3.00)')\n",
    "axarr[1, 0].legend(loc='upper right')\n",
    "\n",
    "for key in markers.keys():\n",
    "    axarr[1, 1].plot(epoch_list[1:], validation_errors[key][1:], marker=markers[key], markevery=2, label=key)\n",
    "axarr[1, 1].set_ylabel('Validation - Total Error')\n",
    "axarr[1, 1].set_xlabel('Epochs')\n",
    "axarr[1, 1].grid(True)\n",
    "axarr[1, 1].set_ylim(0, 0.2)\n",
    "axarr[1, 1].set_title('Validation Error (0.00 ~ 1.00)')\n",
    "axarr[1, 1].legend(loc='upper right')\n",
    "\n",
    "f.subplots_adjust(hspace=0.3)\n",
    "\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAA4IAAAJdCAYAAABnFskvAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nBZXqaYcAAAAASUVORK5CYII=\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x1078204a8>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "f, axarr = plt.subplots(2, 1, figsize=(15,10))\n",
    "for key in markers.keys():\n",
    "    axarr[0].plot(epoch_list[1:], test_accuracy_values[key][1:], marker=markers[key], markevery=1, label=key)\n",
    "axarr[0].set_ylabel('Test Accuracy')\n",
    "axarr[0].set_xlabel('Epochs')\n",
    "axarr[0].grid(True)\n",
    "axarr[0].set_title('Test Accuracy')\n",
    "axarr[0].legend(loc='lower right')\n",
    "\n",
    "for key in markers.keys():\n",
    "    axarr[1].plot(epoch_list[1:], test_accuracy_values[key][1:], marker=markers[key], markevery=1, label=key)\n",
    "axarr[1].set_ylabel('Test Accuracy')\n",
    "axarr[1].set_xlabel('Epochs')\n",
    "axarr[1].grid(True)\n",
    "axarr[1].set_ylim(0.94, 0.99)\n",
    "axarr[1].set_title('Test Accuracy (0.7 ~ 1.0)')\n",
    "axarr[1].legend(loc='lower right')\n",
    "\n",
    "f.subplots_adjust(hspace=0.3)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "N2, SGD, No_Batch_Norm     - Epoch: 49, Max Test Accuracy: 0.96020\n",
      "N2, SGD, Batch_Norm        - Epoch: 17, Max Test Accuracy: 0.97570\n",
      "N2, AdaGrad, No_Batch_Norm - Epoch: 19, Max Test Accuracy: 0.96420\n",
      "N2, AdaGrad, Batch_Norm    - Epoch: 26, Max Test Accuracy: 0.97780\n",
      "He, AdaGrad, No_Batch_Norm - Epoch: 39, Max Test Accuracy: 0.96860\n",
      "He, AdaGrad, Batch_Norm    - Epoch:  6, Max Test Accuracy: 0.97520\n"
     ]
    }
   ],
   "source": [
    "for key in markers.keys():\n",
    "    print(\"{0:26s} - Epoch:{1:3d}, Max Test Accuracy: {2:7.5f}\".format(key, max_test_accuracy_epoch[key], max_test_accuracy_value[key]))"
   ]
  }
 ],
 "metadata": {
  "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": "3.6.0"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 0
}