{"cells":[{"metadata":{"_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5"},"cell_type":"markdown","source":"# A Simple CNN Tutorial with App.\n**Benan AKCA** <a id=\"0\"></a>\n\n![brain.jpg](attachment:brain.jpg)\n\n1. [__INTRODUCTION__](#1)\n    \n2. [__CONVOLUTIONAL NEURAL NETWORKS__](#100)\n    1. [__Convolution Layer__](#110)\n        * [Steps of Convolution Operation](#111)\n        * [Stride](#112)\n        * [An Example of Convolution Operation](#113)\n        * [Why Do We Use Filters?](#114)       \n    2. [__Padding__](#130)\n        * [Why do we use Padding?](#131)\n        * [Equation of Calculating Output Dimension](#132)\n        * [Types of Padding in Keras](#133)\n    3. [__Pooling Layer__](#150)\n        * [Hyper Parameters of Pooling Operation](#151)\n        * [Why do we use Pooling?](#152)\n        * [Types of Pooling in Keras](#153)\n    4. [__Batch Normalization Layer__](#160)\n    5. [__Drop Out Layer__](#180)\n    \n3. [__APPLICATION WITH CNN__](#200)\n    1. [__Import Modules__](#210)\n    2. [__Understanding the Data__](#220)\n    3. [__Data Preprocessing__](#230)\n        * [Normalizing the Data](#231)\n        * [Train and Test Splitting](#232)\n        * [Reshape Data to Appropriate Sizes ](#233)\n    4. [__Building and Training a CNN Model__](#250)  \n        * [Model - Build](#251)\n        * [Model - Compile](#252)\n            * [Categorical Cross Entropy](#253)\n            * [Optimizer](#255)\n            * [On-the-Fly Data Augmentation](#257)\n        * [Model - Fit](#259)\n    5. [__Evaluation of the Model__](#270) \n        * [Accuracy and Loss Curves](#271) * \n        * [Test Set Accuracy Score](#272)\n        * [Confusion Matrix](#273)\n        * [F1 Score Calculation](#274)\n        * [Evaluate with Another Dataset](#275)\n        * [Submit for Competition](#275)\n6. [__CONCLUSION__](#290)","attachments":{"brain.jpg":{"image/jpeg":"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"}}},{"metadata":{},"cell_type":"markdown","source":"# ** 1. Introduction** <a id=\"1\"></a>\n<mark>[Return Contents](#0)\n    \n* Hello everyone, first of all, I am pleased to present this work to you. This kernel was prepared within the scope of handwriting recognition contest using the Kannada MNIST data set and in the competition, it managed to be among the __top 2%__. \n* Without further ado, I would like to give you brief information about the content of the study.\n\nThis study consists of two main parts. \n\n1. Basic Theoretical Knowledge; \n\n   * Causal approaches,\n   * Visual expression\n   * Answers of the questions that may arise in your mind about CNN.\n   \n   \n2. Practicing with an Application;\n\n   * Handwriting recognition with the Kannada handwritten digits dataset which is different than the MNIST handwritten digits dataset.   \n   * In the application part, I also gave some theoretical information with visual details according to the necessity.\n  \n  \n  \n  <font color='green'>\n    \n#### If you will find it useful, I would appreciate it if you upvote.\n#### Then let's begin...\n![rsz_1smile.jpg](attachment:rsz_1smile.jpg)\n","attachments":{"rsz_1smile.jpg":{"image/jpeg":"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"}}},{"metadata":{},"cell_type":"markdown","source":"# ** 2. Convolutional Neural Networks** <a id=\"100\"></a>\n<mark>[Return Contents](#0)"},{"metadata":{},"cell_type":"markdown","source":"* In Deep Learning, Convolutional Neural Network (CNN, or ConvNet) is a class of deep neural networks, most commonly applied to analyzing visual imagery.\n* It has applications in image and video recognition, recommender systems, image classification, medical image analysis, and natural language processing\n* The name “Convolutional Neural Network” indicates that the network employs a mathematical operation called convolution. Convolution is a specialized kind of linear operation. Convolutional networks are simply neural networks that use convolution in place of general matrix multiplication in at least one of their layers\n* A convolutional neural network consists of one or several convolutional layers, followed by some fully connected layers of neurons like in classical multilayer feedforward neural networks.\n* The hidden layers of a CNN typically consist of convolutional layers, pooling layers, fully connected layers and normalization layers. "},{"metadata":{},"cell_type":"markdown","source":"## **Convolution Operation** <a id=\"110\"></a>\n<mark>[Return Contents](#0)"},{"metadata":{},"cell_type":"markdown","source":"![rsz_1rsz_conv_sample.jpg](attachment:rsz_1rsz_conv_sample.jpg)\n* You can think of left one as the “input” signal (or image), and the other (called the kernel) as a “filter” on the input image, producing an output image (so convolution takes two matrix as input and produces a third as output). \n\n#### **Steps of convulation operation** <a id=\"111\"></a> \n1. Take the element wise production of the upper left corner sub-matrix and filter\n2. Then sum all row and column to obtain a single value\n3. Result is the upper corner cell's value of your new output matrix. (output(0,0))\n4. After that, slide the filter over \"S\" column on main image and do the same thing. You have your output(0,1) value.\n\n#### **Stride** <a id=\"112\"></a>\n* Sliding amount is declared by stride (S) constant. \n* According to problem stride content may vary change and this will directly effect on output dimensions.