{ "nbformat": 4, "nbformat_minor": 0, "metadata": { "colab": { "name": "Real Estate.ipynb", "provenance": [], "collapsed_sections": [] }, "kernelspec": { "name": "python3", "display_name": "Python 3" } }, "cells": [ { "cell_type": "markdown", "metadata": { "id": "c1dETtojSd3y" }, "source": [ "Real Estate market is a type of market wher the sales and purchases between sellsers and buyers refer to the exchange of real estate of anykind, such as housing land, commercial and premises and so on.\r\n", "\r\n", "\r\n", "---\r\n", "Regression analysis is the statistical process of studying the relationship between a set of independent variables (explanatory varaibles and the dependent varaible (response variable) \r\n" ] }, { "cell_type": "markdown", "metadata": { "id": "g5R5aKGAUPs7" }, "source": [ "\r\n", "\r\n", "* Number of instances : 506\r\n", "* Number of attribtes: 14 continuous attributes (including the class attribute medv) and one binary-valued attribute\r\n", "\r\n", "\r\n", "1. crim: per capita crime rate by town\r\n", "\r\n", "1. zn: proportion of residential land zoned for lots over 25000 square feet\r\n", "\r\n", "1. indus: Proportion of nonretail business acres per town\r\n", "2. chas: Charles River dummy variable (= 1 if tract bounds river; 0: otherwise)\r\n", "\r\n", "\r\n", "2. nox: Nitrix oxides concentration (parts per 10 million)\r\n", "\r\n", "\r\n", "2. rm: Average number of rooms per dwelling\r\n", "\r\n", "\r\n", "\r\n", "1. age: Proportion of owner-occupied units built before 1940\r\n", "2. dis: Weighted distances to five Boston employment centers\r\n", "\r\n", "\r\n", "1. Rad: index of accessibility to the radial highways\r\n", "2. ptratio: Pupil teacher ratio by town\r\n", "\r\n", "\r\n", "* black: 1000(BK=0.63)^2 where Bk is the proportion of blacks by town\r\n", "* lstat: Percent of the lower status of the population\r\n", "\r\n", "\r\n", "* medv: Median value of owner-occupied homes in $1000\r\n", "medv is the response variable\r\n", "\r\n", "\r\n", "\r\n", "\r\n", "\r\n", "\r\n", "\r\n" ] }, { "cell_type": "code", "metadata": { "id": "DhHDQ47Oa78K" }, "source": [ "import pandas as pd\r\n" ], "execution_count": 4, "outputs": [] }, { "cell_type": "code", "metadata": { "id": "sCt2TUXMa-bu" }, "source": [ "BHNames = ['crim','zn','indus','chas','nox','rm','age','dis','rad','tax','ptratio','black','lstat','medv']" ], "execution_count": 5, "outputs": [] }, { "cell_type": "code", "metadata": { "id": "07_VuwMUW4i5" }, "source": [ "url='https://archive.ics.uci.edu/ml/machine-learning-databases/housing/housing.data'\r\n", "data = pd.read_csv(url,delim_whitespace=True, names=BHNames)\r\n" ], "execution_count": 6, "outputs": [] }, { "cell_type": "code", "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "lBm8_iSnb1Vp", "outputId": "58145af8-438c-4e89-f82b-519f02929e3c" }, "source": [ "print(data.head(20))" ], "execution_count": 7, "outputs": [ { "output_type": "stream", "text": [ " crim zn indus chas nox ... tax ptratio black lstat medv\n", "0 0.00632 18.0 2.31 0 0.538 ... 296.0 15.3 396.90 4.98 24.0\n", "1 0.02731 0.0 7.07 0 0.469 ... 242.0 17.8 396.90 9.14 21.6\n", "2 0.02729 0.0 7.07 0 0.469 ... 242.0 17.8 392.83 4.03 34.7\n", "3 0.03237 0.0 2.18 0 0.458 ... 222.0 18.7 394.63 2.94 33.4\n", "4 0.06905 0.0 2.18 0 0.458 ... 222.0 18.7 396.90 5.33 36.2\n", "5 0.02985 0.0 2.18 0 0.458 ... 222.0 18.7 394.12 5.21 28.7\n", "6 0.08829 12.5 7.87 0 0.524 ... 311.0 15.2 395.60 12.43 22.9\n", "7 0.14455 12.5 7.87 0 0.524 ... 311.0 15.2 396.90 19.15 27.1\n", "8 0.21124 12.5 7.87 0 0.524 ... 311.0 15.2 386.63 29.93 16.5\n", "9 0.17004 12.5 7.87 0 0.524 ... 311.0 15.2 386.71 17.10 18.9\n", "10 0.22489 12.5 7.87 0 0.524 ... 311.0 15.2 392.52 20.45 15.0\n", "11 0.11747 12.5 7.87 0 0.524 ... 311.0 15.2 396.90 13.27 18.9\n", "12 0.09378 12.5 7.87 0 0.524 ... 311.0 15.2 390.50 15.71 21.7\n", "13 0.62976 0.0 8.14 0 0.538 ... 307.0 21.0 396.90 8.26 20.4\n", "14 0.63796 0.0 8.14 0 0.538 ... 307.0 21.0 380.02 10.26 18.2\n", "15 0.62739 0.0 8.14 0 0.538 ... 307.0 21.0 395.62 8.47 19.9\n", "16 1.05393 0.0 8.14 0 0.538 ... 307.0 21.0 386.85 6.58 23.1\n", "17 0.78420 0.0 8.14 0 0.538 ... 307.0 21.0 386.75 14.67 17.5\n", "18 0.80271 0.0 8.14 0 0.538 ... 307.0 21.0 288.99 11.69 20.2\n", "19 0.72580 0.0 8.14 0 0.538 ... 307.0 21.0 390.95 11.28 18.2\n", "\n", "[20 rows x 14 columns]\n" ], "name": "stdout" } ] }, { "cell_type": "code", "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "BnQBCBu0dV64", "outputId": "25e51b28-bfd1-4094-b371-cc608aad33dc" }, "source": [ "print(data.info())" ], "execution_count": 8, "outputs": [ { "output_type": "stream", "text": [ "\n", "RangeIndex: 506 entries, 0 to 505\n", "Data columns (total 14 columns):\n", " # Column Non-Null Count Dtype \n", "--- ------ -------------- ----- \n", " 0 crim 506 non-null float64\n", " 1 zn 506 non-null float64\n", " 2 indus 506 non-null float64\n", " 3 chas 506 non-null int64 \n", " 4 nox 506 non-null float64\n", " 5 rm 506 non-null float64\n", " 6 age 506 non-null float64\n", " 7 dis 506 non-null float64\n", " 8 rad 506 non-null int64 \n", " 9 tax 506 non-null float64\n", " 10 ptratio 506 non-null float64\n", " 11 black 506 non-null float64\n", " 12 lstat 506 non-null float64\n", " 13 medv 506 non-null float64\n", "dtypes: float64(12), int64(2)\n", "memory usage: 55.5 KB\n", "None\n" ], "name": "stdout" } ] }, { "cell_type": "code", "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "iAdzdtYYdjRn", "outputId": "91a0652d-63c1-4c4b-9ac6-56dfd1152d33" }, "source": [ "summary = data.describe()\r\n", "summary = summary.transpose()\r\n", "print(summary)" ], "execution_count": 9, "outputs": [ { "output_type": "stream", "text": [ " count mean std ... 50% 75% max\n", "crim 506.0 3.613524 8.601545 ... 0.25651 3.677082 88.9762\n", "zn 506.0 11.363636 23.322453 ... 0.00000 12.500000 100.0000\n", "indus 506.0 11.136779 6.860353 ... 9.69000 18.100000 27.7400\n", "chas 506.0 0.069170 0.253994 ... 0.00000 0.000000 1.0000\n", "nox 506.0 0.554695 0.115878 ... 0.53800 0.624000 0.8710\n", "rm 506.0 6.284634 0.702617 ... 6.20850 6.623500 8.7800\n", "age 506.0 68.574901 28.148861 ... 77.50000 94.075000 100.0000\n", "dis 506.0 3.795043 2.105710 ... 3.20745 5.188425 12.1265\n", "rad 506.0 9.549407 8.707259 ... 5.00000 24.000000 24.0000\n", "tax 506.0 408.237154 168.537116 ... 330.00000 666.000000 711.0000\n", "ptratio 506.0 18.455534 2.164946 ... 19.05000 20.200000 22.0000\n", "black 506.0 356.674032 91.294864 ... 391.44000 396.225000 396.9000\n", "lstat 506.0 12.653063 7.141062 ... 11.36000 16.955000 37.9700\n", "medv 506.0 22.532806 9.197104 ... 21.20000 25.000000 50.0000\n", "\n", "[14 rows x 8 columns]\n" ], "name": "stdout" } ] }, { "cell_type": "markdown", "metadata": { "id": "YdzKIDmAfVBW" }, "source": [ "x(scaled) = (x - x(min))/(x(max)-x(min))" ] }, { "cell_type": "code", "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "ip1737Rtfvgo", "outputId": "ecc36e00-d440-4862-fda7-5aa0115dc4cd" }, "source": [ "from sklearn.preprocessing import MinMaxScaler\r\n", "scaler = MinMaxScaler()\r\n", "print(scaler.fit(data)) # it computes the minimum and maximum that is to be used for later scaling" ], "execution_count": 10, "outputs": [ { "output_type": "stream", "text": [ "MinMaxScaler(copy=True, feature_range=(0, 1))\n" ], "name": "stdout" } ] }, { "cell_type": "code", "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "bKuJf9jfgN1D", "outputId": "b092391b-ac03-4c0f-9dff-ad55d4241bfe" }, "source": [ "DataScaled = scaler.fit_transform(data)\r\n", "DataScaled = pd.DataFrame(DataScaled,columns=BHNames)\r\n", "summary = DataScaled.describe()\r\n", "summary=summary.transpose()\r\n", "print(summary)" ], "execution_count": 12, "outputs": [ { "output_type": "stream", "text": [ " count mean std min 25% 50% 75% max\n", "crim 506.0 0.040544 0.096679 0.0 0.000851 0.002812 0.041258 1.0\n", "zn 506.0 0.113636 0.233225 0.0 0.000000 0.000000 0.125000 1.0\n", "indus 506.0 0.391378 0.251479 0.0 0.173387 0.338343 0.646628 1.0\n", "chas 506.0 0.069170 0.253994 0.0 0.000000 0.000000 0.000000 1.0\n", "nox 506.0 0.349167 0.238431 0.0 0.131687 0.314815 0.491770 1.0\n", "rm 506.0 0.521869 0.134627 0.0 0.445392 0.507281 0.586798 1.0\n", "age 506.0 0.676364 0.289896 0.0 0.433831 0.768280 0.938980 1.0\n", "dis 506.0 0.242381 0.191482 0.0 0.088259 0.188949 0.369088 1.0\n", "rad 506.0 0.371713 0.378576 0.0 0.130435 0.173913 1.000000 1.0\n", "tax 506.0 0.422208 0.321636 0.0 0.175573 0.272901 0.914122 1.0\n", "ptratio 506.0 0.622929 0.230313 0.0 0.510638 0.686170 0.808511 1.0\n", "black 506.0 0.898568 0.230205 0.0 0.945730 0.986232 0.998298 1.0\n", "lstat 506.0 0.301409 0.197049 0.0 0.144040 0.265728 0.420116 1.0\n", "medv 506.0 0.389618 0.204380 0.0 0.267222 0.360000 0.444444 1.0\n" ], "name": "stdout" } ] }, { "cell_type": "markdown", "metadata": { "id": "_zRiJcE1g8j1" }, "source": [ "Lower Whisker -> 25 percentile -> median (50 percentile) -> 75 percentile -> upper Whisker" ] }, { "cell_type": "code", "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 265 }, "id": "QearNcCzhv0U", "outputId": "3769830c-f7f5-42fc-82d3-6d0905c4f05f" }, "source": [ "import matplotlib.pyplot as plt\r\n", "boxplot = data.boxplot(column=BHNames)\r\n", "plt.show()" ], "execution_count": 13, "outputs": [ { "output_type": "display_data", "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "tags": [], "needs_background": "light" } } ] }, { "cell_type": "markdown", "metadata": { "id": "g0CGXCUmjBr9" }, "source": [ "There are 3 methods of correlation coefficient:\r\n", "\r\n", "\r\n", "1. Pearson (standard correlation coefficient)\r\n", "\r\n", "1. Kendall (Kendall Tau correlation coefficient)\r\n", "2. spearman (Spearman rank correlation)\r\n", "\r\n", "\r\n", "\r\n", "\r\n" ] }, { "cell_type": "code", "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "m1PsOJpBjaEH", "outputId": "c4efacfe-a24f-423f-e14a-4b772bbffb81" }, "source": [ "CorData = DataScaled.corr(method='pearson')\r\n", "with pd.option_context('display.max_rows',None,'display.max_columns', CorData.shape[1]):\r\n", " print(CorData)" ], "execution_count": 14, "outputs": [ { "output_type": "stream", "text": [ " crim zn indus chas nox rm age \\\n", "crim 1.000000 -0.200469 0.406583 -0.055892 0.420972 -0.219247 0.352734 \n", "zn -0.200469 1.000000 -0.533828 -0.042697 -0.516604 0.311991 -0.569537 \n", "indus 0.406583 -0.533828 1.000000 0.062938 0.763651 -0.391676 0.644779 \n", "chas -0.055892 -0.042697 0.062938 1.000000 0.091203 0.091251 0.086518 \n", "nox 0.420972 -0.516604 0.763651 0.091203 1.000000 -0.302188 0.731470 \n", "rm -0.219247 0.311991 -0.391676 0.091251 -0.302188 1.000000 -0.240265 \n", "age 0.352734 -0.569537 0.644779 0.086518 0.731470 -0.240265 1.000000 \n", "dis -0.379670 0.664408 -0.708027 -0.099176 -0.769230 0.205246 -0.747881 \n", "rad 0.625505 -0.311948 0.595129 -0.007368 0.611441 -0.209847 0.456022 \n", "tax 0.582764 -0.314563 0.720760 -0.035587 0.668023 -0.292048 0.506456 \n", "ptratio 0.289946 -0.391679 0.383248 -0.121515 0.188933 -0.355501 0.261515 \n", "black -0.385064 0.175520 -0.356977 0.048788 -0.380051 0.128069 -0.273534 \n", "lstat 0.455621 -0.412995 0.603800 -0.053929 0.590879 -0.613808 0.602339 \n", "medv -0.388305 0.360445 -0.483725 0.175260 -0.427321 0.695360 -0.376955 \n", "\n", " dis rad tax ptratio black lstat medv \n", "crim -0.379670 0.625505 0.582764 0.289946 -0.385064 0.455621 -0.388305 \n", "zn 0.664408 -0.311948 -0.314563 -0.391679 0.175520 -0.412995 0.360445 \n", "indus -0.708027 0.595129 0.720760 0.383248 -0.356977 0.603800 -0.483725 \n", "chas -0.099176 -0.007368 -0.035587 -0.121515 0.048788 -0.053929 0.175260 \n", "nox -0.769230 0.611441 0.668023 0.188933 -0.380051 0.590879 -0.427321 \n", "rm 0.205246 -0.209847 -0.292048 -0.355501 0.128069 -0.613808 0.695360 \n", "age -0.747881 0.456022 0.506456 0.261515 -0.273534 0.602339 -0.376955 \n", "dis 1.000000 -0.494588 -0.534432 -0.232471 0.291512 -0.496996 0.249929 \n", "rad -0.494588 1.000000 0.910228 0.464741 -0.444413 0.488676 -0.381626 \n", "tax -0.534432 0.910228 1.000000 0.460853 -0.441808 0.543993 -0.468536 \n", "ptratio -0.232471 0.464741 0.460853 1.000000 -0.177383 0.374044 -0.507787 \n", "black 0.291512 -0.444413 -0.441808 -0.177383 1.000000 -0.366087 0.333461 \n", "lstat -0.496996 0.488676 0.543993 0.374044 -0.366087 1.000000 -0.737663 \n", "medv 0.249929 -0.381626 -0.468536 -0.507787 0.333461 -0.737663 1.000000 \n" ], "name": "stdout" } ] }, { "cell_type": "code", "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 258 }, "id": "ngOBtH11j8ty", "outputId": "f306545b-e631-4b11-8127-d4bdcf1895f0" }, "source": [ "# plot correlogram is a graph of correlation matrix\r\n", "plt.matshow(CorData)\r\n", "# set the current tick locations and labels of the x-axis and y-axis\r\n", "plt.xticks(range(len(CorData.columns)), CorData.columns)\r\n", "plt.yticks(range(len(CorData.columns)), CorData.columns)\r\n", "plt.colorbar()\r\n", "plt.show()\r\n" ], "execution_count": 17, "outputs": [ { "output_type": "display_data", "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "tags": [], "needs_background": "light" } } ] }, { "cell_type": "code", "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "TybfOdJiqiMs", "outputId": "d1071afd-7946-4c2d-f8c8-8da49271316d" }, "source": [ "from sklearn.model_selection import train_test_split\r\n", "#divide the predictor(X) and target(Y)\r\n", "X = DataScaled.drop('medv',axis = 1)\r\n", "print(X.describe())\r\n", "Y = DataScaled['medv']\r\n", "print(Y.describe())" ], "execution_count": 19, "outputs": [ { "output_type": "stream", "text": [ " crim zn indus ... ptratio black lstat\n", "count 506.000000 506.000000 506.000000 ... 506.000000 506.000000 506.000000\n", "mean 0.040544 0.113636 0.391378 ... 0.622929 0.898568 0.301409\n", "std 0.096679 0.233225 0.251479 ... 0.230313 0.230205 0.197049\n", "min 0.000000 0.000000 0.000000 ... 0.000000 0.000000 0.000000\n", "25% 0.000851 0.000000 0.173387 ... 0.510638 0.945730 0.144040\n", "50% 0.002812 0.000000 0.338343 ... 0.686170 0.986232 0.265728\n", "75% 0.041258 0.125000 0.646628 ... 0.808511 0.998298 0.420116\n", "max 1.000000 1.000000 1.000000 ... 