diff --git a/doc/HandwrittenNotes/2023/NotesDec182023.pdf b/doc/HandwrittenNotes/2023/NotesDec182023.pdf new file mode 100644 index 0000000..9c400e4 Binary files /dev/null and b/doc/HandwrittenNotes/2023/NotesDec182023.pdf differ diff --git a/doc/pub/day7/ipynb/day7.ipynb b/doc/pub/day7/ipynb/day7.ipynb index b294358..f5028c0 100644 --- a/doc/pub/day7/ipynb/day7.ipynb +++ b/doc/pub/day7/ipynb/day7.ipynb @@ -3,9 +3,7 @@ { "cell_type": "markdown", "id": "81a0f176", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "\n", @@ -15,9 +13,7 @@ { "cell_type": "markdown", "id": "f8220ceb", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "# Convolutional (CNN) and Recurrent (RNN) Neural Networks\n", "**Morten Hjorth-Jensen**, Department of Physics, University of Oslo and Department of Physics and Astronomy and Facility for Rare Ion Beams, Michigan State University, USA\n", @@ -30,9 +26,7 @@ { "cell_type": "markdown", "id": "cf40bf6e", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "## December 13 and 18\n", "\n", @@ -62,9 +56,7 @@ { "cell_type": "markdown", "id": "8580f3c5", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "## Convolutional Neural Networks (recognizing images)\n", "\n", @@ -89,9 +81,7 @@ { "cell_type": "markdown", "id": "7e859741", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "## What is the Difference\n", "\n", @@ -105,9 +95,7 @@ { "cell_type": "markdown", "id": "8f267713", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "## Neural Networks vs CNNs\n", "\n", @@ -123,9 +111,7 @@ { "cell_type": "markdown", "id": "cf6b4588", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "## Why CNNS for images, sound files, medical images from CT scans etc?\n", "\n", @@ -153,9 +139,7 @@ { "cell_type": "markdown", "id": "a641c887", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "## Regular NNs don’t scale well to full images\n", "\n", @@ -183,9 +167,7 @@ { "cell_type": "markdown", "id": "5bfb53b8", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "## 3D volumes of neurons\n", "\n", @@ -223,9 +205,7 @@ { "cell_type": "markdown", "id": "30a4390a", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "## Layers used to build CNNs\n", "\n", @@ -252,9 +232,7 @@ { "cell_type": "markdown", "id": "5a227109", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "## Transforming images\n", "\n", @@ -274,9 +252,7 @@ { "cell_type": "markdown", "id": "9cca89be", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "## CNNs in brief\n", "\n", @@ -302,9 +278,7 @@ { "cell_type": "markdown", "id": "c96a8b7a", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "## Key Idea\n", "\n", @@ -319,9 +293,7 @@ { "cell_type": "markdown", "id": "2cac31ab", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "## Mathematics of CNNs\n", "\n", @@ -339,9 +311,7 @@ { "cell_type": "markdown", "id": "98d89819", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "$$\n", "y(t) = \\int x(a) w(t-a) da,\n", @@ -351,9 +321,7 @@ { "cell_type": "markdown", "id": "e271bdce", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "where $x(a)$ represents a so-called input and $w(t-a)$ is normally called the weight function or kernel.\n", "\n", @@ -363,9 +331,7 @@ { "cell_type": "markdown", "id": "2fd4bdb4", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "$$\n", "y(t) = \\left(x * w\\right)(t).\n", @@ -375,9 +341,7 @@ { "cell_type": "markdown", "id": "0419c54a", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "The discretized version reads" ] @@ -385,9 +349,7 @@ { "cell_type": "markdown", "id": "494f5728", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "$$\n", "y(t) = \\sum_{a=-\\infty}^{a=\\infty}x(a)w(t-a).\n", @@ -397,9 +359,7 @@ { "cell_type": "markdown", "id": "6851c52f", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "Computing the inverse of the above convolution operations is known as deconvolution.\n", "\n", @@ -409,9 +369,7 @@ { "cell_type": "markdown", "id": "26bf3a3a", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "## Convolution Examples: Polynomial multiplication\n", "\n", @@ -424,9 +382,7 @@ { "cell_type": "markdown", "id": "28238c11", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "$$\n", "p(t) = \\alpha_0+\\alpha_1 t+\\alpha_2 t^2,\n", @@ -436,9 +392,7 @@ { "cell_type": "markdown", "id": "7303cb8d", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "and" ] @@ -446,9 +400,7 @@ { "cell_type": "markdown", "id": "bfd47f2f", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "$$\n", "s(t) = \\beta_0+\\beta_1 t+\\beta_2 t^2+\\beta_3 t^3.\n", @@ -458,9 +410,7 @@ { "cell_type": "markdown", "id": "1df68583", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "The polynomial multiplication gives us a new polynomial of degree $5$" ] @@ -468,9 +418,7 @@ { "cell_type": "markdown", "id": "3a22d91a", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "$$\n", "z(t) = \\delta_0+\\delta_1 t+\\delta_2 t^2+\\delta_3 t^3+\\delta_4 t^4+\\delta_5 t^5.\n", @@ -480,9 +428,7 @@ { "cell_type": "markdown", "id": "a1145019", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "## Efficient Polynomial Multiplication\n", "\n", @@ -493,9 +439,7 @@ { "cell_type": "markdown", "id": "42616957", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "$$\n", "\\begin{split}\n", @@ -512,9 +456,7 @@ { "cell_type": "markdown", "id": "27d00553", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "We note that $\\alpha_i=0$ except for $i\\in \\left\\{0,1,2\\right\\}$ and $\\beta_i=0$ except for $i\\in\\left\\{0,1,2,3\\right\\}$.\n", "\n", @@ -524,9 +466,7 @@ { "cell_type": "markdown", "id": "e7f2ed8e", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "$$\n", "\\delta_j = \\sum_{i=-\\infty}^{i=\\infty}\\alpha_i\\beta_{j-i}=(\\alpha * \\beta)_j,\n", @@ -536,9 +476,7 @@ { "cell_type": "markdown", "id": "f7d036a8", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "or as a double sum with restriction $l=i+j$" ] @@ -546,9 +484,7 @@ { "cell_type": "markdown", "id": "9aee1a68", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "$$\n", "\\delta_l = \\sum_{ij}\\alpha_i\\beta_{j}.\n", @@ -558,9 +494,7 @@ { "cell_type": "markdown", "id": "b29c325d", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "Do you see a potential drawback with these equations?" ] @@ -568,9 +502,7 @@ { "cell_type": "markdown", "id": "2a6101ad", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "## A more efficient way of coding the above Convolution\n", "\n", @@ -582,9 +514,7 @@ { "cell_type": "markdown", "id": "4d8b1e03", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "$$\n", "\\boldsymbol{\\delta}=\\begin{bmatrix}\\alpha_0 & 0 & 0 & 0 \\\\\n", @@ -600,9 +530,7 @@ { "cell_type": "markdown", "id": "bfef406c", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "The process is commutative and we can easily see that we can rewrite the multiplication in terms of a matrix holding $\\beta$ and a vector holding $\\alpha$.\n", "In this case we have" @@ -611,9 +539,7 @@ { "cell_type": "markdown", "id": "23a56386", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "$$\n", "\\boldsymbol{\\delta}=\\begin{bmatrix}\\beta_0 & 0 & 0 \\\\\n", @@ -629,9 +555,7 @@ { "cell_type": "markdown", "id": "10566cdb", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "Note that the use of these matrices is for mathematical purposes only and not implementation purposes.\n", "When implementing the above equation we do not encode (and allocate memory) the matrices explicitely.\n", @@ -649,9 +573,7 @@ { "cell_type": "markdown", "id": "2a61ed4d", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "$$\n", "\\boldsymbol{A}=\\begin{bmatrix}a_0 & 0 & 0 \\\\\n", @@ -667,9 +589,7 @@ { "cell_type": "markdown", "id": "cef457df", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "with elements $a_{ii}=a_{i+1,j+1}=a_{i-j}$ is an example of a Toeplitz\n", "matrix. Such a matrix does not need to be a square matrix. Toeplitz\n", @@ -684,9 +604,7 @@ { "cell_type": "markdown", "id": "a2b0ff1e", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "## Convolution Examples: Principle of Superposition and Periodic Forces (Fourier Transforms)\n", "\n", @@ -696,9 +614,7 @@ { "cell_type": "markdown", "id": "7131b590", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "$$\n", "m\\frac{d^2x}{dt^2}+\\eta\\frac{dx}{dt}+x(t)=F(t),\n", @@ -708,9 +624,7 @@ { "cell_type": "markdown", "id": "0e4b132a", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "where $F(t)$ is an applied external force acting on the system (often\n", "called a driving force), one can use the theory of Fourier\n", @@ -724,9 +638,7 @@ { "cell_type": "markdown", "id": "3b97b431", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "\n", "
\n", @@ -742,9 +654,7 @@ { "cell_type": "markdown", "id": "0ed4a6c0", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "This is known as the principle of superposition. It only applies when\n", "the homogenous equation is linear. \n", @@ -759,9 +669,7 @@ { "cell_type": "markdown", "id": "ac010076", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "$$\n", "\\begin{eqnarray}\n", @@ -773,9 +681,7 @@ { "cell_type": "markdown", "id": "599408a8", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "One example of a non-sinusoidal periodic force is a square wave. Many\n", "components in electric circuits are non-linear, for example diodes. This \n", @@ -786,9 +692,7 @@ { "cell_type": "markdown", "id": "52a36dc6", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "## Simple Code Example\n", "\n", @@ -801,11 +705,19 @@ "cell_type": "code", "execution_count": 1, "id": "72a6cd36", - "metadata": { - "collapsed": false, - "editable": true - }, - "outputs": [], + "metadata": {}, + "outputs": [ + { + "data": { + "image/png": "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\n", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], "source": [ "%matplotlib inline\n", "\n", @@ -831,9 +743,7 @@ { "cell_type": "markdown", "id": "e99f5529", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "For the sinusoidal example the\n", "period is $\\tau=2\\pi/\\omega$. However, higher harmonics can also\n", @@ -845,9 +755,7 @@ { "cell_type": "markdown", "id": "ae3407bb", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "\n", "
\n", @@ -863,9 +771,7 @@ { "cell_type": "markdown", "id": "12aea4dc", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "## Wrapping up Fourier transforms\n", "\n", @@ -878,9 +784,7 @@ { "cell_type": "markdown", "id": "2e74fadd", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "\n", "
\n", @@ -896,9 +800,7 @@ { "cell_type": "markdown", "id": "77edc27c", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "The solutions for $x(t)$ then come from replacing $\\omega$ with\n", "$n\\omega$ for each term in the particular solution," @@ -907,9 +809,7 @@ { "cell_type": "markdown", "id": "3cafcaf7", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "$$\n", "\\begin{eqnarray}\n", @@ -927,9 +827,7 @@ { "cell_type": "markdown", "id": "1ed5b2a8", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "## Finding the Coefficients\n", "\n", @@ -946,9 +844,7 @@ { "cell_type": "markdown", "id": "ec8ca83d", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "\n", "
\n", @@ -966,9 +862,7 @@ { "cell_type": "markdown", "id": "9b54f9e3", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "To check the consistency of these expressions and to verify\n", "Eq. ([4](#eq:fourierdef2)), one can insert the expansion of $F(t)$ in\n", @@ -979,9 +873,7 @@ { "cell_type": "markdown", "id": "d3279bae", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "$$\n", "f_n=\\frac{2}{\\tau}\\int_{-\\tau/2}^{\\tau/2} dt~\\left\\{\\frac{f_0}{2}+\\sum_{m>0}f_m\\cos(m\\omega t)+g_m\\sin(m\\omega t)\\right\\}\\cos(n\\omega t).\n", @@ -991,9 +883,7 @@ { "cell_type": "markdown", "id": "90e25215", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "Immediately, one can throw away all the terms with $g_m$ because they\n", "convolute an even and an odd function. The term with $f_0/2$\n", @@ -1008,9 +898,7 @@ { "cell_type": "markdown", "id": "3c3ee2f3", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "\n", "
\n", @@ -1026,9 +914,7 @@ { "cell_type": "markdown", "id": "c3c2d810", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "and" ] @@ -1036,9 +922,7 @@ { "cell_type": "markdown", "id": "07669a30", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "$$\n", "f_n=\\frac{2}{\\tau}\\int_{-\\tau/2}^{\\tau/2} dt~f_n/2=f_n.\n", @@ -1048,9 +932,7 @@ { "cell_type": "markdown", "id": "38f13b44", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "The same method can be used to check for the consistency of $g_n$." ] @@ -1058,9 +940,7 @@ { "cell_type": "markdown", "id": "6dd53f79", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "## Final words on Fourier Transforms\n", "\n", @@ -1077,11 +957,19 @@ "cell_type": "code", "execution_count": 2, "id": "a963e98a", - "metadata": { - "collapsed": false, - "editable": true - }, - "outputs": [], + "metadata": {}, + "outputs": [ + { + "data": { + "image/png": "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\n", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], "source": [ "import numpy as np\n", "import math\n", @@ -1117,9 +1005,7 @@ { "cell_type": "markdown", "id": "a0937703", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "### Fourier transforms and convolution\n", "\n", @@ -1129,9 +1015,7 @@ { "cell_type": "markdown", "id": "1074ba99", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "$$\n", "\\hat{f}(y)=\\boldsymbol{F}[f(y)]=\\frac{1}{2\\pi}\\int_{-\\infty}^{\\infty} d\\omega \\exp{-i\\omega y} f(\\omega),\n", @@ -1141,9 +1025,7 @@ { "cell_type": "markdown", "id": "73471a54", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "and similarly we have" ] @@ -1151,9 +1033,7 @@ { "cell_type": "markdown", "id": "db59500e", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "$$\n", "\\hat{g}(y)=\\boldsymbol{F}[g(y)]=\\frac{1}{2\\pi}\\int_{-\\infty}^{\\infty} d\\omega \\exp{-i\\omega y} g(\\omega).\n", @@ -1163,9 +1043,7 @@ { "cell_type": "markdown", "id": "18bd1a6d", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "The inverse Fourier transform is given by" ] @@ -1173,9 +1051,7 @@ { "cell_type": "markdown", "id": "76d764c3", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "$$\n", "\\boldsymbol{F}^{-1}[g(y)]=\\frac{1}{2\\pi}\\int_{-\\infty}^{\\infty} d\\omega \\exp{i\\omega y} g(\\omega).\n", @@ -1185,9 +1061,7 @@ { "cell_type": "markdown", "id": "4433bc5a", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "The inverse Fourier transform of the product of the two functions $\\hat{f}\\hat{g}$ can be written as" ] @@ -1195,9 +1069,7 @@ { "cell_type": "markdown", "id": "fdba6cf5", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "$$\n", "\\boldsymbol{F}^{-1}[(\\hat{f}\\hat{g})(x)]=\\frac{1}{2\\pi}\\int_{-\\infty}^{\\infty} d\\omega \\exp{i\\omega x} \\hat{f}(\\omega)\\hat{g}(\\omega).\n", @@ -1207,9 +1079,7 @@ { "cell_type": "markdown", "id": "20605999", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "We can rewrite the latter as" ] @@ -1217,9 +1087,7 @@ { "cell_type": "markdown", "id": "897f9611", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "$$\n", "\\boldsymbol{F}^{-1}[(\\hat{f}\\hat{g})(x)]=\\int_{-\\infty}^{\\infty} d\\omega \\exp{i\\omega x} \\hat{f}(\\omega)\\left[\\frac{1}{2\\pi}\\int_{-\\infty}^{\\infty}g(y)dy \\exp{-i\\omega y}\\right]=\\frac{1}{2\\pi}\\int_{-\\infty}^{\\infty}dy g(y)\\int_{-\\infty}^{\\infty} d\\omega \\hat{f}(\\omega) \\exp{i\\omega(x- y)},\n", @@ -1229,9 +1097,7 @@ { "cell_type": "markdown", "id": "280297ad", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "which is simply" ] @@ -1239,9 +1105,7 @@ { "cell_type": "markdown", "id": "41207e9a", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "$$\n", "\\boldsymbol{F}^{-1}[(\\hat{f}\\hat{g})(x)]=\\int_{-\\infty}^{\\infty}dy g(y)f(x-y)=(f*g)(x),\n", @@ -1251,9 +1115,7 @@ { "cell_type": "markdown", "id": "9a65ea40", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "the convolution of the functions $f$ and $g$." ] @@ -1261,9 +1123,7 @@ { "cell_type": "markdown", "id": "f3b5a713", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "## Two-dimensional Objects\n", "\n", @@ -1276,9 +1136,7 @@ { "cell_type": "markdown", "id": "4f55453c", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "$$\n", "S_(i,j)=(I * K)(i,j) = \\sum_m\\sum_n I(m,n)K(i-m,j-n).\n", @@ -1288,9 +1146,7 @@ { "cell_type": "markdown", "id": "a67c185d", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "Convolution is a commutatitave process, which means we can rewrite this equation as" ] @@ -1298,9 +1154,7 @@ { "cell_type": "markdown", "id": "89864236", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "$$\n", "S_(i,j)=(I * K)(i,j) = \\sum_m\\sum_n I(i-m,j-n)K(m,n).