\n* Calculation of output matrix dimension for $l$'th layer:\n\\begin{equation}\nn^{l} = \\frac{n^{l-1} - f}{s}+1 \\\\\n\\text{output} =  n^l x n^l\n\\end{equation}\nWhere;\n * $l$ demonstrates the layer number.\n * $n^{l}$ is the horizontal/vertical dimension of output matrix.\n * $n^{l-1}$ is the horizontal/vertical dimension of input matrix.\n * $f$ is the horizontal/vertical dimension of filter (kernel) matrix.\n * $s$ is the stride constant. Using for determine how many columns will kernel shift to right side in order to calculate output matrixes next cell.","attachments":{"rsz_1rsz_conv_sample.jpg":{"image/jpeg":"/9j/4AAQSkZJRgABAQEBkAGQAAD/4S4mRXhpZgAATU0AKgAAAAgABgALAAIAAAAmAAAIYgESAAMAAAABAAEAAAExAAIAAAAmAAAIiAEyAAIAAAAUAAAIrodpAAQAAAABAAAIwuocAAcAAAgMAAAAVgAAEUYc6gAAAAgAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAFdpbmRvd3MgUGhvdG8gRWRpdG9yIDEwLjAuMTAwMTEuMTYzODQAV2luZG93cyBQaG90byBFZGl0b3IgMTAuMC4xMDAxMS4xNjM4NAAyMDE5OjExOjIzIDExOjM1OjE1AAAGkAMAAgAAABQAABEckAQAAgAAABQAABEwkpEAAgAAAAMwMAAAkpIAAgAAAAMwMAAAoAEAAwAAAAEAAQAA6hwABwAACAwAAAkQAAAAABzqAAAACAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAMjAxOToxMToyMyAxMToyOToxMgAyMDE5OjExOjIzIDExOjI5OjEyAAAAAAYBAwADAAAAAQAGAAABGgAFAAAAAQAAEZQBGwAFAAAAAQAAEZwBKAADAAAAAQACAAACAQAEAAAAAQAAEaQCAgAEAAAAAQAAHHkAAAAAAAAAYAAAAAEAAABgAAAAAf/Y/9sAQwAIBgYHBgUIBwcHCQkICgwUDQwLCwwZEhMPFB0aHx4dGhwcICQuJyAiLCMcHCg3KSwwMTQ0NB8nOT04MjwuMzQy/9sAQwEJCQkMCwwYDQ0YMiEcITIyMjIyMjIyMjIyMjIyMjIyMjIyMjIyMjIyMjIyMjIyMjIyMjIyMjIyMjIyMjIyMjIy/8AAEQgAawEAAwEhAAIRAQMRAf/EAB8AAAEFAQEBAQEBAAAAAAAAAAABAgMEBQYHCAkKC//EALUQAAIBAwMCBAMFBQQEAAABfQECAwAEEQUSITFBBhNRYQcicRQygZGhCCNCscEVUtHwJDNicoIJChYXGBkaJSYnKCkqNDU2Nzg5OkNERUZHSElKU1RVVldYWVpjZGVmZ2hpanN0dXZ3eHl6g4SFhoeIiYqSk5SVlpeYmZqio6Slpqeoqaqys7S1tre4ubrCw8TFxsfIycrS09TV1tfY2drh4uPk5ebn6Onq8fLz9PX29/j5+v/EAB8BAAMBAQEBAQEBAQEAAAAAAAABAgMEBQYHCAkKC//EALURAAIBAgQEAwQHBQQEAAECdwABAgMRBAUhMQYSQVEHYXETIjKBCBRCkaGxwQkjM1LwFWJy0QoWJDThJfEXGBkaJicoKSo1Njc4OTpDREVGR0hJSlNUVVZXWFlaY2RlZmdoaWpzdHV2d3h5eoKDhIWGh4iJipKTlJWWl5iZmqKjpKWmp6ipqrKztLW2t7i5usLDxMXGx8jJytLT1NXW19jZ2uLj5OXm5+jp6vLz9PX29/j5+v/aAAwDAQACEQMRAD8A9/ooAK4/UtG8UTa3dz6dq7WlnK4dVVlY8CBcYdGAGFnPHcrQBk6rb/EGytXmj1JJEWGGLEUIlfd5kG6TaqZPyifIA7gjrhN/wrb+Jkmln1u+MtvJEnkwPCiunA+8VON3UMBxnoSKAOnooAKKACigAooAKKACigAooAKKACigAooAKKACigAooA5oeNLInBsb9cLuLNGoUD/e3Y/Wnr4xsnTelrdOpIGVMZ68f3663g6hw/2hR8yT/hKbf/nxvPyj/wDi6Y/i+1jeJWsb3MjbV4j64J/v+gNL6pUD+0KPmP8A+Ept/wDnxvPyj/8Ai6dF4k+0SiK30m/mbGSFMI2jjnmQevaplhpxV2XDGU5y5Y7j/wDhIVAdpNNv4VQ4LTrHEufYs4B/CpodXe43+Tpt24UgErJCR0z/AM9KxcWtTpU09CX7dc/9Am8/77h/+OVNZ3QvLbzhFJF87oUkxkFWKnoSOo9akosUUAFFABRQAUUAFFABRQAUUAFFABRQAUUAFFAHml1NLBpqyQqzNmMHahYhSwDEAdSFJP4U1U+1afbS3lugnZYy6lPuscZHPSvcu1sfKsqai1xBdLHZmdSYiS3lyOg64xgMN2fbpn1FPBuZItJkZmV3k3Ms6DcpMTnBxj3HSnfuKxDfXmqQXMjRQO8MZUFUUkuSDwvydsDrkc4yK6rw/eLFqRMsU6loiABEX7r125xWOIV6bsdWDdq8bmRonjPxBqWoRW72jbvtQR0+xyDC5h3bz/yz2q8pGeCVADNtJbq9ViEVlrN7b2UdxfQwtJAPI8xmcR5UADBPOOAQTXle9B9j3/dmu5z3hu/1+/vUhu4dRslk8zc7wSYEakhXDSgqGJAG3apI+baoOB02lR3qWzbLiJ4xPOCskR3sfNfncCAP++afMnuhcrWzLv2i8Rcy2Qc+kEob/wBCC0ov4w6pJHPGxGTuhbaPqwBUfnRyp7MOdr4kcDqXhG51u21iTTtQsJ5L66uTkurBI2s5oUXcFLA75FJGeADjqQbD+HvG8TXMdnrMEcBjuvILzO7CR2nMZJK8D54OOceWccEhpaa0ZSaaujvYYxDBHEGdwihdztljgdSe5p9IYUUAFFABRQAUUAFFABRQAUUAFFAHnsWfJj4/hHekmzsHH8a9/wDaFe4fLMk59P1qpd5+02HH/Lc9/wDpm9Ai3z6frWr4dz/ab4A/1J7/AO0tYYj+EzqwX8eP9dDpZoEuIzHPDFLGequNwP4EVQgsIftVz5atEFZQFilZFHyjsOP0rzFNrQ95wi9Sx9nvEDmK9LMR8omRWVf++QpP51T0pr9LXaYreVftE/mOJChz5r9Fwf1aneL8hWmvMS78Rw2M3lXNleLJtDbVRX4JIB+Vj6GoB4w04sqlJ1ZuitsVj+BbNaRw1SSvHUwljKUHyydmE2uaZdgC40+SYKcgSRo2D+JqP+17ANuji1CM9tsnyj/gJbb+lWqNVK1jOWKw7d76kcfiPfbJJbTXDiQB1a4t0b5Tz0Vl/Wll8X/Zlmlm0+Q28SFi8brvOBz8p4H/AH1R9Xk9bWBYyCdr3Nz7eEUGa2uYie3lF/8A0DcKfHfWksvkpcxNLjJj3jcPw61z8j6HWprroWKKksKKACigAooAKKACigAooA8zu1nfTALcOZP3ZKo21mXcNwByMErkdR9RT4VnXT7Zblt04EYkPq2Rn9a9w+WZV1O2uZ7hWgNwqpExYxS43N0VQu4Duxzx0HNOAmEWki4ULMHHmKGLAN5T55JJP5mgRQvoNZa9umt/N8kkbAsoX+AgY57PgngcAj5s12/hvP8AaTZ6+Qc/mtYYj+EzqwX8eP8AXQw9JsPGq31s179sCG8LszXSFY1zEW3AOd6somVcAYZs7Ixjb2GoLdvp+spYFheNEwgKsFPmeX8uCQQDnHUYryj6A53wtZ+KYdRt21YXQiCSFmluFdRGWOyMqHY+YDht2WwuFLsQc9TpP/HnJ/183H/o56AMDxD/AMh0/wDXtH/6FJXNWl9c3GqyQTQNDF9nWRY5EG9W3EEFlYqeMHA9a9Sg2qcTwcUk60y0tnAI2WOPy8sSfKJTJ9yuKzNAn1G+smmvGeJwyhQYtoIMaMeG+bhiy9f4a35ndJnNyqzZNbveQ+HopImgLi2UoXVgF+XuBkn8MUx7ya58NvLNbSK0lkXdsAAMU5GM7hz7UnZqy7DjvfzPTRqdntDSTeSD089TET+DAU65uLFYP9KmtxDJx+9Zdrfn1rx+WSPo+aLKAk0FFjWG9tYEj+6kF15S/wDfKsAfxpft9ohJj1+3Y9llkjZR+WD+tVdv4lcm0V8LsJ/bKIFH27Spufmb7T5WB7D5s/nR/wAJLpy+YZpVjRDgMJUff9AjE/mBRyJ7B7S25JH4j0SVgi6rZhyM7HmVW/I81pI6SxrJG6ujDKspyCPUGpcXHcuM4y2Y6ipKCigAooAKKAPOYo28lP38n3R2X/CkmjfYP38n317L/eHtXuHyzH7GHW4k/wDHf8Kq3UbfabD9/Icznsv/ADzf2oEWvLb/AJ+JPyX/AArV8PwSNqTgXUy/uTyAnqvqtYYj+EzqwX8eP9dDpfs8n/QQn646R/8AxNQQW0v2q6/064++v8Mf90f7NeUfQE4t5D01Cc8Z6R//ABNYjeI9J8Nacp1i/MCyT3jJLJGxDbHdmGVXG7GSF6tg4BxQBQ8RyzNravBEjK1pGf3jMhHzP22k/nWXvvf+fe3/AO/5/wDiK9TD39mjwMXy+2lcRXvcH/R7fqf+W5/+Ipd97/z72/8A3/P/AMRWyvY52o33K2mvef2VZ4t4MeQmP35/uj/YpNSe8/sq83QQBfIfJExP8J/2al35So8vOtep6lXM+JrC0Jgl+zRCU7h5ioA3b+Ic15uHbVRWPcxaToyOPl1MW2rRacvmu0hCq0gG0MUdgu7O77sbHJB+tSx3Kpq9z56mL9xFy33fvP36Dr3wa9VWlseC1KK16j7PVob27mt445V8ssA7AbX2sUbGDnhhjkD2zTxL5AvpdhcJJkgEDjYvckD8zU3T1G007XK+la5BqzFFt7iBvKSVVuFVS6uobIGSSBuwT2IIrt9EtpLfQrCW0Iw0CM8DH5WyoyV/unv6Hnuc1y4iScV2PQwUHGcl1RrW9zHcqSmVdTh42GGQ+hH+QeoyKmrhas7Hqp3VwrF8Ra1JpA09I/s6Ne3P2fz7ltsUOI3ky312bQMjlhSGc1D8UIJrCBl0yQXjxxSSQtKqqof7Lk7jzj/ShgkDOxulTzfE/SLeS8WW2uE+zNIu4tHhyvncA7uGJt3wp55U96AOi8Pay2uafNcvbfZ2iu7i1MfmB/8AVStHkkdM7c49+/WtagDzS5tftmnJDlesb4YZB2srYPscY/GnQ25tdOtrcvvMQjTdjGcEDNe4fLMhv9Ljv7mOWVI2VI2XaRgknHccgAbh/wAC9qTyWt00mB5BI0cmwuF27iInGcdqBFK98Otd3txceeg84klWTI/1ZQflnPuR2rtPDYxqTDJOID1+q1hiP4TOrBfx4/10MjSvhxJp13BO9/DIyXIuGYQ4ZSDCSUOfl3eTgg54fGTj5uq1GwbVNO1rT1lETXULQCQrnbuj25xkZxn1ryj6Aw/DfgdtB1CK5N1FJ5ZlYFYsOA7MfKz/AHBuz0GWycDOKl1PwjY+LtLit9QuLuOK3vLmWNbeQJiXzHCyZwTuTJK9snkHigBuvArrQUsWItYwWOMn5n54rmLY6pJrm65gaC2W3IYJKskbyFhjHRhtAP8ADzuP90Z9Sjf2cbHg4q3tp3NVc7Tjrk1l+H11NLBhqm/zSy7RIylgNi7sleOX3kexHToNdbo5/ds77ksDSJ4ciaGJ5pBaqUjRwrMdvABPA+tRbblfCbreGQ3K2jCUybdxbacn5SRSd7fIcbX87nqtc94qlWKG2Zg5BZh8iFj29BXmUP4iPdxX8GRyRNi14t2bWQ3CrtEhtnyBz/s+5/M+tRx3kX9r3B2z/wCoi/5YP/ek9q9S6R4Nm9wVLKOZ5oIp4JX4Z47dxnnPI247nt3PrUC3KyrfQXNtJcQyuVcLA43AoAQVI6Y9/wAKq6ejFaW5ZjuNPF7JKkUguioVz9nfdt7dunFd/oB3eHtOIzzbRnkY/hFcWMVkkejl13KTZZuLRLghw7xTKMLNHgMv5ggj2IIqLfqFvnfGl3H2MfySD0GCcH3OR9K5E09GepZrVEkF/bzyeUr7ZsEmKRSj4HGdp5I9+lTyRpKhSRFdT1VhkGpaadmNNMRoYnLFokYsNrEqOR6GoYNPs7aIxQ20SxmRpCoXqzEkn6kk/nSGWFRUztULk5OBjJ9aWgDlZfD2j2mnR3c93c2sW1NzG6Ygs2AB8xPJJAAHUkAUSaFbPZpdWzw3UEpiaArPKocFlwd4dgQQeoWuj6xN7s5fqlNbIjvF0TS5oINStpIZplJGy9cpkAnALMpJwp4AzxVe6g0CefQ54DMLae6JMryyqjJ9nlIIZjjqB0NP2lR/DK4exor4o2Lj/wDCJJcrbG6Bmb7qLcysW4zxhuePSrMmgWK6tbxxNdwhoJSTFeSoSQ0eOje5rN1am0maRoUlrFFONtIkdYrXxNJLNK5SMTXsjAkbeAFdc/fTv/EvqKs/YhZzXk1y8gtYV3zTnU54yuEBJwWwBjuWqbxfkXaS21IrTUtDvJUiS41DznVmWNb2aRsKxU8I7YwQQQeRg1oaHdWaWf2ZLld/2ifakkpMh/ev13Hd+dHI91qCmtnoZHiMOde+Vwv+jR9Vz/FJWZsm/wCeq/8AfH/169LDp+zR4eLa9tLQaqS4P71ep/g/+vTtk3/PVf8Avj/69apOxztq+xU0xZf7Ks/3o/1Cfwf7I96NTWX+ybzMgI8h/wCH/ZPvSafKVFrnWnU7XxE2rLaw/wBkLcGXf8/kJCx247+ayj8uapaqbg6Vpxuw4uNn7zeFDbsDOdpK5+hIry6H8RHu4r+DI4+bWHi8RwaYIkYSAZ5+cArI2/H90FAv1ccjGDcj/wCQxc/9e8X/AKFJXqJ3PBlHlXqippurtfapeWhRB5BIIB+ZMOyjcO24LuHsfbJL+/8A7MsNSvAqsY5VwGOByEHsO/cgepA5C5tLj5Pe5fQo6Nr39uXUcEttDg26znacmJtkTDPpnzG2n/YJ5zx6TocFzHoWntBcZU28ZMcw3D7vQHqPqc/SuXET5oK56GDp8tSSTL325ol/0q2lib1jUyqTjnBUZ9uQM0n2932+TY3Uin+IqI8fUOQfyFcnJ1voekpPa2pyWueL7m01CfTrnQbO5WFlOWvDg8BgcGLg81lDx3qkBH2bTogmeY579pRjvgmMNn6kj2rsp4OUop30ZyTxcYyatqjs7PUtcvbK3u4tL04RzxrIgbUHBAYZGf3PXmnXF9r1tayzvpemlYkLkDUZMkAZ/wCeNcLVnY7U7ol+0eIP+gZpn/gxk/8AjFOjutYWeMXen2McLMFZ4r13YZ6YUxKDz7ikMbdWEOraJBayTvFgwTK8ZXcrxusinkEfeQdulOis7fS9EstPt3JhtRBDGXYE7VZQM+/FAEOr6BZ6zdQXFxcSq9vGVhCMuEYuj78EH5gY1AzxgsO5qvNaQ6c/hy0ilZ1jvXy7kbmJt5yWOMDJJJ4AHPAFADNY8H6Vrk93PdyN51wiRiUJGWhVQwHlllJQ5dm3D5gcc8Yq3JZxprEIhu7iIvBKxbzjIR80fTfuAH0FUpMlxXQwbP4fW2nXEcltqs7xrMs0kcyqfNZWjYFiAOd0SsSBkktnOeNi8Sa+sdYsri3Yx3KGE/Y518zayYJBcKAcH1NHuvyF7y8zP0Xw9pWg3kbpcagCheby5owY1dsgncq4GFO0KG2gAcZ5ra0W4tbuxlWOWGZftM+QrBuPNenyyWqDni9Gc9rthaw6yY4IVgT7PG22H92Cdz/3cVz1vp9/Frct1JNE8T26x78ncWDE/cxwMN/e/nXp0W3Tjc8LFJRrTSNAfaAhA8pzk85K4/nWX4dsLnR7CS3uk/iDDyjuQYRVOP4ssVLnjq569TryptNHPzWTTRPbyJJ4egjUx+Y9qqqkzGMMdvQnGQPwNJ5Etr4SNvPsMsViY3KMWUkJjIJA9PSplFpX8ioSTdvM9VrB8TZ8u3wM8t/SvLofxEe9iv4MjnMn+6aqRk/2xc/Kf+PeLv8A7UlerqeAku5byf7pqvbE+dd/Kf8AW/8Asi0agkrbljJ/umuosmu08GQvYeR9sWxBg+0EiPzNny78c7c4zjtXHjNkejltuaVit4I1m+8Q+FrXVr9rfzLnLKsELRqoHBHLtu+YNhgcEEEV0VcJ6x438QzeDxJcfYllZ/Ph3+Xs4TYu7O/gjHHBzyK5bTzrX26L7Us32c793meUMDJ2k7STu6DA4xznPFe1S5+WNtrI8ipyc0r73Z734e/5FrSv+vOH/wBAFTar/wAge+/695P/AEE140t2etHYuVBdfdj/AOuqfzpDMy6k0/StEhu5rFZf9TEscUSlneRlRQM4HLMBkkD1pyf2bqWjWd/a20RgufImjJiAJVmUjIxxwaAGa3f6VoFqlxd2IeNi24xQqdiqrOznOPlVVJOMn0BNN1aytRqWhAW0IzfMD+7HP+jzUAOvL7SrHVLawlsQzzbcyJCpSLcdqbu/zMCBgHnrip5LK0/tq2H2WHH2eX/lmP70dAFaHUtIn8Qz6KlkPtEKMxcwrsJURFlB65AmiPTHzcE4OLsFlafarr/RYPvr/wAsx/dFAFPStQ0nV7u8toLEJJannzIVAdd7oHXGeC0Ug5wflzjBBNjTbO2l09o5LaF0W5uMKyAgfvn7U02ndCaTVmNu/DemXk/nSRzLIEEY8q5kQBRkj5QwXue1UB4NtYowsd1cyNuyWuJpGOPQbHWto15pWOeeEpyfNYX/AIRi2RsGyd09U1GcMf8AgJOP1pDoukRx757DU4stgATzSH6/u3bj60/aze0iPq1JfFAdB4f8N7haQs2+NQPJF/LuUdsjfkVI/grQZFdWtJsOCrYu5hkH/gdJ1q0dGylhcPLVRNT7CyCNYby6jRDkqWEm/wCpcFvyIrE8RLeKkJeSCUbm2gRlMdOpyc/lToNOoroWKi1RlZnFS3WrL4kghWCQ2ZUeYFQGMLtfLbzg7wwjG3PRmOD1FyO4iGrXbOxRVgiBLqVH3pO5r00mzw5OKSt2K2l3N/Pqt8twXNup+QGMBF+ZguxsfNlNpPJwTjjoHahLdQadqclkHNwJBs2JuI+VASBg9Bk9G/3W6GPetruVaPNptoU9ButamvVTUFl8v7Mhk8yEIA+yPBU4GSxMuR22rwvf0iz0+11bwbb6fexmS1ubJYpkDldylcEZUgjI9DXHiW3FXPSwKiqkuXyLek6RaaJZCzsftAgByqz3Us5XgAAGRmIGAOAce1OfUN7tHZx/aHU4Z922ND6FvXjoMkd8VyxVz0m7HM3eh6Zq15NdSXN1d3Uh+b7Co8slQBjJBVTx0LVGPAUcpyJZrdMg/vHWRiPQgKAD+Jrsjip00k+hySwsJu51WkRCHRbCJWbalvGozjoFFGqg/wBj33zH/j3k/wDQTXE3dnYtC5g/3jUF0Pli5P8ArU/nSAzZZdPv9Kjs7yC7aPbGSv2aZSGUhlIIAIIYAgg5BFK11ZW+nwWtrb3CQwtEkcaWcuFRWXgfL0AFABqH9k6rHHHfWtzMkb71Btphzgg5wOQQSCDwQcGodTvo5b/Rnjhu2WG8Z5CLSX5V8iVcn5fVgPxoAmnOk3N/BfTW1y1xBxG/2aYfmMYbGTjOcE5GKWTUYTq1vII7vYsEqlvskuAS0eB932P5UANjXR4tWl1SO0uFvZVKPL9mm5B2g8bcZIjQE4yQi56CpodSgW4uWMd0AzAg/ZJeflH+zQBDZDSNOmuJbS1uY5Lht0h+zTHPLNgZHA3MxwMDLE9zVvSCTYMxR13XE7AOhU4MrkHB56c0AX6KACigBskccyFJUV0PVWGQarf2bagARxtCB2gdox+SkVSm1sTKEZbi/Zp0ZmjvZD8uFSVFZQfXgBj/AN9VmatpurX1vbpHLZNIhJeRldAc+i5P86uE4xkpWMqtKU4OF9ylF4Y1Aj97fWqn/YhY/wDswqJvB98LqSePVbdWdFQhrNmwFLH/AJ6D+8a6njF2OFZa+sgHg69Zt02pWTN/eWwYH8/NNRL4GvUkkePX2TzG3EC2B7AfxMfSj68/5Q/suP8AMPHg7VFbP9vo64+61kASfqG/pWnBo2qQ6dbWy6lCpiiVD+6kIyBjjbItZ1MSqi1ibUcG6Tdpbk66LK8LR3N677hgmNpB+juwP0IIqymk2gVRLGZ9oGBMdyjHTC/dX8AKxdV9NDrjTtu7ltPvP/vf0FPrI0K2nf8AILtP+uKf+gimar/yB77/AK95P/QTQBcqC6+7H/11T+dAE9FABRQAUUAFFABRQAUUAFFABRQAUUAFFABRQAUUAFFAFKTToLieWV3ugxYZEd1Kg6DsrACm/wBkW3/PW9/8Dpv/AIugCtp+k2x0y1Pm3vMKdL2b0H+1TdU0m2GkXpEl7xA/W9mP8J/2qALf9kW3/PW9/wDA6b/4umSadBbvDKj3RYSrgSXUrjr6MxBoA0qKACigAooAKKACigAooAKKACigAooAKKACigAooAKKAGr95/8Ae/oKdQBW07/kF2n/AFxT/wBBFM1X/kD33/XvJ/6CaALlQXX3Y/8Arqn86AJ6KACigAooAKKACigAooAKKACigAooAKKACigAooAKKAK8ljaTSGSW1gdz1ZowSfxpv9mWH/Pjbf8Afpf8KAD+zLD/AJ8bb/v0v+FH9mWH/Pjbf9+l/wAKAD+zLD/nxtv+/S/4U6Ows4pA8dpAjjoyxgEUAf/ZAP/hMeRodHRwOi8vbnMuYWRvYmUuY29tL3hhcC8xLjAvADw/eHBhY2tldCBiZWdpbj0n77u/JyBpZD0