1.000000 1.000000 1.000000\n", "\n", "[8 rows x 13 columns]\n", "count 506.000000\n", "mean 0.389618\n", "std 0.204380\n", "min 0.000000\n", "25% 0.267222\n", "50% 0.360000\n", "75% 0.444444\n", "max 1.000000\n", "Name: medv, dtype: float64\n" ], "name": "stdout" } ] }, { "cell_type": "code", "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "kOc104gErRev", "outputId": "cfc1e8a6-7d09-49fa-a6c0-d815616ef780" }, "source": [ "X_train, X_test, Y_train,Y_test = train_test_split(X,Y,test_size=0.30, random_state = 5)\r\n", "print('X train shape = ',X_train.shape)\r\n", "print('X test shape = ',X_test.shape)\r\n", "print('Y train shape = ',Y_train.shape)\r\n", "\r\n", "print('Y test shape = ',Y_test.shape)" ], "execution_count": 21, "outputs": [ { "output_type": "stream", "text": [ "X train shape = (354, 13)\n", "X test shape = (152, 13)\n", "Y train shape = (354,)\n", "Y test shape = (152,)\n" ], "name": "stdout" } ] }, { "cell_type": "markdown", "metadata": { "id": "tJNkfKR9tYH0" }, "source": [ "\r\n", "\r\n", "* Import Sequential classs from keras.models\r\n", "\r\n", "* stack the layers using .add() method\r\n", "* Configure the learning process using .compile() method\r\n", "\r\n", "\r\n", "* Train the model on the train dataset using .fit() method\r\n", "\r\n" ] }, { "cell_type": "code", "metadata": { "id": "WXb8-B6mtsSg" }, "source": [ "from keras.models import Sequential\r\n", "from keras.layers import Dense\r\n", "from keras import metrics" ], "execution_count": 23, "outputs": [] }, { "cell_type": "markdown", "metadata": { "id": "oV_A0R5-t5zm" }, "source": [ "\r\n", "\r\n", "1. Sequential class: This is used to define a linear stack of network layers that make up a model. We will use the Sequential constructor to create the mode, which will be enriched with layers using the add() method\r\n", "\r\n", "1. Dense class: this is used to instantiate a Dense layer, which is the basic feedforward fully connected layer.\r\n", "2. Metric class: This is a function that is used to evaluate the performnace of the model.\r\n", "\r\n" ] }, { "cell_type": "code", "metadata": { "id": "Z95ASeTIuY8X" }, "source": [ "model = Sequential()\r\n", "model.add(Dense(20,input_dim=13,activation = 'relu'))\r\n", "model.add(Dense(10, activation = 'relu'))\r\n", "\r\n", "model.add(Dense(1, activation = 'linear'))" ], "execution_count": 24, "outputs": [] }, { "cell_type": "code", "metadata": { "id": "kDCHvMGlvMkM" }, "source": [ "model.compile(optimizer='adam',loss='mean_squared_error',metrics=['accuracy'])\r\n" ], "execution_count": 25, "outputs": [] }, { "cell_type": "markdown", "metadata": { "id": "Ub3BAoZ_vXlK" }, "source": [ "\r\n", "\r\n", "1. adam optimizer: This is an alogorithm for the first-order, gradient-based optimization of stochastic objective functions based on adaptive estimates of lower order moments\r\n", "\r\n", "1. The mean_squared_error: loss function. it measures the varege of the squares of the errors\r\n", "2. Accuracy metric: function that is used to evaluate the performance of the model durnoiing the training and testing\r\n", "\r\n", "\r\n", "\r\n", "\r\n" ] }, { "cell_type": "code", "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "WSQMr8vIv2km", "outputId": "bf77a020-5373-459e-d861-4a2fedf38d23" }, "source": [ "model.fit(X_train,Y_train, epochs=1000, verbose = 1)" ], "execution_count": 26, "outputs": [ { "output_type": "stream", "text": [ "Epoch 1/1000\n", "12/12 [==============================] - 1s 2ms/step - loss: 0.1160 - accuracy: 0.0015\n", "Epoch 2/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0615 - accuracy: 0.0121\n", "Epoch 3/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0422 - accuracy: 0.0117\n", "Epoch 4/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0272 - accuracy: 0.0074\n", "Epoch 5/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0270 - accuracy: 0.0064\n", "Epoch 6/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0221 - accuracy: 0.0083\n", "Epoch 7/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0173 - accuracy: 0.0106\n", "Epoch 8/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0217 - accuracy: 0.0153\n", "Epoch 9/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0162 - accuracy: 0.0071\n", "Epoch 10/1000\n", "12/12 [==============================] - 0s 1ms/step - loss: 0.0160 - accuracy: 0.0239\n", "Epoch 11/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0149 - accuracy: 0.0158\n", "Epoch 12/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0143 - accuracy: 0.0150\n", "Epoch 13/1000\n", "12/12 [==============================] - 0s 1ms/step - loss: 0.0136 - accuracy: 0.0128\n", "Epoch 14/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0153 - accuracy: 0.0179\n", "Epoch 15/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0145 - accuracy: 0.0274\n", "Epoch 16/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0133 - accuracy: 0.0175\n", "Epoch 17/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0138 - accuracy: 0.0231\n", "Epoch 18/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0122 - accuracy: 0.0180\n", "Epoch 19/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0114 - accuracy: 0.0189\n", "Epoch 20/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0121 - accuracy: 0.0189\n", "Epoch 21/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0103 - accuracy: 0.0176\n", "Epoch 22/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0093 - accuracy: 0.0178\n", "Epoch 23/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0099 - accuracy: 0.0384\n", "Epoch 24/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0095 - accuracy: 0.0318\n", "Epoch 25/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0098 - accuracy: 0.0147\n", "Epoch 26/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0121 - accuracy: 0.0256\n", "Epoch 27/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0092 - accuracy: 0.0213\n", "Epoch 28/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0095 - accuracy: 0.0200\n", "Epoch 29/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0092 - accuracy: 0.0249\n", "Epoch 30/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0101 - accuracy: 0.0275\n", "Epoch 31/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0092 - accuracy: 0.0243\n", "Epoch 32/1000\n", "12/12 [==============================] - 0s 1ms/step - loss: 0.0079 - accuracy: 0.0289\n", "Epoch 33/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0104 - accuracy: 0.0311\n", "Epoch 34/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0095 - accuracy: 0.0359\n", "Epoch 35/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0101 - accuracy: 0.0246\n", "Epoch 36/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0074 - accuracy: 0.0158\n", "Epoch 37/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0101 - accuracy: 0.0206\n", "Epoch 38/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0097 - accuracy: 0.0214\n", "Epoch 39/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0072 - accuracy: 0.0183\n", "Epoch 40/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0091 - accuracy: 0.0211\n", "Epoch 41/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0089 - accuracy: 0.0240\n", "Epoch 42/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0083 - accuracy: 0.0181\n", "Epoch 43/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0075 - accuracy: 0.0191\n", "Epoch 44/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0077 - accuracy: 0.0304\n", "Epoch 45/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0078 - accuracy: 0.0186\n", "Epoch 46/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0080 - accuracy: 0.0220\n", "Epoch 47/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0094 - accuracy: 0.0336\n", "Epoch 48/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0085 - accuracy: 0.0182\n", "Epoch 49/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0061 - accuracy: 0.0113\n", "Epoch 50/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0065 - accuracy: 0.0277\n", "Epoch 51/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0080 - accuracy: 0.0215\n", "Epoch 52/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0083 - accuracy: 0.0226\n", "Epoch 53/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0063 - accuracy: 0.0209\n", "Epoch 54/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0085 - accuracy: 0.0153\n", "Epoch 55/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0092 - accuracy: 0.0201\n", "Epoch 56/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0071 - accuracy: 0.0228\n", "Epoch 57/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0089 - accuracy: 0.0185\n", "Epoch 58/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0079 - accuracy: 0.0349\n", "Epoch 59/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0065 - accuracy: 0.0131\n", "Epoch 60/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0066 - accuracy: 0.0168\n", "Epoch 61/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0061 - accuracy: 0.0284\n", "Epoch 62/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0083 - accuracy: 0.0311\n", "Epoch 63/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0071 - accuracy: 0.0207\n", "Epoch 64/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0091 - accuracy: 0.0270\n", "Epoch 65/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0077 - accuracy: 0.0299\n", "Epoch 66/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0074 - accuracy: 0.0175\n", "Epoch 67/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0072 - accuracy: 0.0295\n", "Epoch 68/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0073 - accuracy: 0.0310\n", "Epoch 69/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0083 - accuracy: 0.0200\n", "Epoch 70/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0078 - accuracy: 0.0146\n", "Epoch 71/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0070 - accuracy: 0.0198\n", "Epoch 72/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0084 - accuracy: 0.0245\n", "Epoch 73/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0057 - accuracy: 0.0172\n", "Epoch 74/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0063 - accuracy: 0.0325\n", "Epoch 75/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0063 - accuracy: 0.0212\n", "Epoch 76/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0070 - accuracy: 0.0286\n", "Epoch 77/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0059 - accuracy: 0.0177\n", "Epoch 78/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0059 - accuracy: 0.0257\n", "Epoch 79/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0063 - accuracy: 0.0362\n", "Epoch 80/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0050 - accuracy: 0.0244\n", "Epoch 81/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0081 - accuracy: 0.0315\n", "Epoch 82/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0086 - accuracy: 0.0233\n", "Epoch 83/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0073 - accuracy: 0.0162\n", "Epoch 84/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0076 - accuracy: 0.0264\n", "Epoch 85/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0080 - accuracy: 0.0185\n", "Epoch 86/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0067 - accuracy: 0.0291\n", "Epoch 87/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0058 - accuracy: 0.0270\n", "Epoch 88/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0059 - accuracy: 0.0242\n", "Epoch 89/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0064 - accuracy: 0.0324\n", "Epoch 90/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0055 - accuracy: 0.0320\n", "Epoch 91/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0059 - accuracy: 0.0277\n", "Epoch 92/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0060 - accuracy: 0.0288\n", "Epoch 93/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0054 - accuracy: 0.0280\n", "Epoch 94/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0054 - accuracy: 0.0293\n", "Epoch 95/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0080 - accuracy: 0.0282\n", "Epoch 96/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0075 - accuracy: 0.0201\n", "Epoch 97/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0063 - accuracy: 0.0220\n", "Epoch 98/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0052 - accuracy: 0.0267\n", "Epoch 99/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0055 - accuracy: 0.0219\n", "Epoch 100/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0059 - accuracy: 0.0359\n", "Epoch 101/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0050 - accuracy: 0.0175\n", "Epoch 102/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0064 - accuracy: 0.0204\n", "Epoch 103/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0045 - accuracy: 0.0190\n", "Epoch 104/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0080 - accuracy: 0.0301\n", "Epoch 105/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0076 - accuracy: 0.0192\n", "Epoch 106/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0048 - accuracy: 0.0276\n", "Epoch 107/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0051 - accuracy: 0.0219\n", "Epoch 108/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0061 - accuracy: 0.0308\n", "Epoch 109/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0055 - accuracy: 0.0302\n", "Epoch 110/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0064 - accuracy: 0.0254\n", "Epoch 111/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0053 - accuracy: 0.0237\n", "Epoch 112/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0058 - accuracy: 0.0253\n", "Epoch 113/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0053 - accuracy: 0.0263\n", "Epoch 114/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0047 - accuracy: 0.0291\n", "Epoch 115/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0061 - accuracy: 0.0248\n", "Epoch 116/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0066 - accuracy: 0.0266\n", "Epoch 117/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0051 - accuracy: 0.0228\n", "Epoch 118/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0070 - accuracy: 0.0267\n", "Epoch 