\n", @@ -1310,9 +1164,7 @@ { "cell_type": "markdown", "id": "d9393c12", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "Normally the latter is more straightforward to implement in a machine larning library since there is less variation in the range of values of $m$ and $n$.\n", "\n", @@ -1322,9 +1174,7 @@ { "cell_type": "markdown", "id": "2439061d", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "$$\n", "S_(i,j)=(I * K)(i,j) = \\sum_m\\sum_n I(i+m,j+n)K(m,n).\n", @@ -1334,9 +1184,7 @@ { "cell_type": "markdown", "id": "d44d3b9e", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "## More on Dimensionalities\n", "\n", @@ -1361,9 +1209,7 @@ { "cell_type": "markdown", "id": "6cd817d4", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "$$\n", "\\mathrm{NumberParameters}=10^{10}+10^4+10^4+1 \\approx 10^{10},\n", @@ -1373,9 +1219,7 @@ { "cell_type": "markdown", "id": "a1be6e55", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "that is ten billion parameters to determine." ] @@ -1383,9 +1227,7 @@ { "cell_type": "markdown", "id": "197131f7", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "## Further Dimensionality Remarks\n", "\n", @@ -1409,9 +1251,7 @@ { "cell_type": "markdown", "id": "4131383b", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "## CNNs in more detail\n", "\n", @@ -1422,9 +1262,7 @@ { "cell_type": "markdown", "id": "7b92bf48", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "$$\n", "\\boldsymbol{I}=\\begin{bmatrix}i_{00} & i_{01} & i_{02} \\\\\n", @@ -1436,9 +1274,7 @@ { "cell_type": "markdown", "id": "5f5dee43", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "and" ] @@ -1446,9 +1282,7 @@ { "cell_type": "markdown", "id": "2c6f002d", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "$$\n", "\\boldsymbol{W}=\\begin{bmatrix}w_{00} & w_{01} \\\\\n", @@ -1459,9 +1293,7 @@ { "cell_type": "markdown", "id": "77222e3e", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "We introduce now the hyperparameter $S$ **stride**. Stride represents how the filter $W$ moves the convolution process on the matrix $I$.\n", "We strongly recommend the repository on [Arithmetic of deep learning by Dumoulin and Visin](https://github.com/vdumoulin/conv_arithmetic) \n", @@ -1474,9 +1306,7 @@ { "cell_type": "markdown", "id": "b573519f", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "$$\n", "S_(i,j)=(I * W)(i,j) = \\sum_m\\sum_n I(i-m,j-n)W(m,n),\n", @@ -1486,9 +1316,7 @@ { "cell_type": "markdown", "id": "44d9b70a", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "and obtain" ] @@ -1496,9 +1324,7 @@ { "cell_type": "markdown", "id": "f6f6c2a9", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "$$\n", "\\boldsymbol{S}=\\begin{bmatrix}i_{00}w_{00}+i_{01}w_{01}+i_{10}w_{10}+i_{11}w_{11} & i_{01}w_{00}+i_{02}w_{01}+i_{11}w_{10}+i_{12}w_{11} \\\\\n", @@ -1509,9 +1335,7 @@ { "cell_type": "markdown", "id": "6f02029e", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "We can rewrite this operation in terms of a matrix-vector multiplication by defining a new vector where we flatten out the inputs as a vector $\\boldsymbol{I}'$ of length $9$ and\n", "a matrix $\\boldsymbol{W}'$ with dimension $4\\times 9$ as" @@ -1520,9 +1344,7 @@ { "cell_type": "markdown", "id": "9aee3566", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "$$\n", "\\boldsymbol{I}'=\\begin{bmatrix}i_{00} \\\\ i_{01} \\\\ i_{02} \\\\ i_{10} \\\\ i_{11} \\\\ i_{12} \\\\ i_{20} \\\\ i_{21} \\\\ i_{22} \\end{bmatrix},\n", @@ -1532,9 +1354,7 @@ { "cell_type": "markdown", "id": "c6e48b06", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "and the new matrix" ] @@ -1542,9 +1362,7 @@ { "cell_type": "markdown", "id": "2d94c116", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "$$\n", "\\boldsymbol{W}'=\\begin{bmatrix} w_{00} & w_{01} & 0 & w_{10} & w_{11} & 0 & 0 & 0 & 0 \\\\\n", @@ -1557,9 +1375,7 @@ { "cell_type": "markdown", "id": "928af442", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "We see easily that performing the matrix-vector multiplication $\\boldsymbol{W}'\\boldsymbol{I}'$ is the same as the above convolution with stride $S=1$, that is" ] @@ -1567,9 +1383,7 @@ { "cell_type": "markdown", "id": "8821a09b", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "$$\n", "S=(\\boldsymbol{W}*\\boldsymbol{I}),\n", @@ -1579,9 +1393,7 @@ { "cell_type": "markdown", "id": "731fee27", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "is now given by $\\boldsymbol{W}'\\boldsymbol{I}'$ which is a vector of length $4$ instead of the originally resulting $2\\times 2$ output matrix.\n", "\n", @@ -1592,9 +1404,7 @@ { "cell_type": "markdown", "id": "16d8c94a", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "$$\n", "\\begin{split}\n", @@ -1608,9 +1418,7 @@ { "cell_type": "markdown", "id": "185e7843", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "The following properties affect the output size $o_j$ of a convolutional layer\n", "along axis $j$:\n", @@ -1636,9 +1444,7 @@ { "cell_type": "markdown", "id": "7c2d4cf7", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "## Pooling\n", "\n", @@ -1686,9 +1492,7 @@ { "cell_type": "markdown", "id": "81697a8c", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "## No zero padding, unit strides\n", "\n", @@ -1701,9 +1505,7 @@ { "cell_type": "markdown", "id": "0c95a9ae", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "$$\n", "o = (i - k) + 1.\n", @@ -1713,9 +1515,7 @@ { "cell_type": "markdown", "id": "9b84745b", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "## Zero padding, unit strides\n", "\n", @@ -1730,9 +1530,7 @@ { "cell_type": "markdown", "id": "59aec9c5", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "$$\n", "o = (i - k) + 2p + 1.\n", @@ -1742,9 +1540,7 @@ { "cell_type": "markdown", "id": "e864b8dc", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "## Half (same) padding\n", "\n", @@ -1758,9 +1554,7 @@ { "cell_type": "markdown", "id": "a89692e0", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "$$\n", "\\begin{split}\n", @@ -1774,9 +1568,7 @@ { "cell_type": "markdown", "id": "b0883462", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "## Full padding\n", "\n", @@ -1790,9 +1582,7 @@ { "cell_type": "markdown", "id": "e9e8ab25", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "$$\n", "\\begin{split}\n", @@ -1805,9 +1595,7 @@ { "cell_type": "markdown", "id": "a960733b", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "This is sometimes referred to as full padding, because in this\n", "setting every possible partial or complete superimposition of the kernel on the\n", @@ -1817,9 +1605,7 @@ { "cell_type": "markdown", "id": "2bfd64a6", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "## Pooling arithmetic\n", "\n", @@ -1839,9 +1625,7 @@ { "cell_type": "markdown", "id": "6fa0d5ac", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "$$\n", "o = \\left\\lfloor \\frac{i - k}{s} \\right\\rfloor + 1.\n", @@ -1851,9 +1635,7 @@ { "cell_type": "markdown", "id": "6dfa0405", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "## CNNs in more detail, building convolutional neural networks in Tensorflow and Keras\n", "\n", @@ -1870,9 +1652,7 @@ { "cell_type": "markdown", "id": "b1bd03a6", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "## Setting it up\n", "\n", @@ -1883,9 +1663,7 @@ { "cell_type": "markdown", "id": "ddaf7697", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "$$\n", "(n_{inputs},\\, n_{pixels, width},\\, n_{pixels, height},\\, depth) .\n", @@ -1895,9 +1673,7 @@ { "cell_type": "markdown", "id": "e2036553", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "## The MNIST dataset again\n", "\n", @@ -1916,9 +1692,7 @@ { "cell_type": "markdown", "id": "2d512a4e", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "## Strong correlations\n", "\n", @@ -1937,9 +1711,7 @@ { "cell_type": "markdown", "id": "1137479b", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "## Layers of a CNN\n", "The layers of a convolutional neural network arrange neurons in 3D: width, height and depth. \n", @@ -1962,9 +1734,7 @@ { "cell_type": "markdown", "id": "376a654c", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "## Systematic reduction\n", "\n", @@ -1981,9 +1751,7 @@ { "cell_type": "markdown", "id": "8caa6a7c", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "## Prerequisites: Collect and pre-process data" ] @@ -1992,11 +1760,27 @@ "cell_type": "code", "execution_count": 3, "id": "524435a0", - "metadata": { - "collapsed": false, - "editable": true - }, - "outputs": [], + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "inputs = (n_inputs, pixel_width, pixel_height, depth) = (1797, 8, 8, 1)\n", + "labels = (n_inputs) = (1797,)\n" + ] + }, + { + "data": { + "image/png": "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\n", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], "source": [ "# import necessary packages\n", "import numpy as np\n", @@ -2043,9 +1827,7 @@ { "cell_type": "markdown", "id": "843d44ab", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "## Importing Keras and Tensorflow" ] @@ -2054,10 +1836,7 @@ "cell_type": "code", "execution_count": 4, "id": "7336b32c", - "metadata": { - "collapsed": false, - "editable": true - }, + "metadata": {}, "outputs": [], "source": [ "from tensorflow.keras import datasets, layers, models\n", @@ -2087,9 +1866,7 @@ { "cell_type": "markdown", "id": "bcfbe707", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "## Running with Keras" ] @@ -2098,10 +1875,7 @@ "cell_type": "code", "execution_count": 5, "id": "ad322da4", - "metadata": { - "collapsed": false, - "editable": true - }, + "metadata": {}, "outputs": [], "source": [ "def create_convolutional_neural_network_keras(input_shape, receptive_field,\n", @@ -2135,9 +1909,7 @@ { "cell_type": "markdown", "id": "8cf26231", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "## Final part" ] @@ -2146,11 +1918,276 @@ "cell_type": "code", "execution_count": 6, "id": "008c88b7", - "metadata": { - "collapsed": false, - "editable": true - }, - "outputs": [], + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Metal device set to: Apple M1\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/Users/mhjensen/miniforge3/envs/myenv/lib/python3.9/site-packages/keras/optimizer_v2/gradient_descent.py:102: UserWarning: The `lr` argument is deprecated, use `learning_rate` instead.\n", + " super(SGD, self).__init__(name, **kwargs)\n", + "2023-12-18 07:44:46.909176: W tensorflow/core/platform/profile_utils/cpu_utils.cc:128] Failed to get CPU frequency: 0 Hz\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "12/12 [==============================] - 0s 13ms/step - loss: 3.4427 - accuracy: 0.1194\n", + "Learning rate = 1e-05\n", + "Lambda = 1e-05\n", + "Test accuracy: 0.119\n", + "\n", + "12/12 [==============================] - 0s 12ms/step - loss: 3.4532 - accuracy: 0.1194\n", + "Learning rate = 1e-05\n", + "Lambda = 0.0001\n", + "Test accuracy: 0.119\n", + "\n", + "12/12 [==============================] - 0s 12ms/step - loss: 3.5386 - accuracy: 0.1194\n", + "Learning rate = 1e-05\n", + "Lambda = 0.001\n", + "Test accuracy: 0.119\n", + "\n", + "12/12 [==============================] - 0s 13ms/step - loss: 4.3984 - accuracy: 0.1194\n", + "Learning rate = 1e-05\n", + "Lambda = 0.01\n", + "Test accuracy: 0.119\n", + "\n", + "12/12 [==============================] - 0s 14ms/step - loss: 12.9401 - accuracy: 0.1194\n", + "Learning rate = 1e-05\n", + "Lambda = 0.1\n", + "Test accuracy: 0.119\n", + "\n", + "12/12 [==============================] - 0s 14ms/step - loss: 93.4274 - accuracy: 0.1194\n", + "Learning rate = 1e-05\n", + "Lambda = 1.0\n", + "Test accuracy: 0.119\n", + "\n", + "12/12 [==============================] - 1s 18ms/step - loss: 528.0518 - accuracy: 0.1139\n", + "Learning rate = 1e-05\n", + "Lambda = 10.0\n", + "Test accuracy: 0.114\n", + "\n", + "12/12 [==============================] - 0s 18ms/step - loss: 1.1928 - accuracy: 0.6306\n", + "Learning rate = 0.0001\n", + "Lambda = 1e-05\n", + "Test accuracy: 0.631\n", + "\n", + "12/12 [==============================] - 0s 19ms/step - loss: 1.2010 - accuracy: 0.6278\n", + "Learning rate = 0.0001\n", + "Lambda = 0.0001\n", + "Test accuracy: 0.628\n", + "\n", + "12/12 [==============================] - 0s 18ms/step - loss: 1.2893 - accuracy: 0.6333\n", + "Learning rate = 0.0001\n", + "Lambda = 0.001\n", + "Test accuracy: 0.633\n", + "\n", + "12/12 [==============================] - 0s 16ms/step - loss: 2.1458 - accuracy: 0.6333\n", + "Learning rate = 0.0001\n", + "Lambda = 0.01\n", + "Test accuracy: 0.633\n", + "\n", + "12/12 [==============================] - 0s 17ms/step - loss: 10.2151 - accuracy: 0.6333\n", + "Learning rate = 0.0001\n", + "Lambda = 0.1\n", + "Test accuracy: 0.633\n", + "\n", + "12/12 [==============================] - 0s 17ms/step - loss: 54.1239 - accuracy: 0.6278\n", + "Learning rate = 0.0001\n", + "Lambda = 1.0\n", + "Test accuracy: 0.628\n", + "\n", + "12/12 [==============================] - 0s 18ms/step - loss: 4.6629 - accuracy: 0.0889\n", + "Learning rate = 0.0001\n", + "Lambda = 10.0\n", + "Test accuracy: 0.089\n", + "\n", + "12/12 [==============================] - 0s 20ms/step - loss: 0.2087 - accuracy: 0.9361\n", + "Learning rate = 0.001\n", + "Lambda = 1e-05\n", + "Test accuracy: 0.936\n", + "\n", + "12/12 [==============================] - 0s 18ms/step - loss: 0.2305 - accuracy: 0.9361\n", + "Learning rate = 0.001\n", + "Lambda = 0.0001\n", + "Test accuracy: 0.936\n", + "\n", + "12/12 [==============================] - 0s 17ms/step - loss: 0.3050 - accuracy: 0.9389\n", + "Learning rate = 0.001\n", + "Lambda = 0.001\n", + "Test accuracy: 0.939\n", + "\n", + "12/12 [==============================] - 0s 17ms/step - loss: 1.1320 - accuracy: 0.9333\n", + "Learning rate = 0.001\n", + "Lambda = 0.01\n", + "Test accuracy: 0.933\n", + "\n", + "12/12 [==============================] - 0s 19ms/step - loss: 5.7910 - accuracy: 0.9278\n", + "Learning rate = 0.001\n", + "Lambda = 0.1\n", + "Test accuracy: 0.928\n", + "\n", + "12/12 [==============================] - 1s 17ms/step - loss: 2.6616 - accuracy: 0.6333\n", + "Learning rate = 0.001\n", + "Lambda = 1.0\n", + "Test accuracy: 0.633\n", + "\n", + "12/12 [==============================] - 0s 18ms/step - loss: 2.3032 - accuracy: 0.0889\n", + "Learning rate = 0.001\n", + "Lambda = 10.0\n", + "Test accuracy: 0.089\n", + "\n", + "12/12 [==============================] - 0s 22ms/step - loss: 0.0632 - accuracy: 0.9806\n", + "Learning rate = 0.01\n", + "Lambda = 1e-05\n", + "Test accuracy: 0.981\n", + "\n", + "12/12 [==============================] - 0s 23ms/step - loss: 0.0723 - accuracy: 0.9750\n", + "Learning rate = 0.01\n", + "Lambda = 0.0001\n", + "Test accuracy: 0.975\n", + "\n", + "12/12 [==============================] - 0s 24ms/step - loss: 0.1600 - accuracy: 0.9833\n", + "Learning rate = 0.01\n", + "Lambda = 0.001\n", + "Test accuracy: 0.983\n", + "\n", + "12/12 [==============================] - 0s 23ms/step - loss: 0.6691 - accuracy: 0.9861\n", + "Learning rate = 0.01\n", + "Lambda = 0.01\n", + "Test accuracy: 0.986\n", + "\n", + "12/12 [==============================] - 1s 28ms/step - loss: 0.9318 - accuracy: 0.9528\n", + "Learning rate = 0.01\n", + "Lambda = 0.1\n", + "Test accuracy: 0.953\n", + "\n", + "12/12 [==============================] - 1s 26ms/step - loss: 2.3063 - accuracy: 0.0889\n", + "Learning rate = 0.01\n", + "Lambda = 1.0\n", + "Test accuracy: 0.089\n", + "\n", + "12/12 [==============================] - 0s 22ms/step - loss: 2.3064 - accuracy: 0.0778\n", + "Learning rate = 0.01\n", + "Lambda = 10.0\n", + "Test accuracy: 0.078\n", + "\n", + "12/12 [==============================] - 0s 21ms/step - loss: 0.2576 - accuracy: 0.9528\n", + "Learning rate = 0.1\n", + "Lambda = 1e-05\n", + "Test accuracy: 0.953\n", + "\n", + "12/12 [==============================] - 0s 21ms/step - loss: 0.1659 - accuracy: 0.9472\n", + "Learning rate = 0.1\n", + "Lambda = 0.0001\n", + "Test accuracy: 0.947\n", + "\n", + "12/12 [==============================] - 0s 21ms/step - loss: 0.2022 - accuracy: 0.9722\n", + "Learning rate = 0.1\n", + "Lambda = 0.001\n", + "Test accuracy: 0.972\n", + "\n", + "12/12 [==============================] - 0s 21ms/step - loss: 0.3663 - accuracy: 0.9500\n", + "Learning rate = 0.1\n", + "Lambda = 0.01\n", + "Test accuracy: 0.950\n", + "\n", + "12/12 [==============================] - 0s 21ms/step - loss: 2.3088 - accuracy: 0.0889\n", + "Learning rate = 0.1\n", + "Lambda = 0.1\n", + "Test accuracy: 0.089\n", + "\n", + "12/12 [==============================] - 0s 20ms/step - loss: 2.3082 - accuracy: 0.0778\n", + "Learning rate = 0.1\n", + "Lambda = 1.0\n", + "Test accuracy: 0.078\n", + "\n", + "12/12 [==============================] - 0s 20ms/step - loss: nan - accuracy: 0.0778\n", + "Learning rate = 0.1\n", + "Lambda = 10.0\n", + "Test accuracy: 0.078\n", + "\n", + "12/12 [==============================] - 0s 21ms/step - loss: 61.1328 - accuracy: 0.0889\n", + "Learning rate = 1.0\n", + "Lambda = 1e-05\n", + "Test accuracy: 0.089\n", + "\n", + "12/12 [==============================] - 0s 20ms/step - loss: 235.3527 - accuracy: 0.0889\n", + "Learning rate = 1.0\n", + "Lambda = 0.0001\n", + "Test accuracy: 0.089\n", + "\n", + "12/12 [==============================] - 1s 26ms/step - loss: 14.3476 - accuracy: 0.0889\n", + "Learning rate = 1.0\n", + "Lambda = 0.001\n", + "Test accuracy: 0.089\n", + "\n", + "12/12 [==============================] - 1s 22ms/step - loss: 2.3107 - accuracy: 0.0889\n", + "Learning rate = 1.0\n", + "Lambda = 0.01\n", + "Test accuracy: 0.089\n", + "\n", + "12/12 [==============================] - 1s 23ms/step - loss: 2.3077 - accuracy: 0.0889\n", + "Learning rate = 1.0\n", + "Lambda = 0.1\n", + "Test accuracy: 0.089\n", + "\n", + "12/12 [==============================] - 1s 30ms/step - loss: nan - accuracy: 0.0778\n", + "Learning rate = 1.0\n", + "Lambda = 1.0\n", + "Test accuracy: 0.078\n", + "\n", + "12/12 [==============================] - 1s 23ms/step - loss: nan - accuracy: 0.0778\n", + "Learning rate = 1.0\n", + "Lambda = 10.0\n", + "Test accuracy: 0.078\n", + "\n", + "12/12 [==============================] - 1s 27ms/step - loss: 24263728.0000 - accuracy: 0.0889\n", + "Learning rate = 10.0\n", + "Lambda = 1e-05\n", + "Test accuracy: 0.089\n", + "\n", + "12/12 [==============================] - 1s 26ms/step - loss: 1520352.1250 - accuracy: 0.0889\n", + "Learning rate = 10.0\n", + "Lambda = 0.0001\n", + "Test accuracy: 0.089\n", + "\n", + "12/12 [==============================] - 1s 29ms/step - loss: 2.4657 - accuracy: 0.0861\n", + "Learning rate = 10.0\n", + "Lambda = 0.001\n", + "Test accuracy: 0.086\n", + "\n", + "12/12 [==============================] - 1s 27ms/step - loss: 2.3695 - accuracy: 0.1056\n", + "Learning rate = 10.0\n", + "Lambda = 0.01\n", + "Test accuracy: 0.106\n", + "\n", + "12/12 [==============================] - 1s 30ms/step - loss: nan - accuracy: 0.0778\n", + "Learning rate = 10.0\n", + "Lambda = 0.1\n", + "Test accuracy: 0.078\n", + "\n", + "12/12 [==============================] - 1s 29ms/step - loss: nan - accuracy: 0.0778\n", + "Learning rate = 10.0\n", + "Lambda = 1.0\n", + "Test accuracy: 0.078\n", + "\n", + "12/12 [==============================] - 1s 30ms/step - loss: nan - accuracy: 0.0778\n", + "Learning rate = 10.0\n", + "Lambda = 10.0\n", + "Test accuracy: 0.078\n", + "\n" + ] + } + ], "source": [ "CNN_keras = np.zeros((len(eta_vals), len(lmbd_vals)), dtype=object)\n", " \n", @@ -2173,9 +2210,7 @@ { "cell_type": "markdown", "id": "2a7457d0", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "## Final visualization" ] @@ -2184,11 +2219,139 @@ "cell_type": "code", "execution_count": 7, "id": "a64c8a37", - "metadata": { - "collapsed": false, - "editable": true - }, - "outputs": [], + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "45/45 [==============================] - 1s 18ms/step - loss: 3.5461 - accuracy: 0.1086\n", + "12/12 [==============================] - 0s 15ms/step - loss: 3.4427 - accuracy: 0.1194\n", + "45/45 [==============================] - 1s 17ms/step - loss: 3.5563 - accuracy: 0.1086\n", + "12/12 [==============================] - 0s 15ms/step - loss: 3.4532 - accuracy: 0.1194\n", + "45/45 [==============================] - 1s 18ms/step - loss: 3.6421 - accuracy: 0.1086\n", + "12/12 [==============================] - 0s 15ms/step - loss: 3.5386 - accuracy: 0.1194\n", + "45/45 [==============================] - 1s 18ms/step - loss: 4.5017 - accuracy: 0.1086\n", + "12/12 [==============================] - 0s 16ms/step - loss: 4.3984 - accuracy: 0.1194\n", + "45/45 [==============================] - 1s 18ms/step - loss: 13.0427 - accuracy: 0.1086\n", + "12/12 [==============================] - 0s 16ms/step - loss: 12.9401 - accuracy: 0.1194\n", + "45/45 [==============================] - 1s 18ms/step - loss: 93.5225 - accuracy: 0.1051\n", + "12/12 [==============================] - 0s 15ms/step - loss: 93.4274 - accuracy: 0.1194\n", + "45/45 [==============================] - 1s 18ms/step - loss: 528.0969 - accuracy: 0.0946\n", + "12/12 [==============================] - 0s 16ms/step - loss: 528.0518 - accuracy: 0.1139\n", + "45/45 [==============================] - 1s 18ms/step - loss: 1.0985 - accuracy: 0.6778\n", + "12/12 [==============================] - 0s 15ms/step - loss: 1.1928 - accuracy: 0.6306\n", + "45/45 [==============================] - 1s 18ms/step - loss: 1.1075 - accuracy: 0.6806\n", + "12/12 [==============================] - 0s 16ms/step - loss: 1.2010 - accuracy: 0.6278\n", + "45/45 [==============================] - 1s 18ms/step - loss: 1.1963 - accuracy: 0.6771\n", + "12/12 [==============================] - 0s 15ms/step - loss: 1.2893 - accuracy: 0.6333\n", + "45/45 [==============================] - 1s 18ms/step - loss: 2.0512 - accuracy: 0.6757\n", + "12/12 [==============================] - 0s 16ms/step - loss: 2.1458 - accuracy: 0.6333\n", + "45/45 [==============================] - 1s 18ms/step - loss: 10.1260 - accuracy: 0.6743\n", + "12/12 [==============================] - 0s 15ms/step - loss: 10.2151 - accuracy: 0.6333\n", + "45/45 [==============================] - 1s 17ms/step - loss: 54.0709 - accuracy: 0.6597\n", + "12/12 [==============================] - 0s 15ms/step - loss: 54.1239 - accuracy: 0.6278\n", + "45/45 [==============================] - 1s 17ms/step - loss: 4.6627 - accuracy: 0.1044\n", + "12/12 [==============================] - 0s 16ms/step - loss: 4.6629 - accuracy: 0.0889\n", + "45/45 [==============================] - 1s 18ms/step - loss: 0.1533 - accuracy: 0.9631\n", + "12/12 [==============================] - 0s 16ms/step - loss: 0.2087 - accuracy: 0.9361\n", + "45/45 [==============================] - 1s 18ms/step - loss: 0.1647 - accuracy: 0.9624\n", + "12/12 [==============================] - 0s 16ms/step - loss: 0.2305 - accuracy: 0.9361\n", + "45/45 [==============================] - 1s 18ms/step - loss: 0.2489 - accuracy: 0.9652\n", + "12/12 [==============================] - 0s 15ms/step - loss: 0.3050 - accuracy: 0.9389\n", + "45/45 [==============================] - 1s 18ms/step - loss: 1.0795 - accuracy: 0.9624\n", + "12/12 [==============================] - 0s 16ms/step - loss: 1.1320 - accuracy: 0.9333\n", + "45/45 [==============================] - 1s 18ms/step - loss: 5.7283 - accuracy: 0.9548\n", + "12/12 [==============================] - 0s 15ms/step - loss: 5.7910 - accuracy: 0.9278\n", + "45/45 [==============================] - 1s 17ms/step - loss: 2.6596 - accuracy: 0.6792\n", + "12/12 [==============================] - 0s 16ms/step - loss: 2.6616 - accuracy: 0.6333\n", + "45/45 [==============================] - 1s 18ms/step - loss: 2.3024 - accuracy: 0.1044\n", + "12/12 [==============================] - 0s 16ms/step - loss: 2.3032 - accuracy: 0.0889\n", + "45/45 [==============================] - 1s 19ms/step - loss: 0.0122 - accuracy: 1.0000\n", + "12/12 [==============================] - 0s 16ms/step - loss: 0.0632 - accuracy: 0.9806\n", + "45/45 [==============================] - 1s 18ms/step - loss: 0.0213 - accuracy: 1.0000\n", + "12/12 [==============================] - 0s 16ms/step - loss: 0.0723 - accuracy: 0.9750\n", + "45/45 [==============================] - 1s 18ms/step - loss: 0.1137 - accuracy: 0.9986\n", + "12/12 [==============================] - 0s 16ms/step - loss: 0.1600 - accuracy: 0.9833\n", + "45/45 [==============================] - 1s 18ms/step - loss: 0.6319 - accuracy: 0.9951\n", + "12/12 [==============================] - 0s 16ms/step - loss: 0.6691 - accuracy: 0.9861\n", + "45/45 [==============================] - 1s 18ms/step - loss: 0.8919 - accuracy: 0.9652\n", + "12/12 [==============================] - 0s 16ms/step - loss: 0.9318 - accuracy: 0.9528\n", + "45/45 [==============================] - 1s 17ms/step - loss: 2.3020 - accuracy: 0.1044\n", + "12/12 [==============================] - 0s 15ms/step - loss: 2.3063 - accuracy: 0.0889\n", + "45/45 [==============================] - 1s 17ms/step - loss: 2.3020 - accuracy: 0.1044\n", + "12/12 [==============================] - 0s 16ms/step - loss: 2.3064 - accuracy: 0.0778\n", + "45/45 [==============================] - 1s 17ms/step - loss: 0.0045 - accuracy: 1.0000\n", + "12/12 [==============================] - 0s 16ms/step - loss: 0.2576 - accuracy: 0.9528\n", + "45/45 [==============================] - 1s 18ms/step - loss: 0.0480 - accuracy: 0.9930\n", + "12/12 [==============================] - 0s 15ms/step - loss: 0.1659 - accuracy: 0.9472\n", + "45/45 [==============================] - 1s 17ms/step - loss: 0.1039 - accuracy: 1.0000\n", + "12/12 [==============================] - 0s 15ms/step - loss: 0.2022 - accuracy: 0.9722\n", + "45/45 [==============================] - 1s 18ms/step - loss: 0.2698 - accuracy: 0.9868\n", + "12/12 [==============================] - 0s 16ms/step - loss: 0.3663 - accuracy: 0.9500\n", + "45/45 [==============================] - 1s 17ms/step - loss: 2.3020 - accuracy: 0.1044\n", + "12/12 [==============================] - 0s 16ms/step - loss: 2.3088 - accuracy: 0.0889\n", + "45/45 [==============================] - 1s 17ms/step - loss: 2.3020 - accuracy: 0.1044\n", + "12/12 [==============================] - 0s 15ms/step - loss: 2.3082 - accuracy: 0.0778\n", + "45/45 [==============================] - 1s 17ms/step - loss: nan - accuracy: 0.1044\n", + "12/12 [==============================] - 0s 16ms/step - loss: nan - accuracy: 0.0778\n", + "45/45 [==============================] - 1s 17ms/step - loss: 61.1235 - accuracy: 0.1044\n", + "12/12 [==============================] - 0s 16ms/step - loss: 61.1328 - accuracy: 0.0889\n", + "45/45 [==============================] - 1s 18ms/step - loss: 235.3435 - accuracy: 0.1044\n", + "12/12 [==============================] - 0s 16ms/step - loss: 235.3527 - accuracy: 0.0889\n", + "45/45 [==============================] - 1s 18ms/step - loss: 14.3389 - accuracy: 0.1037\n", + "12/12 [==============================] - 0s 16ms/step - loss: 14.3476 - accuracy: 0.0889\n", + "45/45 [==============================] - 1s 18ms/step - loss: 2.3042 - accuracy: 0.1037\n", + "12/12 [==============================] - 0s 16ms/step - loss: 2.3107 - accuracy: 0.0889\n", + "45/45 [==============================] - 1s 17ms/step - loss: 2.3025 - accuracy: 0.1044\n", + "12/12 [==============================] - 0s 16ms/step - loss: 2.3077 - accuracy: 0.0889\n", + "45/45 [==============================] - 1s 17ms/step - loss: nan - accuracy: 0.1044\n", + "12/12 [==============================] - 0s 16ms/step - loss: nan - accuracy: 0.0778\n", + "45/45 [==============================] - 1s 17ms/step - loss: nan - accuracy: 0.1044\n", + "12/12 [==============================] - 0s 17ms/step - loss: nan - accuracy: 0.0778\n", + "45/45 [==============================] - 1s 17ms/step - loss: 24263740.0000 - accuracy: 0.1044\n", + "12/12 [==============================] - 0s 15ms/step - loss: 24263728.0000 - accuracy: 0.0889\n", + "45/45 [==============================] - 1s 18ms/step - loss: 1520352.1250 - accuracy: 0.1037\n", + "12/12 [==============================] - 0s 17ms/step - loss: 1520352.1250 - accuracy: 0.0889\n", + "45/45 [==============================] - 1s 18ms/step - loss: 2.4219 - accuracy: 0.0995\n", + "12/12 [==============================] - 0s 16ms/step - loss: 2.4657 - accuracy: 0.0861\n", + "45/45 [==============================] - 1s 19ms/step - loss: 2.3568 - accuracy: 0.1009\n", + "12/12 [==============================] - 0s 16ms/step - loss: 2.3695 - accuracy: 0.1056\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "45/45 [==============================] - 1s 18ms/step - loss: nan - accuracy: 0.1044\n", + "12/12 [==============================] - 0s 16ms/step - loss: nan - accuracy: 0.0778\n", + "45/45 [==============================] - 1s 17ms/step - loss: nan - accuracy: 0.1044\n", + "12/12 [==============================] - 0s 16ms/step - loss: nan - accuracy: 0.0778\n", + "45/45 [==============================] - 1s 18ms/step - loss: nan - accuracy: 0.1044\n", + "12/12 [==============================] - 0s 16ms/step - loss: nan - accuracy: 0.0778\n" + ] + }, + { + "data": { + "image/png": "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\n", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "image/png": "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\n", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], "source": [ "# visual representation of grid search\n", "# uses seaborn heatmap, could probably do this in matplotlib\n", @@ -2225,9 +2388,7 @@ { "cell_type": "markdown", "id": "d067c17f", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "## The CIFAR01 data set\n", "\n", @@ -2241,14 +2402,11 @@ "cell_type": "code", "execution_count": 8, "id": "e386cae7", - "metadata": { - "collapsed": false, - "editable": true - }, + "metadata": {}, "outputs": [], "source": [ "import tensorflow as tf\n", - "\n", + "import matplotlib.pyplot as plt\n", "from tensorflow.keras import datasets, layers, models\n", "import matplotlib.pyplot as plt\n", "\n", @@ -2262,9 +2420,7 @@ { "cell_type": "markdown", "id": "c466399c", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "## Verifying the data set\n", "\n", @@ -2275,15 +2431,23 @@ "cell_type": "code", "execution_count": 9, "id": "2095b9fc", - "metadata": { - "collapsed": false, - "editable": true - }, - "outputs": [], + "metadata": {}, + "outputs": [ + { + "data": { + "image/png": "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\n", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], "source": [ "class_names = ['airplane', 'automobile', 'bird', 'cat', 'deer',\n", " 'dog', 'frog', 'horse', 'ship', 'truck']\n", - "​\n", + "\n", "plt.figure(figsize=(10,10))\n", "for i in range(25):\n", " plt.subplot(5,5,i+1)\n", @@ -2300,9 +2464,7 @@ { "cell_type": "markdown", "id": "3b78d7e7", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "## Set up the model\n", "\n", @@ -2315,11 +2477,36 @@ "cell_type": "code", "execution_count": 10, "id": "4c64c00e", - "metadata": { - "collapsed": false, - "editable": true - }, - "outputs": [], + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Model: \"sequential_49\"\n", + "_________________________________________________________________\n", + " Layer (type) Output Shape Param # \n", + "=================================================================\n", + " conv2d_49 (Conv2D) (None, 30, 30, 32) 896 \n", + " \n", + " max_pooling2d_49 (MaxPoolin (None, 15, 15, 32) 0 \n", + " g2D) \n", + " \n", + " conv2d_50 (Conv2D) (None, 13, 13, 64) 18496 \n", + " \n", + " max_pooling2d_50 (MaxPoolin (None, 6, 6, 64) 0 \n", + " g2D) \n", + " \n", + " conv2d_51 (Conv2D) (None, 4, 4, 64) 36928 \n", + " \n", + "=================================================================\n", + "Total params: 56,320\n", + "Trainable params: 56,320\n", + "Non-trainable params: 0\n", + "_________________________________________________________________\n" + ] + } + ], "source": [ "model = models.Sequential()\n", "model.add(layers.Conv2D(32, (3, 3), activation='relu', input_shape=(32, 32, 3)))\n", @@ -2336,9 +2523,7 @@ { "cell_type": "markdown", "id": "dd841de3", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "You can see that the output of every Conv2D and MaxPooling2D layer is a 3D tensor of shape (height, width, channels). The width and height dimensions tend to shrink as you go deeper in the network. The number of output channels for each Conv2D layer is controlled by the first argument (e.g., 32 or 64). Typically, as the width and height shrink, you can afford (computationally) to add more output channels in each Conv2D layer." ] @@ -2346,9 +2531,7 @@ { "cell_type": "markdown", "id": "1ebfaeb2", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "## Add Dense layers on top\n", "\n", @@ -2363,18 +2546,49 @@ }, { "cell_type": "code", - "execution_count": 11, + "execution_count": 12, "id": "103d280c", - "metadata": { - "collapsed": false, - "editable": true - }, - "outputs": [], + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Model: \"sequential_49\"\n", + "_________________________________________________________________\n", + " Layer (type) Output Shape Param # \n", + "=================================================================\n", + " conv2d_49 (Conv2D) (None, 30, 30, 32) 896 \n", + " \n", + " max_pooling2d_49 (MaxPoolin (None, 15, 15, 32) 0 \n", + " g2D) \n", + " \n", + " conv2d_50 (Conv2D) (None, 13, 13, 64) 18496 \n", + " \n", + " max_pooling2d_50 (MaxPoolin (None, 6, 6, 64) 0 \n", + " g2D) \n", + " \n", + " conv2d_51 (Conv2D) (None, 4, 4, 64) 36928 \n", + " \n", + " flatten_49 (Flatten) (None, 1024) 0 \n", + " \n", + " dense_98 (Dense) (None, 64) 65600 \n", + " \n", + " dense_99 (Dense) (None, 10) 650 \n", + " \n", + "=================================================================\n", + "Total params: 122,570\n", + "Trainable params: 122,570\n", + "Non-trainable params: 0\n", + "_________________________________________________________________\n" + ] + } + ], "source": [ "model.add(layers.Flatten())\n", "model.add(layers.Dense(64, activation='relu'))\n", "model.add(layers.Dense(10))\n", - "Here's the complete architecture of our model.