119/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0051 - accuracy: 0.0291\n", "Epoch 120/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0063 - accuracy: 0.0281\n", "Epoch 121/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0053 - accuracy: 0.0254\n", "Epoch 122/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0061 - accuracy: 0.0263\n", "Epoch 123/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0054 - accuracy: 0.0153\n", "Epoch 124/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0068 - accuracy: 0.0210\n", "Epoch 125/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0053 - accuracy: 0.0247\n", "Epoch 126/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0061 - accuracy: 0.0289\n", "Epoch 127/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0056 - accuracy: 0.0187\n", "Epoch 128/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0062 - accuracy: 0.0364\n", "Epoch 129/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0043 - accuracy: 0.0129\n", "Epoch 130/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0055 - accuracy: 0.0164\n", "Epoch 131/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0044 - accuracy: 0.0307\n", "Epoch 132/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0056 - accuracy: 0.0239\n", "Epoch 133/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0057 - accuracy: 0.0309\n", "Epoch 134/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0043 - accuracy: 0.0154\n", "Epoch 135/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0082 - accuracy: 0.0291\n", "Epoch 136/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0056 - accuracy: 0.0285\n", "Epoch 137/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0062 - accuracy: 0.0296\n", "Epoch 138/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0065 - accuracy: 0.0277\n", "Epoch 139/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0051 - accuracy: 0.0186\n", "Epoch 140/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0058 - accuracy: 0.0316\n", "Epoch 141/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0066 - accuracy: 0.0360\n", "Epoch 142/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0063 - accuracy: 0.0245\n", "Epoch 143/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0054 - accuracy: 0.0295\n", "Epoch 144/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0059 - accuracy: 0.0227\n", "Epoch 145/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0050 - accuracy: 0.0226\n", "Epoch 146/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0050 - accuracy: 0.0296\n", "Epoch 147/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0053 - accuracy: 0.0221\n", "Epoch 148/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0040 - accuracy: 0.0240\n", "Epoch 149/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0045 - accuracy: 0.0187\n", "Epoch 150/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0038 - accuracy: 0.0258\n", "Epoch 151/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0046 - accuracy: 0.0217\n", "Epoch 152/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0062 - accuracy: 0.0197\n", "Epoch 153/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0072 - accuracy: 0.0199\n", "Epoch 154/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0065 - accuracy: 0.0269\n", "Epoch 155/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0059 - accuracy: 0.0248\n", "Epoch 156/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0058 - accuracy: 0.0235\n", "Epoch 157/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0043 - accuracy: 0.0265\n", "Epoch 158/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0048 - accuracy: 0.0267\n", "Epoch 159/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0051 - accuracy: 0.0299\n", "Epoch 160/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0054 - accuracy: 0.0162\n", "Epoch 161/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0050 - accuracy: 0.0396\n", "Epoch 162/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0045 - accuracy: 0.0313\n", "Epoch 163/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0051 - accuracy: 0.0281\n", "Epoch 164/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0054 - accuracy: 0.0320\n", "Epoch 165/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0045 - accuracy: 0.0275\n", "Epoch 166/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0046 - accuracy: 0.0262\n", "Epoch 167/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0057 - accuracy: 0.0290\n", "Epoch 168/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0050 - accuracy: 0.0192\n", "Epoch 169/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0047 - accuracy: 0.0257\n", "Epoch 170/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0049 - accuracy: 0.0342\n", "Epoch 171/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0049 - accuracy: 0.0211\n", "Epoch 172/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0057 - accuracy: 0.0201\n", "Epoch 173/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0036 - accuracy: 0.0159\n", "Epoch 174/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0039 - accuracy: 0.0250\n", "Epoch 175/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0040 - accuracy: 0.0309\n", "Epoch 176/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0040 - accuracy: 0.0250\n", "Epoch 177/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0042 - accuracy: 0.0355\n", "Epoch 178/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0040 - accuracy: 0.0214\n", "Epoch 179/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0048 - accuracy: 0.0328\n", "Epoch 180/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0045 - accuracy: 0.0170\n", "Epoch 181/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0045 - accuracy: 0.0192\n", "Epoch 182/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0046 - accuracy: 0.0227\n", "Epoch 183/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0045 - accuracy: 0.0180\n", "Epoch 184/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0043 - accuracy: 0.0366\n", "Epoch 185/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0044 - accuracy: 0.0158\n", "Epoch 186/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0048 - accuracy: 0.0304\n", "Epoch 187/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0036 - accuracy: 0.0247\n", "Epoch 188/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0060 - accuracy: 0.0314\n", "Epoch 189/1000\n", "12/12 [==============================] - 0s 4ms/step - loss: 0.0041 - accuracy: 0.0255\n", "Epoch 190/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0043 - accuracy: 0.0203\n", "Epoch 191/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0045 - accuracy: 0.0424\n", "Epoch 192/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0044 - accuracy: 0.0344\n", "Epoch 193/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0040 - accuracy: 0.0214\n", "Epoch 194/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0048 - accuracy: 0.0362\n", "Epoch 195/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0043 - accuracy: 0.0260\n", "Epoch 196/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0036 - accuracy: 0.0236\n", "Epoch 197/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0042 - accuracy: 0.0255\n", "Epoch 198/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0048 - accuracy: 0.0425\n", "Epoch 199/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0037 - accuracy: 0.0314\n", "Epoch 200/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0035 - accuracy: 0.0311\n", "Epoch 201/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0041 - accuracy: 0.0309\n", "Epoch 202/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0031 - accuracy: 0.0213\n", "Epoch 203/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0043 - accuracy: 0.0210\n", "Epoch 204/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0034 - accuracy: 0.0174\n", "Epoch 205/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0032 - accuracy: 0.0278\n", "Epoch 206/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0037 - accuracy: 0.0253\n", "Epoch 207/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0036 - accuracy: 0.0292\n", "Epoch 208/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0032 - accuracy: 0.0303\n", "Epoch 209/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0032 - accuracy: 0.0233\n", "Epoch 210/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0037 - accuracy: 0.0316\n", "Epoch 211/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0039 - accuracy: 0.0388\n", "Epoch 212/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0034 - accuracy: 0.0290\n", "Epoch 213/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0031 - accuracy: 0.0221\n", "Epoch 214/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0046 - accuracy: 0.0303\n", "Epoch 215/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0039 - accuracy: 0.0281\n", "Epoch 216/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0038 - accuracy: 0.0324\n", "Epoch 217/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0036 - accuracy: 0.0305\n", "Epoch 218/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0035 - accuracy: 0.0209\n", "Epoch 219/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0031 - accuracy: 0.0165\n", "Epoch 220/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0042 - accuracy: 0.0265\n", "Epoch 221/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0033 - accuracy: 0.0301\n", "Epoch 222/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0033 - accuracy: 0.0180\n", "Epoch 223/1000\n", "12/12 [==============================] - 0s 4ms/step - loss: 0.0032 - accuracy: 0.0301\n", "Epoch 224/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0031 - accuracy: 0.0192\n", "Epoch 225/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0032 - accuracy: 0.0274\n", "Epoch 226/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0031 - accuracy: 0.0253\n", "Epoch 227/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0034 - accuracy: 0.0291\n", "Epoch 228/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0038 - accuracy: 0.0212\n", "Epoch 229/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0028 - accuracy: 0.0229\n", "Epoch 230/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0033 - accuracy: 0.0329\n", "Epoch 231/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0040 - accuracy: 0.0248\n", "Epoch 232/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0032 - accuracy: 0.0320\n", "Epoch 233/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0033 - accuracy: 0.0256\n", "Epoch 234/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0034 - accuracy: 0.0226\n", "Epoch 235/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0028 - accuracy: 0.0248\n", "Epoch 236/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0033 - accuracy: 0.0337\n", "Epoch 237/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0034 - accuracy: 0.0317\n", "Epoch 238/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0032 - accuracy: 0.0200\n", "Epoch 239/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0034 - accuracy: 0.0244\n", "Epoch 240/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0029 - accuracy: 0.0245\n", "Epoch 241/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0031 - accuracy: 0.0338\n", "Epoch 242/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0035 - accuracy: 0.0270\n", "Epoch 243/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0031 - accuracy: 0.0367\n", "Epoch 244/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0031 - accuracy: 0.0290\n", "Epoch 245/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0035 - accuracy: 0.0296\n", "Epoch 246/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0034 - accuracy: 0.0272\n", "Epoch 247/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0029 - accuracy: 0.0276\n", "Epoch 248/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0031 - accuracy: 0.0369\n", "Epoch 249/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0035 - accuracy: 0.0336\n", "Epoch 250/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0032 - accuracy: 0.0310\n", "Epoch 251/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0030 - accuracy: 0.0283\n", "Epoch 252/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0038 - accuracy: 0.0345\n", "Epoch 253/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0036 - accuracy: 0.0269\n", "Epoch 254/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0030 - accuracy: 0.0287\n", "Epoch 255/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0033 - accuracy: 0.0346\n", "Epoch 256/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0027 - accuracy: 0.0311\n", "Epoch 257/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0030 - accuracy: 0.0328\n", "Epoch 258/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0026 - accuracy: 0.0232\n", "Epoch 259/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0035 - accuracy: 0.0211\n", "Epoch 260/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0027 - accuracy: 0.0283\n", "Epoch 261/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0032 - accuracy: 0.0313\n", "Epoch 262/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0033 - accuracy: 0.0328\n", "Epoch 263/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0055 - accuracy: 0.0294\n", "Epoch 264/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0041 - accuracy: 0.0382\n", "Epoch 265/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0036 - accuracy: 0.0261\n", "Epoch 266/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0028 - accuracy: 0.0462\n", "Epoch 267/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0031 - accuracy: 0.0391\n", "Epoch 268/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0029 - accuracy: 0.0173\n", "Epoch 269/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0036 - accuracy: 0.0357\n", "Epoch 270/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0030 - accuracy: 0.0294\n", "Epoch 271/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0031 - accuracy: 0.0337\n", "Epoch 272/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0035 - accuracy: 0.0298\n", "Epoch 273/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0029 - accuracy: 0.0223\n", "Epoch 274/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0029 - accuracy: 0.0197\n", "Epoch 275/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0029 - accuracy: 0.0306\n", "Epoch 276/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0028 - accuracy: 0.0257\n", "Epoch 277/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0029 - accuracy: 0.0227\n", "Epoch 278/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0027 - accuracy: 0.0342\n", "Epoch 279/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0040 - accuracy: 0.0384\n", "Epoch 280/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0033 - accuracy: 0.0315\n", "Epoch 281/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0023 - accuracy: 0.0250\n", "Epoch 282/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0028 - accuracy: 0.0243\n", "Epoch 283/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0027 - accuracy: 0.0221\n", "Epoch 284/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0027 - accuracy: 0.0324\n", "Epoch 285/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0035 - accuracy: 0.0270\n", "Epoch 286/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0030 - accuracy: 0.0228\n", "Epoch 287/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0028 - accuracy: 0.0249\n", "Epoch 288/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0026 - accuracy: 0.0305\n", "Epoch 289/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0028 - accuracy: 0.0295\n", "Epoch 290/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0029 - accuracy: 0.0305\n", "Epoch 291/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0027 - accuracy: 0.0278\n", "Epoch 292/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0032 - accuracy: 0.0193\n", "Epoch 293/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0045 - accuracy: 0.0277\n", "Epoch 294/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0028 - accuracy: 0.0171\n", "Epoch 295/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0025 - accuracy: 0.0276\n", "Epoch 296/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0029 - accuracy: 0.0251\n", "Epoch 297/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0027 - accuracy: 0.0321\n", "Epoch 298/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0026 - accuracy: 0.0161\n", "Epoch 299/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0028 - accuracy: 0.0356\n", "Epoch 300/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0025 - accuracy: 0.0342\n", "Epoch 301/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0027 - accuracy: 0.0307\n", "Epoch 302/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0029 - accuracy: 0.0225\n", "Epoch 303/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0028 - accuracy: 0.0291\n", "Epoch 304/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0027 - accuracy: 0.0181\n", "Epoch 305/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0027 - accuracy: 0.0258\n", "Epoch 306/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0024 - accuracy: 0.0270\n", "Epoch 307/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0031 - accuracy: 0.0252\n", "Epoch 308/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0026 - accuracy: 0.0168\n", "Epoch 309/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0026 - accuracy: 0.0239\n", "Epoch 310/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0028 - accuracy: 0.0252\n", "Epoch 311/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0028 - accuracy: 0.0334\n", "Epoch 312/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0031 - accuracy: 0.0257\n", "Epoch 313/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0026 - accuracy: 0.0229\n", "Epoch 314/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0026 - accuracy: 0.0206\n", "Epoch 315/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0035 - accuracy: 0.0225\n", "Epoch 316/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0031 - accuracy: 0.0179\n", "Epoch 317/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0026 - accuracy: 0.0250\n", "Epoch 318/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0031 - accuracy: 0.0341\n", "Epoch 319/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0023 - accuracy: 0.0274\n", "Epoch 320/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0029 - accuracy: 0.0250\n", "Epoch 321/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0026 - accuracy: 0.0278\n", "Epoch 322/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0029 - accuracy: 0.0238\n", "Epoch 323/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0035 - accuracy: 0.0348\n", "Epoch 324/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0027 - accuracy: 0.0247\n", "Epoch 325/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0027 - accuracy: 0.0173\n", "Epoch 326/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0024 - accuracy: 0.0166\n", "Epoch 327/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0027 - accuracy: 0.0218\n", "Epoch 328/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0025 - accuracy: 0.0285\n", "Epoch 329/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0033 - accuracy: 0.0337\n", "Epoch 330/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0027 - accuracy: 0.0318\n", "Epoch 331/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0025 - accuracy: 0.0228\n", "Epoch 332/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0024 - accuracy: 0.0248\n", "Epoch 333/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0025 - accuracy: 0.0437\n", "Epoch 334/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0026 - accuracy: 0.0168\n", "Epoch 335/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0030 - accuracy: 0.0301\n", "Epoch 336/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0027 - accuracy: 0.0226\n", "Epoch 337/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0023 - accuracy: 0.0236\n", "Epoch 338/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0024 - accuracy: 0.0300\n", "Epoch 339/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0022 - accuracy: 0.0399\n", "Epoch 340/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0028 - accuracy: 0.0334\n", "Epoch 341/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0023 - accuracy: 0.0285\n", "Epoch 342/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0025 - accuracy: 0.0198 \n", "Epoch 343/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0027 - accuracy: 0.0165\n", "Epoch 344/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0028 - accuracy: 0.0262\n", "Epoch 345/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0028 - accuracy: 0.0285\n", "Epoch 346/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0027 - accuracy: 0.0243\n", "Epoch 347/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0028 - accuracy: 0.0267\n", "Epoch 348/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0027 - accuracy: 0.0260\n", "Epoch 349/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0028 - accuracy: 0.0227\n", "Epoch 350/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0023 - accuracy: 0.0235\n", "Epoch 351/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0024 - accuracy: 0.0265\n", "Epoch 352/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0024 - accuracy: 0.0213\n", "Epoch 353/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0026 - accuracy: 0.0278\n", "Epoch 354/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0026 - accuracy: 0.0416\n", "Epoch 355/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0025 - accuracy: 0.0276\n", "Epoch 356/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0024 - accuracy: 0.0276\n", "Epoch 357/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0023 - accuracy: 0.0428\n", "Epoch 358/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0022 - accuracy: 0.0254\n", "Epoch 359/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0022 - accuracy: 0.0256\n", "Epoch 360/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0033 - accuracy: 0.0284\n", "Epoch 361/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0031 - accuracy: 0.0259\n", "Epoch 362/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0024 - accuracy: 0.0202\n", "Epoch 363/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0023 - accuracy: 0.0236\n", "Epoch 364/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0023 - accuracy: 0.0392\n", "Epoch 365/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0022 - accuracy: 0.0300\n", "Epoch 366/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0032 - accuracy: 0.0345\n", "Epoch 367/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0025 - accuracy: 0.0218\n", "Epoch 368/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0027 - accuracy: 0.0252\n", "Epoch 369/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0023 - accuracy: 0.0293\n", "Epoch 370/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0022 - accuracy: 0.0149\n", "Epoch 371/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0025 - accuracy: 0.0297\n", "Epoch 372/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0023 - accuracy: 0.0196\n", "Epoch 373/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0026 - accuracy: 0.0316\n", "Epoch 374/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0026 - accuracy: 0.0192\n", "Epoch 375/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0024 - accuracy: 0.0255\n", "Epoch 376/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0023 - accuracy: 0.0282\n", "Epoch 377/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0028 - accuracy: 0.0363\n", "Epoch 378/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0028 - accuracy: 0.0325\n", "Epoch 379/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0022 - accuracy: 0.0296\n", "Epoch 380/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0022 - accuracy: 0.0316\n", "Epoch 381/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0023 - accuracy: 0.0196\n", "Epoch 382/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0024 - accuracy: 0.0339\n", "Epoch 383/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0024 - accuracy: 0.0294\n", "Epoch 384/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0021 - accuracy: 0.0199\n", "Epoch 385/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0026 - accuracy: 0.0260\n", "Epoch 386/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0023 - accuracy: 0.0297\n", "Epoch 387/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0024 - accuracy: 0.0294\n", "Epoch 388/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0022 - accuracy: 0.0244\n", "Epoch 389/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0029 - accuracy: 0.0353\n", "Epoch 390/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0027 - accuracy: 0.0231\n", "Epoch 391/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0030 - accuracy: 0.0378\n", "Epoch 392/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0025 - accuracy: 0.0290\n", "Epoch 393/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0025 - accuracy: 0.0404\n", "Epoch 394/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0027 - accuracy: 0.0230\n", "Epoch 395/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0026 - accuracy: 0.0206\n", "Epoch 396/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0030 - accuracy: 0.0245\n", "Epoch 397/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0028 - accuracy: 0.0292\n", "Epoch 398/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0028 - accuracy: 0.0325\n", "Epoch 399/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0022 - accuracy: 0.0295\n", "Epoch 400/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0023 - accuracy: 0.0369\n", "Epoch 401/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0026 - accuracy: 0.0196\n", "Epoch 402/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0027 - accuracy: 0.0391\n", "Epoch 403/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0019 - accuracy: 0.0221\n", "Epoch 404/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0029 - accuracy: 0.0235\n", "Epoch 405/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0027 - accuracy: 0.0327\n", "Epoch 406/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0027 - accuracy: 0.0251\n", "Epoch 407/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0024 - accuracy: 0.0220\n", "Epoch 408/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0023 - accuracy: 0.0367\n", "Epoch 409/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0026 - accuracy: 0.0325\n", "Epoch 410/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0024 - accuracy: 0.0345\n", "Epoch 411/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0022 - accuracy: 0.0374\n", "Epoch 412/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0024 - accuracy: 0.0413\n", "Epoch 413/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0019 - accuracy: 0.0252\n", "Epoch 414/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0022 - accuracy: 0.0193\n", "Epoch 415/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0022 - accuracy: 0.0312\n", "Epoch 416/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0021 - accuracy: 0.0254\n", "Epoch 417/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0022 - accuracy: 0.0468\n", "Epoch 418/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0024 - accuracy: 0.0241\n", "Epoch 419/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0024 - accuracy: 0.0251\n", "Epoch 420/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0021 - accuracy: 0.0284\n", "Epoch 421/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0024 - accuracy: 0.0270\n", "Epoch 422/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0020 - accuracy: 0.0307\n", "Epoch 423/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0022 - accuracy: 0.0288\n", "Epoch 424/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0022 - accuracy: 0.0237\n", "Epoch 425/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0020 - accuracy: 0.0259\n", "Epoch 426/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0021 - accuracy: 0.0354\n", "Epoch 427/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0021 - accuracy: 0.0275\n", "Epoch 428/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0023 - accuracy: 0.0281\n", "Epoch 429/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0023 - accuracy: 0.0275\n", "Epoch 430/1000\n", "12/12 [==============================] - 0s 4ms/step - loss: 0.0021 - accuracy: 0.0199\n", "Epoch 431/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0023 - accuracy: 0.0450\n", "Epoch 432/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0023 - accuracy: 0.0210\n", "Epoch 433/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0022 - accuracy: 0.0252\n", "Epoch 434/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0028 - accuracy: 0.0444\n", "Epoch 435/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0024 - accuracy: 0.0246\n", "Epoch 436/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0022 - accuracy: 0.0230\n", "Epoch 437/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0019 - accuracy: 0.0377\n", "Epoch 438/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0021 - accuracy: 0.0303\n", "Epoch 439/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0025 - accuracy: 0.0310\n", "Epoch 440/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0026 - accuracy: 0.0320\n", "Epoch 441/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0027 - accuracy: 0.0217\n", "Epoch 442/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0028 - accuracy: 0.0379\n", "Epoch 443/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0023 - accuracy: 0.0366\n", "Epoch 444/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0023 - accuracy: 0.0335\n", "Epoch 445/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0027 - accuracy: 0.0215\n", "Epoch 446/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0028 - accuracy: 0.0300\n", "Epoch 447/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0024 - accuracy: 0.0164\n", "Epoch 448/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0020 - accuracy: 0.0273\n", "Epoch 449/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0019 - accuracy: 0.0300\n", "Epoch 450/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0023 - accuracy: 0.0381\n", "Epoch 451/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0020 - accuracy: 0.0204\n", "Epoch 452/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0017 - accuracy: 0.0234\n", "Epoch 453/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0018 - accuracy: 0.0243\n", "Epoch 454/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0020 - accuracy: 0.0515\n", "Epoch 455/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0022 - accuracy: 0.0259\n", "Epoch 456/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0020 - accuracy: 0.0211\n", "Epoch 457/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0023 - accuracy: 0.0347\n", "Epoch 458/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0021 - accuracy: 0.0266\n", "Epoch 459/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0022 - accuracy: 0.0140\n", "Epoch 460/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0020 - accuracy: 0.0210\n", "Epoch 461/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0022 - accuracy: 0.0335\n", "Epoch 462/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0024 - accuracy: 0.0327\n", "Epoch 463/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0020 - accuracy: 0.0362\n", "Epoch 464/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0019 - accuracy: 0.0252\n", "Epoch 465/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0021 - accuracy: 0.0187\n", "Epoch 466/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0020 - accuracy: 0.0386\n", "Epoch 467/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0025 - accuracy: 0.0261\n", "Epoch 468/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0025 - accuracy: 0.0240\n", "Epoch 469/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0022 - accuracy: 0.0266\n", "Epoch 470/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0018 - accuracy: 0.0159\n", "Epoch 471/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0020 - accuracy: 0.0276\n", "Epoch 472/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0020 - accuracy: 0.0267\n", "Epoch 473/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0021 - accuracy: 0.0385\n", "Epoch 474/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0020 - accuracy: 0.0233\n", "Epoch 475/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0019 - accuracy: 0.0226\n", "Epoch 476/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0021 - accuracy: 0.0328\n", "Epoch 477/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0025 - accuracy: 0.0290\n", "Epoch 478/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0019 - accuracy: 0.0377\n", "Epoch 479/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0019 - accuracy: 0.0209\n", "Epoch 480/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0022 - accuracy: 0.0355\n", "Epoch 481/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0018 - accuracy: 0.0356\n", "Epoch 482/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0022 - accuracy: 0.0304\n", "Epoch 483/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0020 - accuracy: 0.0324\n", "Epoch 484/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0019 - accuracy: 0.0326\n", "Epoch 485/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0024 - accuracy: 0.0336\n", "Epoch 486/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0020 - accuracy: 0.0266 \n", "Epoch 487/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0023 - accuracy: 0.0259\n", "Epoch 488/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0019 - accuracy: 0.0469\n", "Epoch 489/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0020 - accuracy: 0.0222\n", "Epoch 490/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0021 - accuracy: 0.0268\n", "Epoch 491/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0019 - accuracy: 0.0202\n", "Epoch 492/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0021 - accuracy: 0.0225\n", "Epoch 493/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0023 - accuracy: 0.0287\n", "Epoch 494/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0021 - accuracy: 0.0231\n", "Epoch 495/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0024 - accuracy: 0.0202\n", "Epoch 496/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0019 - accuracy: 0.0200\n", "Epoch 497/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0021 - accuracy: 0.0319\n", "Epoch 498/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0021 - accuracy: 0.0362\n", "Epoch 499/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0021 - accuracy: 0.0263\n", "Epoch 500/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0022 - accuracy: 0.0319\n", "Epoch 501/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0020 - accuracy: 0.0304\n", "Epoch 502/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0022 - accuracy: 0.0315\n", "Epoch 503/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0020 - accuracy: 0.0323\n", "Epoch 504/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0019 - accuracy: 0.0306\n", "Epoch 505/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0019 - accuracy: 0.0198\n", "Epoch 506/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0018 - accuracy: 0.0415\n", "Epoch 507/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0021 - accuracy: 0.0254\n", "Epoch 508/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0022 - accuracy: 0.0207\n", "Epoch 509/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0018 - accuracy: 0.0212\n", "Epoch 510/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0019 - accuracy: 0.0306\n", "Epoch 511/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0022 - accuracy: 0.0360\n", "Epoch 512/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0020 - accuracy: 0.0279\n", "Epoch 513/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0018 - accuracy: 0.0308\n", "Epoch 514/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0023 - accuracy: 0.0390\n", "Epoch 515/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0019 - accuracy: 0.0223\n", "Epoch 516/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0019 - accuracy: 0.0229\n", "Epoch 517/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0020 - accuracy: 0.0222\n", "Epoch 518/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0019 - accuracy: 0.0271\n", "Epoch 519/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0021 - accuracy: 0.0223\n", "Epoch 520/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0020 - accuracy: 0.0233\n", "Epoch 521/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0038 - accuracy: 0.0245\n", "Epoch 522/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0034 - accuracy: 0.0314\n", "Epoch 523/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0026 - accuracy: 0.0286\n", "Epoch 524/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0021 - accuracy: 0.0291\n", "Epoch 525/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0021 - accuracy: 0.0368\n", "Epoch 526/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0021 - accuracy: 0.0371\n", "Epoch 527/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0020 - accuracy: 0.0302\n", "Epoch 528/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0023 - accuracy: 0.0337\n", "Epoch 529/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0020 - accuracy: 0.0186\n", "Epoch 530/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0020 - accuracy: 0.0326\n", "Epoch 531/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0019 - accuracy: 0.0385\n", "Epoch 532/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0021 - accuracy: 0.0340\n", "Epoch 533/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0020 - accuracy: 0.0408\n", "Epoch 534/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0022 - accuracy: 0.0385\n", "Epoch 535/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0022 - accuracy: 0.0160\n", "Epoch 536/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0020 - accuracy: 0.0326\n", "Epoch 537/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0022 - accuracy: 0.0398\n", "Epoch 538/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0020 - accuracy: 0.0261\n", "Epoch 539/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0020 - accuracy: 0.0138\n", "Epoch 540/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0019 - accuracy: 0.0310\n", "Epoch 541/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0019 - accuracy: 0.0333\n", "Epoch 542/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0016 - accuracy: 0.0230\n", "Epoch 543/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0017 - accuracy: 0.0364\n", "Epoch 544/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0021 - accuracy: 0.0299\n", "Epoch 545/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0019 - accuracy: 0.0319\n", "Epoch 546/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0018 - accuracy: 0.0268\n", "Epoch 547/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0019 - accuracy: 0.0317\n", "Epoch 548/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0021 - accuracy: 0.0198\n", "Epoch 549/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0019 - accuracy: 0.0241\n", "Epoch 550/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0019 - accuracy: 0.0165\n", "Epoch 551/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0017 - accuracy: 0.0404\n", "Epoch 552/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0017 - accuracy: 0.0380\n", "Epoch 553/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0020 - accuracy: 0.0167\n", "Epoch 554/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0022 - accuracy: 0.0262\n", "Epoch 555/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0017 - accuracy: 0.0164\n", "Epoch 556/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0019 - accuracy: 0.0221\n", "Epoch 557/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0016 - accuracy: 0.0337\n", "Epoch 558/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0016 - accuracy: 0.0340\n", "Epoch 559/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0019 - accuracy: 0.0188\n", "Epoch 560/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0022 - accuracy: 0.0355\n", "Epoch 561/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0022 - accuracy: 0.0367\n", "Epoch 562/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0019 - accuracy: 0.0188\n", "Epoch 563/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0018 - accuracy: 0.0245\n", "Epoch 564/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0020 - accuracy: 0.0340\n", "Epoch 565/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0018 - accuracy: 0.0397\n", "Epoch 566/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0017 - accuracy: 0.0380\n", "Epoch 567/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0022 - accuracy: 0.0198\n", "Epoch 568/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0022 - accuracy: 0.0309\n", "Epoch 569/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0017 - accuracy: 0.0220\n", "Epoch 570/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0018 - accuracy: 0.0317\n", "Epoch 571/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0017 - accuracy: 0.0203\n", "Epoch 572/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0021 - accuracy: 0.0289\n", "Epoch 573/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0020 - accuracy: 0.0204\n", "Epoch 574/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0018 - accuracy: 0.0325\n", "Epoch 575/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0023 - accuracy: 0.0213\n", "Epoch 576/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0017 - accuracy: 0.0290\n", "Epoch 577/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0018 - accuracy: 0.0179\n", "Epoch 578/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0020 - accuracy: 0.0448\n", "Epoch 579/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0019 - accuracy: 0.0286\n", "Epoch 580/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0019 - accuracy: 0.0320\n", "Epoch 581/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0017 - accuracy: 0.0119\n", "Epoch 582/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0019 - accuracy: 0.0332\n", "Epoch 583/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0018 - accuracy: 0.0239\n", "Epoch 584/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0018 - accuracy: 0.0179\n", "Epoch 585/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0016 - accuracy: 0.0364\n", "Epoch 586/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0018 - accuracy: 0.0308\n", "Epoch 587/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0019 - accuracy: 0.0210\n", "Epoch 588/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0018 - accuracy: 0.0390\n", "Epoch 589/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0019 - accuracy: 0.0380\n", "Epoch 590/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0017 - accuracy: 0.0206\n", "Epoch 591/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0019 - accuracy: 0.0248\n", "Epoch 592/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0021 - accuracy: 0.0262\n", "Epoch 593/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0020 - accuracy: 0.0340\n", "Epoch 594/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0023 - accuracy: 0.0248\n", "Epoch 595/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0022 - accuracy: 0.0194\n", "Epoch 596/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0017 - accuracy: 0.0212 \n", "Epoch 597/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0020 - accuracy: 0.0446\n", "Epoch 598/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0019 - accuracy: 0.0232\n", "Epoch 599/1000\n", "12/12 [==============================] - 0s 4ms/step - loss: 0.0019 - accuracy: 0.0227\n", "Epoch 600/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0019 - accuracy: 0.0325\n", "Epoch 601/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0020 - accuracy: 0.0271\n", "Epoch 602/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0019 - accuracy: 0.0235\n", "Epoch 603/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0017 - accuracy: 0.0206\n", "Epoch 604/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0019 - accuracy: 0.0378\n", "Epoch 605/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0016 - accuracy: 0.0237\n", "Epoch 606/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0020 - accuracy: 0.0286\n", "Epoch 607/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0019 - accuracy: 0.0277\n", "Epoch 608/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0016 - accuracy: 0.0380\n", "Epoch 609/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0018 - accuracy: 0.0348\n", "Epoch 610/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0019 - accuracy: 0.0369\n", "Epoch 611/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0022 - accuracy: 0.0443\n", "Epoch 612/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0022 - accuracy: 0.0144\n", "Epoch 613/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0018 - accuracy: 0.0228\n", "Epoch 614/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0017 - accuracy: 0.0126\n", "Epoch 615/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0019 - accuracy: 0.0341\n", "Epoch 616/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0021 - accuracy: 0.0318\n", "Epoch 617/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0016 - accuracy: 0.0393\n", "Epoch 618/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0018 - accuracy: 0.0389\n", "Epoch 619/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0020 - accuracy: 0.0320\n", "Epoch 620/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0022 - accuracy: 0.0294\n", "Epoch 621/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0021 - accuracy: 0.0112\n", "Epoch 622/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0020 - accuracy: 0.0333\n", "Epoch 623/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0021 - accuracy: 0.0282\n", "Epoch 624/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0019 - accuracy: 0.0207\n", "Epoch 625/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0021 - accuracy: 0.0232\n", "Epoch 626/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0019 - accuracy: 0.0257\n", "Epoch 627/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0018 - accuracy: 0.0171\n", "Epoch 628/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0015 - accuracy: 0.0273 \n", "Epoch 629/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0019 - accuracy: 0.0200\n", "Epoch 630/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0018 - accuracy: 0.0278\n", "Epoch 631/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0017 - accuracy: 0.0173\n", "Epoch 632/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0016 - accuracy: 0.0339\n", "Epoch 633/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0016 - accuracy: 0.0251\n", "Epoch 634/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0018 - accuracy: 0.0362\n", "Epoch 635/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0018 - accuracy: 0.0307\n", "Epoch 636/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0016 - accuracy: 0.0155\n", "Epoch 637/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0018 - accuracy: 0.0404\n", "Epoch 638/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0019 - accuracy: 0.0311\n", "Epoch 639/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0021 - accuracy: 0.0289\n", "Epoch 640/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0018 - accuracy: 0.0295\n", "Epoch 641/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0018 - accuracy: 0.0231\n", "Epoch 642/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0018 - accuracy: 0.0182\n", "Epoch 643/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0016 - accuracy: 0.0306\n", "Epoch 644/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0018 - accuracy: 0.0192\n", "Epoch 645/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0022 - accuracy: 0.0248 \n", "Epoch 646/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0025 - accuracy: 0.0272\n", "Epoch 647/1000\n", "12/12 [==============================] - 0s 4ms/step - loss: 0.0019 - accuracy: 0.0294\n", "Epoch 648/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0017 - accuracy: 0.0301\n", "Epoch 649/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0020 - accuracy: 0.0314\n", "Epoch 650/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0017 - accuracy: 0.0400\n", "Epoch 651/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0018 - accuracy: 0.0325\n", "Epoch 652/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0019 - accuracy: 0.0273\n", "Epoch 653/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0015 - accuracy: 0.0406\n", "Epoch 654/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0016 - accuracy: 0.0363\n", "Epoch 655/1000\n", "12/12 [==============================] - 0s 4ms/step - loss: 0.0018 - accuracy: 0.0317\n", "Epoch 656/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0035 - accuracy: 0.0221\n", "Epoch 657/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0026 - accuracy: 0.0185\n", "Epoch 658/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0022 - accuracy: 0.0255\n", "Epoch 659/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0023 - accuracy: 0.0372\n", "Epoch 660/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0020 - accuracy: 0.0275\n", "Epoch 661/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0019 - accuracy: 0.0374\n", "Epoch 662/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0017 - accuracy: 0.0231\n", "Epoch 663/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0016 - accuracy: 0.0203 \n", "Epoch 664/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0016 - accuracy: 0.0255\n", "Epoch 665/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0018 - accuracy: 0.0318\n", "Epoch 666/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0018 - accuracy: 0.0249\n", "Epoch 667/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0015 - accuracy: 0.0369\n", "Epoch 668/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0017 - accuracy: 0.0212\n", "Epoch 669/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0016 - accuracy: 0.0176\n", "Epoch 670/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0017 - accuracy: 0.0323\n", "Epoch 671/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0017 - accuracy: 0.0369\n", "Epoch 672/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0015 - accuracy: 0.0304\n", "Epoch 673/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0018 - accuracy: 0.0244\n", "Epoch 674/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0017 - accuracy: 0.0332\n", "Epoch 675/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0018 - accuracy: 0.0214\n", "Epoch 676/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0015 - accuracy: 0.0393\n", "Epoch 677/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0022 - accuracy: 0.0358\n", "Epoch 678/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0019 - accuracy: 0.0397\n", "Epoch 679/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0017 - accuracy: 0.0486\n", "Epoch 680/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0017 - accuracy: 0.0231 \n", "Epoch 681/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0019 - accuracy: 0.0293\n", "Epoch 682/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0016 - accuracy: 0.0279\n", "Epoch 683/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0016 - accuracy: 0.0323\n", "Epoch 684/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0015 - accuracy: 0.0315\n", "Epoch 685/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0016 - accuracy: 0.0296\n", "Epoch 686/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0018 - accuracy: 0.0179\n", "Epoch 687/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0029 - accuracy: 0.0438\n", "Epoch 688/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0027 - accuracy: 0.0273\n", "Epoch 689/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0021 - accuracy: 0.0285\n", "Epoch 690/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0021 - accuracy: 0.0305\n", "Epoch 691/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0015 - accuracy: 0.0354\n", "Epoch 692/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0019 - accuracy: 0.0338\n", "Epoch 693/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0020 - accuracy: 0.0293\n", "Epoch 694/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0015 - accuracy: 0.0325\n", "Epoch 695/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0015 - accuracy: 0.0307\n", "Epoch 696/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0020 - accuracy: 0.0294\n", "Epoch 697/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0023 - accuracy: 0.0275\n", "Epoch 698/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0017 - accuracy: 0.0207\n", "Epoch 699/1000\n", "12/12 [==============================] - 0s 4ms/step - loss: 0.0018 - accuracy: 0.0175\n", "Epoch 700/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0018 - accuracy: 0.0199\n", "Epoch 701/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0018 - accuracy: 0.0238\n", "Epoch 702/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0017 - accuracy: 0.0281 \n", "Epoch 703/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0019 - accuracy: 0.0258\n", "Epoch 704/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0020 - accuracy: 0.0337\n", "Epoch 705/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0019 - accuracy: 0.0301\n", "Epoch 706/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0015 - accuracy: 0.0272\n", "Epoch 707/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0019 - accuracy: 0.0183\n", "Epoch 708/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0015 - accuracy: 0.0233\n", "Epoch 709/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0014 - accuracy: 0.0242 \n", "Epoch 710/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0015 - accuracy: 0.0299\n", "Epoch 711/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0017 - accuracy: 0.0282\n", "Epoch 712/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0015 - accuracy: 0.0290\n", "Epoch 713/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0017 - accuracy: 0.0234\n", "Epoch 714/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0017 - accuracy: 0.0182\n", "Epoch 715/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0017 - accuracy: 0.0225\n", "Epoch 716/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0016 - accuracy: 0.0316\n", "Epoch 717/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0016 - accuracy: 0.0302\n", "Epoch 718/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0017 - accuracy: 0.0355\n", "Epoch 719/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0015 - accuracy: 0.0292\n", "Epoch 720/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0016 - accuracy: 0.0339\n", "Epoch 721/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0017 - accuracy: 0.0227\n", "Epoch 722/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0019 - accuracy: 0.0408\n", "Epoch 723/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0018 - accuracy: 0.0193\n", "Epoch 724/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0020 - accuracy: 0.0190\n", "Epoch 725/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0018 - accuracy: 0.0205\n", "Epoch 726/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0018 - accuracy: 0.0182\n", "Epoch 727/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0015 - accuracy: 0.0338\n", "Epoch 728/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0017 - accuracy: 0.0279\n", "Epoch 729/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0018 - accuracy: 0.0249\n", "Epoch 730/1000\n", "12/12 [==============================] - 0s 4ms/step - loss: 0.0014 - accuracy: 0.0252\n", "Epoch 731/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0017 - accuracy: 0.0283\n", "Epoch 732/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0018 - accuracy: 0.0392\n", "Epoch 733/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0018 - accuracy: 0.0267\n", "Epoch 734/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0017 - accuracy: 0.0277\n", "Epoch 