\n", + "#Here's the complete architecture of our model.\n", "\n", "model.summary()" ] @@ -2382,9 +2596,7 @@ { "cell_type": "markdown", "id": "422f3176", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "As you can see, our (4, 4, 64) outputs were flattened into vectors of shape (1024) before going through two Dense layers." ] @@ -2392,27 +2604,49 @@ { "cell_type": "markdown", "id": "0182ff20", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "## Compile and train the model" ] }, { "cell_type": "code", - "execution_count": 12, + "execution_count": 13, "id": "04a6b37c", - "metadata": { - "collapsed": false, - "editable": true - }, - "outputs": [], + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Epoch 1/10\n", + "1563/1563 [==============================] - 28s 16ms/step - loss: 1.5513 - accuracy: 0.4312 - val_loss: 1.2810 - val_accuracy: 0.5345\n", + "Epoch 2/10\n", + "1563/1563 [==============================] - 25s 16ms/step - loss: 1.1772 - accuracy: 0.5793 - val_loss: 1.1010 - val_accuracy: 0.6109\n", + "Epoch 3/10\n", + "1563/1563 [==============================] - 24s 15ms/step - loss: 1.0265 - accuracy: 0.6384 - val_loss: 0.9898 - val_accuracy: 0.6476\n", + "Epoch 4/10\n", + "1563/1563 [==============================] - 21s 13ms/step - loss: 0.9308 - accuracy: 0.6709 - val_loss: 0.9328 - val_accuracy: 0.6758\n", + "Epoch 5/10\n", + "1563/1563 [==============================] - 21s 13ms/step - loss: 0.8669 - accuracy: 0.6962 - val_loss: 0.9152 - val_accuracy: 0.6791\n", + "Epoch 6/10\n", + "1563/1563 [==============================] - 21s 13ms/step - loss: 0.8167 - accuracy: 0.7154 - val_loss: 0.9360 - val_accuracy: 0.6754\n", + "Epoch 7/10\n", + "1563/1563 [==============================] - 20s 13ms/step - loss: 0.7703 - accuracy: 0.7279 - val_loss: 0.8678 - val_accuracy: 0.6973\n", + "Epoch 8/10\n", + "1563/1563 [==============================] - 22s 14ms/step - loss: 0.7220 - accuracy: 0.7455 - val_loss: 0.8853 - val_accuracy: 0.7000\n", + "Epoch 9/10\n", + "1563/1563 [==============================] - 21s 13ms/step - loss: 0.6873 - accuracy: 0.7572 - val_loss: 0.8889 - val_accuracy: 0.7026\n", + "Epoch 10/10\n", + "1563/1563 [==============================] - 21s 14ms/step - loss: 0.6460 - accuracy: 0.7729 - val_loss: 0.8414 - val_accuracy: 0.7182\n" + ] + } + ], "source": [ "model.compile(optimizer='adam',\n", " loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True),\n", " metrics=['accuracy'])\n", - "​\n", + "\n", "history = model.fit(train_images, train_labels, epochs=10, \n", " validation_data=(test_images, test_labels))" ] @@ -2420,22 +2654,36 @@ { "cell_type": "markdown", "id": "f128fdd6", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "## Finally, evaluate the model" ] }, { "cell_type": "code", - "execution_count": 13, + "execution_count": 14, "id": "c0c1e25a", - "metadata": { - "collapsed": false, - "editable": true - }, - "outputs": [], + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "313/313 - 2s - loss: 0.8414 - accuracy: 0.7182 - 2s/epoch - 7ms/step\n", + "0.7182000279426575\n" + ] + }, + { + "data": { + "image/png": "iVBORw0KGgoAAAANSUhEUgAAA+0AAAPlCAYAAAAXFAx+AAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjUuMSwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy/YYfK9AAAACXBIWXMAAA9hAAAPYQGoP6dpAACkUUlEQVR4nOzdd3Rd5Z3u8Wefrt6sZllyt+VugxvGxoBtSiCBEBhCAiEFQipJZubOZM3Nncmkcdckc5kQhpBMCgkpEAgtBAimYwNuGPdeJVu9t9P23vePIx9L2IBlH+ls6Xw/a2VZvHvr7J+cV8d69DbDtm1bAAAAAADAcVzJLgAAAAAAAJweoR0AAAAAAIcitAMAAAAA4FCEdgAAAAAAHIrQDgAAAACAQxHaAQAAAABwKEI7AAAAAAAORWgHAAAAAMChCO0AAAAAADiUo0L7fffdp1tuueV972lpadE//MM/aMGCBVqwYIH+z//5P+ru7h6iCgEAAAAAGDqOCe0PPPCA7rnnng+8784771RVVVX8/rVr1+rf//3fh6BCAAAAAACGlifZBdTV1el//+//rU2bNmn8+PHve+/mzZu1fv16PfPMM5o4caIk6Tvf+Y5uu+02/f3f/72Ki4uHomQAAAAAAIZE0kfad+zYoZycHD311FOaM2fO+967ceNGFRYWxgO7JC1cuFCGYWjTpk2DXSoAAAAAAEMq6SPtl156qS699NIzureurk6lpaX92nw+n3Jzc1VTUzMY5QEAAAAAkDRJH2kfiJ6eHvl8vlPa/X6/QqHQWb+ubdvnUhYAAAAAAIMi6SPtAxEIBBQOh09pD4VCSk9PP+vXtSxb7e3O3oHe7XYpOztN7e09Mk0r2eUAg4r+jlRCf0cqob8jldDf8X6ys9Pkdp/ZGPqwCu0lJSV64YUX+rWFw2G1trae8yZ00ejw+EYyTWvY1AqcK/o7Ugn9HamE/o5UQn/HuRpW0+MXLFig2tpaHTlyJN62bt06SdJ5552XrLIAAAAAABgUjg7tpmmqoaFBwWBQkjRnzhydd955+sY3vqGtW7fqrbfe0r/927/p2muv5bg3AAAAAMCI4+jQXlNTo6VLl+qZZ56RJBmGoXvvvVdjxozRrbfeqq9//eu66KKL9O1vfzu5hQIAAAAAMAgMm63TZZqWmpu7kl3G+/J4XMrLy1BLSxdrYjDi0d+RSujvSCX0d6QS+jveT35+xhlvROfokXYAAAAAAFIZoR0AAAAAAIcitAMAAAAA4FCEdgAAAAAAHIrQDgAAAACAQxHaAQAAAABwKEI7AAAAAAAORWgHAAAAAMChCO0AAAAAADgUoR0AAAAAAIcitAMAAAAA4FCEdgAAAAAAHIrQDgAAAACAQxHaAQAAAABwKEI7AAAAAAAORWgHAAAAAMChCO0AAAAAADgUoR0AAAAAAIcitAMAAAAA4FCEdgAAAAAAHIrQDgAAAACAQxHaAQAAAABwKEI7AAAAAAAORWgHAAAAAMChCO0AAAAAADgUoR0AAAAAAIcitAMAAAAA4FCEdgAAAAAAHIrQDgAAAACAQxHaAQAAAABwKEI7AAAAAAAORWgHAAAAAMChCO0AAAAAADgUoR0AAAAAAIcitAMAAAAA4FCEdgAAAAAAHIrQDgAAAACAQxHaAQAAAABwKEI7AAAAAAAORWgHAAAAAMChCO0AAAAAADgUoR0AAAAAAIcitAMAAAAA4FCEdgAAAAAAHIrQDgAAAACAQxHaAQAAAABwKEI7AAAAAAAORWgHAAAAAMChCO0AAAAAADgUoR0AAAAAAIcitAMAAAAA4FCEdgAAAAAAHIrQDgAAAACAQxHaAQAAAABwKEI7AAAAAAAORWgHAAAAAMChCO0AAAAAADgUoR0AAAAAAIcitAMAAAAA4FCEdgAAAAAAHIrQDgAAAACAQxHaAQAAAABwKEI7AAAAAAAORWgHAAAAAMChCO0AAAAAADgUoR0AAAAAAIcitAMAAAAA4FCEdgAAAAAAHIrQDgAAAACAQxHaAQAAAABwKEI7AAAAAAAORWgHAAAAAMChCO0AAAAAADgUoR0AAAAAAIcitAMAAAAA4FCEdgAAAAAAHIrQDgAAAACAQxHaAQAAAABwKEI7AAAAAAAORWgHAAAAAMChCO0AAAAAADgUoR0AAAAAAIcitAMAAAAA4FCEdgAAAAAAHIrQDgAAAACAQxHaAQAAAABwKEI7AAAAAAAORWgHAAAAAMChCO0AAAAAADgUoR0AAAAAAIcitAMAAAAA4FCEdgAAAAAAHIrQDgAAAACAQxHaAQAAAABwKEI7AAAAAAAORWgHAAAAAMChCO0AAAAAADgUoR0AAAAAAIcitAMAAAAA4FCEdgAAAAAAHIrQDgAAAACAQxHaAQAAAABwKEI7AAAAAAAORWgHAAAAAMChCO0AAAAAADgUoR0AAAAAAIcitAMAAAAA4FCEdgAAAAAAHIrQDgAAAACAQxHaAQAAAABwKEI7AAAAAAAORWgHAAAAAMChCO0AAAAAADgUoR0AAAAAAIcitAMAAAAA4FCEdgAAAAAAHIrQDgAAAACAQxHaAQAAAABwKEI7AAAAAAAORWgHAAAAAMChCO0AAAAAADgUoR0AAAAAAIcitAMAAAAA4FCEdgAAAAAAHIrQDgAAAACAQxHaAQAAAABwKEI7AAAAAAAORWgHAAAAAMChCO0AAAAAADgUoR0AAAAAAIcitAMAAAAA4FCEdgAAAAAAHIrQDgAAAACAQxHaAQAAAABwKEI7AAAAAAAORWgHAAAAAMChCO0AAAAAADgUoR0AAAAAAIcitAMAAAAA4FCEdgAAAAAAHIrQDgAAAACAQxHaAQAAAABwKEI7AAAAAAAORWgHAAAAAMChCO0AAAAAADgUoR0AAAAAAIcitAMAAAAA4FCEdgAAAAAAHIrQDgAAAACAQxHaAQAAAABwKEI7AAAAAAAORWgHAAAAAMChCO0AAAAAADgUoR0AAAAAAIcitAMAAAAA4FCEdgAAAAAAHIrQDgAAAACAQxHaAQAAAABwKEI7AAAAAAAORWgHAAAAAMChCO0AAAAAADgUoR0AAAAAAIcitAMAAAAA4FCEdgAAAAAAHIrQDgAAAACAQxHaAQAAAABwKEI7AAAAAAAORWgHAAAAAMChCO0AAAAAADgUoR0AAAAAAIcitAMAAAAA4FCEdgAAAAAAHIrQDgAAAACAQyU9tFuWpXvuuUfLli3TnDlz9NnPflZHjhx5z/urqqr0hS98QQsXLtSFF16o733ve+rp6RnCigEAAAAAGBpJD+333XefHnroIX3ve9/Tww8/LMMwdPvttyscDp9yb0dHh2666Sa1tbXpF7/4he6//35t375dX/7yl5NQOQAAAAAAgyupoT0cDutXv/qVvvrVr2r58uWqrKzU3Xffrbq6Oq1evfqU+x9//HF1dnbqv//7vzV79mzNmjVLd999t9544w1t3LgxCV8BAAAAAACDJ6mhfffu3erq6tLixYvjbdnZ2Zo+fbo2bNhwyv2HDh3ShAkTlJ+fH28rLS1VXl6e1q9fPyQ1AwAAAAAwVDzJfHhtba2kWPDuq6ioSDU1NafcX1hYqIaGBpmmKbfbLUnq7OxUW1ubmpqazqkWjyfpKwXel9vt6vcnMJLR35FK6O9IJfR3pBL6OxIlqaH9xAZyPp+vX7vf71dbW9sp91911VW6//779YMf/EB///d/L9M09e///u8yDOO0a+DPlMtlKC8v46w/fyhlZ6cluwRgyNDfkUro70gl9HekEvo7zlVSQ3sgEJAUW9t+4mNJCoVCSks7tXOPHTtWP/nJT/Sv//qv+v3vf69AIKBbbrlFM2fOVGZm5lnXYVm22tu7z/rzh4Lb7VJ2dpra23tkmlayywEGFf0dqYT+jlRCf0cqob/j/WRnp53xLIykhvYT0+Lr6+tVUVERb6+vr1dlZeVpP2f58uV69dVX1dDQoKysLAUCAS1ZskTXXXfdOdUSjQ6PbyTTtIZNrcC5or8jldDfkUro70gl9Hecq6QusKisrFRmZqbWrVsXb2tvb9fOnTs1f/78U+7ftGmTbr75ZoXDYRUWFioQCGj9+vVqaWnRkiVLhrJ0AAAAAAAGXVJH2n0+n26++Wb96Ec/Un5+vsrKyvTDH/5QJSUlWrVqlUzTVHNzc3xEfeLEidq3b59+8IMf6HOf+5yqqqr0T//0T/r4xz+u8vLyZH4pAAAAAAAkXFJDuyTdeeedikaj+ta3vqVgMKgFCxbol7/8pXw+n6qrq7VixQrddddduu6665Sbm6uf//znuuuuu/ThD39YeXl5+vjHP64vfvGLyf4yAAAAAABIOMO2bTvZRSSbaVpqbu5Kdhnvy+NxKS8vQy0tXayJwYhHf0cqob8jldDfkUro73g/+fkZZ7wRHYcGAgAAAADgUIR2AAAAAAAcitAOAAAAAIBDEdoBAAAAAHAoQjsAAAAAAA5FaAcAAAAAwKEI7QAAAAAAOBShHQAAAAAAhyK0AwAAAADgUIR2AAAAAAAcitAOAAAAAIBDEdoBAAAAAHAoQjsAAAAAAA5FaAcAAAAAwKEI7QAAAAAAOBShHQAAAAAAhyK0AwAAAADgUIR2AAAAAAAcitAOAAAAAIBDEdoBAAAAAHAoQjsAAAAAAA5FaAcAAAAAwKEI7QAAAAAAOBShHQAAAAAAhyK0AwAAAADgUIR2AAAAAAAcitAOAAAAAIBDEdoBAAAAAHAoQjsAAAAAAA5FaAcAAAAAwKEI7QAAAAAAOBShHQAAAAAAhyK0AwAAAADgUIR2AAAAAAAcitAOAAAAAIBDEdoBAAAAAHAoQjsAAAAAAA5FaAcAAAAAwKEI7QAAAAAAOBShHQAAAAAAhyK0AwAAAADgUIR2AAAAAAAcitAOAAAAAIBDEdoBAAAAAHAoQjsAAAAAAA5FaAcAAAAAwKEI7QAAAAAAOBShHQAAAAAAhyK0AwAAAADgUIR2AAAAAAAcitAOAAAAAIBDEdoBAAAAAHAoQjsAAAAAAA5FaAcAAAAAwKEI7QAAAAAAOBShHQAAAAAAhyK0AwAAAADgUIR2AAAAAAAcitAOAAAAAIBDEdoBAAAAAHAoQjsAAAAAAA5FaAcAAAAAwKEI7QAAAAAAOBShHQAAAAAAhyK0AwAAAADgUIR2AAAAAAAcitAOAAAAAIBDEdoBAAAAAHAoQjsAAAAAAA5FaAcAAAAAwKEI7QAAAAAAOBShHQAAAAAAhyK0AwAAAADgUIR2AAAAAAAcitAOAAAAAIBDEdoBAAAAAHAoQjsAAAAAAA5FaAcAAAAAwKEI7QAAAAAAOBShHQAAAAAAhyK0AwAAAADgUIR2AAAAAAAcitAOAAAAAIBDEdoBAAAAAHAoQjsAAAAAAA5FaAcAAAAAwKEI7QAAAAAAOBShHQAAAAAAhyK0AwAAAADgUIR2AAAAAAAcitAOAAAAAIBDEdoBAAAAAHAoQjsAAAAAAA5FaAcAAAAAwKEI7QAAAAAAOBShHQAAAAAAhyK0AwAAAADgUIR2AAAAAAAcitAOAAAAAIBDEdoBAAAAAHAoQjsAAAAAAA5FaAcAAAAAwKEI7QAAAAAAOBShHQAAAAAAhyK0AwAAAADgUIR2AAAAAAAcitAOAAAAAIBDEdoBAAAAAHAoQjsAAAAAAA5FaAcAAAAAwKEI7QAAAAAAOBShHQAAAAAAhyK0AwAAAADgUIR2AAAAAAAcitAOAAAAAIBDEdoBAAAAAHAoQjsAAAAAAA5FaAcAAAAAwKEI7QAAAAAAOBShHQAAAAAAhyK0AwAAAADgUIR2AAAAAAAcitAOAAAAAIBDEdoBAAAAAHAoQjsAAAAAAA5FaAcAAAAAwKEI7QAAAAAAOBShHQAAAAAAhyK0AwAAAADgUIR2AAAAAAAcitAOAAAAAIBDEdoBAAAAAHAoQjsAAAAAAA5FaAcAAAAAwKEI7QAAAAAAOBShHQAAAAAAhyK0AwAAAADgUIR2AAAAAAAcitAOAAAAAIBDEdoBAAAAAHAoQjsAAAAAAA5FaAcAAAAAwKEI7QAAAAAAOBShHQAAAAAAhyK0AwAAAADgUIR2AAAAAAAcitAOAAAAAIBDEdoBAAAAAHAoQjsAAAAAAA5FaAcAAAAAwKEI7QAAAAAAOBShHQAAAAAAhyK0AwAAAADgUIR2AAAAAAAcitAOAAAAAIBDEdoBAAAAAHAoQjsAAAAAAA5FaAcAAAAAwKEI7QAAAAAAOBShHQAAAAAAhyK0AwAAAADgUIR2AAAAAAAcitAOAAAAAIBDEdoBAAAAAHAoQjsAAAAAAA5FaAcAAAAAwKEI7QAAAAAAOBShHQAAAAAAhyK0AwAAAADgUIR2AAAAAAAcitAOAAAAAIBDEdoBAAAAAHAoQjsAAAAAAA6V9NBuWZbuueceLVu2THPmzNFnP/tZHTly5D3vb2ho0N///d9r0aJFWrRokb72ta+ptrZ2CCsGAAAAAGBoJD2033fffXrooYf0ve99Tw8//LAMw9Dtt9+ucDh82vu/8Y1vqKamRr/+9a/161//WrW1tfrSl740xFUDAAAAADD4khraw+GwfvWrX+mrX/2qli9frsrKSt19992qq6vT6tWrT7m/vb1dGzZs0O23367p06dr+vTp+vznP68dO3aopaUlCV8BAAAAAACDJ6mhfffu3erq6tLixYvjbdnZ2Zo+fbo2bNhwyv1+v1/p6el64okn1NnZqc7OTj355JMaN26ccnJyhrJ0AAAAAAAGnSeZDz+xFr20tLRfe1FRkWpqak653+/36/vf/76+853vaP78+TIMQ4WFhfrd734nl+vcfv/g8SR9pcD7crtd/f4ERjL6O1IJ/R2phP6OVEJ/R6IkNbT39PRIknw+X792v9+vtra2U+63bVt79uzRvHnzdNttt8k0Td1999368pe/rD/+8Y/KzMw8qzpcLkN5eRln9blDLTs7LdklAEOG/o5UQn9HKqG/I5XQ33GukhraA4GApNja9hMfS1IoFFJa2qmd+69//av+8Ic/6OWXX44H9Pvvv1+XXHKJ/vznP+vWW289qzosy1Z7e/dZfe5Qcbtdys5OU3t7j0zTSnY5wKCivyOV0N+RSujvSCX0d7yf7Oy0M56FkdTQfmJafH19vSoqKuLt9fX1qqysPOX+TZs2afz48f1G1HNycjR+/HgdPnz4nGqJRofHN5JpWsOmVuBc0d+RSujvSCX0d6QS+jvOVVIXWFRWViozM1Pr1q2Lt7W3t2vnzp2aP3/+KfeXlpbqyJEjCoVC8baenh5VV1dr7NixQ1IzAAAAAABDJamh3efz6eabb9aPfvQjvfjii9q9e7e+8Y1vqKSkRKtWrZJpmmpoaFAwGJQkXXvttZKkr3/969q9e3f8fp/Pp+uuuy6JXwkAAAAAAImX9K0M77zzTl1//fX61re+pZtuuklut1u//OUv5fP5VFNTo6VLl+qZZ56RFNtV/g9/+INs29att96qz3zmM/J6vfrjH/+o7OzsJH8lAAAAAAAklmHbtp3sIpLNNC01N3clu4z35fG4lJeXoZaWLtbEYMSjvyOV0N+RSujvSCX0d7yf/PyMM96ILukj7QAAAAAA4PQI7QAAAAAAOBShHQAAAAAAhyK0AwAAAADgUIR2AAAAAAAcitAOAAAAAIBDEdoBAAAAAHAoQjsAAAAAAA5FaAcAAAAAwKEI7QAAAAAAOBShHQAAAAAAhyK0AwAAAADgUIR2AAAAAAAcitAOAAAAAIBDEdoBAAAAAHAoQjsAAAAAAA5FaAcAAAAAwKEI7QAAAAAAOBShHQAAAAAAhyK0AwAAAADgUIR2AAAAAAAcitAOAAAAAIBDEdoBAAAAAHAoQjsAAAAAAA5FaAcAAAAAwKEI7QAAAAAAOBShHQAAAAAAhyK0AwAAAADgUIR2AAAAAAAcitAOAAAAAIBDEdoBAAAAAHAoQjsAAAAAAA5FaAcAAAAAwKEI7QAAAAAAOBShHQAAAAAAhyK0AwAAAADgUIR2AAAAAAAcitAOAAAAAIBDEdoBAAAAAHAoQjsAAAAAAA5FaAcAAAAAwKEI7QAAAAAAOJQn2QUAAAAAAHC2WjpC2rK/UZv3NWpvVasuW1Cuj140IdllJQyhHQAAAAAwbNi2rWONXdq8r1Hv7GvUoZr2ftcNI0mFDRJCOwAAAADA0UzL0v7qtnhQr2/t6Xd9wuhszZs8SnMnF2p0QXqSqhwchHYAAAAAgOOEwqa2H2rS5n2N2nqgSZ09kfg1j9ul6ePyNHfyKM2dNEq5mf4kVjq4CO0AAAAAAEdo6wzpnd716TsPtyhqWvFrGQGPZk8cpXmTR2nmhHwFfKkRZ1PjqwQAAAAAOI5t26pp6tbmfQ16Z1+jDh5vl93n+qicgOZNLtS8yaM0uTxHblfqHYBGaAcAAAAADBnLsrX/WJve2deozfsaVNfSf336uJIszZs8SvMmF6qsMEPGSNtZboAI7QAAAACAQRWKmNp5qFmb9zVqy4FGdXT3XZ9uqHJsnuZNim0kl5c1ctennw1COwAAAAAg4dq7wvHz03ceblY4enJ9errfo9mTCjRvcqFmjs9Xmp9o+l74mwEAAAAAJERtc2x9+uZ9jTpQ3dZvfXpBdqB32vsoTS7PlcedeuvTz8aAQ/vx48c1evTowagFAAAAADCMWLatg8fb4xvJ1TR197s+tjir9/z0USovykz59elnY8ChfcWKFVq8eLGuu+46XXbZZfL7WW8AAAAAAKkiHDG180iL3tnXoHf2N6m9Kxy/5nYZqqzI1dzeHd/zswNJrHRkGHBo/9GPfqQnnnhC3/zmN/Xv//7v+tCHPqTrrrtOc+fOHYTyAAAAAADJ1tEd1tYDTdq8r1HbDzUpHDm5Pj3N79asCbH16bMmFCg9wCrsRBrw3+ZVV12lq666Sg0NDXriiSf05JNP6k9/+pPGjRun6667Ttdcc42Ki4sHo1YAAAAAwBCpa+nuPZatUfuqW2X3WaCen+3X3EmxY9mmVrA+fTAZtt33r/7s7Nq1S3fddZc2bNggl8uliy66SLfddpvOP//8RNQ46EzTUnNzV7LLeF8ej0t5eRlqaelStM+ui8BIRH9HKqG/I5XQ35FKhmN/t2xbh2ra40H9eGP/jFRelBk/P72imPXp5yI/P0PuM/xFxznNW9i4caOefPJJPf/88+ro6NCFF16oSy65RK+88opuvvlm/dM//ZM+85nPnMsjAAAAAACDJBI1tetIizbva9Q7+xvV1nlyfbrLMDS1IldzJ4/SvEmjNCo3LYmVpq4Bh/YjR47oySef1FNPPaVjx46prKxMn/rUp/Sxj31MJSUlkqRPfvKT+sd//Ef99Kc/JbQDAAAAgIN09kS09UBj7/r0ZoXCZvya33diffoozZ5YoIyAN4mVQjqL0H755ZfL7/dr5cqV+u53v6sLLrjgtPdNmDBBhw8fPtf6AAAAAADnqKG1Jzaavq9Be6vaZPVZJZ2XFVufPnfyKFVW5MnrYX26kwx4Tfvvf/97feQjH1FWVtZg1TTkWNMOOAv9HamE/o5UQn9HKkl2f7dtW4drO+JBvbqhf94ZU5gRP5ZtXEkW69OH2KCuaf/kJz+pp556SuvWrdP3v/99SbG17d///vf1pS99SatWrRroSwIAAAAAzlHUtLS7z/r0lo5Q/JrLMDSlPEdzJxdq7uRRKmJ9+rAx4ND+2GOP6V/+5V/0oQ99KN5WUFCgMWPG6Gtf+5p+/OMfE9wBAAAAYAh0ByPx89O3HWxSsO/6dK9bMyfk965PH6XMNNanD0cDnh5/9dVX6+KLL9Y//uM/nnLthz/8od544w09/vjjCStwKDA9HnAW+jtSCf0dqYT+jlQymP29sa0nfizb3qpWmdbJSJeT4Yvt9j55lKaNzZPX407os5EYgzo9vqqqSkuXLj3ttaVLl+r3v//9QF8SAAAAAPAebNvW0bpObd7XoHf2NepofWe/66NHZWje5NhGcuNLs+ViffqIMuDQXlRUpK1bt2rx4sWnXNu5c6fy8vISUhgAAAAApKqoaWnP0Va9s69R7+xvUFP7yfXphiFNLoutT583ZZSK89KTWCkG24BD+7XXXquf/vSnysjI0MqVK5Wfn6/m5ma98MILuvfee/WpT31qMOoEAAAAgBGtOxjVtoNN2ryvQdsONqsnFI1f83ldmjEuX/MmF2rOpAJlpfuSWCmG0oBD+x133KEDBw7ou9/9rr73ve/F223b1hVXXKGvfvWrCS0QAAAAAEaq5vZg/Fi23Uf7r0/PTvdq7uRRmju5UNPH5snnZX16KhpwaPd4PPp//+//6Ytf/KI2btyotrY2ZWVl6fzzz1dlZeVg1AgAAAAAI4Jt26qq74xvJHekrqPf9dKC9N6N5Ao1YTTr03EWof2EyZMna/Lkyae0d3R0KCsr65yKAgAAAICRImpa2lfVGj8/vbEtGL9mSJo4JkfzeoN6ST7r09HfgEN7OBzWAw88oPXr1ysSiejEiXG2bau7u1v79+/Xli1bEl4oAAAAAAwXPaGodmw5ptffrtaW/Y3qCp5cn+71nFifPkpzJo1Sdgbr0/HeBhza/+M//kO/+93vNGXKFDU3N8vv9ys/P1979+5VJBLRV77ylcGoEwAAAAAcq6UjpH3Vrdpf3ab9x9p0tK5Tln1yfXpmmldzJ8XOT58+Pl9+1qfjDA04tD///PP69Kc/rW9+85v62c9+pp07d+rHP/6x6urqdPPNN8uyrMGoEwAAAAAcwbJsVTd0av+xNu2vbtO+6jY1tQdPuW/0qAzNmTRKcyYWaFJZjlwu1qdj4AYc2pubm7V8+XJJ0tSpU/Xwww9LkoqLi/X5z39ev/71rxltBwAAADBi9ISiOljTHhtFr27VgePtCobNfvcYhlRelKnJZbmaNCZHU8fmafK4ArW0dCkaZWATZ2/AoT0rK0vhcFiSNG7cONXU1Kizs1OZmZnx/wYAAACA4aqpLah9x3qnule3qaqhU31mukuSAj63JpblaFJZjiaNydGE0myl+U/GK4/HNcRVY6QacGifP3++HnzwQS1YsEBjxoxRWlqaVq9erY9+9KPavHmzMjMzB6NOAAAAAEg407JUVd+pfb0Bff+xNrV0hE65ryA7oMljYgF9UlmOxhRmMt0dQ2LAof3LX/6ybr75Zt1xxx168MEH9YlPfEL/+q//qgcffFB79uzRTTfdNBh1AgAAAMA56w5GdeB4bB36gWNtOni8XaFI/6nuLsNQRXGmJo3J0eQxuZpUlqO8LH+SKkaqG3Bor6ys1LPPPqu9e/dKkv7hH/5BmZmZevvtt3XppZfq85//fMKLBAAAAICBsm1bDW1BHahu075jsfXoxxq69K6Z7krze+LT3CeX5Wh8abb8PnZ3hzMMOLR/+9vf1jXXXKMLL7xQkmQYhr7whS8kvDAAAAAAGIioaeloXaf2V7f2hvQ2tXWFT7mvKDctPs190pgcjR6VIZfBVHc404BD+1/+8hddfvnlg1ELAAAAAJyxzp6IDhyLrUPfV92mwzXtCr9rp3a3y9DYkixNKsuJrUkvy1FOJlPdMXwMOLTPmjVLr732mi644ILBqAcAAAAATmHbtupbemIbxh1r1f5j7Tre2HXKfRmBPlPdx+RqXEmWfF6mumP4GnBonzp1qh588EH97W9/06RJk1RQUNDvumEY+sEPfpCwAgEAAACknkjU0pHajvjRaweOtam9O3LKfcX56ZpcdnJX95KCdKa6Y0QZcGhfvXq1ioqKJEn79+/X/v37+103+AYBAAAAMEDt3eHYVPfeTeMO13Qoavaf6u5xGxpXmh2b6l6Wo4ljcpSd7ktSxcDQGHBof+mllwajDgAAAAApwrZt1TZ3x89G33esTXXN3afcl5Xu7bOre67GlmTJ63EloWIgeQYc2gEAAABgIMIRU4drO7SvOjbVff+xNnUFo6fcV1qQ3rtZXK4mj8lRUV4aM3mR8gYc2j/1qU994D2//e1vz6oYAAAAAMNfW1c4duxa71r0w7UdMq3+p6N7PS6NL82O7+g+sSxHmWneJFUMONeAQ7tt26e0dXd368CBA0pPT9dll12WkMIAAAAAOJ9l2zre2BUfQd9f3ab61p5T7svJ8PVOc4+tRR9bnCWPm6nuwAcZcGh/8MEHT9ve1tamO+64QxMmTDjnogAAAAA4Uyhs6mBNezygHzjWpu5Q/6nuhqSywoz4evRJY3JVmBNgqjtwFhK2pj0nJ0e33367vv/975/RFHoAAAAAztfSEdL+Y23x9ehV9Z2nTHX3eV2aUJqtSWNia9Enjs5WeoCp7kAiJHQjOtu21dTUlMiXBAAAADBELMtWdUNnfBR9X3WbmtqDp9yXl+U/uav7mByNKcxkqjswSAYc2jds2HBKm2maqq2t1b333qsZM2YkpDAAAAAAg6snFI1Nde9dj37weJt6Qma/ewxDKi/MjE1z7w3qBdlMdQeGyoBD+y233CLDMGTbdvwb9cTmdKWlpfqXf/mXxFYIAAAAICGa2oLad+zksWtV9Z169z7Tfp9bE0dna1JZjiaPydWE0dlK83NSNJAsA/7uO91xboZhKDMzU1OnTpXLxbQYAAAAwAnau8LatLdBe462aF91m1o6QqfcU5