735/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0016 - accuracy: 0.0489\n", "Epoch 736/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0016 - accuracy: 0.0380\n", "Epoch 737/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0018 - accuracy: 0.0355\n", "Epoch 738/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0017 - accuracy: 0.0285\n", "Epoch 739/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0014 - accuracy: 0.0346\n", "Epoch 740/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0017 - accuracy: 0.0329\n", "Epoch 741/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0018 - accuracy: 0.0373\n", "Epoch 742/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0018 - accuracy: 0.0322\n", "Epoch 743/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0021 - accuracy: 0.0333\n", "Epoch 744/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0020 - accuracy: 0.0322\n", "Epoch 745/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0016 - accuracy: 0.0312\n", "Epoch 746/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0015 - accuracy: 0.0299\n", "Epoch 747/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0014 - accuracy: 0.0278 \n", "Epoch 748/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0016 - accuracy: 0.0327\n", "Epoch 749/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0023 - accuracy: 0.0310\n", "Epoch 750/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0022 - accuracy: 0.0334\n", "Epoch 751/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0020 - accuracy: 0.0288\n", "Epoch 752/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0017 - accuracy: 0.0387\n", "Epoch 753/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0022 - accuracy: 0.0251\n", "Epoch 754/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0017 - accuracy: 0.0293\n", "Epoch 755/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0016 - accuracy: 0.0348\n", "Epoch 756/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0016 - accuracy: 0.0382\n", "Epoch 757/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0016 - accuracy: 0.0204\n", "Epoch 758/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0015 - accuracy: 0.0282\n", "Epoch 759/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0015 - accuracy: 0.0448\n", "Epoch 760/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0014 - accuracy: 0.0281\n", "Epoch 761/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0017 - accuracy: 0.0257\n", "Epoch 762/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0016 - accuracy: 0.0350\n", "Epoch 763/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0017 - accuracy: 0.0196\n", "Epoch 764/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0014 - accuracy: 0.0259\n", "Epoch 765/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0016 - accuracy: 0.0200\n", "Epoch 766/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0016 - accuracy: 0.0302 \n", "Epoch 767/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0017 - accuracy: 0.0270\n", "Epoch 768/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0015 - accuracy: 0.0414\n", "Epoch 769/1000\n", "12/12 [==============================] - 0s 4ms/step - loss: 0.0019 - accuracy: 0.0283\n", "Epoch 770/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0014 - accuracy: 0.0328\n", "Epoch 771/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0014 - accuracy: 0.0266\n", "Epoch 772/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0016 - accuracy: 0.0278\n", "Epoch 773/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0016 - accuracy: 0.0336\n", "Epoch 774/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0018 - accuracy: 0.0288\n", "Epoch 775/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0018 - accuracy: 0.0372\n", "Epoch 776/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0017 - accuracy: 0.0200\n", "Epoch 777/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0018 - accuracy: 0.0264\n", "Epoch 778/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0015 - accuracy: 0.0284\n", "Epoch 779/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0014 - accuracy: 0.0249 \n", "Epoch 780/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0018 - accuracy: 0.0179\n", "Epoch 781/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0017 - accuracy: 0.0292\n", "Epoch 782/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0013 - accuracy: 0.0407\n", "Epoch 783/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0018 - accuracy: 0.0226\n", "Epoch 784/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0015 - accuracy: 0.0243\n", "Epoch 785/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0016 - accuracy: 0.0224\n", "Epoch 786/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0016 - accuracy: 0.0233\n", "Epoch 787/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0017 - accuracy: 0.0288\n", "Epoch 788/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0014 - accuracy: 0.0203\n", "Epoch 789/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0015 - accuracy: 0.0241\n", "Epoch 790/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0015 - accuracy: 0.0190\n", "Epoch 791/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0014 - accuracy: 0.0198\n", "Epoch 792/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0014 - accuracy: 0.0216 \n", "Epoch 793/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0014 - accuracy: 0.0298\n", "Epoch 794/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0014 - accuracy: 0.0259\n", "Epoch 795/1000\n", "12/12 [==============================] - 0s 4ms/step - loss: 0.0015 - accuracy: 0.0315\n", "Epoch 796/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0015 - accuracy: 0.0374\n", "Epoch 797/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0016 - accuracy: 0.0227\n", "Epoch 798/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0016 - accuracy: 0.0210\n", "Epoch 799/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0017 - accuracy: 0.0282\n", "Epoch 800/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0016 - accuracy: 0.0230\n", "Epoch 801/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0017 - accuracy: 0.0298\n", "Epoch 802/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0016 - accuracy: 0.0233 \n", "Epoch 803/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0014 - accuracy: 0.0300\n", "Epoch 804/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0013 - accuracy: 0.0305 \n", "Epoch 805/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0016 - accuracy: 0.0202\n", "Epoch 806/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0015 - accuracy: 0.0264\n", "Epoch 807/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0015 - accuracy: 0.0291\n", "Epoch 808/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0015 - accuracy: 0.0193 \n", "Epoch 809/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0017 - accuracy: 0.0278\n", "Epoch 810/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0016 - accuracy: 0.0328\n", "Epoch 811/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0015 - accuracy: 0.0322\n", "Epoch 812/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0013 - accuracy: 0.0283\n", "Epoch 813/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0014 - accuracy: 0.0192\n", "Epoch 814/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0015 - accuracy: 0.0242\n", "Epoch 815/1000\n", "12/12 [==============================] - 0s 4ms/step - loss: 0.0014 - accuracy: 0.0309\n", "Epoch 816/1000\n", "12/12 [==============================] - 0s 4ms/step - loss: 0.0017 - accuracy: 0.0360\n", "Epoch 817/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0019 - accuracy: 0.0231\n", "Epoch 818/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0019 - accuracy: 0.0254\n", "Epoch 819/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0017 - accuracy: 0.0279\n", "Epoch 820/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0020 - accuracy: 0.0376\n", "Epoch 821/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0019 - accuracy: 0.0245\n", "Epoch 822/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0015 - accuracy: 0.0266\n", "Epoch 823/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0016 - accuracy: 0.0297\n", "Epoch 824/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0014 - accuracy: 0.0193\n", "Epoch 825/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0016 - accuracy: 0.0328\n", "Epoch 826/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0015 - accuracy: 0.0353\n", "Epoch 827/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0016 - accuracy: 0.0212\n", "Epoch 828/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0015 - accuracy: 0.0221\n", "Epoch 829/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0014 - accuracy: 0.0391\n", "Epoch 830/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0018 - accuracy: 0.0294\n", "Epoch 831/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0018 - accuracy: 0.0343\n", "Epoch 832/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0017 - accuracy: 0.0291\n", "Epoch 833/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0017 - accuracy: 0.0387\n", "Epoch 834/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0018 - accuracy: 0.0299\n", "Epoch 835/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0017 - accuracy: 0.0292\n", "Epoch 836/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0014 - accuracy: 0.0347\n", "Epoch 837/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0015 - accuracy: 0.0310\n", "Epoch 838/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0016 - accuracy: 0.0289\n", "Epoch 839/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0014 - accuracy: 0.0249\n", "Epoch 840/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0014 - accuracy: 0.0324\n", "Epoch 841/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0015 - accuracy: 0.0211\n", "Epoch 842/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0015 - accuracy: 0.0342\n", "Epoch 843/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0017 - accuracy: 0.0335\n", "Epoch 844/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0017 - accuracy: 0.0233\n", "Epoch 845/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0016 - accuracy: 0.0307\n", "Epoch 846/1000\n", "12/12 [==============================] - 0s 4ms/step - loss: 0.0014 - accuracy: 0.0281\n", "Epoch 847/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0015 - accuracy: 0.0265\n", "Epoch 848/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0015 - accuracy: 0.0406\n", "Epoch 849/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0014 - accuracy: 0.0207\n", "Epoch 850/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0015 - accuracy: 0.0400\n", "Epoch 851/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0018 - accuracy: 0.0215\n", "Epoch 852/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0017 - accuracy: 0.0188\n", "Epoch 853/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0014 - accuracy: 0.0353\n", "Epoch 854/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0014 - accuracy: 0.0237\n", "Epoch 855/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0013 - accuracy: 0.0254 \n", "Epoch 856/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0015 - accuracy: 0.0421\n", "Epoch 857/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0015 - accuracy: 0.0359\n", "Epoch 858/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0019 - accuracy: 0.0264\n", "Epoch 859/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0017 - accuracy: 0.0299\n", "Epoch 860/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0017 - accuracy: 0.0220\n", "Epoch 861/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0017 - accuracy: 0.0245\n", "Epoch 862/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0014 - accuracy: 0.0341\n", "Epoch 863/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0016 - accuracy: 0.0197\n", "Epoch 864/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0015 - accuracy: 0.0298\n", "Epoch 865/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0018 - accuracy: 0.0353\n", "Epoch 866/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0016 - accuracy: 0.0299\n", "Epoch 867/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0016 - accuracy: 0.0266\n", "Epoch 868/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0017 - accuracy: 0.0325\n", "Epoch 869/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0015 - accuracy: 0.0318\n", "Epoch 870/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0016 - accuracy: 0.0286\n", "Epoch 871/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0015 - accuracy: 0.0319\n", "Epoch 872/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0017 - accuracy: 0.0236\n", "Epoch 873/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0020 - accuracy: 0.0351\n", "Epoch 874/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0016 - accuracy: 0.0177\n", "Epoch 875/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0014 - accuracy: 0.0214\n", "Epoch 876/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0020 - accuracy: 0.0263\n", "Epoch 877/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0013 - accuracy: 0.0443\n", "Epoch 878/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0017 - accuracy: 0.0337\n", "Epoch 879/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0014 - accuracy: 0.0239\n", "Epoch 880/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0015 - accuracy: 0.0227\n", "Epoch 881/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0016 - accuracy: 0.0255\n", "Epoch 882/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0013 - accuracy: 0.0229 \n", "Epoch 883/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0017 - accuracy: 0.0274\n", "Epoch 884/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0016 - accuracy: 0.0293\n", "Epoch 885/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0015 - accuracy: 0.0155\n", "Epoch 886/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0016 - accuracy: 0.0280\n", "Epoch 887/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0016 - accuracy: 0.0262\n", "Epoch 888/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0015 - accuracy: 0.0315\n", "Epoch 889/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0017 - accuracy: 0.0330\n", "Epoch 890/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0016 - accuracy: 0.0292\n", "Epoch 891/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0016 - accuracy: 0.0302\n", "Epoch 892/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0017 - accuracy: 0.0359\n", "Epoch 893/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0017 - accuracy: 0.0347\n", "Epoch 894/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0018 - accuracy: 0.0298\n", "Epoch 895/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0015 - accuracy: 0.0292\n", "Epoch 896/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0015 - accuracy: 0.0195\n", "Epoch 897/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0014 - accuracy: 0.0292\n", "Epoch 898/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0014 - accuracy: 0.0222\n", "Epoch 899/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0017 - accuracy: 0.0408\n", "Epoch 900/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0016 - accuracy: 0.0400\n", "Epoch 901/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0013 - accuracy: 0.0192\n", "Epoch 902/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0016 - accuracy: 0.0202\n", "Epoch 903/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0013 - accuracy: 0.0229 \n", "Epoch 904/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0016 - accuracy: 0.0272\n", "Epoch 905/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0013 - accuracy: 0.0351\n", "Epoch 906/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0017 - accuracy: 0.0276\n", "Epoch 907/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0015 - accuracy: 0.0193\n", "Epoch 908/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0019 - accuracy: 0.0261\n", "Epoch 909/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0015 - accuracy: 0.0218\n", "Epoch 910/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0017 - accuracy: 0.0295\n", "Epoch 911/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0013 - accuracy: 0.0328\n", "Epoch 912/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0012 - accuracy: 0.0369\n", "Epoch 913/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0017 - accuracy: 0.0310\n", "Epoch 914/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0018 - accuracy: 0.0315\n", "Epoch 915/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0016 - accuracy: 0.0299\n", "Epoch 916/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0016 - accuracy: 0.0253\n", "Epoch 917/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0016 - accuracy: 0.0239 \n", "Epoch 918/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0017 - accuracy: 0.0287\n", "Epoch 919/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0013 - accuracy: 0.0218 \n", "Epoch 920/1000\n", "12/12 [==============================] - 0s 4ms/step - loss: 0.0015 - accuracy: 0.0276\n", "Epoch 921/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0014 - accuracy: 0.0180 \n", "Epoch 922/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0012 - accuracy: 0.0265\n", "Epoch 923/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0014 - accuracy: 0.0289\n", "Epoch 924/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0012 - accuracy: 0.0328\n", "Epoch 925/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0021 - accuracy: 0.0246\n", "Epoch 926/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0017 - accuracy: 0.0403\n", "Epoch 927/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0014 - accuracy: 0.0276\n", "Epoch 928/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0015 - accuracy: 0.0196\n", "Epoch 929/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0013 - accuracy: 0.0412\n", "Epoch 930/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0016 - accuracy: 0.0358\n", "Epoch 931/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0018 - accuracy: 0.0254\n", "Epoch 932/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0015 - accuracy: 0.0322\n", "Epoch 933/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0017 - accuracy: 0.0225\n", "Epoch 934/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0013 - accuracy: 0.0339\n", "Epoch 935/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0013 - accuracy: 0.0178 \n", "Epoch 936/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0014 - accuracy: 0.0237\n", "Epoch 937/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0014 - accuracy: 0.0389\n", "Epoch 938/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0015 - accuracy: 0.0260\n", "Epoch 939/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0014 - accuracy: 0.0209\n", "Epoch 940/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0015 - accuracy: 0.0289\n", "Epoch 941/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0015 - accuracy: 0.0244\n", "Epoch 942/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0016 - accuracy: 0.0257\n", "Epoch 943/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0014 - accuracy: 0.0228\n", "Epoch 944/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0014 - accuracy: 0.0283\n", "Epoch 945/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0015 - accuracy: 0.0266\n", "Epoch 946/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0016 - accuracy: 0.0255\n", "Epoch 947/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0015 - accuracy: 0.0381\n", "Epoch 948/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0015 - accuracy: 0.0282\n", "Epoch 949/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0013 - accuracy: 0.0344\n", "Epoch 950/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0014 - accuracy: 0.0263\n", "Epoch 951/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0018 - accuracy: 0.0236\n", "Epoch 952/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0016 - accuracy: 0.0366\n", "Epoch 953/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0014 - accuracy: 0.0283\n", "Epoch 954/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0015 - accuracy: 0.0204\n", "Epoch 955/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0013 - accuracy: 0.0272\n", "Epoch 956/1000\n", "12/12 [==============================] - 0s 4ms/step - loss: 0.0017 - accuracy: 0.0328\n", "Epoch 957/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0015 - accuracy: 0.0266\n", "Epoch 958/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0016 - accuracy: 0.0375\n", "Epoch 959/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0014 - accuracy: 0.0514\n", "Epoch 960/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0013 - accuracy: 0.0288\n", "Epoch 961/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0017 - accuracy: 0.0264\n", "Epoch 962/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0015 - accuracy: 0.0230 \n", "Epoch 963/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0016 - accuracy: 0.0294\n", "Epoch 964/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0015 - accuracy: 0.0313\n", "Epoch 965/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0013 - accuracy: 0.0227\n", "Epoch 966/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0015 - accuracy: 0.0331\n", "Epoch 967/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0013 - accuracy: 0.0384\n", "Epoch 968/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0015 - accuracy: 0.0234\n", "Epoch 969/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0014 - accuracy: 0.0310\n", "Epoch 970/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0015 - accuracy: 0.0145\n", "Epoch 971/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0015 - accuracy: 0.0208\n", "Epoch 972/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0013 - accuracy: 0.0283\n", "Epoch 973/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0016 - accuracy: 0.0197\n", "Epoch 974/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0017 - accuracy: 0.0352\n", "Epoch 975/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0017 - accuracy: 0.0295\n", "Epoch 976/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0014 - accuracy: 0.0226\n", "Epoch 977/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0013 - accuracy: 0.0245\n", "Epoch 978/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0015 - accuracy: 0.0345\n", "Epoch 979/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0013 - accuracy: 0.0185\n", "Epoch 980/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0013 - accuracy: 0.0312\n", "Epoch 981/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0015 - accuracy: 0.0251 \n", "Epoch 982/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0017 - accuracy: 0.0354\n", "Epoch 983/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0016 - accuracy: 0.0203\n", "Epoch 984/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0015 - accuracy: 0.0403\n", "Epoch 985/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0015 - accuracy: 0.0296\n", "Epoch 986/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0014 - accuracy: 0.0195 \n", "Epoch 987/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0027 - accuracy: 0.0296\n", "Epoch 988/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0027 - accuracy: 0.0246\n", "Epoch 989/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0017 - accuracy: 0.0186\n", "Epoch 990/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0017 - accuracy: 0.0318\n", "Epoch 991/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0016 - accuracy: 0.0324\n", "Epoch 992/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0015 - accuracy: 0.0284\n", "Epoch 993/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0014 - accuracy: 0.0207\n", "Epoch 994/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0014 - accuracy: 0.0246\n", "Epoch 995/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0015 - accuracy: 0.0256\n", "Epoch 996/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0013 - accuracy: 0.0261\n", "Epoch 997/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0013 - accuracy: 0.0293\n", "Epoch 998/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0013 - accuracy: 0.0253\n", "Epoch 999/1000\n", "12/12 [==============================] - 0s 3ms/step - loss: 0.0022 - accuracy: 0.0409\n", "Epoch 1000/1000\n", "12/12 [==============================] - 0s 2ms/step - loss: 0.0027 - accuracy: 0.0283\n" ], "name": "stdout" }, { "output_type": "execute_result", "data": { "text/plain": [ "" ] }, "metadata": { "tags": [] }, "execution_count": 26 } ] }, { "cell_type": "code", "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "AGNpWVQ8wMHn", "outputId": "271c190a-bc20-457d-e12c-3c3ef7b2b0c8" }, "source": [ "model.summary()" ], "execution_count": 27, "outputs": [ { "output_type": "stream", "text": [ "Model: \"sequential\"\n", "_________________________________________________________________\n", "Layer (type) Output Shape Param # \n", "=================================================================\n", "dense (Dense) (None, 20) 280 \n", "_________________________________________________________________\n", "dense_1 (Dense) (None, 10) 210 \n", "_________________________________________________________________\n", "dense_2 (Dense) (None, 1) 11 \n", "=================================================================\n", "Total params: 501\n", "Trainable params: 501\n", "Non-trainable params: 0\n", "_________________________________________________________________\n" ], "name": "stdout" } ] }, { "cell_type": "code", "metadata": { "id": "IiSjKIP2wYQt" }, "source": [ "y_predKM = model.predict(X_test)" ], "execution_count": 28, "outputs": [] }, { "cell_type": "code", "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "usmZagk2wieM", "outputId": "6ca5301a-e8bf-4e97-a498-32b2c1af747e" }, "source": [ "score = model.evaluate(X_test,Y_test,verbose=0)\r\n", "print('Keras Model')\r\n", "print(score[0])" ], "execution_count": 29, "outputs": [ { "output_type": "stream", "text": [ "Keras Model\n", "0.006955331191420555\n" ], "name": "stdout" } ] }, { "cell_type": "code", "metadata": { "id": "n653Ky6Ax7t0" }, "source": [ "from sklearn.linear_model import LinearRegression\r\n", "LModel = LinearRegression()\r\n", "LModel.fit(X_train, Y_train)\r\n", "Y_predLM = LModel.predict(X_test)" ], "execution_count": 39, "outputs": [] }, { "cell_type": "code", "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 312 }, "id": "8RI2wXE6ye51", "outputId": "275c289a-4311-496f-a9f1-7e6862126c8a" }, "source": [ "plt.figure(1)\r\n", "plt.subplot(121)\r\n", "plt.scatter(Y_test, Y_predLM)\r\n", "plt.xlabel(\"Actual values\")\r\n", "plt.ylabel(\"Predicted values\")\r\n", "plt.title(\"Neural Network Model\")\r\n", "\r\n" ], "execution_count": 40, "outputs": [ { "output_type": "execute_result", "data": { "text/plain": [ "Text(0.5, 1.0, 'Neural Network Model')" ] }, "metadata": { "tags": [] }, "execution_count": 40 }, { "output_type": "display_data", "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "tags": [], "needs_background": "light" } } ] }, { "cell_type": "code", "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 295 }, "id": "PCMSMWLmzXj4", "outputId": "0ae9f3e7-5034-49f1-f003-fb69478a1625" }, "source": [ "plt.subplot(122)\r\n", "plt.scatter(Y_test, Y_predLM)\r\n", "plt.xlabel(\"Actual values\")\r\n", "plt.ylabel(\"Predicted values\")\r\n", "plt.title(\"SKLearn Linear Regression Model\")\r\n", "plt.show()" ], "execution_count": 41, "outputs": [ { "output_type": "display_data", "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "tags": [], "needs_background": "light" } } ] }, { "cell_type": "code", "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "Z9Kt13Tg0k1g", "outputId": "4b1a1867-5ec5-440a-ccac-0700754189b6" }, "source": [ "from sklearn.metrics import mean_squared_error\r\n", "mse = mean_squared_error(Y_test,Y_predLM)\r\n", "print('Linear Regression Model')\r\n", "print(mse)\r\n", "#Keras Model\r\n", "0.006955331191420555" ], "execution_count": 42, "outputs": [ { "output_type": "stream", "text": [ "Linear Regression Model\n", "0.015159030964982022\n" ], "name": "stdout" } ] } ] }