Dt16Qxub0hPTbV3eViFB1wigGH9oULF8o0Te3Zs0fTp0+XJNXX12vbtm2aNGkSoR0AAABIou5gRJv2Nmj9zjrtPNLSbyTdZRgqL87U5BO7upflKD87kLxiAXygAYf22tpafe5zn1MoFNILL7wgSdq9e7e+/OUva9asWfrZz36m/Pz8hBcKAAAA4PRCEVNb9jdq3c46bTvYpKh5MqmPL83SnEmjNLksR+NHZyvgY6o7MJwM+Dv2P/7jP2Sapu6+++5420UXXaQnn3xS3/jGN/Sf//mf+v73v5/QIgEAAAD0FzUtbT/YrPW76rR5X6NCkZMbyI0elaFF04q0cHqxivPSk1glgHM14ND+5ptv6rvf/a5mzZrVr33q1Km688479b3vfS9hxQEAAAA4ybJs7TnaonW76rRpT4O6gtH4tVE5AS2aXqxF04pVVpjB7u7ACDHg0B6JRN7zDcDv96urq+uciwIAAAAQY9u2Dh5v17qdddqwu15tXeH4tZwMnxZMK9Ki6cWaUJpNUAdGoAGH9rlz5+qBBx7QRRddJK/XG2+PRCL6zW9+o9mzZye0QAAAACDV2Lat6oYurdtZp/W76tTYFoxfywh4dP7UWFCfWp7LTu/ACDfg0P71r39dn/jEJ7RixQpddNFFKigoUHNzs15//XW1tLTowQcfHIw6AQAAgBGvrqW7N6jX63jjyRmsfq9b86aM0sJpxZo5Pl8eNyc2AaliwKF95syZ+tOf/qT77rtPr7zyilpbW5WVlaX58+frS1/6kqZNmzYYdQIAAAAjUnN7UBt212vdzjodru2It3vchmZNKNCi6cWaM2mU/F53EqsEkCxndd5DZWWl/vM//zM+Pb67u1vhcFi5ubmJrA0AAAAYkTq6w9q4p0HrdtZpX1WrThzQ5jIMTRuXp0XTinXelEKlBzieDUh1A34XCIfD+s53vqMdO3bo8ccflyS98847+vznP6+bbrpJ3/zmN+V281tAAAAAoK+eUFRv723Qul112nmoRZZ98iz1yWNytGh6seZPLVJ2hi+JVQJwmgGH9nvuuUfPPPOMvva1r8XbZsyYoX/+53/Wj3/8YxUUFOgLX/hCQosEAAAAhqNwxNTWA01at7NOWw40KWpa8Wtji7O0cHqRFlYWqyAnkMQqATjZgEP7X//6V/3zP/+zbrzxxnhbTk6ObrnlFrlcLj3wwAOEdgAAAKSsqGlp5+FmrdtZr837GhQMm/FrJfnpWjS9WAunFam0ICOJVQIYLgYc2ltaWjRmzJjTXhs/frzq6urOuSgAAABgOLFsW/uqWrVuZ5027mlQZ08kfq0g26+F04q1aHqxyosyOUsdwIAMOLRPnDhRf/vb33ThhReecm316tUaO3ZsQgoDAAAAnMy2bR2u7Yifpd7aGY5fy073akFlLKhPKMuWi6AO4CwNOLR/9rOf1T/8wz+otbVVK1eujJ/T/sILL+j555/XXXfdNRh1AgAAAI5wrKFT63bVaf3OetW39sTb0/wenT+1UIumFatybK7cLs5SB3DuBhzar7rqKnV0dOjee+/V888/H2/Py8vTv/7rv+rqq69OaIEAAABAstW39mjDrjqt21mn6oaueLvP49LcyaO0aFqxZk4okNdDUAeQWGd18OPHP/5x3XjjjTp06JBaW1uVnZ0tv9+vRx55RBdffLHWrFmT6DoBAACAIdXaGdKGXfVat6tOB4+3x9vdLkOzJhRo4fQizZ00SgEfZ6kDGDxn/Q5jGIbGjx+vl19+Wffff7/Wrl0r0zQ1YcKERNYHAAAADJnOnog27anXup112nO0VSdOUjcMqbIiT4umF+u8KYXKTPMmtU4AqeOsQnt9fb0eeeQRPfroo6qtrVV2drZuvPFGXXvttZo9e3aiawQAAAAGTTAc1eZ9jVq3s047DjXLtOz4tYll2Vo4rVgLK4uUk+lPYpUAUtWAQvvatWv10EMP6eWXX5Zt21q0aJFqa2t17733asGCBYNVIwAAAJBQkaiprQeatX5Xnbbsb1Q4asWvlRdlauG0Ii2aVqxRuWlJrBIAzjC0/+IXv9Cf/vQnHT16VOPHj9edd96pj370o/L7/Vq4cOFg1wgAAACcM9OytOtIi9btrNPbexvUEzLj14ry0rRoWrEWTi9W2aiMJFYJAP2dUWj/0Y9+pKlTp+rBBx/sN6Le0dExaIUBAAAA58qybe2vbtO6XXXauLteHd2R+LW8LH9sRH16scYWZ8ngLHUADnRGof0jH/mIVq9erdtuu02LFy/WtddeqxUrVgx2bQAAAMCA2bato3WdWrezTut316m5PRS/lpnm1YLKIi2cVqTJ5blyEdQBONwZhfb/+I//UFdXl55++mk99thj+sY3vqGcnBytWLFChmHwW0kAAAAkXU1Tl9btrNO6XfWqa+6Otwd8bp03pVCLphdr2tg8edycpQ5g+DBs27Y/+Lb+Dhw4oEcffVR/+ctf1NjYqLKyMl199dW66qqrNGXKlMGoc1CZpqXm5q5kl/G+PB6X8vIy1NLSpWifjVKAkYj+jlRCf0cqGYz+3tjWEztLfWedjtZ3xtu9HpfmTCzQounFmj2xQF6POyHPA84U7+94P/n5GXKf4S8Qzyq0n2Capl5++WU9+uijWrNmjUzT1OTJk/XUU0+d7UsmBaEdcBb6O1IJ/R2pJFH9va0rrI27Y0F9/7G2eLvbZWjG+HwtmlasuZNHKc1/VqcbAwnB+zvez0BC+zm9k7ndbq1cuVIrV65UU1OTHnvsMT3xxBPn8pIAAADAKbqDEW3a06B1u+q060iLTgw7GZKmVuRq4fRinT+lUFnpvqTWCQCJlrBfPxYUFOj222/X7bffnqiXBAAAQAoLhU29s79R63fVadvBJkXNkxNEx5dma9G0Ii2YVqy8LH8SqwSAwcWcIQAAADhG1LS0/WCz1u2q0zv7GhWKnDxLvWxUhhZOL9aiaUUqyktPYpUAMHQI7QAAAEgqy7K1+2iL1u2s06Y9DeoORePXCnMDWjitWIumF2tMYWYSqwSA5CC0AwAAYMjZtq0Dx9u1bmedNuyuV3tXOH4tJ9OnhZWxoD6+NIvjhQGkNEI7AAAAhoRt2zp0vE3Pv3lYb+2oVWNbMH4tI+DR/MoiLZxWrKnluXK5COoAIBHaAQAAMIia24Pac7RVe6pi/6tr7o5f83vdmjdllBZNK9aM8fnynOHxRwCQSgjtAAAASAjbttXQFtSeoy3a2xvU+46mS5LX49LsiQVaOK1YsycWyO91J6laABgeCO0AAAA4K7Ztq7a5W3uqWuMhvaUj1O8el2FobEmmppbnadq4PC2aXaZwMKxo1EpS1QAwvBDaAQAAcEYs29bxhq74VPe9Va39NpCTJLfL0PjSbE2tyNXU8lxNLMtRmj/2I6fH41JGmlfhYPh0Lw8AOA1COwAAAE7Lsmwdre+Ij6LvrWpVVzDa7x6vx6WJo7M1pTwW0ieU5TDlHQASiNAOAAAASVLUtHSktiMe0PdVt6onZPa7x+91a1JZtqZU5Glqea7Gl2bL62EDOQAYLIR2AACAFBWJWjpU0649R1u0p6pV+4+1KRzpv9Y8ze/W5DGxUfQpFbkaW5zFLu8AMIQI7QAAACkiFDF14Fib9la1as/RVh043q6o2T+kZwQ8sanuvSPp5UWZnJkOAElEaAcAABihekJR7T/W1ntOeosO13TItOx+92Rn+OLr0adW5Gr0qAy5DEI6ADgFoR0AAGCE6ApGtLd3Pfqeo606Utchu39GV16WX1MrcuNBvSQ/XQYhHQAci9AOAAAwTLV3h/vt7F5d36l3ZXSNygn0Hr+WpykVuSrMCRDSAWAYIbQDAAAMEy0dodgoelWr9hxtUU1T9yn3lOSn9xtJz88OJKFSAECiENoBAAAcqrGtR3uOtsaDen1Lzyn3lBVm9K5Hz9OUMTnKyfQnoVIAwGAhtAMAADiAbduqb+npHUVv1d6qFjW1h/rdYxhSRVFW7+7usdH0zDRvkioGAAwFQjsAAEAS2Lat403d2tt7Rvqeqla1dYb73eMyDI0rzYrv7D6pLFfpAX58A4BUwrs+AADAELBsW9X1nbFN43o3j+vsifS7x+M2NKE0W1N6N46bWJatgI8f1wAglfGvAAAAwCAwLUtH6zrja9L3VrWqOxTtd4/P49LEshxNLY9NdZ8wOls+rztJFQMAnIjQDgAAkABR09Lhmg7tqWrRnqOt2nesTaGw2e8ev8+tyWU58SPYxpVmyeN2JaliAMBwQGgHAAA4C+GIqYPH2+M7ux841qZw1Op3T7rfoym9o+hTK3JVUZwpt4uQDgCJZHW3KnrkHUWPbJZZu1e+WZfLf/61yS4rYQjtAAAAZyAUNrX/WJv2VLVo79FWHaxpV9S0+92TmeaNTXWviJ2RPqYwUy6XkaSKAWBksm1bVstxRY9sVvTI27LqD/a/wTJP/4nDFKEdAADgNLqDUe0/Fjt+bU9Vq47Udsi0+of0nExfbGf38lxNqcjT6IJ0GQYhHQASzbZMmbX7eoP6Ztnt9f2uuwonyDN2rjzjzpMrryxJVQ4OQjsAAICkzp5IbKp778ZxR+s7ZPfP6CrI9mtKeV7vmvRcFeWlEdIBYJDY4R5Fq7fHgvrRLVKo6+RFt0fu0dPlGTtPnrFz5crIS16hg4zQDgAAUlJbV7g3pMfOST/W0HXKPUV5afGd3adW5GpUTloSKgWA1GF1tfSOpr8j89hOyepz6oY/Q56KufKMmyfPmJkyvIHkFTqECO0AACBltHeH9db2Wq3dXquq+s5TrpcWpGtqRV48qOdl+ZNQJQCkjtj69GpFD8emvVsNh/pdN7KLYqPp486Tu3iSDFfqHYtJaAcAACNa1LS07WCT1myt0dYDTfF16YakMUWZsVH03pCeneFLbrEAkAJsKyqzZm98RN3uaOhz1ZCraEJsNH3sPLlyR6f8MiRCOwAAGJGONXRqzbYavbmjTu1d4Xj7+NIsLZ1VqgXTipWZ5k1ihQCQOuxwj6JV206uTw93n7zo9spdNiMW1CvmyJWem7Q6nYjQDgAARozuYETrdtVrzdbjOlTTEW/PTvfqgpklWjqrVGWFmUmsEABSh9XZHN/t3Ty+q99RbEYgS+6KufKMmytP2UwZXpYjvRdCOwAAGNYsy9auIy1as61Gb+9tUCRqSZLcLkOzJxZo6exSzZpQII/bleRKAWBks21bVtNRRY+8Ezs/vfFIv+tGTsnJ9elFE2W4eF8+E4R2AAAwLNW3dGvNtlq9sb1Gze2hePuYwgwtnVWqxTNKWKMOAIPMNqMya/YoeuTt2Pr0zqY+Vw25iyfJPXaevOPmyZVbmrQ6hzNCOwAAGDaC4ag27m7Qmm012lvVGm9P93u0aEaxls4q1biSrJTftAgABpMd6jq5Pr1qqxTuOXnR7ZNnzIzYaHrFHLnSspNX6AhBaAcAAI5m27b2VbdpzdYabdhTr1A4tibSkDRjfL6Wzi7VvMmj5PWk3jFAADBUrI7Gk+enH98t2X3Wp6dlyzN2rjxj58ldNkOGh1lOiURoBwAAjtTcHtQb22u1dluN6lpOjuIU5aVp6axSLZlZovzsQBIrBICRy7ZtWY1HeoP627Kaqvpdd+WOPnksW9EEGQbr0wcLoR0AADhGJGpq875Grdlaox2Hm2XHjlSX3+fWgsoiLZ1Vqsljcpj+DgCDwDYjMo/vPnl+elfzyYuGIXfJlPiIuiunJHmFphhCOwAASCrbtnW4tkNrttVo/c46dQWj8WtTynO1dFap5lcWKuDjxxYASDQ71KXo0S2969O3SZHgyYsevzxjZsozbl5sfXogK3mFpjD+9QMAAEnR3hXWmztqtWZbjY41dMXb87P9WjKzVEtnlagoLz2JFQLAyGS1N5w8P71mj2Rb8WtGeq48FXNjQX30NNanOwChHQAADJmoaWnbwSat2VqjrQeaZFqx+e8et0vnTy3U0lmlmjY2Ty4X098BIFFs25LVcDge1K3m6n7XXXljTq5PLxzH+nSHIbQDAIBBd6yhU2u21ejN7bVq747E28eXZmnprFItnF6sjIA3iRUCwMhiR8O969N7z0/vbj150XDF1qefCOrZRUmrEx+M0A4AAAZFdzCidTvrtGZbjQ7VdMTbs9O9umBmiZbOKlVZYWYSKwSAkcUOdvZfnx4NnbzoDchTPkuesfPkKZ8tI8D773BBaAcAAAljWbZ2HmnWmq01entvo6JmbJ2k22Vo9sQCLZ1dqlkTCuRxM/USABLBaq9X9PDbsfXptXsVP3ZDkpGRFwvpY+fG1qe7mdE0HBHaAQDAOatv6daabbV6Y3uNmttPjuyMKczQ0lmlWjyjRNkZbGYEAOfKti1Z9QcVPfJO7Pz0luP9rrvyy3unvZ8n16ixHJE5AhDaAQDAWQmGo9q4u0FrttVob1VrvD3d79GiGcVaOqtU40qy+IERAM6RHQ3LPLbz5Pr0nvaTFw233KOnxkfUXVmFySsUg4LQDgAAzpht29pX3aY1W2u0YXe9QhFTkmRImjE+X0tnl2re5FHyetzJLRQAhjmrp13mifXp1dulaPjkRW9abH36uPPkKZ8lw5+RvEIx6AjtAADgAzW3B7V2e63WbqtRfUtPvL0oL01LZ5VqycwS5WcHklghAAx/VmttfDTdrNv3rvXp+fHd3t2llTLcRLlUwf/TAADgtCJRU5v3Ner1rTXaeahZJ3509PvcWlBZpKWzSjV5TA7T3wHgLNmWJav+wMnz01tr+l13FYw9eSxbQQXvtymK0A4AAOJs29bh2g6t2VajdTvq1B2Kxq9NKc/V0lmlml9ZqICPHyEA4GzY0ZCi1TtkHtkcW58ePHkkplxuuUdPk2fs3FhQzyxIXqFwDP7FBQAAau8K680dtVqzrUbHGrri7fnZfi2ZWaqls0pUlJeexAoBYPiyutsUPfqOooc3yzy2QzIjJy/60uWpmN17fvosGT7ea9EfoR0AgBQVNS1tO9CkNdtqtPVAk0wrNgHe43bp/KmFWjqrVNPG5snlYjomAHwQ27YlMyI7EpQiQUUj3WrdtV/tO9+SWXdAUp/16ZkFsU3kxs6Tu3SKDBexDO8t6b3Dsizde++9euSRR9Te3q7zzz9f//Zv/6axY8eecu9PfvIT3Xvvvad9neuuu0533XXXYJcLAMCwV93QqTVba/TWjlq1d58c7Rlfmq2ls0u1aFqR0gPeJFYIAEPDtiwp0iM7EoyHbTvc5+Peawq/++O+9wTj7bLN93yWq3B877Fs8+TKH8P6dJwxw7b7bEmYBPfee6/+8Ic/6K677lJxcbF++MMfqqqqSk8//bR8Pl+/e7u6utTd3d2v7dFHH9X999+vhx9+WJWVlWdVg2laam7u+uAbk8jjcSkvL0MtLV2KRq1klwMMKvo7UslQ9feuYETrd9ZpzbYaHao5uX4yO92rC2aWaOmsUpUVZg7a8wGJ93ecu9hodlh2+F2BOdLTJ2z3vCt4ny6Q9wbwvseoJZLHL8MXUKBkgowxc2SUz5ErI29wnoVhKT8/Q26364zuTepIezgc1q9+9Sv9r//1v7R8+XJJ0t13361ly5Zp9erVuuqqq/rdn5GRoYyMk2cQHj16VD/72c/0zW9+86wDOwAAI5Vl2dp5pFlrttbo7b2NipqxkOR2GZo9sUBLZ5dq1oQCec7whwYAOBu2ZZ4Mz+GTgdkO97xPqD7R3tOnvUeKhCR7EH7h43JL3oAMb0CGN03ynfg40Kc9IPnS+nwcu7ffPb6A5AnIcLn4JRUSJqmhfffu3erq6tLixYvjbdnZ2Zo+fbo2bNhwSmh/t//7f/+vJk+erBtvvHGwSwUAYNioa+nW2m01WrutVi0doXj7mMIMLZ1VqsUzSpSd4XufVwCQymzblqLhWEgOvys8x4P3e41y904j73NPv03XEul0obo3OBvetD4fn7gnrU/Y7nt/mgw3S4LgXEkN7bW1tZKk0tLSfu1FRUWqqak53afEbdu2TS+++KJ+85vfyOVihAAAkNqC4ag27K7X2q012lvdFm9P93u0aEaxls4q1biSLNZQAiOUbVlSNDZ6HVtffZrR7Pf6uO/IdjgoRYPSYKygdXn6heaTo9P9R6vlTXtX2D5538l7/DIMMgBSQ1JDe09PjySdsnbd7/erra3tdJ8S98ADD2jOnDn9RunPhcfj7G/6E+sdznTdAzCc0d+RSs6lv9u2rb1VrXpty3Gt31mvUCS2AZIhaeaEAi2bU6rzphbK53EnsmTgrPH+3p9tW1IkFA/a/f48sfFZuOfkJmh92uy+beEeKRr64AcOmBELx32mhBu+k4H63dPFT4xw9/2z78i34U76HthDiv6OREnqd04gEJAUW9t+4mNJCoVCSktLe8/P6+7u1urVq/Vv//ZvCanD5TKUl5fxwTc6QHb2e/+9ACMN/R2pZCD9vbG1Ry9uPKoXN1SppvHkRqqlozK0ckGFLp1frlG5fP/AuYbz+7tt27IjIVnhHlmhWIC2Qt2yQj2ntoXf3danPdQ7hVwJHtF2ueXyp8nlS5fLnybDlyaXL623LU2GP00uXyDWFv/vPtfj9wdkMJqdEMO5v8MZkhraT0yLr6+vV0VFRby9vr7+fTeWe/3112VZllatWpWQOizLVnt79wffmERut0vZ2Wlqb++RabKRBUY2+jtSyZn293DU1Nt7GvTaluPacbA5/mN+wOfWwmnFWjZntKaU58Smv9uWWlqcfSoKUlOy3t/j52efZqRa/Ua3Tzfi/a5p5uGexE8dN1wn12GfGLn29R+xjo12n/w4vha77/3egOT2ntEyGFvSex5OFpUUtST1JO5rTEH8PIP3k52dNjx2j6+srFRmZqbWrVsXD+3t7e3auXOnbr755vf8vE2bNmnGjBnKzs5OWC3DZUdH07SGTa3AuaK/I5Wcrr/btq3DtR1as61G63bUqTsUjV+bUp6rpbNKNb+yUAGfp/c1bCV81A4YBGf6/m6b0T6bofVZq31i3XbfDdBOhOu+98fXd7//+dlnxzgZnN+9k3ifIN33npO7kp+YOt77p9t3TvtN9PvO533Acfh5BucqqaHd5/Pp5ptv1o9+9CPl5+errKxMP/zhD1VSUqJVq1bJNE01NzcrKyur3/T53bt3a8qUKUmsHACAwdPeFdabO2q1ZluNjjWcHDHPz/ZrycxSLZ1VoqK89CRWCAycbZmKHN6qtn0t6mltkxnqPjWM99t1vEcyox/8wgN1uuO74hucpfUJ2u8K2e8K4fL4mDoOYEgkfTeIO++8U9FoVN/61rcUDAa1YMEC/fKXv5TP51N1dbVWrFihu+66S9ddd138cxobGzVnzpwkVg0AQGJFTUub9zZozbYabT3QJNOKjZR53C6dP7VQS2eVatrYPLlc7P6O4cUOdiq8+zVFdr4ou7NJnWfzIh5fn5B9+lHs/qPefe/p+zFrtAEMP4ZtD8Z5DsOLaVpqbnb22j+Px6W8vAy1tHQxvQYjHv0dqaS+tUdv7arXSxur1N4VjrePL83W0tmlWjStSOkBzg/G8GM2Vyuy/QVF9r0hmbG+bQSylD5htiLyyfb43zVt/H3CuIsTEDD88PMM3k9+fsbwWNMOAECqqm7o1FNrD2vT7vr46tPsdK8umFmipbNKVVaYmdT6gLNhW5bMo1sU3v68zOO74u2uggr5Zq5SYOoFyi/MI8QAwAAQ2gEAGEJV9Z16au0hbdrTEG9bOL1ES2YWa/rYPHk4zxfDkB3qUmTP6wrveFF2R2/fNgx5xp0v78xVcpdMkWEYMjz0bwAYKEI7AABD4Ghdh55ae1hv7z0Z1udPLdS1F03QnMoSRh4xLJmtx2NT4PeulaKhWKM/Q77K5fLOWCFXZkFyCwSAEYDQDgDAIDpS26Gn1h7S5n2NkiRD0vzKIn34wnEaU5gpDyOPGGZs25JZtU3h7atlVm+Pt7vyxsg7a5W8kxbL8PiTWCEAjCyEdgAABsHh2nY9teaw3tl/MqwvmFakDy8Zx3p1DEt2uEeRvWsU3v6C7Pa63lZDnnHzYlPgSyvP6axxAMDpEdoBAEigQzXtenLNIW090CRJMgxp0bRiXb1knEaPykhydcDAWW21Cu94UZE9r0uRYKzRlyZv5XL5pq+QK7swuQUCwAhHaAcAIAEOHG/TU2sOa9vBk2F98fRYWC8tIKxjeLFtW+axHbEp8Ee3Sr1nHLhyR8s7c6W8k5fEjmMDAAw6QjsAAOdg/7E2PbXmkLYfapYUC+sXzCjR1UvGqSQ/PcnVAQNjR4KK7HtDke2rZbXW9LYaclfMkW/mKrnLZjAFHgCGGKEdAICzsK+6VU+tOaQdh1skSS7D0AUzYyPrxXmEdQwvVnt97xT416RwT6zRG5B36jL5ZqyUK6c4uQUCQAojtAMAMAB7q1r15JpD2nXkZFhfMqtEV18wVkWEdQwjtm3LPL5Lke2rFT3yjk5MgTdyiuWbsUreKRfK8KUltUYAAKEdAIAzsudoi55cc0i7j7ZKktwuQxfOKtFVF4xTYS7BBsOHHQ0psu/N2BT4lmPxdnf5LPlmrJK7fKYMg6MIAcApCO0AALyP3UdiYX1PVaukWFhfOrtUVy0eq1GEdQwjVkejIjtfUnj3q1KoK9bo8cs7Zam8M1fInTs6uQUCAE6L0A4AwLvYth0L62sPa2+fsL5szmh9aHGFRuUQ1jE82LYts3ZvbAr84U2S3TsFPqtQvhkr5a1cJsPHsg4AcDJCOwAAvWzb1s4jLXpqzSHtq26TJHncsbB+1eKxys/miCsMD3Y0rOiBdQpvXy2r6Wi83V02PbYLfPkcGS6mwAPAcEBoBwCkPNu2teNws55ac1j7j50I6y4tnzNaVy6uIKxj2LA6mxXZ+ZIiu1+VHeyINbp98k5ZIu+MVXLnlyW3QADAgBHaAQApy7ZtbT/UrKfWHNKB4+2SYmH94rmjdeXiscrL8ie5QuCD2bYtq26/wttXK3poo2RbkiQjsyA2BX7qMhmBzCRXCQA4W4R2AEDKsW1b2w426ck1h3WoJhbWvR6XLp5bpisXVyg3k7AO57PNiKIH1semwDcejre7SyvlnblKnrFzZbjcySsQAJAQhHYAQMqwbVtbDjTpqTWHdLg2NnXY53Hp4nllunJRhXII6xgGrO5WRXa+rMiul2X3xH7pJLdX3kkXyDtzpdwFFcktEACQUIR2AMCIZ9u23tnfqKfWHtaRE2Hd69Kl88bo8kUVysnwJblC4IOZ9QdjU+APrpcsU5JkZOTJO32FvNOWyxXISnKFAIDBQGgHAIxYtm1r875GPbX2kI7WdUqS/F63Lj2vTJcvrFA2YR0OZ5tRRQ9tjE2Brz8Qb3cXT5Z31ip5xp0nw8WPcwAwkvEuDwAYcSzb1ua9DXpq7WFV1feGdZ9bK84bo8sWlis7nbAOZ7N62hXZ9bIiO1+W3d0aa3R55Jm0SL4Zq+QuHJfM8gAAQ4jQDgAYMSzb1tt7GvTU2kOqbuiSFAvrK88fo8sWlCuLsA6HMxsPx6bA718nWVFJkpGeK+/0S+SddolcadlJrhAAMNQI7QCAYc+ybW3cXa+/vHFYx3rDesDn1sr55bpsQbky07xJrhB4b7ZlKnp4kyLbX5BZuzfe7iqaIN/My+QZP1+Gmx/ZACBV8S8AAGDYsixbG3rD+vHGWFhP87u1an65Vi0oV0aAsA7nsoIdiux+VZEdL8nuao41utzyTFgo38yVchdNTG6BAABHILQDAIYdy7K1fled/vLGYdU0dUuS0vwerZo/hrAOxzObqhTZvlqR/W9KZkSSZKRlyzvtEnmnXyJXem5yCwQAOAqhHQAwbJiWpfU7YyPrtc2xsJ7u9+iyBeVaOX+M0gnrcCjbshQ9slmR7c/LrNkTb3eNGiffzFXyTFwow03/BQCcitAOAHA807L01o46Pf3GYdW19EiSMgKxsL7i/HKlB/jnDM5kh7oU2f2qwjtelN3ZFGs0XPKMny/fzFVyFU+SYRjJLRIA4Gj8lAMAcCzTsvTm9jo9/eZh1fcJ65cvrNCK88cozc8/Y3Ams/mYIjtWK7LvDSkaliQZ/kx5p10s7/RL5crMT3KFAIDhgp92AACOEzUtvbm9Vk+/eVgNrUFJUmaaV5cvLNel5xHW4Uy2Zcms2qLw9hdkHtsRb3cVlMd2gZ+4SIaHYwcBAAPDTz0AAMeImpbe2F6rp984rMa2WFjPSvfqioUVuuS8MgV8/LMF57HD3YrseV3h7S/I7miINRqGPOPOl3fmKrlLpjAFHgBw1vjpBwCQdFHT0pptNfrrG0fU1B4L69npXl2xaKwumVcmv8+d5AqBU1mtNQpvf0GRvWukaCjW6M+Qr3J5bAp81qjkFggAGBEI7QCApIlEY2H9mTcPq6k9FnqyM3y6clGFLp5XJr93eIZ124zKDnXJDndJoW7ZoW7Z4e5YW6hLdri7t71LivSox+uW6Q5IvgwZ/kwZgd4//ZlSoO9/Z8hwDc+/k5HCti2ZVdsV3rFaZtW2eLsrr0zemavknXyBDI8/iRUCAEYaQjsAYMhFopZe33pcf33ziFo6YmE9J8OnKxeP1fK5o5Me1m3bliLB3qDdfWYBPNzVe2+3ZIYH9LzoQG72pfUG+94Q3zfk92s7+d/ypckwXAOqCf3Z4R5F9q5VeMcLsttqe1sNecbOjU2BHz2NKfAAgEFBaAcADJlI1NRrW2r0zFsnw3puZm9YnzNavgSGddsyewN1V5+g/T4BvPe6TgRx2zrHCozegJ0uw5fR+2d6LET3+diTlqGMjIA6mptkdnfIDnb2/kKgU3bwxJ+dUjh2Lr3CPbLDPSfXTp9RKUZs1N6fcWqwj7f1/Tj2pzz+lA+iVludwjteUGTP61IktnRDvjR5p14k34wVcmUXJbdAAMCIR2gHAAy6cMTUq1uO69m3jqi1MzYKnZfl14cWj9VFc0rl9Zwa1m3blsxwfPT6ZNDuOn0A79fWfTJgnQuXJx625c/4wADe9/qZjm57PC5l5mUo0tKlaPS9f1FgW1bsaz0R6oOd/YP96dqCnbG11rYtO9ghBTtktw3068/oN2p/Iuy/7y8A3N4BPMR5bNuWeWyHwttXyzy6VZItSXLllMSmwE+5UIY3kNwiAQApg9AOABg0oXBEazYd0pqNB2QGO1VkhDU929bCiZmaXOSTK/KWzLe6Fe0zvVx9R72tAU0cPz1v4F2hujeAv6stFsBPtMf+J7fPMSPNhsslI5AlBbIG9Hm2GekN9CeD/Ilgr9C7Q36fsG9FJSsqu6dNds9Akr5iI/SnC/vv9wsAB6zXtyMhRfatVWT7C7Jaj8fb3eWz5Zt1mdxl01lmAAAYcoR2AMD7ioW+7ndNKe9dz907wv3uEXAr1KVoT6dc0aAWGtJCv6S+e3MdkaJHzrAAw9W7Lju9X8D+oAAeX8ud4hu3GW6vjPRcKT33jD/Htm0pGu4T8vuO4vedvh/7WH3aZNtSNCQ7GpLd1TywYk/8f/de0/ZPM7IvX/o5/2LFam9QeOeLiux+7eQyBG9A3qnLYlPgc0rO6fUBADgXhHYAgOxIKDYVuG7fOW+qdoJHknqzlOnyyh3IkKs3YMvfG87OIIDLG3DMaHeqMAxD8vpleP1SZsEZf55tW7E1931D/omPTxP2T9yjcE/sBcK9yxwGtF7fdfKXNO8b9vtfk8cns2a3IttXK3pkc+yXDZKM7GL5Zq6Ud8pSGb60gfy1AQAwKAjtAJDCbMtSZO/rCm98XHZ36/vceWJTtXeNZvcGcNOTpr21Yb19uEtNIbd6LJ8CmVlatmCiFsweJ6+PI7BSgWG44lPdNYAN2mzLjI3Yf1DYf1dbbL2+JTvYEVuzP6D1+m7JMuP/6R4zU76Zq+Qun8UUeACAoxDaASBFRau2KbTuYVnN1ZIkI6tQvlmXycjIO3W0+z02VesJRfXS29X629oqdfZEJBWoMDegqy8YpwtmlsjjJvzggxkut4y0bCkte0CfZ0fDJ4/ee1fYf+9fAHTGwrplSh6/vFMulHfGSrnzRg/SVwcAwLkhtANAijGbqhRa97DM6u2xBn+G/PM+Iu+MS8941++eUFQvbqrW39YfVVcwtllcUW6arl4yTotnFBPWMSQMj0+Gxydl5J3x59gn1twHO2UEsmJLAAAAcDBCOwCkCKurReGNjymyZ40kW3K55Z2xUv55H47t4H0GuoNRvbipSs9vqIqH9eK8k2Hd7SKsw9li6/UDHNkGABg2CO0AMMLZkaDCW55VeOuzUjS2qZxnwkL5F14v1xmuO+4ORvTCxmo9v6FK3aHesJ6fro8sGaeF04sI6wAAAIOE0A4AI5RtWYrseS22yVzvOduu4kkKLP643MWTzug1uoMRPb+hSqs3VqunN6yXFqTrw0vGaeG0Yrlc7OoOAAAwmAjtADDC2LYts2qbQuv+JKuld5O57CL5F94gz/j5Z3R8WmdPRKs3VOmFTVXqCcV22B49KkMfXjJOCyqLCOsAAABDhNAOACOI2XRUobcelnlsR6zBnyH/edfIO/1SGe4Pfsvv7Ino+Q1H9cLGagXDsbBeNipDH75wnOZXFsnFeekAAABDitAOACOA1dWi0IbHFN17YpM5j7wzezeZ82d84OdHopaeeeuInlt/VKHesD6mMEMfuXC8zptaSFgHAABIEkI7AAxjdrhH4S3PKLz1b5LZu8ncxEXyL7heruzCM3qNvVWt+s1zu1XT1C1JKi/K1EcuHKd5UwjrAAAAyUZoB4BhyLZMRfa8rvDGx2T3tEuS3CVT5F98o9xFE8/oNbqDUf351QN6efMxSVJOhk83rZzMNHgAAAAHIbQDwDAS22Ruq0LrHpbVclySZGQXy7/o7+QZd94ZbTInSZv3Nuh3q/eqpSMkSbpoTqluuGSSMgLeQasdAAAAA0doB4Bhwmw8otC6h2Ue2ylJMvyZ8p1/jbzTLjmjTeYkqbUzpD+s3quNexokSUV5abr1ikpNG5s3aHUDAADg7BHaAcDhrM5mhTb+WdG9b+jEJnO+WZfJN/eqM9pkToqN0L++tUYPv7RfPaGoXIahKxZV6CMXjpPP6x7cLwAAAABnjdAOAA51cpO55yQzIknyTFos/4KPyZV1ZpvMSVJdc7d+89xu7T7aKkkaV5KlT19ZqYrirMEoGwAAAAlEaAcAh7EtU5Hdryq86Yl3bTL3cbmLJpzx60RNS39bf1RPrjmsqGnJ53Xpo8smaOX8MXK7XINVPgAAABKI0A4ADmHbtsyjW2KbzLXWSJKMnN5N5sae+SZzknSopl0PPLtbVfWdkqQZ4/P1qcunqjA3bVBqBwAAwOAgtAOAA5iNhxV662GZx3dJkoxAlnznXSPv9ItluM78rToUNvX46we1emOVbFvKCHh008rJumBGyYBCPwAAAJyB0A4ASWR1Nim04c+K7nsj1uD2yDfzMvnmXS3Dlz6g19p+qEm/fW6PGtuCkqTF04v18RWTlZ3hS3TZAAAAGCKEdgBIAjvco/A7f1V429/6bDJ3Qe8mc6MG9Fod3WE99OJ+vbmjVpJUkO3XLZdXavbEgoTXDQAAgKFFaAeAIWRbUUV29W4yF+yQJLlLp8Y2mSscP7DXsm2t21mnP7ywT509ERmSVswfo+sumqCAj7d3AACAkYCf6gBgCNi2LfPIO7FN5tpiI+KunBL5F90o99i5A15v3tjWowf/tlfbDjZJksoKM/TpKys1cXROwmsHAABA8hDaAWCQmQ2HFHrrIZk1eyT1bjJ3/rXyTls+oE3mJMmybL24qVqPvXZQoYgpj9vQhy8crysXVcjj5hg3AACAkYbQDgCDxOpojG0yt//NWIPbK9+sy+Wb+6EBbzInSdX1nfr1s7t1qCZ2dvuUMTm69cpKlRZkJLJsAAAAOAihHQASzA53K7z5aYW3Py+ZUUmSZ/KS2CZzmQPfHC4SNfWXNw7r2beOyrRspfnduuHiSbpo7mi5OMYNAABgRCO0A0CC2FZUkZ2vKPz2k302mauU/4KPyz1q3Fm95p6jLXrguT2qa+6WJJ03pVCfXDVFeVn+RJUNAAAAByO0A8A5sm1b0SNvK7TuT7Lb6iRJrtzS2CZzFXMGvMmcJHUHo3r0lf165Z3jkqScTJ9uXjVF508tSmjtAAAAcDZCOwCcA7P+YGyTudq9kno3mZv/UXkrl8twuc/qNTftadDvVu9RW2dYkrR87mjdcPFEpQe8CasbAAAAwwOhHQDOgtXRoND6Pyt64K1Yg9sr3+wr5JvzIRm+tLN6zZaOkP6weq827W2QJBXnpenTV1ZqakVeosoGAADAMENoB4ABsENdCm1+WpHtqyUrKsmQZ8oS+ed/TK7M/LN6Tcu29fqW4/rTywfUE4rK7TJ0xaIKfeTCcfJ6zm60HgAAACMDoR0AzoBtRhXZ9bJCm56QQl2SJPfoafIv/rjco8ae9evWNHXpN8/t0d6qVknS+NIsffrKaSovykxA1QAAABjuCO0A8D5s21b08CaF1j0iu713k7m80bFN5spnn9Umc5IUNS09t+6onlp7WFHTks/r0nUXTdTK88fI5eIYNwAAAMQQ2gHgPZj1BxR68yGZdfskSUZatnzzr5N36rKz3mROkg4eb9cDz+5SdUNsxH7m+Hx96vKpGpV7dmvhAQAAMHIR2gHgXaz2BoXWP6LowfWxBrdPvjlXyDf7yrPeZE6SguGoHn/tkF7YVCXbljLTvLpp5WQtnl581iP2AAAAGNkI7QDQK7bJ3F8U2f5Cn03mlsq/4Dq5Ms5tB/dtB5v02+f2qKk9KEm6YEaxblwxWdnpvgRUDgAAgJGK0A4g5dlmVJGdLyr09lMnN5krmyH/4hvlLqg4p9fu6A7roRf36c0dsfXwBdkB3XrFVM2cUHDOdQMAAGDkI7QDSFm2bSt6aKNC6x+R3V4vSXLllcXC+phZ5zRl3bZtvbWjTn98cZ86eyIyDGnV/HJdu2y8Aj7eegEAAHBm+MkRQEoy6/Yr+NZDsur2S5KMtBz5Flwn75Sl57TJnCQ1tvbot3/bo+2HmiVJYwoz9Okrp2nC6OxzrhsAAACphdAOIKVY7fW9m8xtiDV4fPLNvlK+OVfK8AbO7bUtWy9srNJjrx9UOGLJ43bpmqXjdPnCCnncrgRUDwAAgFRDaAeQEuxgZ2yTuR0vSJYpyZB36lL55p/7JnOSVFXfqQee3aVDNR2SpKnlubr1ykqV5Kef82sDAAAgdRHaAYxothlRZMeLCm3+y8lN5sbMlH/RjXIXlJ/z60eipp5ae1jPrTsq07KV5vfo7y6ZqGVzRsvFMW4AAAA4R4R2ACOSbduKHtwQ22Suo0GS5MobI//iG+Upn5WQZ+w52qIHntujuuZuSdL5Uwv1yVVTlJvpT8jrAwAAAIR2ACOOWbsvtslc/QFJkpGeK9/8j8o7ZZkM17mvLe8ORvSnlw/otS3HJUk5mT7dvGqqzp9aeM6vDQAAAPRFaAcwYlhtdbFN5g5tjDV4fPLN+ZB8s684503mTti0p16/e36v2rrCkqSL547W9RdPVHrAm5DXBwAAAPoitAMY9uxgp0JvP6nIzpdim8wZhrxTl8U2mUvPTcgzWjpC+t3ze7R5X6MkqSQ/XZ++slJTyhPz+gAAAMDpENoBDFu2GVFk+wsKbX5KCvdIktzls+Rf9Hdy55/7JnOSZNm2XnvnuB55Zb96QqbcLkNXLh6rDy8ZK6/n3M5zBwAAAD4IoR3AsGPbtqIH1im04VHZHbGRb1d+eWyTuTEzE/acmqYu/ebZ3dpb3SZJmjA6W5++olJjijIT9gwAAADg/RDaAQwr0dq9Cr35kKyGg5Jim8z5F3xMnskXJmSTOUmKmpaeXXdUf1l7SFHTlt/r1nXLJ2jFeWPkcnGMGwAAAIYOoR3AsGC11Sq07hFFD2+KNXj88s39kHyzrpDhTdwRaweOt+mBZ3frWEPsTPdZEwp0y+VTNConLWHPAAAAAM4UoR2Ao1nBDoU3PanIzpcl+8Qmc8vlm39twjaZk6RgOKrHXj2oFzdVy5aUmebVJ1ZO1qLpxTIMRtcBAACQHIR2AI5kRcMKbv6rejb13WRutvyLbpQ7vyyhz9p6oEkP/m23mtpDkqQlM0t046WTlJXuS+hzAAAAgIEitANwnPCBDap+6yFF2xokSa6CcvkXfVyeMTMS+pz27rAeemGf3tpZJ0kalRPQp66YqpnjCxL6HAAAAOBsEdoBOIYdCSn0xu8U2fO6JMnIyIttMjdpScI2mZNiu8+/uaNWD724X509ERmGdNmCcl27dIL8Po5xAwAAgHMQ2gE4gtl4WD0v3i+7rVaSodwl10ozPiTT8Cb0OQ2tPfrtc7u143CLJKm8KFOfvrJS40uzE/ocAAAAIBEI7QCSyrYtRbY9r9D6RyTLlJGRp4yVdyh/5gK1tHRJUSshzzEtSy9srNbjrx9UOGLJ43bpmqXjdPnCCnnciRvFBwAAABKJ0A4gaazuNgVf+R+Z1dslSZ5x5ylw0WflzUzsqPfRug79+tndOlLbIUmqrMjVrVdUqjg/PaHPAQAAABKN0A4gKaJVWxV85Reye9olt1f+C26Sd9olCT1eLRwx9dTaw3pu3VFZtq10v0d/d+kkLZtdyjFuAAAAGBYI7QCGlG1GFFr3iCLbn5ckufLHKHDpFxN+jNuuIy36zXO7Vd8SOy5ufmWRPrlysnIy/Ql9DgAAADCYCO0AhozZelzBF++X1XRUkuSdsVL+RX8nw5O489C7ghE98vJ+vbalRpKUm+nTLZdN1bwphQl7BgAAADBUCO0ABp1t24rseU2hN34vRcMyAlkKLP+cPGPnJvQZm/Y06Her96q9KyxJumRemT62fKLSA7zVAQAAYHjiJ1kAg8oOdSn42q8VPbRRkuQum6HAxbfJlZGXsGe0dIT0u+f3aPO+RklSaUG6br2iUlPKcxP2DAAAACAZCO0ABk20Zo+CL/1MdlezZLjlX/gxeWdfIcNIzBFrlm3r1c3H9MgrBxQMm3K7DF11wVhddcE4eT0c4wYAAIDhj9AOIOFsy1T47acU3vyUZNsysouVtuILcheOT9gzjjd26YHndmt/dZskaeLobN16ZaXGFGYm7BkAAABAshHaASSU1dGgnpd+JqtuvyTJM+VCBZbcLMOXlpDXj5qWnnnriJ5+47Cipi2/z63rl0/UJfPK5HJxjBsAAABGFkI7gISJHFin4OsPSOEeyZumwLJb5Z20OGGvv/9Ym37z7G4da+ySJM2eWKBbLpuqgpxAwp4BAAAAOAmhHcA5syNBBdf+XtG9r0uSXEUTlXbpF+TKTswxaz2hqB577aBe2lQtW1JWulefWDlFC6cVyTAYXQcAAMDIRWgHcE7MxsPqefF+2W21kgz55l0t3/nXyHAl5u1ly/5GPfj8HjW3hyRJF84q0Y2XTlZmmjchrw8AAAA4GaEdwFmxbUuRbX9TaP2jkmXKyMhX4JLPyzO6MiGv39oR0n2PbdNbO+skSaNyArr1ykrNGJefkNcHAAAAhgNCO4ABs7pbFXzlFzKrt0uSPOPOV+Ciz8gIJGbn9vW76vSbZ3erozsiw5AuX1iha5aOl9/rTsjrAwAAAMMFoR3AgESPblHwlV/IDnZIbp/8F9wk77SLE7a2fOuBJv33Y9tk21JFcaY+fWWlxpVkJ+S1AQAAgOGG0A7gjNhmRKF1f1Jk+2pJkiu/XIEVX5A7ryxhzzha16GfPrldti1dOr9cN6+aLNkJe3kAAABg2CG0A/hAZstxBV/6qaymKkmSd+Yq+RfeIMPjS9gzWjpC+vGjWxUKm5o+Lk9fuWGuOjt6FI1aCXsGAAAAMNwQ2gG8J9u2Fdn9qkJv/EEywzICWQpc/Dl5KuYm9DnBcFQ/fnSLWjpCKi1I11evny2vx5XQZwAAAADDEaEdwGnZwU4FX/u1ooc3SZLcZTMUuOR2udJzE/ocy7L1syd36Ghdp7LSvfr6DXOUEeA4NwAAAEAitAM4jWjNHgVf+pnsrmbJ5ZZ/wfXyzr5chpH40e+HXtynLQea5PW4dOfHZqswNy3hzwAAAACGK0I7gDjbMhV++0mFN/9Fsm0ZOcVKu/QLcheOH5Tnrd5YpRc2VUuSbr96uiaW5QzKcwAAAIDhitAOQJJkdTSo56WfyarbL0nyTFmmwIWflOENDMrzNu9r0EMv7JMk3XDxRM2vLBqU5wAAAADDGaEdgCL731Lw9d9IkR7Jm6bAslvlnbR40J53uLZdP3tqh2xJy+eO1hWLKgbtWQAAAMBwRmgHUpgdCSq49neK7l0jSXIVT1LapXfIlVU4aM9sbg/qx49uVThiacb4fH1y1RQZhjFozwMAAACGM0I7kKLMhkPqeel+2W11kmHIN+/D8p13jQyXe9Ce2ROK6r8e2aK2zrDKCjP0xWtmyuPmaDcAAADgvRDagRRj25YiW59TaMOfJcuUkZGvwKV3yFM6dVCfa1qWfvrkdlU3dCknw6evXz9H6QHeggAAAID3w0/MQAqxulsVfPl/ZB7bIUnyjDtfgYs+IyOQOajPtW1bv39+r7YfbJbP69Kd189WQc7gbHAHAAAAjCSEdiBFRI++o+Arv5Qd7JDcPvmXfELeyuVDsp78b+ur9Mo7x2VIuuPDMzS+NHvQnwkAAACMBIR2YISzo2GF1j+iyPbVkiRXQbkCl35R7rzRQ/L8TXvq9cjLsWPkblwxWfOmDN4mdwAAAMBIQ2gHRjCz5ZiCL94vq7lKkuSduUr+hTfI8PiG5PkHj7frf/6yU7akS88r06r5Y4bkuQAAAMBIQWgHRiDbthXZ9YpCb/5RMsMyAlkKXHybPBVzhqyGxtYe3fPoFoWjlmZPLNBNKydztBsAAAAwQIR2YISxg50KvvZrRQ9vkiS5y2YocMntcqXnDlkN3cGI/uvRrWrvjqi8KFN3fGSG3C6OdgMAAAAGitAOjCDR47sVfPnnsruaJZdb/oXXyzvrchnG0AXmqGnpvx/fruONXcrN9Olr189Wmp+3GgAAAOBs8JM0MALYVlThTU8qvPlpSbaMnGKlXfpFuQvHDW0dtq0H/7ZHu460yO916+s3zFF+Nke7AQAAAGeL0A4Mc1Z7g3peul9W/QFJkmfKMgUu/KQM79CH5WfeOqLXt9bIMKQvXDNDFcVZQ14DAAAAMJIQ2oFhLLL/LQVf/40U6ZF8aQos+7S8ExclpZb1u+r051cPSpI+sXKK5kwalZQ6AAAAgJGE0A4MQ3a4R8E3fqfo3rWSJFfxJKVdeodcWck5A31/dZt+8fQuSdKq+eVacT5HuwEAAACJQGgHhhmz4ZB6XrxfdnudZBjyzfuIfOd9RIbLnZR66lu6dc+ftypqWpo3eZRuvHRSUuoAAAAARiJCOzBM2Lal8JbnFN7wZ8k2ZWTkK3DpHfKUTk1aTZ09Ef3XI1vV2RPR2JIsff7DM+RycRY7AAAAkCiEdmAYsLpbFXz5f2Qe2yFJ8oyfr8BFn5Hhz0haTVHT0n8/tk21zd3Kz/bra9fPlt+XnNF+AAAAYKQitAMOFz3yjoKv/lJ2sEPy+ORf8kl5p14kw0jeiLZt23rg2d3aU9WqgM+tr18/R7mZ/qTVAwAAAIxUhHbAoexoWKF1f1JkxwuSJFdBhQIrviB37ugkVyb9Ze1hvbG9Vi7D0JeunakxRZnJLgkAAAAYkQjtgAOZLccUfPGnspqrJUnemZfJv+gGGW5vkiuT3txeqyfWHJIk3Xz5FM2cUJDkigAAAICRi9AOOIht24rselmhN/8omREZadkKLL9NnorZyS5NkrTnaIt+/WzsaLcrFlXo4rllSa4IAAAAGNkI7YBD2MFOBV/7laKH35YkucfMVODi2+VKz0lyZTG1zd2697Ftipq2zp9aqOsvnpjskgAAAIARj9AOOED0+C4FX/657K4WyeWWf+EN8s66TIbhSnZpkqSO7rD+65Et6gpGNWF0tm6/erpcSdwIDwAAAEgVhHYgiWwrqvDGJxR+56+SbBk5JUpb8QW5R41Ldmlxkaipnzy2TfUtPRqVE9BXPzZbPi9HuwEAAABDgdAOJInVXq+el+6XVX9QkuSdepH8Sz4hwxtIcmUnWbatX/51l/ZXtynN79HXbpijnAxfsssCAAAAUgahHUiCyP43FXz9N1IkKPnSFFj2GXknLkx2Wad44vVDWr+rXm6XoS9/dKbKRmUkuyQAAAAgpRDagSFkh3sUXPugovvekCS5iycrcOkdcmWNSnJlp1qztUZPv3FYkvSpK6Zq+rj85BYEAAAApCBCOzBEzPqD6nnpftnt9ZJhyHfeNfLN+7AMl/PWh+863KzfPLdbknT1krFaNnt0kisCAAAAUhOhHRhktm0pvOVZhTc8JtmmjMwCBS69Q56SKcku7bSON3bp3se3y7RsLZxWpGuXTUh2SQAAAEDKIrQDg8jqalHwlf+ReWynJMkzYYECyz4tw+/MteFtXbGj3XpCUU0qy9HnrprG0W4AAABAEhHagUESPbJZwVd+KTvUKXl88i/5pLxTL5Lh0BAcjpj6yZ+3qrEtqKLcNH31Y7Pk9Thv6j4AAACQSgjtQILZ0bBCbz2syM4XJUmuggqlrfiiXLmlSa7svVm2rV88vVMHj7crI+DR1/9ujrLSOdoNAAAASDZCO5BAZvMxBV/8qayWakmSd9bl8i+8Xobbm+TK3t+fXz2gjXsa5HYZ+sp1s1SSn57skgAAAACI0A4khG3biux6WaE3/yiZERlp2QpcfJs85bOTXdoHevWdY3r2raOSpM9+aJqmVuQluSIAAAAAJxDagXNkBzsVfPWXih7ZLElyl89SYPltcqXnJLmyD7b9UJMe/NteSdI1S8frgpklSa4IAAAAQF+EduAcRI/vUvCln8nubpVcbvkX/p28s1bJMFzJLu0DVTd06r7Ht8uybV0wo1gfuXBcsksCAAAA8C6EduAs2FZU4Y1PKPzOXyXZcuWUKLDii3KPGpvs0s5Ia2dIP35ki4JhU1PKc/XpK6c5dld7AAAAIJUR2oEBstrr1fPi/bIaDkqSvJUXyX/BJ2V4/Umu7MyEwqbueXSrmtpDKs5P11eumyWvx/kzAwAAAIBURGgHBiCy7w0F1/xWigQlX7oCF31G3gkLkl3WGbMsWz//yw4dru1QZppX37hhtjLTnL2zPQAAAJDKCO3AGbDDPQqu+a2i+9+UJLlLpihw6R1yZRYkubKB+dPL+7V5X6M8bpe++rFZKsrjaDcAAADAyQjtwAcw6w+q58Wfyu5okAxDvvOulW/e1TJc7mSXNiAvbqrW8xuqJEmfu2qaJo/JTW5BAAAAAD4QoR14H+GdLyu09neSbcrILFDg0i/IUzI52WUN2NYDjfrDC7Gj3a67aIIWTS9OckUAAAAAzgShHXgPZuOReGD3TFiowLJbZfgzkl3WgB2t69BPn9wh25aWzi7VVRcMjx3uAQAAABDagdOyzaiCr/wiFtjHz1dgxReH5ZFoLR0h/fjRrQqFTU0bm6dPXT51WH4dAAAAQKrinCfgNMKb/yKruUpGIEv+pZ8alkG3JxTVjx/ZopaOkEoL0vXlj86Ux823PAAAADCc8BM88C5m4xGFNz8tSfJfeItcadlJrmjgTMvSz57aoaP1ncpO9+rrN8xReoCj3QAAAIDhhtAO9GGbUQVfPTkt3jOMzmA/wbZt/fGFfdp6oElej0tfvX62CnPTkl0WAAAAgLNAaAf6CL/ztKymKhn+TPkvvGVYTot/YWO1Xnr7mAxJt189XRNH5yS7JAAAAABnidAO9DIbjyj89l8kSf6lt8iVPvzC7ua9DXroxX2SpBsumaT5lUVJrggAAADAuSC0A5Jsq8+0+HHnyzNhYbJLGrDDte362V92yJZ08dzRunxhebJLAgAAAHCOCO2ApPDmv8pqqpL8GcNyt/imtqB+/MhWhSOWZo7P1ycvmzLsvgYAAAAApyK0I+WZTUcVfvspSVLgwuE3Lb4nFNV/PbpFbV1hjSnM0BevnSm3i29tAAAAYCTgJ3ukNNuKKvhKn2nxExclu6QBiZqW7ntiu441dCknw6evXT9HaX5PsssCAAAAkCCEdqS08Dt/ldV0tHda/PDaLd62bf1h9V7tONQsn9elr90wWwU5gWSXBQAAACCBCO1IWWZTVZ9p8TfLlZ6b3IIG6G/rq/TKO8dlSLrjIzM0riQ72SUBAAAASDBCO1JSfFq8Zcoz7jx5Ji5OdkkDsnF3vf708n5J0sdXTNa8yYVJrggAAADAYCC0IyWF33lGVtORYblb/IHjbfqfp3dKklacN0Yr549JckUAAAAABkvSQ7tlWbrnnnu0bNkyzZkzR5/97Gd15MiR97w/EonoP//zP7Vs2TLNnTtXN998s3bt2jWEFWO4i02Lf1KSFFjyyWE1Lb6htUc/eXSrIlFLsycW6OMrJw2rXzgAAAAAGJikh/b77rtPDz30kL73ve/p4YcflmEYuv322xUOh097/7e//W09+uij+u53v6s///nPys3N1e23366Ojo4hrhzDkW1FFXy1d1r82HnyTLog2SWdse5gRP/1yBa1d0dUUZypL1wzg6PdAAAAgBEuqT/xh8Nh/epXv9JXv/pVLV++XJWVlbr77rtVV1en1atXn3J/VVWVHn30Ud111126+OKLNXHiRP3gBz+Qz+fT9u3bk/AVYLgJv/OMrMbeafHLbh02o9RR09J/P75dNU3dysvy62vXz1HAx9FuAAAAwEiX1NC+e/dudXV1afHik5uAZWdna/r06dqwYcMp969Zs0bZ2dm66KKL+t3/0ksv6YILhs+IKZLDbB6e0+Jt29Zvn9ujXUda5Pe59bXrZysvy5/ssgAAAAAMgaQO1dXW1kqSSktL+7UXFRWppqbmlPsPHz6s8vJyPf/88/r5z3+uuro6TZ8+Xd/85jc1ceLEc6rF43H2NGO329XvTwyMbUbV/eovJcuUd9w8BSovHDaj7E+tOaQ122pkGNJXrpulCWU5yS5p0NHfkUro70gl9HekEvo7EiWpob2np0eS5PP5+rX7/X61tbWdcn9nZ6eOHj2q++67T//0T/+k7Oxs/fSnP9UnPvEJPfPMMyooKDirOlwuQ3l5GWf1uUMtOzst2SUMSy1r/yyz4bBcgQyVfuTL8mRlJrukM/La5mo9+soBSdIdH52tixeMTXJFQ4v+jlRCf0cqob8jldDfca6SGtoDgYCk2Nr2Ex9LUigUUlraqZ3b6/Wqo6NDd999d3xk/e6779by5cv1+OOP67bbbjurOizLVnt791l97lBxu13Kzk5Te3uPTNNKdjnDitlUrfbXHpYkBS68WR1Rn9TSleSqPtjeqlb91x83S5IuX1ShJdOL1DIM6k4E+jtSCf0dqYT+jlRCf8f7yc5OO+NZGEkN7SemxdfX16uioiLeXl9fr8rKylPuLykpkcfj6TcVPhAIqLy8XNXV1edUSzQ6PL6RTNMaNrU6gW2Z6n7x55Jlyl0xV64Ji4fF319dS7f+609bFDEtzZs8Sjcsnzgs6k40+jtSCf0dqYT+jlRCf8e5SuoCi8rKSmVmZmrdunXxtvb2du3cuVPz588/5f758+crGo1q27Zt8bZgMKiqqiqNHZta04ZxZsJbnpXVeFjypSswTHaL7+yJ6L8e2arOnojGlWTp8x+eIZfL+XUDAAAASLykjrT7fD7dfPPN+tGPfqT8/HyVlZXphz/8oUpKSrRq1SqZpqnm5mZlZWUpEAho/vz5WrJkif75n/9Z3/nOd5Sbm6t77rlHbrdb11xzTTK/FDiQ2Vyt8KYnJPXuFp+Rl9yCzkAkaunex7aprrlbBdl+fe362fL73MkuCwAAAECSJH0rwzvvvFPXX3+9vvWtb+mmm26S2+3WL3/5S/l8PtXU1Gjp0qV65pln4vf/5Cc/0cKFC/WVr3xF119/vTo7O/Xb3/5W+fn5Sfwq4DS2ZSr46i8lKyp3xRx5Ji9JdkkfyLZtPfDsLu2talWa362v3TBHOZkc7QYAAACkMsO2bTvZRSSbaVpqbnb2Bl8ej0t5eRlqaeliTcwZCL3ztMLrH5V86cq44fvDYpT9yTWH9OSaQ3IZhr7+d7M1c/zZnYYwEtDfkUro70gl9HekEvo73k9+fsYZb0SX9JF2INHM5mMKb3xCkhRY8olhEdjf3F6rJ9cckiTdcvmUlA7sAAAAAE4itGNEiU2L/0WfafEXJrukD7TnaIt+9cwuSdKViyu0fG5ZkisCAAAA4BSEdowo4a3PyWr4/+3dd3RUdd7H8c/MJJNCCKTSQYoQAqE3FURULBRXmgqChaIrCi7CqpRHXOuqCDZwFUEFZUVReGwI2DsJogiEBAg1CIQASUibTHv+SNE8KBBIcu9M3q9zOAfu3Jn5zpyL8sn93N/dLdlDFNznFtOvFn/waJ5eeG+z3B6vurWJ0bC+LU//JAAAAAA1BqEdfsN9/ICKNqyUJAVfYP5afE5+kZ55Z5PyCl1q0TBc4wfFy2ryHzIAAAAAqF6EdvgFr8etwi9LVotv0kEBrXsbPdIpOV1uvfDuZh3JKlR0nWBNHtZB9kBu7QYAAACgPEI7/ELRr2vkObKruBZ/8a2mrsV7vF4t+mibdh7IVmhQgP4xoqPCa9mNHgsAAACACRHa4fPcx39T0U/vSfKNWvyqb3YpcVuGbFaL7hyaoIbRtYweCQAAAIBJEdrh04pr8a9Ibt+oxX+z6Td9+P1eSdLNV8WpbTNz/4ABAAAAgLEI7fBpzs0ltfhA868Wn7znmJasSZUkDbrwPPXu0MDgiQAAAACYHaEdPsud9ZscG0pr8SNlDYs0eKK/diAzT/NXbpHb41XP+Hoa0qe50SMBAAAA8AGEdvgkr8dTvFq82yVbkwQFtOlj9Eh/KTuvSM++s0kFDpdaNa6jsQPiTN0IAAAAAGAehHb4JOfmNfJkpJm+Fu9wuvXcil+VmV2o2IgQTRqaoMAAbu0GAAAA4MwQ2uFzimvx70qSgi64QdawKIMn+nMer1evfJis3QdzVCs4QFNGdFTtUG7tBgAAAODMEdrhU7wejwq/Wlxci2/cXoFtLjZ6pL+04ss0/ZR6RAE2iyYN66B6kaFGjwQAAADAxxDa4VOcW9bIc3inFBis4ItvNW0t/sufD+iT9fskSbcOaKvWTeoaOxAAAAAAn0Roh8/wZB2UI6l4tfigC0aatha/ZddRvbF2uyTp2t7NdUG7+gZPBAAAAMBXEdrhE7wejwq+WiS5naauxadn5GrBqi3yeL26sH19Db7oPKNHAgAAAODDCO3wCc4ta01fiz9+wqFnVmxSYZFbcU3r6parubUbAAAAgHNDaIfpebIOyZFUslp8L3OuFu8oKr6127Ech+pHhmrikAQF2PjrBQAAAODckCpgasW1+FeKa/GN2ikwrq/RI53E4/Hqpfe3au/hEwoLCdQ/RnRQWEig0WMBAAAA8AOEdpiac8u632vxfceasm6+/POd+mVnpgJsVk0e1kGxEdzaDQAAAEDlILTDtDzZh+RIWiHJvLX4z35K17oN+yVJ4we1VavGdQyeCAAAAIA/IbTDlLwejwq/XGTqWvwvOzO17NPiW7sN69tCPdrWM3giAAAAAP6G0A5Tcm5dJ/fhHaZdLX7voRN66X+3yuuV+nRooAG9mhk9EgAAAAA/RGiH6XiyD8mRWLJafM/rZa0dbfBE5R3LKdSzKzbJ4XSrbbMIjbmyjel+qAAAAADAPxDaYSper0eFXy2W3EXFtfi2lxg9UjkFDpeeXfGrsnKL1DC6lu4c0p5buwEAAACoMqQNmIpzy6dyH9peUou/xVRnsN0ej156f6v2Z+QqvJZd/xjeQaHB3NoNAAAAQNUhtMM0PNmH5UgsWS2+53Wy1o4xeKLfeb1eLft0h35NOyp7QPGt3aLrhhg9FgAAAAA/R2iHKRTX4hcV1+IbtlVg235Gj1TOuqT9+mLjAVkkTRjcTi0ahhs9EgAAAIAagNAOU3Bu/ay4Fh8QpOC+Y01Vi9+4/YiWf75TkjSiXyt1bWOeBgAAAAAA/0Zoh+E82YflWP+OJCmo1/WmqsXvPpijl9/fKq+kSzo30pU9mhg9EgAAAIAahNAOQ3m9HhV+vfgPtfhLjB6pjNfr1eKPt6nI5VH7FpG6sf/5pmoAAAAAAPB/hHYYyrn1M7kPphbX4i8eK4vFPIdk+pE8HTiSpwCbRbcNbieb1TyzAQAAAKgZSCEwjCcnQ47Eklp8z+tkDTdPLV6SErcdliQltIhSWAi3dgMAAABQ/QjtMETZavGuklp8vLlWi/d6vWWhvWd8PYOnAQAAAFBTEdphCOfWz01bi5ekPYdO6EhWoeyBVnVsGW30OAAAAABqKHMlJdQIxbX4tyVJQT1HmK4WL0nrk4vPsndqFa0gu83gaQAAAADUVIR2VKtytfgGcQqMv9TokU7i8XqVlJIhSerZlmo8AAAAAOMQ2lGtnMmltXi7gvuarxYvSTvTs3X8hEMhQTa1bxFl9DgAAAAAajDzJSb4LU9OhhzrS1aL73GdrOGxBk/059aXLEDX5fwYBQbwVwQAAACAcUgkqBbFtfjFksshW4M2Cmxnvlq8JLk9Hv1UUo3vwarxAAAAAAxGaEe1cCZ/IffBlJJa/DhT1uIlKWVflnLynQoLCVTbZhFGjwMAAACghjNncoJf8eQckWN9yWrxPUaYthYvSYklq8Z3axOjABt/PQAAAAAYi1SCKuX1elT49R9r8ZcZPdJfcrk9+in1iCSpB6vGAwAAADABQjuqlHPbl3L/tk2ymbsWL0lbdh9TvsOlOmF2tW5S1+hxAAAAAIDQjqrjOXFEjh+XS5KCepq7Fi9JiSWrxnePi5XVajF4GgAAAAAgtKOKlFstvn5rU9fiJcnhdOvnHZmSqMYDAAAAMA9CO6qEL9XiJWlz2lE5ityKCg9Wy4bhRo8DAAAAAJII7agCnhN/XC1+uKx1zH/murQa36NtrCwWqvEAAAAAzIHQjkrl9XpV+PWrkrOwuBbf/nKjRzqtAodLm9KOSqIaDwAAAMBcCO2oVM5tX8p9ILmkFj/W9LV4SfplZ6acLo/qRYaqab0wo8cBAAAAgDLmT1TwGZ4TmXKsL1ktvscwWevUN3iiM5OYXFyN70k1HgAAAIDJENpRKU6uxfc3eqQzklvg1JbdxyRJ3anGAwAAADAZQjsqhTPlK7kPbJVsgT5Ti5ekjduPyO3xqnFMLTWKrmX0OAAAAABQjm8kK5ia50SmHD++JUkK6j7cZ2rx0h9XjecsOwAAAADzIbTjnJSrxdc732dq8ZKUnVekbXuPSyq+1RsAAAAAmA2hHeekfC1+nCxW3zmkfkrNkNcrNW9QW7ERoUaPAwAAAAAn8Z2EBdPx5B79Qy1+mKx1facWL/2+ajzVeAAAAABmRWjHWfF6vSr8arHkLJS1XisFtr/C6JEq5FhOobanZ0uSusdRjQcAAABgToR2nBVn6tdltfgQH6vFS1JSSoYkqXXjOooMDzZ4GgAAAAD4c76VtGAKntyjcvzwX0lSUPehstZtYPBEFVe2anw81XgAAAAA5kVoR4X8cbX44lr8lUaPVGEZx/O1++AJWSxS1zZU4wEAAACYF6EdFeJM/Vru9C2SLcAna/GSlLituBrftlmE6tSyGzwNAAAAAPw130tcMExxLb5ktfhuw3yyFi/9HtpZNR4AAACA2RHacUa8Xq8Kv3lNchbIGttSgQm+V4uXpAOZeUo/kiub1aIurWOMHgcAAAAATonQjjPiSv1G7v2bJVuAgi/xzVq8JCWVLEDXvnmkwkICDZ4GAAAAAE7NN5MXqpUn95gKS1eL7zZUtroNDZ7o7Hi9Xq0vrcazajwAAAAAH0BoxymdXIu/yuiRztq+w7k6fCxfgQFWdWoVbfQ4AAAAAHBahHackmv7t3Lv/7W4Fu+jq8WXKr03e8eWUQoJCjB4GgAAAAA4Pd9NYKhyxbX4ZZIke9ehskX4Zi1eKm4MlIZ2Vo0HAAAA4CsI7fhTZbX4ogJZY1vI3sF3a/GSlPZbjo7mOBRktymhZZTR4wAAAADAGSG040+Vr8WP9+lavPR7Nb7z+dEKCrQZPA0AAAAAnBnfTmKoEp6843+oxQ/x6Vq8JHk8XiWllKwaTzUeAAAAgA8htKOccrX4GN+vxUvS9v1Zys4tUmhQgNo3jzR6HAAAAAA4Y4R2lOPa8Z3c+zZJ1gAFXzJOFqvvV8lLq/Fd28QowMYhDwAAAMB3kGBQxpN3XIXfvylJsne7VraIRgZPdO5cbo82pB6RJPWIpxoPAAAAwLcQ2iHp/9fim8ve4WqjR6oU2/YeV26BU+GhgYprWtfocQAAAACgQgjtkCS5dnz/ey2+73i/qMVLUmJySTU+LlY2H18BHwAAAEDNQ4pB+Vp812tli/T9WrwkOV1ubdxRXI3vyarxAAAAAHwQob2G+70Wn19ci+/oH7V4Sdqy65gKHG5F1A5Sq8Z1jB4HAAAAACqM0F7Dla/F+8dq8aXWl6wa3z0uVlaLxeBpAAAAAKDiCO01mCc/6w+1+L/JFtnY4Ikqj6PIrV92ZkqSerJqPAAAAAAfRWivobxerwq/fq24Fh99nuwdBxg9UqXalJapIqdHMXWDdV792kaPAwAAAABnhdBeQ7l2/iD3vl8kq03Bl/jPavGl1pesGt+jbT1ZqMYDAAAA8FGE9hqoXC2+i3/V4iUpv9ClzbuOSioO7QAAAADgqwjtNYzX65Xjm9clR15xLb7TQKNHqnQ/7zgil9urBlGhahxTy+hxAAAAAOCsEdprGNfOH+Ta+3NJLd6/VosvlbgtQ1LxvdmpxgMAAADwZYT2GuTkWnwTgyeqfCfyi5S855gkqXvbWIOnAQAAAIBzQ2ivIcrX4pvJ3sm/Vosv9dP2I3J7vGpaL0wNoqjGAwAAAPBthPYawpX24++1+L7jZbEGGD1SlUgsWTW+JwvQAQAAAPADhPYawJOfpcLv3pAk2btcI1uU/9XiJSkr16HUfVmSpO5xVOMBAAAA+D5Cu5/zer1yfLukuBYf1cwvV4svlZSSIa+klo3CFV03xOhxAAAAAOCcEdr9nCttvVx7NkoWm4Iv8d9avCQlbiuuxveIoxoPAAAAwD8Q2v2YJz9bhd8tleTftXhJyswuUNqBHFkkdaMaDwAAAMBPENr9VPlafFPZO/tvLV4qrsZLUpumdRVRO8jgaQAAAACgchDa/VRxLf6nGlGLl6TE5OLQ3oNV4wEAAAD4EUK7H/LkZ8tRtlr8YNmimho8UdU6dCxfew+fkNViUdc2MUaPAwAAAACVhtDuZ0pr8V5HbkktfpDRI1W50gXo4ptHqHao3eBpAAAAAKDyENr9jGtX4u+1+L7j/L4W7/V6tT65OLT3pBoPAAAAwM8Q2v2IpyBHjm9LVovvPEi26GYGT1T1DhzJ08Gj+QqwWdT5fKrxAAAAAPwLod2P/F6LbyJ758FGj1Mt1pdU4xNaRCk02L9bBQAAAABqHkK7n3CmJcq1e0NJLX68LDb/D7Ber7fsenZWjQcAAADgjwjtfsBTkCPHdzWrFi9Jew6d0JGsQtkDrerUKtrocQAAAACg0hHa/YDju6XyFp6QNbLm1OKl31eN79QqWkF2m8HTAAAAAEDlI7T7OOeuRLl2JUkWq4IvqRm1eEnyeL1K3JYhiWo8AAAAAP9FaPdhNXG1+FI707N1/IRDIUE2JbSINHocAAAAAKgShHYf5vjujZJafGPZO19j9DjVqrQa3+X8GAUGUI0HAAAA4J8I7T7KuStJrl2JNa4WL0luj0cbUkqq8fFU4wEAAAD4L0K7DyquxS+RJNk7DZQt+jxjB6pmKfuylJPvVFhIoNo2izB6HAAAAACoMoR2H1SuFt/lb0aPU+2SSqrxXdvEKMDGIQwAAADAf5F4fExR2h9q8X1rVi1eklxuj35KPSKJVeMBAAAA+D9Cuw9x5+co/+vXJZXU4mPOM3YgA2zdfUx5hS7VqWVXmyZ1jR4HAAAAAKoUod2HZK55Rd6CHFkjGsvepWatFl+qdNX47nGxslotBk8DAAAAAFWL0O4jinZtUF7ydyWrxY+TxRZo9EjVrsjp1sYdmZJYNR4AAABAzUBo9xFF27+XJAV3HihbTHODpzHGr2lH5ShyKyo8WC0bhhs9DgAAAABUuZq1ipkPC+kxTHXadJWraU+5vUZPY4yyanzbWFksVOMBAAAA+D9Cu4+wRTZSeMvWOn48T3J5jB6n2hU4XNqUdlSS1JNV4wEAAADUENTj4RM27cyU0+VRvYgQNa0XZvQ4AAAAAFAtCO3wCYnbMiQV35udajwAAACAmoLQDtPLK3Rq867iajyrxgMAAACoSQjtML2NqUfk9njVOKaWGkXXMnocAAAAAKg2hHaYXumq8T1YgA4AAABADcPq8TC1nLwiJe89Lknq0TbW4GkAAABQE3k8Hrndrgo+x6LCQpuKihxy19R7NtdQNluArNbKOz9OaIepbUjNkNcrnVe/tmIjQo0eBwAAADWI1+tVTs4xFRTkntXzMzOt8nhq3u2aIYWEhCk8PLJSFtEmtMPUEpOpxgMAAMAYpYE9LCxCdntQhQOYzWbhLHsN4/V6VVTkUG5ucVu4Tp2oc35NQjtM61hOoXakZ0uiGg8AAIDq5fG4ywJ7WFj4Wb1GQIBVLhdn2msauz1IkpSbe1y1a0ecc1WehehgWhtSMuSVdH7jOooMDzZ6HAAAANQgbrdb0u8BDKiI0uOmomsh/BlCO0xr/bYMSVTjAQAAYJzKuCYZNU9lHjeEdphSRlaBdh/MkcUidYujGg8AAACgZiK0w5SSSu7N3rZZhOrUshs8DQAAAAAYg9AOU1qfTDUeAAAAAAjtMJ3fMvOUfiRXNqtFXVrHGD0OAAAAABiGW77BdBJLqvHtmkcqLCTQ4GkAAACA33m9XhU5z+w2bm6Pt9Jv+WYPtFZ4kbNdu9K0cOECbdr0i/Lz81SvXn0NG3a9rrtupCQpKelHLVr0snbsSFV4eB1deeUATZhwh2w2m1wul15/fZFWr/5Qx48fU7NmzXXbbRPVq9eF2rhxgyZP/rveeed9NWjQUJJ08OBvGjHiGj333H/UpUs3Pfrog8rLy1NBQb62bt2iMWNu0ejRt+i//12qjz56X7/9dkB2u10dO3bWP/7xTzVs2EiSVFBQoJdemq8vvvhU+fl5at06Tnfeebdat47TtdderWHDrtOtt04o+4yrVq3QokUva+XKjxUQ4F8x178+DXye1+tVYsmq8T2pxgMAAMBEvF6vHn9jo3YeyDZshlaN62j6jV3OOLgXFhZqypSJ6tq1hxYseEUBAQH66KP39dxzT6tz5y4qKnJq6tTJGjFipKZPf0CHDx/SQw/NktVq1W23TdRzzz2tzz9fpylT7lNcXFutXv2hpk+fqsWL3zzjmb/++gtNnDhZU6bcq6CgIL399jItWfKqZs36l1q1Ol+//XZATz75qJ5/fp4ef3yOJGn27OnavXu3pk9/QI0bN9Gbb76ue+6ZpLfeWqkrr7xaa9Z8XC60f/LJx7riiqv9LrBLhHaYzP6MXB06lq/AAKs6nR9t9DgAAABAeT52B7iCggKNGDFSQ4YMV61aYZKksWNv09Klryotbad+/PF7tW3bTpMmTZEkNWt2nv75z5nKzDyi/Pw8ffDBKt199zRddll/SdL48X+X2+1Wfn7+Gc9Qu3a4Ro26qezPjRo10axZD6p374slSfXrN1C/fpfrs8/WSpL27dur77//Vk8//bx69rxAkjRlyr0KDQ1VTk6WBg78m5YvX6YtW35V+/YdtH//Pm3Z8qv++c8Z5/6FmRChHaayvqQa36FllEKCODwBAABgHhaLRdNv7HLG9fiAAKvh9fiIiAgNHTpCn366Vjt3bld6+n7t2LFdkuTxeJSWtkPdu/cs95y+fftJklJSkuV0OtWuXUK5x2+//U5J0saNG85ohsaNm5T7c+/eF2vr1i1atOgl7d+/T3v37tauXWmKiSm+1XNa2g5JKve+drtdkybdU/bntm3j9cknH6l9+w5avfpDxcXFq2XLVmc0j69hITqYhtfrVWIy1XgAAACYl8ViUZDdZtivil7PfuzYUd1880i9//5KRUZG6W9/G6ZFi5aWPR4QEPCXr2mzBZR95lPxer1lv3e5XCc9HhQUVO7Pb775uiZNul3Hjx9X585dNXXqdI0cOabcTMXv+9fvOXDgNfrss3VyOp1at+4TDRgw+JQz+jJCO0xj1285OppTqCC7TQkto4weBwAAAPB5a9euVnZ2tv7zn8W65Zbx6tu3n06cOCGpOGyfd14LbduWXO45b7+9TGPH3qgmTZoqICBAKSlbyz0+YcJNWrZsiQIDixeNzsvLLXssPX3/aWd6/fXFGjt2gqZNu19/+9tQtW+foP3795aF/2bNmktSublcLpeGDh2oTz9dI0m6/PKrVFTk0FtvvamjRzN1+eVXVvSr8RmEdphGaTW+8/nRCgq0GTwNAAAA4PtiY+ursLBAn3++TocOHVJi4o+aPbv42m+ns0ijRo3R1q2btXDhi9q3b69++OE7LVnyqvr0uUTBwcEaNux6LVz4or799isdOJCul19eoN27d+nCC/uoZctWCg2tpddfX6T09P365ZeNevnl+ac9Mx8bW09JSeu1e/cu7du3Ry+/vEBfffWFnE6nJKlp02bq27ef5s59Qj/9lKR9+/bqqacek9PpVNeuPSRJYWFh6tv3Ur322kL16dNX4eHhVftFGoiLhmEKHo9XSSnF1fgecVTjAQAAgMrQr99lSk0doxdeeEZ5eblq0KChBg36m7799mslJ2/VtdcO1+OPP61XXvmPli1bosjIKA0ffr1uummsJOnvf79LAQEBmjPn3zpxIkctW56vp556VuedV3w2/IEHHtZ//vOCxoy5Tk2bNtNdd03RtGmTTznT//zPQ5o79wmNHz9GoaG11K5de02bNl1PP/1vHTz4mxo0aKgZM2Zr/vxnNXv2dDkcDsXHJ2jevPmKiIgoe52rrx6ktWtXa8CAa6ruCzQBi/ePFyDUUG63R8eO5Rk9xikFBFgVEVFLx4/nVfpiFmaQuu+4nlj2s0KDAjRvUm8FBlACqcn8/XgH/ojjHTUJxzt8idNZpKNHDyoqqoECA+1n9RpVsRAdfrd69YdauPBFrVjxgaxWc+WH0x0/kZG1ZLOd2cycaYcprC+5N3uXNjEEdgAAAAB/KTU1RXv37tHChS9q+PDrTRfYK5t/fzr4BJfbow0prBoPAAAA4PS2bPlVTzzxsNq1S9B1140yepwqx5l2GC5l73HlFjhVOzRQcc3qGj0OAAAAABMbNuw6DRt2ndFjVBvOtMNwpavGd4uLlc3Pqy0AAAAAUBEkJBjK6fJo4/YjkqjGAwAAAMD/R2iHobbsOqoCh1sRtYPUqnEdo8cBAAAAAFMhtMNQpdX47nGxslosBk8DAAAAAOZCaIdhHEVu/bIzU5LUg2o8AAAAAJyE0A7DbErLVJHTo+g6wWreoLbR4wAAAACA6RDaYZjEbSX3Zo+vJwvVeAAAAAA4CaEdhsgvdOnXtKOSqMYDAAAAZjV8+GAtWvSS0WPUaIR2GOLnHUfkcnvUICpUjWNqGT0OAAAAAJgSoR2GKKvGt6UaDwAAAAB/hdCOapdb4FTynmOSpO5tYw2eBgAAADhzXq9XXqfDuF9eb4XmffTRBzVhws3ltmVkHNbFF/fQhg2J+uij93XrraN06aUX6fLLe+uuu25TamrKWX8/GRmH9dBD/6PBg69Q3749NXToQL300nx5PJ6yfVJStukf/5io/v37aPDgK/Tkk4+qoKCg7PEVK97SyJFDdemlF2n06BFas+ZjSdLBg7+pd+9u2rhxQ7n37N27mz7++ANJ0qJFL+mOO8Zq9uwZuuKKvnr66Sck6bSf0+VyadGilzR8+GBddtlFGjt2tH788XtJ0q23jtJjj/2r3Hv++OP3uuSSXsrKyjrr7+pMBVT5OwD/z0+pGXJ7vGoaG6YGUVTjAQAA4Bu8Xq/y339UnsM7DZvBVu98hVwz44zbqldfPUiTJ/9d6en71bhxE0nS2rWrFR0do9zcE5oz53Hde+9Mde7cVUePHtUzzzylf//7Ib366rKzmu/ee6coIiJCc+c+r9DQWvrhh2/1zDNzFB/fTn36XKKDB3/TpEm3qXfvvnrppVeVl5enRx/9l5566jE98MDDWrZsqRYt+o/uvnuaunbtrvXrf9Bjj/1LkZGRaty46RnNsHnzrxoxop1effVNeTweffXVF6f9nM8997Q+/3ydpky5T3FxbbV69YeaPn2qFi9+UwMGXKOFC1/U1Kn3KSgoWJL0yScf6aKL+qhu3bpn9T1VBGfaUe1Kq/E94lmADgAAAL7FIt+6tLNz565q2LCR1q5dXbZt7drVuuqqgapbN0L33TdLV189SPXrN1C7du01ePC1Sks7ux9KOByFuvLKAbrvvlk6//w2atSosYYPv0HR0TFlr/n++ytVu3a4Zs58UC1atFJCQkfdf/8sNW3aTJL09tvLNGLESF1zzRA1atRYQ4eO0O233yW323Oqtz7JuHG3q1GjxmrSpKnq1Klzys+Zn5+nDz5YpfHj79Bll/VXo0aNNX7833XDDaOVn5+vK6+8Wi6XU19//aUkKS8vV99886UGDLjmrL6niuJMO6pVVq5DKXuPS5J6xFGNBwAAgO+wWCwKuWaG5Co6o/0DAqxyuSoWNk//ovYKrQllsVh01VUDtXbtJxo79jbt2JGqXbvS9MgjT6pp02bas2e3XnvtFaWn79e+fXu1c+f2clX2iggKCtawYdfpyy8/09tvL1N6+n7t3LlDmZlH5Ha7JUlpaTvUpk1bBQT8HkU7deqiTp26KCsrS5mZR9SuXftyrztq1BhJxfX4MxEREamwsLByr3+qz7lv3145nU61a5dQ7nVuv/3Ost9fdNHF+uSTj9W//1X6/PNPFRYWpp49L6jAt3P2ONOOarUhJUNeSS0bhiu6bojR4wAAAAAVYrFYZAkMMu7XWSziPGDAYB04sF/btm3VmjWrlZDQQU2bNtOnn67RzTffoPT0/Wrbtp0mTpysu+6actbfTWFhoe64Y5xef32RatUK05VXDtT8+QsVG/t7w9ZmC/jLzxAYWBzkK/IZXS7XSduCgoLK/fl0n9NmO/37Dhx4jTZsWK9jx45qzZqPdeWVA8r94KEqcaYd1aqsGs+92QEAAIBqUb9+A3Xu3FVffPGpPv98nW6+eZwkaenSVzV48LWaNm162b7ffPOVpOLr9yv6A4L1679Xauo2vf/+GkVGRkmScnKydezY0bJ9zjuvudat+0Rut1s2m02S9NVXX+iZZ57Sf//7nqKjY7RtW7J69+5b9pxZs+5VdHSMRo++RZKUm5tb9lh6+v7TznW6z9mkSVMFBAQoJWWrWrU6v2yfCRNuUr9+l2vUqJvUo0cvRUVF64MPVmnz5k2aOvX+Cn0354LQjmqTmV2gnQeyZZHUjWo8AAAAUG0GDBisuXOflMvl0mWXXSFJio2tp82bNyk1NUVhYWH69tuv9N57b0uSioqKTjpjfToxMcX/xl+zZrX69btMhw8f1ksvvSCXy6WiouJLCoYNu04rVizXnDmP6/rrb1R2dpZefPF5de/eU8HBwRo9+ma99NICNWnSVAkJHfXjj9/rm2++0rx58xUVFa2GDRtp+fI31aRJUzkchXruubmy2+2nnOt0nzM4OFjDhl2vhQtfVN26EWrevKU++uh97d69SzNn9pEkWa1WXXXVQC1Zslht2rRV8+YtKvTdnAvq8ag2SSnFZ9nbNK2riNoV+w8AAAAAgLN3ySWXSZL69Olbdr33lCn3KiIiUnfddZtuu+1mff/9t5o1q/jWZsnJWyr8HvHx7TVp0hS9885/NWrUcD322IPq1KmLLr/8yrLXi46O0bx5L2jfvr0aO3a0Hnjgfl144UWaOvU+SdKwYdfr1lvHa9GilzRmzHV6//339NBDj6tLl26yWCx64IGHVVTk0NixN+rBB2dqyJDhZT8s+Ctn8jn//ve7dNVVgzRnzr91003Xa8OGRD311LM677zmZa8zYMBgORwODRgwuMLfzbmweCt6oz8/5HZ7dOxYntFjnFJAgFUREbV0/Hhe5S9mUU3+9WqS9h4+oTFXtlG/zo2MHgcm5g/HO3CmON5Rk3C8w5c4nUU6evSgoqIaKDDw1Gdy/0qVLEQHw/zyy0ZNmzZZq1Z9Um6huz9zuuMnMrKWbLYzO4dOPR7V4vCxfO09fEJWi0Vd28QYPQ4AAAAAnJG9e/coLW2nlixZrKuvHnzawF7ZCO2oFonbDkuS4s+LUHjo2f2kEgAAAIAx5s59QqtXf3jKfR5++An16nVhNU1Uffbv36vHHntQ8fHtddttE6v9/QntqBasGg8AAAD4rltvvU3XXTfqlPtER/tno7Z377769NNvDXt/QjuqXPqRXB3IzFOAzaIuraONHgcAAABABUVERCgiIsLoMWokVo9HlSutxie0iFJocKDB0wAAAACA7yC0o0p5vV4lJlONBwAAgG/iZls4G5V53BDaUaX2HDqhjKwC2QOt6tSKajwAAAB8g81mkyQVFTkMngS+qPS4sdnO/Yp0rmlHlSqtxndsGa0gu83gaQAAAIAzY7XaFBISptzc45Ikuz1IFoulQq/h8VjkdnOmvibxer0qKnIoN/e4QkLCZLWe+3lyQjuqjMfrVVIK1XgAAAD4pvDwSEkqC+4VZbVa5fF4KnMk+IiQkLCy4+dcEdpRZdIOZOtYjkPBdps6tKycAxYAAACoLhaLRXXqRKl27Qi53a4KPddms6hOnVBlZ+dztr2GsdkCKuUMeynDQ7vH49ELL7ygd955Rzk5Oeratatmz56tZs2a/en+K1eu1P3333/S9rVr1/7lc2CM0gXourSOUWAA1XgAAAD4JqvVKqvVXqHnBARYFRwcrIICt1wuzrbj7Bke2hcsWKC33npLjz/+uOrVq6ennnpKEyZM0Icffii7/eS/GKmpqerRo4fmzp1bbntkJGdyzcTt8Sgppfh6dqrxAAAAAHB2DF09vqioSIsXL9akSZPUt29fxcXFad68eTp8+LDWrVv3p8/Zvn274uLiFBMTU+5X6eqOMIfUfVnKyXeqVnCA4s+LMHocAAAAAPBJhob2lJQU5eXlqVevXmXbwsPDFR8fr6SkpD99Tmpqqlq1alVdI+Isla4a3y0uVgE27iwIAAAAAGfD0Hr8oUOHJEkNGjQotz02NlYHDx48af9jx44pMzNTSUlJWrp0qbKystSxY0dNmzZNzZs3P+s5rFaLIiNrnfXzq0Pp3SXq1AmR1wfWsbhpUHuNGdhOdcOCFBhAaEfF+NrxDpwLjnfUJBzvqEk43nEqVuuZ3z7Q0NBeUFAgSSddux4UFKTs7OyT9t++fbskyWaz6YknnlB+fr4WLFigUaNG6YMPPlB0dPRZzWGxWGSzVeyei0apzFUIq1K9yFCjR4Af8JXjHagMHO+oSTjeUZNwvONcGRrag4ODJRVf2176e0lyOBwKCQk5af9evXopMTFRderUKds2f/589evXT++9955uu+22qh8aAAAAAIBqYuiPfUpr8RkZGeW2Z2RkqH79+n/6nD8GdkkKDQ1V48aNdfjw4aoZEgAAAAAAgxga2uPi4hQWFqb169eXbcvJyVFycrK6det20v7Lli1Tz549VVhYWLYtNzdXe/bsYXE6AAAAAIDfMTS02+12jR49WnPmzNFnn32mlJQUTZkyRfXr11f//v3ldrt15MiRspDer18/eb1e3XvvvdqxY4c2b96sSZMmKTIyUkOGDDHyowAAAAAAUOkMXxVh8uTJGj58uGbNmqWRI0fKZrNp0aJFstvtOnjwoHr37q2PP/5YUnGd/vXXX1deXp5GjhypW265RbVr19aSJUvKXRMPAAAAAIA/sHi93IAAAAAAAAAzMvxMOwAAAAAA+HOEdgAAAAAATIrQDgAAAACASRHaAQAAAAAwKUI7AAAAAAAmRWgHAAAAAMCkCO0AAAAAAJgUod0HeDwePffcc+rTp486duyosWPHau/evUaPBVS6rKwsPfDAA7r44ovVpUsXjRw5Uhs2bDB6LKDK7d69W507d9Z7771n9ChAlVm1apUGDBighIQEDRw4UKtXrzZ6JKBKOJ1OzZs3T5dccok6d+6sUaNGaePGjUaPBR9GaPcBCxYs0FtvvaVHHnlEy5cvl8Vi0YQJE1RUVGT0aECluueee7Rp0ybNnTtXK1asULt27TRu3DilpaUZPRpQZZxOp6ZNm6b8/HyjRwGqzP/+7/9qxowZuv766/Xhhx9qwIABuueee/Tzzz8bPRpQ6V588UW9++67euSRR7Rq1Sq1aNFCEyZM0OHDh40eDT6K0G5yRUVFWrx4sSZNmqS+ffsqLi5O8+bN0+HDh7Vu3TqjxwMqzd69e/Xdd99p9uzZ6tatm1q0aKGZM2eqXr16+vDDD40eD6gyzz//vGrVqmX0GECV8Xq9evbZZ3XzzTfr5ptvVrNmzXTnnXfqwgsvVGJiotHjAZXus88+06BBg9S7d281a9ZM999/v3Jzc/XLL78YPRp8FKHd5FJSUpSXl6devXqVbQsPD1d8fLySkpIMnAyoXBEREXr55ZfVvn37sm0Wi0Ver1fZ2dkGTgZUnaSkJC1fvlxPPPGE0aMAVWbXrl06cOCABg8eXG77okWLdPvttxs0FVB16tatqy+++ELp6elyu91avny57Ha72rZta/Ro8FEBRg+AUzt06JAkqUGDBuW2x8bG6uDBg0aMBFSJ8PBw9e3bt9y21atXa9++ferdu7dBUwFVJycnR/fee69mzZp10n/jAX+yZ88eSVJ+fr7GjRun5ORkNW7cWHfccYcuvfRSY4cDqsDMmTM1ZcoUXXbZZbLZbLJarXr22WfVtGlTo0eDj+JMu8kVFBRIkux2e7ntQUFBcjgcRowEVIuffvpJM2bM0GWXXcY/6uCXHnzwQXXq1Omks4+Av8nNzZUk3XfffRo0aJAWL16siy66SBMnTtQPP/xg8HRA5UtLS1N4eLjmz5+v5cuXa+jQobrvvvuUkpJi9GjwUZxpN7ng4GBJxde2l/5ekhwOh0JCQowaC6hSn376qaZNm6aOHTtq7ty5Ro8DVLpVq1Zpw4YN+uCDD4weBahygYGBkqRx48ZpyJAhkqS2bdsqOTlZr776qi644AIjxwMq1YEDB/TPf/5Tr732mrp16yZJSkhI0M6dO/X8889r/vz5Bk8IX8SZdpMrrUxmZGSU256RkaH69esbMRJQpd544w1NmjRJF198sRYuXFjuh1WAv3j33Xd19OjRstsBde7cWZI0e/ZsDRw40ODpgMpV+u+V1q1bl9veqlUrpaenGzESUGV+/fVXOZ1OJSQklNvesWPHsktFgIriTLvJxcXFKSwsTOvXry+7DiYnJ0fJyckaPXq0wdMBlWvZsmV6+OGHNWbMGM2YMUNWKz9XhH+aM2eOCgsLy2274oorNHnyZA0YMMCgqYCqER8fr1q1amnTpk1lZx4lafv27VzjC79TesItNTVVHTp0KNu+fft2NWvWzKix4OMI7SZnt9s1evRozZkzR5GRkWrUqJGeeuop1a9fX/379zd6PKDS7N69W4899pj69++v22+/XUePHi17LDg4WLVr1zZwOqBy1atX70+3R0VFqVGjRtU8DVC1goODNX78eM2fP1/16tVThw4d9NFHH+m7777Ta6+9ZvR4QKXq0KGDunXrpvvuu0+zZ89W/fr1tWrVKv3www9atmyZ0ePBRxHafcDkyZPlcrk0a9YsFRYWqnv37lq0aNFJi9MBvmzNmjVyOp1at26d1q1bV+6xIUOG6N///rdBkwEAztXEiRMVEhKiefPm6fDhw2rZsqWef/559ezZ0+jRgEpltVq1YMECPfPMM5o+fbqys7PVunVrvfbaa+rUqZPR48FHWbxer9foIQAAAAAAwMm4YBQAAAAAAJMitAMAAAAAYFKEdgAAAAAATIrQDgAAAACASRHaAQAAAAAwKUI7AAAAAAAmRWgHAAAAAMCkAoweAAAAVL37779fK1eu/MvH69atq/Xr11fjRFKbNm101113adKkSdX6vgAA+BJCOwAANURMTIxeeOGFP30sIIB/EgAAYEb8HxoAgBrCbrerU6dORo8BAAAqgNAOAADKjBkzRo0aNVLz5s21ZMkSFRQUqGfPnpoxY4aaNGlStt/mzZv1zDPPaMuWLXI6nerRo4emTp2q888/v2yfo0eP6umnn9aXX36pgoICxcfH65577lHXrl3L9snNzdXMmTO1bt06OZ1O9enTR7Nnz1ZUVFS1fm4AAMyKhegAAKhBXC7Xn/7yer1l+3z22Wd69913NXPmTD300ENKSUnRTTfdpPz8fEnSjz/+qJEjR8rj8ejRRx/VI488ooMHD+qGG25QWlqaJCk/P1833HCDvv/+e02dOlUvvPCCatWqpfHjx5ftI0lLliyR0+nUs88+qylTpujzzz/Xv/71r+r9UgAAMDHOtAMAUEMcOHBA7dq1+9PH7r77bk2cOFFSceB+99131bRpU0lSixYtNGTIEK1cuVI33nijnn76aTVp0kSvvPKKbDabJKl3797q37+/nn/+eT3zzDNauXKl9u/fr1WrVikuLk6S1K1bN1177bVKSkpSy5YtJUkJCQl68sknJUkXXHCBfv31V3399ddV+j0AAOBLCO0AANQQMTExevHFF//0sXr16pX9vnPnzmWBXZLi4+PVpEkTbdiwQUOGDNHmzZt15513lgV2SQoPD1e/fv301VdfSZI2bNigxo0blwV2SQoKCtLq1avLve8fq/KS1KRJE+Xk5Jz9hwQAwM8Q2gEAqCHsdrsSEhJOu19sbOxJ26KiopSTk6MTJ07I6/UqOjr6pH2io6N14sQJSVJWVtYZXZceGhpa7s9Wq7VcVR8AgJqOa9oBAEA5WVlZJ23LzMxUZGSkateuLYvFoszMzJP2OXLkiOrWrStJql27to4dO3bSPj///LN27NhR2SMDAOC3CO0AAKCcn3/+uVzg3rp1q9LT03XBBRcoNDRU7du318cffyy32122z4kTJ/Tll1+W1d27deum/fv3KzU1tWyfoqIiTZo0SW+//Xb1fRgAAHwc9XgAAGqIoqIi/fLLL3/5eOvWrSVJBQUFmjBhgu644w7l5eVp3rx5at26tQYNGiRJmjp1qsaNG6fx48dr9OjRcjqdevnll1VUVKS77rpLkjR06FAtXbpUd9xxh+6++25FRkbqzTffVGFhocaMGVPlnxUAAH9BaAcAoIY4cuSIrr/++r98fMWKFZKKz5L36tVLM2fOlCRdeumluvfee2W32yUVr/L+6quv6rnnntM999wju92ubt266Yknnii7T3tYWJjeeOMNPfnkk3r00UflcrnUsWNHLV26tNwidwAA4NQsXlZ7AQAAJUrPgi9dutTgSQAAgMQ17QAAAAAAmBahHQAAAAAAk6IeDwAAAACASXGmHQAAAAAAkyK0AwAAAABgUoR2AAAAAABMitAOAAAAAIBJEdoBAAAAADApQjsAAAAAACZFaAcAAAAAwKQI7QAAAAAAmBShHQAAAAAAk/o/j57UMtbt9lwAAAAASUVORK5CYII=\n", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], "source": [ "plt.plot(history.history['accuracy'], label='accuracy')\n", "plt.plot(history.history['val_accuracy'], label = 'val_accuracy')\n", @@ -2452,9 +2700,7 @@ { "cell_type": "markdown", "id": "0268a14c", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "## Building our own CNN code\n", "\n", @@ -2483,9 +2729,7 @@ { "cell_type": "markdown", "id": "639210da", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "### List of contents:\n", "\n", @@ -2507,9 +2751,7 @@ { "cell_type": "markdown", "id": "4e1db5cf", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "### Schedulers\n", "\n", @@ -2528,12 +2770,9 @@ }, { "cell_type": "code", - "execution_count": 14, + "execution_count": null, "id": "b346c680", - "metadata": { - "collapsed": false, - "editable": true - }, + "metadata": {}, "outputs": [], "source": [ "import autograd.numpy as np\n", @@ -2671,9 +2910,7 @@ { "cell_type": "markdown", "id": "1cd97a7e", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "### Usage of schedulers\n", "\n", @@ -2682,12 +2919,9 @@ }, { "cell_type": "code", - "execution_count": 15, + "execution_count": null, "id": "d2a3bb1b", - "metadata": { - "collapsed": false, - "editable": true - }, + "metadata": {}, "outputs": [], "source": [ "momentum_scheduler = Momentum(eta=1e-3, momentum=0.9)\n", @@ -2697,21 +2931,16 @@ { "cell_type": "markdown", "id": "fc108e70", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "Here is a small example for how a segment of code using schedulers could look. Switching out the schedulers is simple." ] }, { "cell_type": "code", - "execution_count": 16, + "execution_count": null, "id": "9b4ce329", - "metadata": { - "collapsed": false, - "editable": true - }, + "metadata": {}, "outputs": [], "source": [ "weights = np.ones((3,3))\n", @@ -2730,9 +2959,7 @@ { "cell_type": "markdown", "id": "180ab837", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "### Cost functions\n", "\n", @@ -2744,12 +2971,9 @@ }, { "cell_type": "code", - "execution_count": 17, + "execution_count": null, "id": "658a2e43", - "metadata": { - "collapsed": false, - "editable": true - }, + "metadata": {}, "outputs": [], "source": [ "def CostOLS(target):\n", @@ -2793,9 +3017,7 @@ { "cell_type": "markdown", "id": "d8191be9", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "### Usage of cost functions\n", "\n", @@ -2806,12 +3028,9 @@ }, { "cell_type": "code", - "execution_count": 18, + "execution_count": null, "id": "7378bb3a", - "metadata": { - "collapsed": false, - "editable": true - }, + "metadata": {}, "outputs": [], "source": [ "from autograd import grad\n", @@ -2829,9 +3048,7 @@ { "cell_type": "markdown", "id": "1ed42637", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "### Activation functions\n", "\n", @@ -2844,12 +3061,9 @@ }, { "cell_type": "code", - "execution_count": 19, + "execution_count": null, "id": "435f1e1f", - "metadata": { - "collapsed": false, - "editable": true - }, + "metadata": {}, "outputs": [], "source": [ "\n", @@ -2905,9 +3119,7 @@ { "cell_type": "markdown", "id": "f8d589b0", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "### Usage of activation functions\n", "\n", @@ -2920,12 +3132,9 @@ }, { "cell_type": "code", - "execution_count": 20, + "execution_count": null, "id": "c761d9af", - "metadata": { - "collapsed": false, - "editable": true - }, + "metadata": {}, "outputs": [], "source": [ "z = np.array([[4, 5, 6]]).T\n", @@ -2943,9 +3152,7 @@ { "cell_type": "markdown", "id": "b58d25c7", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "### Convolution\n", "\n", @@ -2960,9 +3167,7 @@ { "cell_type": "markdown", "id": "2a7c88e4", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "$$\n", "(f \\ast g)(t):=\\int_{-\\infty}^{\\infty} f(\\tau) g(t-\\tau) d \\tau.\n", @@ -2972,9 +3177,7 @@ { "cell_type": "markdown", "id": "a3b7b088", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "Here, f and g are the two functions on which we want to perform an\n", "operation. The outcome of the convolution operation is represented by\n", @@ -2988,9 +3191,7 @@ { "cell_type": "markdown", "id": "ab613e53", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "$$\n", "(f \\ast g)[n]=\\sum_{m=0}^{n-1} f[m] g[n-m].\n", @@ -3000,9 +3201,7 @@ { "cell_type": "markdown", "id": "19572f8d", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "The key idea we utilize to extract the information contained in an\n", "image is to slide an $m \\times n$ matrix *g* over an $m \\times n$\n", @@ -3015,9 +3214,7 @@ { "cell_type": "markdown", "id": "bf00be7e", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "$$\n", "(f \\ast g)[i, j]\\sum_{m=0}^{M-1}\\sum_{n=0}^{N-1} f[m,n] g[i-m, j-n].\n", @@ -3027,9 +3224,7 @@ { "cell_type": "markdown", "id": "3c9571ca", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "It is imperative to note that the size of the kernel g is\n", "significantly smaller than the size of the input image f, thereby\n", @@ -3045,9 +3240,7 @@ { "cell_type": "markdown", "id": "dc5f8ea1", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "$$\n", "f = \\begin{bmatrix}\n", @@ -3064,9 +3257,7 @@ { "cell_type": "markdown", "id": "26b8664b", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "and a $3 \\times 3$ kernel *g* called a low-pass filter. Note that the\n", "kernel is usually rotated by 180 degrees during convolution, however\n", @@ -3076,9 +3267,7 @@ { "cell_type": "markdown", "id": "4c7800d2", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "$$\n", "g = \\frac{1}{9}\n", @@ -3093,9 +3282,7 @@ { "cell_type": "markdown", "id": "95a4de06", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "In order to filter the image, we have to extract a $3 \\times 3$\n", "element from the upper left corner of *f*, and perform element-wise\n", @@ -3106,9 +3293,7 @@ { "cell_type": "markdown", "id": "17d7792e", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "$$\n", "\\begin{bmatrix}\n", @@ -3135,9 +3320,7 @@ { "cell_type": "markdown", "id": "47640ade", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "Then, following the multiplication, we summarize all the elements of the resulting matrix A:" ] @@ -3145,9 +3328,7 @@ { "cell_type": "markdown", "id": "d6d9cb14", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "$$\n", "(f \\ast g)[0, 0]= \\sum_{i=0}^{2} \\sum_{j=0}^{2} a_{i,j} = 5\n", @@ -3157,9 +3338,7 @@ { "cell_type": "markdown", "id": "b44a3db3", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "Which corresponds to the first element of the filtered image $(f \\ast g)$.\n", "\n", @@ -3178,9 +3357,7 @@ { "cell_type": "markdown", "id": "0b8f34fd", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "$$\n", "(f \\ast g) =\n", @@ -3196,9 +3373,7 @@ { "cell_type": "markdown", "id": "72f4bfca", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "The result is markedly smaller in shape than the original image. This occurs when using convolution without first padding the image with additional columns and rows, allowing us to keep the original image shape after sliding the kernel over the image.\n", "How many rows and columns we wish to pad the image with depends strictly on the shape of the kernel, as we wish to pad the image with *r* additional rows and *c* additional columns." @@ -3207,9 +3382,7 @@ { "cell_type": "markdown", "id": "234e1f8c", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "$$\n", "r =\\lfloor \\frac{kernel\\ height}{2} \\rfloor \\cdot 2 \\\\\n", @@ -3220,9 +3393,7 @@ { "cell_type": "markdown", "id": "c58d78cf", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "Note the notation $\\lfloor \\frac{kernel width}{2} \\rfloor$ means that\n", "we floor the result of the division, meaning we round down to a whole\n", @@ -3244,9 +3415,7 @@ { "cell_type": "markdown", "id": "6d4ae310", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "$$\n", "\\begin{bmatrix}\n", @@ -3266,21 +3435,16 @@ { "cell_type": "markdown", "id": "aa5353c9", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "Below we have provided code that demonstrates padding and convolution. As you will see when we run the code, the size of the image will remain unchanged when using padding.~" ] }, { "cell_type": "code", - "execution_count": 21, + "execution_count": null, "id": "702a0a53", - "metadata": { - "collapsed": false, - "editable": true - }, + "metadata": {}, "outputs": [], "source": [ "import numpy as np\n", @@ -3359,9 +3523,7 @@ { "cell_type": "markdown", "id": "d478eb55", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "Fun fact: When filtering images, you will see that convolution involves rotating the kernel by 180 degrees. \n", "However, this is not the case when applying convolution in a CNN, where the same operation not rotated by 180 degrees is called \n", @@ -3370,12 +3532,9 @@ }, { "cell_type": "code", - "execution_count": 22, + "execution_count": null, "id": "b58c6241", - "metadata": { - "collapsed": false, - "editable": true - }, + "metadata": {}, "outputs": [], "source": [ "\n", @@ -3399,9 +3558,7 @@ { "cell_type": "markdown", "id": "0a1720de", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "As you can see, the resulting image is of the same size as the\n", "original image. To round of our demonstration of convolution, we will\n", @@ -3418,12 +3575,9 @@ }, { "cell_type": "code", - "execution_count": 23, + "execution_count": null, "id": "9d414175", - "metadata": { - "collapsed": false, - "editable": true - }, + "metadata": {}, "outputs": [], "source": [ "# Now an example using a real image and first a gaussian low-pass filter and then a sobel filter\n", @@ -3470,9 +3624,7 @@ { "cell_type": "markdown", "id": "8e763bfe", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "### Layers\n", "\n", @@ -3483,12 +3635,9 @@ }, { "cell_type": "code", - "execution_count": 24, + "execution_count": null, "id": "f12e5767", - "metadata": { - "collapsed": false, - "editable": true - }, + "metadata": {}, "outputs": [], "source": [ "import math\n", @@ -3526,9 +3675,7 @@ { "cell_type": "markdown", "id": "12149359", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "### Convolution2DLayer: convolution in a hidden layer\n", "\n", @@ -3566,12 +3713,9 @@ }, { "cell_type": "code", - "execution_count": 25, + "execution_count": null, "id": "835f0094", - "metadata": { - "collapsed": false, - "editable": true - }, + "metadata": {}, "outputs": [], "source": [ "class Convolution2DLayer(Layer):\n", @@ -3854,9 +3998,7 @@ { "cell_type": "markdown", "id": "cc1101ec", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "### Backpropagation in the convolutional layer\n", "\n", @@ -3877,9 +4019,7 @@ { "cell_type": "markdown", "id": "611a1739", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "### Demonstration\n", "\n", @@ -3888,12 +4028,9 @@ }, { "cell_type": "code", - "execution_count": 26, + "execution_count": null, "id": "234719cb", - "metadata": { - "collapsed": false, - "editable": true - }, + "metadata": {}, "outputs": [], "source": [ "import numpy as np\n", @@ -3938,9 +4075,7 @@ { "cell_type": "markdown", "id": "0fa82959", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "We cobserve that the result has half the pixels on each axis due to\n", "the fact that we've used a horizontal and vertical stride of 2. The\n", @@ -3960,9 +4095,7 @@ { "cell_type": "markdown", "id": "331b1049", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "### Pooling Layer\n", "\n", @@ -3980,12 +4113,9 @@ }, { "cell_type": "code", - "execution_count": 27, + "execution_count": null, "id": "c109cedf", - "metadata": { - "collapsed": false, - "editable": true - }, + "metadata": {}, "outputs": [], "source": [ "class Pooling2DLayer(Layer):\n", @@ -4144,9 +4274,7 @@ { "cell_type": "markdown", "id": "8490c970", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "### Flattening Layer\n", "\n", @@ -4163,12 +4291,9 @@ }, { "cell_type": "code", - "execution_count": 28, + "execution_count": null, "id": "a744635e", - "metadata": { - "collapsed": false, - "editable": true - }, + "metadata": {}, "outputs": [], "source": [ "class FlattenLayer(Layer):\n", @@ -4228,9 +4353,7 @@ { "cell_type": "markdown", "id": "a420128f", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "### Fully Connected Layers\n", "\n", @@ -4250,12 +4373,9 @@ }, { "cell_type": "code", - "execution_count": 29, + "execution_count": null, "id": "c842ab65", - "metadata": { - "collapsed": false, - "editable": true - }, + "metadata": {}, "outputs": [], "source": [ "class FullyConnectedLayer(Layer):\n", @@ -4480,9 +4600,7 @@ { "cell_type": "markdown", "id": "36841fd2", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "### Optimized Convolution2DLayer\n", "\n", @@ -4499,12 +4617,9 @@ }, { "cell_type": "code", - "execution_count": 30, + "execution_count": null, "id": "6a38a5d2", - "metadata": { - "collapsed": false, - "editable": true - }, + "metadata": {}, "outputs": [], "source": [ "class Convolution2DLayerOPT(Convolution2DLayer):\n", @@ -4805,9 +4920,7 @@ { "cell_type": "markdown", "id": "d88774e4", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "### The Convolutional Neural Network (CNN)\n", "\n", @@ -4816,12 +4929,9 @@ }, { "cell_type": "code", - "execution_count": 31, + "execution_count": null, "id": "719f26bc", - "metadata": { - "collapsed": false, - "editable": true - }, + "metadata": {}, "outputs": [], "source": [ "import math\n", @@ -5353,9 +5463,7 @@ { "cell_type": "markdown", "id": "6537f8a1", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "### Usage of CNN code\n", "\n", @@ -5370,12 +5478,9 @@ }, { "cell_type": "code", - "execution_count": 32, + "execution_count": null, "id": "7705e079", - "metadata": { - "collapsed": false, - "editable": true - }, + "metadata": {}, "outputs": [], "source": [ "adam_scheduler = Adam(eta=1e-3, rho=0.9, rho2=0.999)\n", @@ -5385,9 +5490,7 @@ { "cell_type": "markdown", "id": "50be8217", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "Now that we have our CNN object, we can begin to add layers to it!\n", "Many of the add_layer functions have default values, for example\n", @@ -5399,12 +5502,9 @@ }, { "cell_type": "code", - "execution_count": 33, + "execution_count": null, "id": "333f479d", - "metadata": { - "collapsed": false, - "editable": true - }, + "metadata": {}, "outputs": [], "source": [ "cnn.add_Convolution2DLayer(\n", @@ -5427,9 +5527,7 @@ { "cell_type": "markdown", "id": "95bda376", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "Here we have created a CNN with the following architecture:\n", "\n", @@ -5449,12 +5547,9 @@ }, { "cell_type": "code", - "execution_count": 34, + "execution_count": null, "id": "6f0dff0d", - "metadata": { - "collapsed": false, - "editable": true - }, + "metadata": {}, "outputs": [], "source": [ "from sklearn.datasets import fetch_openml\n", @@ -5486,9 +5581,7 @@ { "cell_type": "markdown", "id": "728e1ad0", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "Now we may train our model. Note that we can utilize regularization in\n", "the CNN by using the lam (lambda) parameter in fit(), and utilize\n", @@ -5503,12 +5596,9 @@ }, { "cell_type": "code", - "execution_count": 35, + "execution_count": null, "id": "381239db", - "metadata": { - "collapsed": false, - "editable": true - }, + "metadata": {}, "outputs": [], "source": [ "scores = cnn.fit(\n", @@ -5533,9 +5623,7 @@ { "cell_type": "markdown", "id": "44142503", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "Considering we only trained the model for 100 epochs without any tuning of the hyperparameters, this result is pretty good.\n", "\n", @@ -5560,12 +5648,9 @@ }, { "cell_type": "code", - "execution_count": 36, + "execution_count": null, "id": "587f7f42", - "metadata": { - "collapsed": false, - "editable": true - }, + "metadata": {}, "outputs": [], "source": [ "adam_scheduler = Adam(eta=1e-3, rho=0.9, rho2=0.999)\n", @@ -5631,9 +5716,7 @@ { "cell_type": "markdown", "id": "6e19ac0b", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "Here we see the use of asymmetrical 1D kernels such as the $7 \\times\n", "1$ kernel in the first convolutional layer, both max and average\n", @@ -5649,9 +5732,7 @@ { "cell_type": "markdown", "id": "31116577", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "### Additional Remarks\n", "\n", @@ -5671,12 +5752,9 @@ }, { "cell_type": "code", - "execution_count": 37, + "execution_count": null, "id": "d4aa9689", - "metadata": { - "collapsed": false, - "editable": true - }, + "metadata": {}, "outputs": [], "source": [ "def convolve(image, kernel, stride=1):\n", @@ -5704,9 +5782,7 @@ { "cell_type": "markdown", "id": "5b56f4d2", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "### Remarks on the speed\n", "\n", @@ -5734,21 +5810,16 @@ { "cell_type": "markdown", "id": "0823799d", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "### Convolution using separable kernels" ] }, { "cell_type": "code", - "execution_count": 38, + "execution_count": null, "id": "6fba75a5", - "metadata": { - "collapsed": false, - "editable": true - }, + "metadata": {}, "outputs": [], "source": [ "def conv2DSep(image, kernel, coef, stride=1, pad=\"zero\"):\n", @@ -5795,9 +5866,7 @@ { "cell_type": "markdown", "id": "a17bbdb4", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "By taking advantage of the capabilities of separable kernels, we can\n", "effectively cut the computational expense of filtering an image in\n", @@ -5816,21 +5885,16 @@ { "cell_type": "markdown", "id": "27fe636e", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "### Convolution in the Fourier domain" ] }, { "cell_type": "code", - "execution_count": 39, + "execution_count": null, "id": "6c88a500", - "metadata": { - "collapsed": false, - "editable": true - }, + "metadata": {}, "outputs": [], "source": [ "start_time = time.time()\n", @@ -5848,9 +5912,7 @@ { "cell_type": "markdown", "id": "ce1231c8", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "It is evident that executing convolution in the Fourier domain yields\n", "the quickest computation time. Nonetheless, one should exercise\n", @@ -5867,9 +5929,7 @@ { "cell_type": "markdown", "id": "312351ed", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "## Recurrent Neural Networks\n", "\n", @@ -5891,9 +5951,7 @@ { "cell_type": "markdown", "id": "ce348c95", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "## Recurrent neural networks (RNNs): Overarching view\n", "\n", @@ -5918,21 +5976,16 @@ { "cell_type": "markdown", "id": "c5ffdce5", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "## A simple example" ] }, { "cell_type": "code", - "execution_count": 40, + "execution_count": null, "id": "928f7e8f", - "metadata": { - "collapsed": false, - "editable": true - }, + "metadata": {}, "outputs": [], "source": [ "# Start importing packages\n", @@ -6002,9 +6055,7 @@ { "cell_type": "markdown", "id": "23cf23e7", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "### RNNs\n", "\n", @@ -6022,9 +6073,7 @@ { "cell_type": "markdown", "id": "4442e294", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "## Basic layout\n", "\n", @@ -6038,9 +6087,7 @@ { "cell_type": "markdown", "id": "c5223d62", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "### We need to specify the initial activity state of all the hidden and output units\n", "\n", @@ -6060,9 +6107,7 @@ { "cell_type": "markdown", "id": "d36d83fb", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "### We can specify inputs in several ways\n", "\n", @@ -6078,9 +6123,7 @@ { "cell_type": "markdown", "id": "d2291b48", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "### We can specify targets in several ways\n", "\n", @@ -6124,9 +6167,7 @@ { "cell_type": "markdown", "id": "0f9978f3", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "### Backpropagation through time\n", "\n", @@ -6145,9 +6186,7 @@ { "cell_type": "markdown", "id": "b729f64a", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "### The backward pass is linear\n", "\n", @@ -6206,9 +6245,7 @@ { "cell_type": "markdown", "id": "a4bc535f", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "## The problem of exploding or vanishing gradients\n", "* What happens to the magnitude of the gradients as we backpropagate through many layers?\n", @@ -6231,9 +6268,7 @@ { "cell_type": "markdown", "id": "10399a51", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "## Four effective ways to learn an RNN\n", "1. Long Short Term Memory Make the RNN out of little modules that are designed to remember values for a long time.\n", @@ -6250,9 +6285,7 @@ { "cell_type": "markdown", "id": "f2a086c8", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "### Long Short Term Memory (LSTM)\n", "\n", @@ -6274,9 +6307,7 @@ { "cell_type": "markdown", "id": "e15684e8", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "### Implementing a memory cell in a neural network\n", "\n", @@ -6356,9 +6387,7 @@ { "cell_type": "markdown", "id": "2458d6f1", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "## An extrapolation example\n", "\n", @@ -6370,12 +6399,9 @@ }, { "cell_type": "code", - "execution_count": 41, + "execution_count": null, "id": "e5bf925a", - "metadata": { - "collapsed": false, - "editable": true - }, + "metadata": {}, "outputs": [], "source": [ "\n", @@ -6411,9 +6437,7 @@ { "cell_type": "markdown", "id": "4a8ce65f", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "## Formatting the Data\n", "\n", @@ -6453,12 +6477,9 @@ }, { "cell_type": "code", - "execution_count": 42, + "execution_count": null, "id": "91a277ae", - "metadata": { - "collapsed": false, - "editable": true - }, + "metadata": {}, "outputs": [], "source": [ "# FORMAT_DATA\n", @@ -6538,21 +6559,16 @@ { "cell_type": "markdown", "id": "1fac4d39", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "## Predicting New Points With A Trained Recurrent Neural Network" ] }, { "cell_type": "code", - "execution_count": 43, + "execution_count": null, "id": "e7b2f41f", - "metadata": { - "collapsed": false, - "editable": true - }, + "metadata": {}, "outputs": [], "source": [ "def test_rnn (x1, y_test, plot_min, plot_max):\n", @@ -6651,9 +6667,7 @@ { "cell_type": "markdown", "id": "8bfa51c4", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "## Other Things to Try\n", "\n", @@ -6671,12 +6685,9 @@ }, { "cell_type": "code", - "execution_count": 44, + "execution_count": null, "id": "d992cbb4", - "metadata": { - "collapsed": false, - "editable": true - }, + "metadata": {}, "outputs": [], "source": [ "def rnn_2layers(length_of_sequences, batch_size = None, stateful = False):\n", @@ -6770,9 +6781,7 @@ { "cell_type": "markdown", "id": "3230b96c", - "metadata": { - "editable": true - }, + "metadata": {}, "source": [ "## Other Types of Recurrent Neural Networks\n", "\n", @@ -6794,12 +6803,9 @@ }, { "cell_type": "code", - "execution_count": 45, + "execution_count": null, "id": "613e9cae", - "metadata": { - "collapsed": false, - "editable": true - }, + "metadata": {}, "outputs": [], "source": [ "def lstm_2layers(length_of_sequences, batch_size = None, stateful = False):\n", @@ -6995,7 +7001,25 @@ ] } ], - "metadata": {}, + "metadata": { + "kernelspec": { + "display_name": "Python 3 (ipykernel)", + "language": "python", + "name": "python3" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.9.10" + } + }, "nbformat": 4, "nbformat_minor": 5 }