nVzVNME1wQ2VoaUh6cmVTek5UY3prYzlkJz8+DQo8eDp4bXBtZXRhIHhtbG5zOng9ImFkb2JlOm5zOm1ldGEvIj48cmRmOlJERiB4bWxuczpyZGY9Imh0dHA6Ly93d3cudzMub3JnLzE5OTkvMDIvMjItcmRmLXN5bnRheC1ucyMiPjxyZGY6RGVzY3JpcHRpb24gcmRmOmFib3V0PSJ1dWlkOmZhZjViZGQ1LWJhM2QtMTFkYS1hZDMxLWQzM2Q3NTE4MmYxYiIgeG1sbnM6eG1wPSJodHRwOi8vbnMuYWRvYmUuY29tL3hhcC8xLjAvIj48eG1wOkNyZWF0b3JUb29sPldpbmRvd3MgUGhvdG8gRWRpdG9yIDEwLjAuMTAwMTEuMTYzODQ8L3htcDpDcmVhdG9yVG9vbD48eG1wOkNyZWF0ZURhdGU+MjAxOS0xMS0yM1QxMToyOToxMjwveG1wOkNyZWF0ZURhdGU+PC9yZGY6RGVzY3JpcHRpb24+PC9yZGY6UkRGPjwveDp4bXBtZXRhPg0KICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgIAogICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgCiAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAKICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgIAogICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgCiAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAKICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgIAogICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgCiAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAKICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgIAogICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgCiAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAKICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgIAogICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgCiAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAKICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgIAogICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgCiAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAKICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgIAogICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgCiAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAKICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgIAogICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgCiAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAKICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgIAogICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgCiAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAKICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgIAogICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgCiAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAKICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgIAogICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgCiAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAKICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgIAogICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgCiAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAKICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgIAogICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgCiAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAKICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgIAogICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgCiAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAKICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgIAogICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgCiAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAKICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgIAogICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgCiAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAKICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgIAogICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgCiAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAKICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgIAogICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgCiAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAKICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgIAogICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgCiAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAKICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgIAogICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgCiAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAKICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgIAogICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgCiAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAKICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgIAogICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgCiAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAKICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgIAogICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgCiAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAKICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgIAogICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgCiAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAKICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgIAogICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgCiAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAKICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgIAogICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgCiAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAKICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgIAogICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgCiAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAKICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgIAogICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgCiAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAKICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgIAogICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgCiAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAKICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgIAogICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgCiAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAKICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgIAogICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgCiAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAKICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgIAogICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgCiAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAKICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgIAogICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgCiAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAKICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgIAogICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgCiAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAKICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgIAogICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgCiAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAKICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgIAogICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgCiAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAKICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgIAogICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgCiAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAKICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgIAogICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgCiAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAKICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgIAogICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgCiAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAKICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgIAogICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgCiAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAKICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgIAogICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgPD94cGFja2V0IGVuZD0ndyc/Pv/bAEMABQMEBAQDBQQEBAUFBQYHDAgHBwcHDwsLCQwRDxISEQ8RERMWHBcTFBoVEREYIRgaHR0fHx8TFyIkIh4kHB4fHv/bAEMBBQUFBwYHDggIDh4UERQeHh4eHh4eHh4eHh4eHh4eHh4eHh4eHh4eHh4eHh4eHh4eHh4eHh4eHh4eHh4eHh4eHv/AABEIAO4COAMBIgACEQEDEQH/xAAfAAABBQEBAQEBAQAAAAAAAAAAAQIDBAUGBwgJCgv/xAC1EAACAQMDAgQDBQUEBAAAAX0BAgMABBEFEiExQQYTUWEHInEUMoGRoQgjQrHBFVLR8CQzYnKCCQoWFxgZGiUmJygpKjQ1Njc4OTpDREVGR0hJSlNUVVZXWFlaY2RlZmdoaWpzdHV2d3h5eoOEhYaHiImKkpOUlZaXmJmaoqOkpaanqKmqsrO0tba3uLm6wsPExcbHyMnK0tPU1dbX2Nna4eLj5OXm5+jp6vHy8/T19vf4+fr/xAAfAQADAQEBAQEBAQEBAAAAAAAAAQIDBAUGBwgJCgv/xAC1EQACAQIEBAMEBwUEBAABAncAAQIDEQQFITEGEkFRB2FxEyIygQgUQpGhscEJIzNS8BVictEKFiQ04SXxFxgZGiYnKCkqNTY3ODk6Q0RFRkdISUpTVFVWV1hZWmNkZWZnaGlqc3R1dnd4eXqCg4SFhoeIiYqSk5SVlpeYmZqio6Slpqeoqaqys7S1tre4ubrCw8TFxsfIycrS09TV1tfY2dri4+Tl5ufo6ery8/T19vf4+fr/2gAMAwEAAhEDEQA/APsuiiigAooooAKKKKACvKPFfj/VdD+P8HhuWVT4ej8IXGs3EKQqZWljlIyGPP3VxjOK9Xryrxz8N9Z134uyeLrW7sI7F/CF1oflyMwl8+V2ZWwFI2Ybk5z7UAY1n+0r4Ou300ReGfGpTV7Yy6S/9kEjUZVxughw2WcE4J+5kH5scnotG+Mek634GTxPonhfxXqcp1F9Ml0q208NeW9wgJdZRuCIAMZYtjkDrxXPeHPhH4h06P4OCe+0xm8ER3K6lskc+aZYdg8rKjOD13bePyrB1L4JeNl8Manp9lqmk3C3fje71+fTpLy4t7e/tJgAsE0ka7wQRnABUn1xQB3Fv8cvC8/g4a9HpWvm8Otf2CNF+yL9v+34yYNm/aDjnJbAHftVex+Pfhq60C71NvDvim3uINYXRIdOls4/tV1fEEtBEqyEErj5ixAHHPNeHfEP4d6z8Ofh5YaVq02lW8OpePf7Ya5tFu/sFhF9m2qJJExPHhwQpVsnHLCtPwj4EvPif8MI7LR9C0G0PhnxK13ZXExvDp/iAOn753aXM53EgGTJ5GB7AH0b8N/Hel+OLXUTaWWo6ZfaXdmz1DT9QhEdxbSgBgGCllIIIIZSQRXWV538DfBV34O0jUUvvDvhbQ7i8uVk8nQ5Z5UZFQAGR5sFmzu6AADHWvRKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKK5BfiX4JeaWGPWhLJE7RusdtM5VlJBHCHuDTz8RvCAODqcw+tjcf/EVr7Cr/K/uMvb0v5l951lFcn/wsbwf/wBBOb/wBn/+Io/4WN4P/wCgnN/4Az//ABFHsKv8r+4Pb0v5l951lFcjH8SvBkgJj1aRgrFTiyn4IOCPuU7/AIWN4P8A+gnN/wCAM/8A8RR7Cr/K/uD29L+ZfedZRXJ/8LG8H/8AQTm/8AZ//iKP+FjeD/8AoJzf+AM//wARR7Cr/K/uD29L+ZfedZRXIp8SvBjs6pq0jFG2sBZT8HAOD8noRTv+FjeD/wDoJzf+AM//AMRR7Cr/ACv7g9vS/mX3nWUVyf8Awsbwf/0E5v8AwBn/APiKP+FjeD/+gnN/4A3H/wARR7Cr/K/uD29L+ZfedZRXC33xc+H9i7Ld65JFtALM2n3O1c9Mny8A+1S2HxU8D6hGJNP1W5vEPQ2+mXUg/wDHYzUypzjuilUhLRM7WiuSPxF8LA4M2qA++jXn/wAao/4WL4W/57ap/wCCa8/+NVBZ1tFccvxM8HtcvareaiZ40V3jGkXm5VYkKSPK6Eq2Poak/wCFi+Fv+e2qf+Ca8/8AjVAHW0VyX/CxfC3/AD21T/wTXn/xqj/hYvhb/ntqn/gmvP8A41QB1tFYGgeMfD+u6m+m6ddXDXiQfaDFPZTQHy923cPMRcjPHFb9ABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQB8+aTo+lXulpJdafbSyGWb94Uw/wDrn/iGD+tWRoaRD/QdV1ez9FS7aRf++ZNwqXw5/wAgeP8A66zf+jnqp461ibQfC13qVtGj3C7I4Q/3d7uEUt7AnP4V9nGclFan5vXinVl6sm8jxHB/qdYtLsf3bq1KH/vqNh/Kj+0Neh/4+NEE4/vWd6rf+OuFP61maBf6xbeL7vw1rF7FqJWxS9huUtxCRlyjIVBxjPINdQelVz33X9fIy5TmdC8QWltBdi9S+syb+4Yma2faMyE4LKCuR35rcstX069/489Ttpz6Rzgn8s5qv4cJFveYJH/Exuun/XU1z3xQtp4tFutXjudJt4bOAyFbnT0maaTPCbj90HgDHOTSvDsFmdqS46s4+pNJubH32/OvIdUuLrTtX00z6tfeE7OXSYrmc28Ek0K3DNgo2SQox69K9Fjs9ZWJZLPxClyjKGX7VaI4YEcHchU4o5YvZhdroTaGzfbNZ+Zv+Qge/wD0xirU3N/eb865bR7jXYLvVt2mWl5/px8w2915Z3eVH0Vx0xjv61W8VaxqMNsbtbrVNAit4maXzNLS5Rz2+cMQvp6c0/ZvoHMjstzf3m/Ojc395vzryA+ONVjsvD41LxPb2D3VvPLfzRaeszQtuHlIUxwcHqK9V0qVbjS7W4ju1vUkiVhcooCy8feAHAz1x2qGmt0Udd8KPmvvEQbkGeDrz/ywWuj1Hwj4a1B/MudEsjL181IhHJ/30uD+tc58Jf8Aj/8AEP8A13t//RC1gftIeONc8Gf8IytrrUPhnRNRu5YNT197D7a1mwj3QoIe/mEMC2DjHvXzWLnKGIk4ux93gKcZ4SmpK+h2zeDkhbdpfiLxDp+Puot8Z0H/AAGYOMUhsfHFoP8ARtf0rUh/dvbFom/77ibH/jteOeEPiB8SvG1r4G8M2uuafomraxpd5q93rC6fHP5trHMI7cpCWKK0gIZgTlenByB6f8BfF+qeNfh1b6rrkNvHqsF1c2N4bcERSSQStGXUHkBtoOOxJrD6xN/Fr6pP8dzp+rQXw3Xo2vw2M/T9X8TWnxN1lr3wt9qf+yLEONNvkkwolusMBL5Z5yePb3rpP+E50eAf8TS21bST/wBPunyov/fagp+tJpv/ACVbXP8AsC6f/wCjruub/aM8X674M8H2GpaReRaVaT6pDbanq72v2n+zbd8gzCHPzndtXvjdnFHPTfxR+5/53D2dRfDP71f8rHdaV4g0LVcDTdZsLwn+GG5Vz+QOa0+K+WNK8V6/420nwtoTSeHby/8AE/iDUbXT/E0ujQu0unWke8z+QThJWbKhTjAGcc13fwMs7nXdN8RabqOpahY6t4b1240ia60u7kihuhGFZJfJdnRCVcZUDGRxRak+rXyv+P8AwAvWW6T+dvw/4J3sn/JZIP8AsX5f/SmOuwry6TTPE9p8WIUsvEsd5KNBkKnUbFW+X7SnykxFPzwa6j+0fG1oALrw5p2oj+/Yahsb/viVQP8Ax6j2N/hkn87fnYPb2+KLXyv+VzqaK5f/AITS3tyRquh6/pgHV5bBpUH/AAOHeKuab4v8MaiwSz17TpJSceUZ1WT/AL5bB/Sk6FRK/LoNYik3bmVzcopAQRkcj1payNgrzMfGrwxL43u/CVppHii+vLLUV066ntdIkltoZSQPnkXhVGcknsCa9MPQ182/BrQfFOofGn4lahpPjS50XTLTxeGvdOTToZlvlChipkcbkyvy/L65oA9J1f4t2OlwWEt/4Y8Q2X27xWvhqFbu3WFnkYnFwoLfNCccMOT6V2Og+JtD13UdW0/StQS5utHufst/GqMDDLt3bSSADweoyK+Sk+0PounswlZk+PTFd2ThQ38qrto+leGNa+OOm+FbO5svHUQmk0SKJpzP9gdY2nePkgnBJB+9nG2gD7UVlbOCDjg4oDAkgEEjr7V8VeALfSh4a8bXvhnxP4ZMD+AL1bzR9EjvAzyCP5LifziQswJKnkMcnjqa+hP2YfCWkeHvhRomrWUV0dS13TLO91O4uLmSV55jCME7iQuAdoAA4AoA9SooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKAPCvDn/IHj/66zf8Ao56Z4p0aHxBoNzpM8rwrMFKyp96N1YMrD1wQKpaJrej2+nCCfU7SKVJpwyPIAVPnP1q7/wAJDoX/AEGLH/v6K+wjsj84rfxJerKegaFe2utXWt6xqUV/qE9ulsrQ2/lRxxKS2ACScknJOa36zP8AhIdC/wCgxY/9/RQfEOhf9Bix/wC/oqjMXw7/AMe15/2Ebr/0aayfFfh3VtX1ywv7bVbKK3sRuitbq0aZPO/56kBgCQMAZ6c1JoGvaIlvdh9Ws1Jv7lhmUcgyHBrR/wCEh0L/AKDFj/39FAGVr+heItZ0p9Mn8RWsdtdQCK9VNP5bn5jGS3y5GOucdq6KxtorKxgs7cEQ28SxRgnJ2qAB+gql/wAJDoX/AEGLH/v6KP8AhIdC/wCgxY/9/RSAND/4/NZ/7CB/9FRVW8a6DJ4j0qPS/tgtrZriOS7GwsZo1OTGORjJxz7VW0bXtFS71cvq1moe/LKTKOR5UYz+hrS/4SHQv+gxY/8Af0UwKnivRtR1WD7PYahZWkDxGJ0nsFn2g8bkJIKsBx3HApuleD9I03Tre0tTeRPDGE8+K6eOSQjqzbTgk/Srv/CQ6F/0GLH/AL+ij/hIdC/6DFj/AN/RTUpLZiaTNv4a6Rrn23XP7L8T3EHlzwblu7aO4D/uQeT8rcdODVH4m+BPifrPirw/4s0XU/C51XQknjt1uLaRoZFmChiY2J2uNvDBxwcVf+G/jLwpp1/rv27xDplv5s0DR+ZcKu4CEAkZ9xiuz/4WL4F/6GzR/wDwKWvnMbWft5JpP5f5WZ9xl1FfVYNNrTv+jujxHRPhvr3g8aLqmkS6zpHiSwN79pvW0ZL6xuEunEjoILeXdGqsAUA4HOQc8elfCCbwV4J8HWXhaHxPFNcxNJLcz6gptZrmeVy8jlJMYyzHA5wMCuk/4WJ4F/6GzRv/AAKWobvx38PbuEw3XiXQp4z1SSdGB/A1y89J7xt6P/O/5nbyVVtK/qv8rfkO0aaG4+KOtywSpLG2i6fhkYMD++u+4rP+L3gK98Zt4fv9K1qHTNU0DUPt1obmzF1bSPsKYki3LnAJIYEFT0rkIb34US/EXVmXVtGsrYaZZtE9lefZcSmS43kGMrzgJn8K2v7b8LWwJ0v4uvb+iXV3Ddp/5EXd/wCPUclJ7S+9f5XDnqreN/R/52/M5+y+BWpWBh8RWXi23i8aRa5NrK3q6YFst00Qilh+zq4IRlAyd+4nk16D8J/BLeCdEv4rvUv7V1bVtRm1PU73yfKE1xKRnamTtUAKoGTwK58fEF7RgF8aeBtVjH/PSZ7Rz+IMi/pTx8ZNBtiRqUUIA/jsNQgul/IMr/8AjtHsG/hafz/zsw+sJfEmvl+qujek/wCSywf9i9L/AOlMddhXkmkfEXwbq/xPg1S21uGO1GiPAz3KtAFc3CEKd4HYGvUrDULDUIvNsL22u4/70EquPzBqZ0pw+KLRcK1OfwyTLOKpalpGlammzUtNs71fSeBZP5g1doqE2ndFuKkrM5c+A/D0ZLadFeaU5/i0+9lgA/4Crbf0o/4R/wAR2uP7N8Z3jKOkeo2kVwP++lCN+tdRRWv1ip1d/XX8zH6tS6K3pp+Ry32jx3Z5Mum6FqqD/n3uZLZz/wABdWH/AI9QPFdxanGqeE9esieWeK3W6T65hZj+ldTRR7WL+KK/Ff8AA/APZTXwzfzs/wDg/ic3Z+NfCFzL5I1qygmznyro/Z3z/uyBTmt+B7eYCeFo5AwwHQg5H1FNvLS1vIjDd20NxGeqSxhwfwNYM3gTwq0pmt9JSwlP/LSwke1bPr+7K0fuX3X3P/IP367P71/mdEkUSbgiIu45bAAz9aeAAMAYArlv+EX1S2H/ABK/GOsw/wCxdiO7T/x9d3/j1GPHlmeH8P6sg9Vls3P/AKMX+VHsov4ZL8v+B+Ie2kvig/wf/B/A6miuW/4SbWLUf8TTwZq0Y/v2UkV0v5Kwf/x2nx+PPC/mCK71I6dKf4NQgktSD/20UD9aPq9Tor+mv5B9ZpdXb10/M6aiq9jfWV9F5tld29zH/fhkDj8wasVk01ozZNNXQUUUUhhRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAeFeHCf7Hj5P+tm/9HPWjk+p/Os7w5/yB4/+us3/AKOeofGOs/2B4cutVEInkiCrFETgPIzBVBPYZPNfYR2R+c1v4kvVmvk+p/Ogk46mua0DWNX/AOEluvDuuxWJu47RLyKazDiN0LbSpDEkEN3zzXSVRkZvh0n7Necn/kI3X/o01p5PqfzrM8O/8e15/wBhG6/9Gmsvx1qWu6Lp11q9ldaPFYWtvvdLqGRpHfPRSrAc5UD3oA6fJ9T+dGT6n8686uvGGvQanpum3l34d0ie40qO8la+WTZ5ruR5a4YY4x19DXoa52jJBOOSOlIDN0Mn7ZrPJ/5CB/8ARUVamT6n86y9D/4/NZ/7CB/9ExVkeOPEV5o17p9nbPp1lHdrKzX+o7/IjKDIj+XHzN2ye3egDq8n1P50ZPqfzrhbDxT4i1f+yrHT9PsbPUrjTW1C5F4JCiJv2IFAIPz9QT0BFdH4P1keIPDVlq/keQ06nfFuzsdWKsAe4yDTA7z4Tc3/AIhz/wA97f8A9ELXf1wHwl/4/wDxD/13t/8A0QtZ3x2+IOs+Crnw3YaUdF05NZuZYpta1vzPsFjsTcqybCvzSchcsB8p618vjv48j73Lf90p+h6hRXgnh34s/EDxZY+DtG0PSNBsPE2t2N3qNzPqCTtZpawS+XHLGgKyETEgrk8DnkEV6P8ABfxpP488BWuu3tgun36zT2l7bo+9EnhkaN9rd1JXI+uO1cp3FrTf+Sra5/2BdP8A/R13XVVyum/8lW1z/sC6f/6Ou6xfjx451XwL4c0280q3sEe/1OKxl1DUg/2LTkfP76fZg7cgL1UZYZNAHolFfP2h/GLxxrWj6DpNhp3h5/Eeva9fabp+o7ZjplzaWqb5LyNd29lP3QN3JBIJFei/Bjxpqfi/SdZt9esrW01vQdXn0jUBasxgkkj2kSR7uQrKwOCSR60AW7hFf4xQo6hlPh6UEEZB/wBJjrRv/BfhS9k82fQbBZc582KIRSf99Jg/rWfJ/wAllg/7F6X/ANKY67CrhUlDWLsROnCeklc5f/hDzbndpPiXxBp+Pup9s+0Rj/gMwfj8a80n8Q/Eu4lvk0/xTpaC01C5swJ9KUlxFKyBiQ2ATtz0xXudeG6X/wAfWt/9h3Uf/Sl69HAP21RxqK+nVfrueNm7eFoqdF8rv09H02K//CT/ABRh/wCPrUBIP71nZW8n/jrMppP+E68TR8Xvi64sD/09eHVQf99ZK/rWtWWPEmhf8JIPDK6vanWGiab7Ej5kCAZJYDheOcHBr1XhML1hb5ngRzLHP4Zt/Jf5Fyz8UeKb0Zs/Htlcf9ctNgY/kHqvo3ifx7e3OqxS+K4UFlftapjSIvmURxtk/N1+c/kKfe6RpV7lrvTLOZv7zQru/PGa5zwxo0Ju9fFreahYiLVpI0FvckKFEUR5Vsg9Tyeal4HC3Wn9feOOaYzlb5/y/wAjsv7Y8cf9DfH/AOCiL/4qj+2PHH/Q3x/+CiL/AOKrGNprtuC0OuQTqBnF5aDp7tGV/lWB4b8f2eu309jpM2kazcW67pE06/w20HBZVlVdy57qxHvTeAwydtPv/wAxLNMa02pOy8v+Adx/bHjj/ob4/wDwURf/ABVZ+neJvHlzq+rWT+LIVSykhRCNIiy2+IOc/N6nFVjr9vF/x/WGqWPqZbRmX/vpNwqh4a1PTrnxJ4geC/tnEs1sY/3gBbFuoOAeTg8UpZdSTXuDhm2Jal+86eXdHT/2v44/6G+P/wAFEP8A8VSS6r42ljMcvi2J0PBVtHhIP4bqXBxnBxWTpfiTQdU1m90fTdXtLy/sFDXcML7zDk4G4jjOeMZyO9J4PDroCzPGyTtN/cv8iC60W+uXMkl/payk582HQoYpM/7yMD+tbXwxsPEl14h1zTZfHGtbLK2tJrbCxsqmUzBgVkD5H7tccjvTq1/hL/yPXif/AK8NO/8AQrmscdFUqN4/5/mdeVVp18TyzfR+X4qzOl+yeO7MYg1fRNUX0urN7d/++o2Yf+O0DXvE1qf+Jj4NnlQdZNNvYpx/3y+xv0rqaK8X2yfxRT/D8rH1HsGvhk1+P53OXHjzQYcDU/7Q0lj2v7GWEf8AfZXb+tbOl61o+qDOm6pY3o/6YXCyfyNX8CsbVPCnhrU2L32hadPIf+WjW6h/++gM/rRei+jX4/5fmFq0eqf4f5/kbOaK5f8A4Qmyt8f2Vq+u6WB0WDUHdB/wCXev6Uh0zxnZ5Np4nsr8dk1DTgD/AN9xMv8A6DR7OD2n99/+CHtai+KH3NP/AC/I6miuWGq+MrQgXnha1vlHV9O1EZP/AACVU/8AQqP+E30+DP8Aaul65pWOrXOnyMn/AH3HuX9aPq83tr6NP8g+s0/taeqa/M6misfS/FHhzVCF0/XNOuXP/LNLhd//AHznP6VsZrOUJRdpKxrGcZq8XcKKKKkoKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooA8K8Of8geP/rrN/6OeoPGWinxB4cutKWcW8kmx4pSuQjowZSR3GRzTdBv7CLS0jlv7SN1lnDK86KQfOfqCav/ANp6Z/0ErH/wJT/GvsI7I/Oa38SXqzG8P6Rq3/CR3fiHXXsRdy2iWcUVmXZERWLMxLAElmPTHFdHVX+09M/6CVj/AOBKf40h1PTP+glY/wDgSn+NMyIPDv8Ax7Xn/YRuv/RprP8AGuhXfiBtKshJCmmRXi3F+rE75VTlUUYwQT1z7VN4f1HTlt7zdqFkM6hckZuEGQZDg9a0v7T0z/oJWP8A4Ep/jQBg+OtI13XLK60qzXRRY3kQieW5RzNBz8xUAYb25GK6HTrVbHTrayR3dLeFIlZ/vMFUDJ9+KZ/aemf9BKx/8CU/xpP7T0z/AKCVj/4Ep/jQBX0P/j81n/sIH/0TFWR4w0DUtS1qx1K0j0u+ht4JImsNS3+TuY/60bQfmA45HQ8Vd0XUdOW81gtqFmN1+SM3CDI8qLnrWn/aemf9BKx/8CU/xoA4vSfCGv6C1he6Tf2F1fQ2UllOl2ZFiCNIZE8sjLAITgA9RXU+ENGXQPDdlpAm85oEPmSYxvdmLMQOwyTxVv8AtPTP+glY/wDgSn+NH9p6Z/0ErH/wJT/GmB2Hwl/4/wDxD/13t/8A0QtZfxr8B+JPFHiLw5reiL4f1WDSPPE2ia/5n2KdpAAs3yBsumCBuUj5jjBp/wAMNe0Kzv8AXvtWtabBvngK+ZdxruHkqOMnmu3/AOEr8L/9DHo//gdF/wDFV8vjf48j73Lf90p+h4t4Y+DvjzwX/wAI74g8N6r4fvNe06O+tp7C8aeOwS2uZRKsMDAM6LEwGARzk9K9Q+DPgybwJ4BtNCvL1L6/Ms11e3EalUknmkaRyoPRQWwPYVs/8JX4X/6GPR//AAOi/wDiqP8AhK/C/wD0Mej/APgdF/8AFVyncZ2m/wDJVtc/7Aun/wDo67rC+OfgnX/GNpoT6HNpU/8AZWoC7n0rV9/2LUAFICy7AT8pO4ZBGRyKn07xN4cHxQ1qY+INJEbaPYKr/bY8Eia6yM7uoyPzrp/+Er8L/wDQx6P/AOB0X/xVAHiOjfBXxpon9m+J9Lv/AA5b+ItN1661O10iMzLpMENzCIpbeM4LpnG/cFxk8KK9M+DPgzUfCOj6vPrt3a3Wua9q8+rai1qGECSS4Ajj3YJVVVRkgE8mui/4Svwv/wBDHo//AIHRf/FUf8JX4X/6GPR//A6L/wCKoAyJP+Sywf8AYvS/+lMddhXCWOp6bqXxiifTtQtLxU8PyBjBOsm3/SU67ScV3dABXhul/wDH1rf/AGHdR/8ASl69yrw3S/8Aj61v/sO6j/6UvXpZV/Gfp/keHn/+7L1/RlTxHdeJLaW0Gg6Lp+oxux+0tdX5tzEMjBUbG3cZ9Og9a868Q634R0/9oTw8ItT0e1nWz1CK/wBroj/aZNgRZMc+Y2ABnk167ULWdm0plaztmkJyXMKls+ucZzXs1aTns+q/A+Yo1o073XRrTz77kzDGQeorC8J/8fviT/sNSf8AomGt09DWF4T/AOP3xJ/2GpP/AETDWkt0ZR+GX9dQ+ItvfXfw/wDEVrpiyNfTaXcx26x/eLmNgAPc15d4M1HSte8X/C2Pw5PFO2i6DcLqqQnBtFMCRiKQD7rGQH5T7mvbqbHFFGztHFGjOcuVQAsfU46n61nUo88lK/8AV7m9HEKnTcbd/wAVYeCR0OPpXOafZWV74k8SLeWdvcgTWuBLEHx/oy+oroqxND/5GfxL/wBdrX/0mWtJNpqxhBXjL0/VEq+HNMjYGyF1YPng2l1JHz/u5x+leVeDtR8PwfGnWNL8NeJdHRpdLtooG2xyfaJBI7PCFTaCynLEgbuTnNe11ClnaRyCSO0tkkByHWFQwP1AzTqOcmnfburjpShCMk1uujsZ/neI4f8AWWOm3q+sFw0LH8HBH61o/DTxCNO8ZeIZtQ0bV4hJZWKt5Nsbny9rXHzN5W7AOeDjselS1rfCX/kevE//AF4ad/6Fc1y5jOPsPej1PQyWMvrS5X0Z11l428KXcnlR69Yxy/8APKeTyZP++Xwf0reikSVA8bq6nkMpyD+NRX1jZX0XlXtpb3Mf9yaMOPyIrBk8B+F/MMtppp06U/x6fPJakf8AftgP0r5/9y+6+5/5H2H79dn96/zOmozXKv4X1i3QrpfjXWIQeNt2kV0o/FlDf+PV4Vo2j6w1m93Nf3esObm4WUSapdW8jFJ5EJVlk2c7c4IGM4zXRQwXt21Ca/H/ACt+Jy4rMfqsVKpB2+X+d/wPp/NGa+b4V0Hzlt76TW9MuG4Ed5qt2gY/7L+bsb8DWt/wj+n8fvdW5/6i93/8drd5RWju0cK4hw72i/w/zPes0nFeCnw/p+P9dq3/AIN7v/47WR4W0e2ubfUWnutXkMeq3cKZ1e74RZSFH+t7CoeV1E7XRaz6g03yv8P8z6B1TQ9F1XP9paTY3uf+e9urn8yKx/8AhBdDhydMk1PSW/6cb+WJf++MlP0ry7/hH9P/AOeurf8Ag3u//jtH/CP6f/z11b/wb3f/AMdraOAxMVZT/FmEs5wcnd03f0X+Z6j/AGH4otD/AMS/xjJOg6R6lYRzZ9t0flt/Oj7Z46tBmfRNH1RfWzvXgf8A74kUj/x6vLv+Ef0//ntq3/g3u/8A47WR4f0e1n1HX45rrV3W31LyogdXu/kTyIWwP3vqzH8abwVXRS5X8rflYFm+Hs3HmVvO/wCbZ7SPGDQNt1Twz4isSPvOLP7Sg/4FCX4/CrVh4x8MXsnlQ63ZrL08qZ/Kk/75fB/SvIx4f08HIm1YH/sMXf8A8dqC+8J6HfxmO+hvbtD1WfUrmQfk0hp/2ZffT0f+a/Un+3Yra79Uv0f6Hv6OrqGUgg9COQadXzta+BvDdmhWwtr6xB/59dUuov8A0GStz4XR6/oWreIzo817rVhbzWxmsLy8eWchodxaGSRjhh/cOA3qD15q2XSpK/MjtwucQxEuRQff+up7bRWd4f1vTtdsftWnT71ViksbKUkhcdUdDyjD0NaNefKLi7Pc9aMlJXi9AooopFBRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAeB6BZWUmlo8llau7Szks0Kkn98/UkVe/s/T/wDoH2f/AIDp/hUHhz/kDx/9dZv/AEc9R+LNZj0Dw/daq8JnMIURxA4MjswVVz2ySOa+wjsj84rfxJerLf8AZ+n/APQPs/8AwHT/AAo/s/T/APoH2f8A4Dp/hWNoGt6lL4guvD+uWVrbX8Vsl2jWsrPFJGzbSPmAIYNwe1dFTMzE8PWNi1vebrG0ONQuQMwIePMPtWl/Z+n/APQPs/8AwHT/AAqt4d/49rz/ALCN1/6NNZ3jXVdc0WxudUs4dHbT7W3MspupZVkLDsoUYOeAOepoA2v7P0//AKB9n/4Dp/hR/Z+n/wDQPs//AAHT/CuKfxlrh1HTdNNtoFhdXWlx30gv7t41DO5URrjqcYOPrXfDO0bsZxzj1oAxNEsbE3msA2NocagQMwJwPKi9q0v7P0//AKB9n/4Dp/hVXQ/+PzWf+wgf/RMVZvjDxFdaRqOn6dZw2CzXiSyfaNQnMVugjGSu4Dlznge1AG5/Z+n/APQPs/8AwHT/AAo/s/T/APoH2f8A4Dp/hXJWXi/WNWj0u20nRrZdRurBr+eO8mdEijD7FAIGSXPI9sV0XhTWYvEHh6z1eKFoRcId0THJRgSrLnvgg80AdX8MNE0a7v8AX/tOkafNsngC77VDtHkqeMiu4/4Rjw3/ANADSv8AwDj/APia5b4S/wDH/wCIf+u9v/6IWqvxo+IWp+DtS8NaLpFppC3mvzzRJf6zdtbWFt5SbyJHUE736KvfB9K+Yxv8eR97lv8AulP0Oz/4Rjw3/wBADSv/AADj/wDiaP8AhGPDf/QA0r/wDj/+JryLQ/jH4t8U6d4T0zw14Y0qPxNrlrd3sy6hdypZw21vJ5YmVlQu6ytjYcdDk5HNeifB/wAajx94FtfEL6e2nXRlltru0Z9/kzxSGORQ2BuGVyD6EVyncUdO8O6AfijrcJ0PTDGuj2DBfskeATNd5OMew/Kun/4Rjw3/ANADSv8AwDj/APiay9N/5Ktrn/YF0/8A9HXdZfxr8d3ngXRNLl0+ysprvVdTi06K41CcwWVozgnzJ5ACVT5ccDkkUAdR/wAIx4b/AOgBpX/gHH/8TR/wjHhv/oAaV/4Bx/8AxNePaV8aPFGq6RpOl2Hh3SJPFWra/eaRZP8AbJDpk8dqm+W7jkCb3iA+UYHLA88V6B8HvG91400fVV1XTY9N1rRNUm0nUreGUyRedFg7o2IBKMrAjIyOhoAZZ6dp+nfGKJbCxtbRX8PyFhBCqbv9JTrgCuttdX0q61GfTrXU7Ke9t+ZreOdWkj7fMoOR1HUd65yT/kssH/YvS/8ApTHXy/8AtcXD/Dr46WHjH4e3bx+JtS0e5OsWVvGSBCIyv2h8dOAW56GENQB9iaZqumaoJjpuo2d75D+XL9nnWTy2/uttJwfY14HFD4lfVdeaw1HR4bY67qGxJ7GWRx/pL5yyyqDz7V037HWh+HtH+A2h3OgzrdvqiG81C5x88lyTtkVv9wrs/wCA571n6X/x9a3/ANh3Uf8A0pevRyxXqv0/yPFz2XLh16/ozP8As/jH/oL+H/8AwWzf/HqPs/jH/oL+H/8AwWzf/Hq3apNrGkLqy6Q2raeuosu5bQ3KCYj12Z3fpXuuKW7/ABPk1OT2X4Gcbfxjj/kL+H//AAWzf/HqxfC8Hiw3niHy9V0NSNYkD7tOlOW8mHkfvuBjHHPeu4PSsLwn/wAfviT/ALDUn/omGplBcy1LjVfLLRfcu4fZ/GP/AEF/D/8A4LZv/j1H2fxj/wBBfw//AOC2b/49W9VHTtY0jUp7iDTdVsL2W2bbPHb3KSNEemGCklfxquVLr+JCnJq6X4Gf9n8Y/wDQX8P/APgtm/8Aj1Y2jQeLT4j8QhNV0IOJrbeTp0pB/wBHXGB53HH1rtqxND/5GfxL/wBdrX/0mWplBXX9dC4VHyy0W3Zd0N+z+Mf+gv4f/wDBbN/8eo+z+Mf+gv4f/wDBbN/8erdqja6xpF3qM2m2urafcX0H+utorlHlj/3kByPxFVypdfxIU5PZfgUPs/jH/oL+H/8AwWzf/Hq6j4IJqaeNPFI1W5s7iX7Fp21raBolC7rnghmY5981UrX+Ev8AyPXif/rw07/0K5rhzKNqHzR6uSzbxSXkz06iiivnz7EDXg3hf/kFP/1/Xv8A6VTV7ya8G8L/APIKf/r+vf8A0qmr1Mq/iv0PB4g/gR9f0ZJ4m1HTNJ8PX+p6yUGnWkDTXG9N42gc/L3PYD1NcZ4S1uy1TWJNI02113wlqYtFv4rC/RHint2OBIqBmAGcAgFSM1r/ABh0G+8T/DLXtC0xVa9urYeQjEAO6urhcngZ24yfWsPwqureIvijb+K7jw9quiWOn6AdPK6jCIpJriSUO4RcnKKB97vmvXlWqQqKMdv6v9x87To0pUXKW+vXba336nYHUNVsgRqelmeMdbjT8yD6mM/OPw3VV8BXVtdWepm3mSQnV7yTaDhgrSkqSp5GR6iuiPSuV8PaTp2oQanLdWwaddavtk6MUlX98ejrhh+dbtxcldWOaKag7eR0Oq39ppel3Wp38whtLSF555D0RFBJP5CuZ8I+PrHxBq0OlS6Pq+j3V3Zfb7FdQiRRd2+R86FWbBGQSrYODUfj3w1r2r+CtZ0Gx1WO7S/s3gUXqfvEz0xIuA3T+IfjXOabNc3XxE8KarqunXeh2uj6HPaSSX8flCW5k2JsUnjACltxxmsqiqc65NV/V/uN6KpOm3PfX8tPveh6tWH4Y/5Cvib/ALC3/ttBW4CGUMpBVhkEHIP0rD8Mf8hXxN/2Fv8A22gqpboyh8Mv66oTxXr99onlG18LaxrcbRs8kli0IWEL/e8x17c8elcrp/xZtdTstAm0rwj4iv59diuZrS1iWESCOBtrsdzgYPUYPStH42Lrt14En0Xw5ZXNxf6xKlgZYoyy20Tn95K5H3VC5GfesD4m+F9DttC0zSofBviXVZtN0t7TSLvR2YfZ3I2gOVdSuSqsWIK9a5q06ik+V6I7cPToyhHnWrb6+XXVdfyZ6hZTSXFnBPLbS2skkau0EuN8RIyVbBIyOhwSK6D4O/8AIxeLP+utn/6TiuH+Htrrll4H0a08SXH2jWIrRFvJC+4l/dv4iBgE9yCa7j4O/wDIx+LP+utn/wCk4rnzF3w6fodeSpRxjS7P8zqfEHhpbu9/tjSLttL1tVCi6RdyzKOkcydJE/Jh/CRTNC8StJqC6Jr1qNL1nBKR790N0B1eB+N47lThl7jvXSVQ13R9O1vT2sdTtlnhJDDJIZGHRlYcqw7MCCK8eNRNctTbv1X/AAPL8j6iVJxfNT0fbo/+D5/fcv0Vxo1HV/CB8vXpJtU0McJqgTM1sPS4UD5l/wCmqj/eA+9XW2txBdQJcW00c0Mg3JJGwZWHqCODUzpuGu67lU6qnps10JaKKKzNQooooAK8V+JOveLPEvxx074U+GfEc/hmzi0VtZ1TULaFHuZFMnlpDGXBC84JOM8+3PtVeYfEv4aazq/j3TPiD4K8Sw6B4lsrN7CU3Nn9ot7u2Zt3luoIIIYkgg+npQBwWn/E7xL8Mdb+IXhzxhqVx4wt/DWmW+r6fdukcFzJDKyoYpCo2khnGGxng+oA73xd8VJdN1tfD2leHri/1O58Ky6/bAXCIDtIURHdxnnOc44x3rDh+Bk2peHPG/8Awl3iltV8TeMLZLa51KK0EUVrHHjyo4otx+VSFJyctgdOtO8G/CDxTb+NbLxR4w8a2+szW/h6XQhBbacLdUiYrtZTuJLcMWJ6kjGAKAMPwT8eNetfgx4a8XeMfCF/dXGr6lDptu9jJDm+aTzcSRxA/LgxhNjYJJz0rWuv2gY9M8OeLrrxB4K1PSda8LT2cd7pUl1E7NHdOqxyLKuVI+bJxntzzXDePPhd468M/CnwP4Kt9bOr/wBneNLE6bd2GktvsIB5x86VcsG2s4JJwoxgnmuvvfgLqviDw549/wCEt8YRXniPxcbQG9tbHyobVbVg0KrGWJIyo3c9PzIB0PxQ+K17oOo+K/DehaBPe6xpHhY65FL5yBMGQxnKtjOz75GeQpAGSK2fgD4s8ReNPhhpOveJdFfTby4t42EhkjZbxTGreeioTsViThWwRiuW0D4P+JZvE+v+IfGfjSDV7vXfDD6DMLbThbrArNwyfMcgDJ55LE9BgV2XwU8K+IPBXgKy8Ma/rdnq505Vt7OW2tDAFt0UKisCx3NwSTx19skA7aiiigAooooA8K8Of8geP/rrN/6OeqvjjRpdf8MXWmQTJDO5SSF3GVDo4Zd3sSMGrXh3jR488fvZv/Rz1oZX+8v519hHZH5zW/iS9Wc1oGmavL4pu/EmtwWlrO9mlnDb285lAUMXZi2B1J4HYV0tGR6j86CRjqPzqjIzfDv/AB7Xn/YRuv8A0aazfHWi33iBdL02Pyhpn2xZtRLSYZo05VAMc5PX6CtHw6R9nvOR/wAhG67/APTU1p5HqPzoA5H4g6Lquu2lzptppGiTQ3UIiW8uJCJbbnkhdpzjqMEe9dNptt9i022szK83kQpF5j9X2qBk/XFWMj1H50ZHqPzoAzND/wCPzWf+wgf/AETFWJ440HUdU1ewu47Cw1jT4IZEk029uGij8xukuQCCQMjnpnitrQyPtms8j/kIHv8A9Moq1Mj1H50Aef6R4Y8UaDLp+pWcllqd7Hp8ljPDPcsiopkLx7HKksEztweSBXUeC9GbQPDFjpMkqzSwITK6jCs7MWbHtknFbGR6j86Mj1H50AdN8Jf+P/xD/wBd7f8A9ELWJ8ePBPiTxTrXhzULDS9J8TaNppmN54e1O8a2guZXUCOYkKyuU+bCuCBuyOa2/hKR9u8Q/wDXe3/9ELXfbl9R+dfL47+PI++y3/dKfofO/hP4W/EfwPL4Z8TaT/Y+s6pptvfWEujz6jIkFvZzyiSGGG4ZGYiIgD5l5HAxivUvgf4OvfA3w8tNF1S5hudTknnvL6SDPledNK0jBM87RuwPXGe9dtuHqPzo3D1H51ynactpv/JVtc/7Aun/APo67rnPj94P8ReLtN0RNGgsNUsrDUBc6lod/cvbwapGFO1HdVbhWw21gVJAz0xXR6aR/wALW1zkf8gXT/8A0dd11O4eo/OgD5x0D4RePNA/sXxTpsGjJqGi67d3+n+GRqEhsrWzuYRHJbxzshKtuy/C7QScCvUPgl4Q1fwvpOuXviFrX+2fEOtXGr3kVq5eG3aTaFiViBu2qq5bAyc1324eo/OjcPUfnQByEn/JZYP+xel/9KY6o6X8JfCln8QNf8cXX27VdW1yBrW4N/KskcUDDBiiUKNqFQFwSeBjuc3pOfjJBj/oXpf/AEpjrsKAOH+EHwx0D4W6LeaN4bvNVlsLq5Nz5N7cCVYWIwdmFGAcDPXpXC6X/wAfWt/9h3Uf/Sl69yrw3S/+PrW/+w7qP/pS9ellX8Z+n+R4ef8A+7L1/RlTxHqup6bLaJp/hjUNaWZiJXtZ4YxbgEct5jAnOT0z0Nea+OtP8OeK/iLZaFpFrpVnLpGrR6nrusfu4pBKBlbdHOGklfA3dQoA78V7FXPXfgbwVd38l/deEdCnu5ZDLJPJYxs7OTksWIyTnnNexWpSnoj5vDV40ne1n5frqdExyWJ6nJrB8J/8fviT/sNSf+iYa3T3rC8J/wDH74k/7DUn/omGtZbo54/DL+uonxHkvovh74jk0wyC9XSrk25j+8H8psY968s8GQ6JH4v+E7eF0sldvD1ydRNoFDND5EeDLjknzc/e5zXuNZukeH9B0e5uLnSdE03T57o5uJLa1SNpTnPzFQM881lVouc1L+t7nRQxKp05Ra3v+Ktr6bmlWJof/Iz+Jf8Artaf+ky1t1iaH/yM/iX/AK7Wv/pMtay3X9dDCHwy9P1RuDORjrnivG9EsPDfiP4t6Xq/hq00nS9I8MvcQ/aYPLik1O7fIZEUcvGhJJc/eYkDNex1z9j4H8F2F/Ff2PhLQra7hcPFPFYxrIjDoQwGQazq03Nq3Q1w9aNJSve7VjoK1/hL/wAj14n/AOvDTv8A0K5rIrX+Ev8AyPXif/rw07/0K5rmzP8AgfNHdkf+9r0Z6dRRRXzp9oBrwbwuR/ZT8/8AL9e/+lU1e8mvnDQdCjuLOec6vrsRe/vTsh1J0Rf9Kl6KOgr08rbVR27Hh58k6Ebvr+jOqyPUUZHqKxf+Ecj/AOg54k/8GslH/COR/wDQc8Sf+DWSvbvLsfKcsO/4GySMdRWH4MI+y6rz/wAxq+/9HGnHw5Hj/kOeJP8AwayVjeEfD8b22pn+2fEK7dYvV+TVJBnEp5PqfU1LcuZaGkYw5Hr26HaZHqKa4R42jcKyMMMrAEEe4rH/AOEcj/6DniT/AMGslH/COR/9BzxJ/wCDWSr5pdjPlh3/AAHNoVvAxk0i6n0pzyVgIMLH3ibK/lisbw7ealY6l4g+02DX6f2n++ns8ZDfZ4ekROSMbehJznitf/hHI/8AoOeJP/BrJWL4b8PxvqfiMf2z4hGzVduV1SQFv9HgOT6nnr6AUOrO65lcqNOHLK0v6udPpuq6dqRZbO7jlkX78R+WRPqhww/Krpx3xXN3vgzTL2SOS81DXbh4yCjPqchZfoev61Bf+GNUW4NxYeJdYkjwP9Fnv5EX/gLpyPxBq91pp/Xcysk9WdXkeorb+Dv/ACMXiz/rrZ/+k4rzIR2tuQmsaj4r0ticeZLqsjwH6Sr8v/fWK9C+A9vFbav4rWG9uryNprNlluLkzsc246Me1ebmimqPvLqe1kXJ9Z0fR/oeq0UUV8+fYAQCMEZrkLnwFp8Fw954bvbzw5duSzGxf9y7f7cLZQ/gAfeuvoq4VJQ+FkyhGW6OMGq+NdC41jRYtetF63ek/JMB6tA55P8AuMfpWv4e8W6BrztDp+oRm6T/AFlrKDFPH/vRthh+VblZHiHwzoWvoo1bTLe5dPuSkbZY/dXGGX8DWnPTn8St5r/L/KxHLOPwu/r/AJ/8Oa9FcZ/YHizRPm8O+If7Rtl6WOs5kwPRZ1+cf8CDU6Px3DYOsHizSb3w9ITgTzDzbRj7TplR/wAC20ewcvgd/wA/u/yD2qXxaf13OxoqGzura8t0uLSeKeFxlZInDKw9iODU1YGoUUUUAFFFFABRRRQAUUUUAFFFFAHkHgn4X+CfEXhSDU9S0ZTfzT3Je5imeN2P2iQZODg9O4rVPwl0y2OdOuLNlH8Go6Tb3I/MKjfrW78Iv+RCsv8Artc/+lMtW/iR4u03wJ4K1LxTqqTS21jGD5UIBkmdmCpGoPVmZlA+tdEcVVirc336/mc8sLSk7218tPyOU/4Qqe0JMngbwPqqD/nhGbVz/wABdXH/AI9QdO8LWwxqvwnltPV4dOhukH4xEt/47V34efES81/xXqHhDxJ4WuPDHiGzs478Wkl3HcpNbOxUSK6Y5DDawI4OOTXoB6U/rN/iX4tfrb8BfVmvhl99n+l/xPGPh4nwsubbUob+08PxXH9s3wjjvbdYXCee2xQJACMDAx26V38HgnwJcRiWDwzocsZ6MlrGwP4gVW+Htrb3ej6zDdQRTxnXtSykqBgf9Jfsa4n4v7fBiXmtab8Lba70iysjd3WqWeuppjRbdxZdigMxAAII6lsUe0g+rX4/5A4VF0T/AA/zPQ/+EC8Ff9Cro3/gGn+FIfAXgrH/ACKujf8AgGn+FeI/8LM19dNhuPC+meLrq4g0KLXdatJtRtrhdOtpQzIv75N8shRS4QFTjHOeK9Y8Mav4t1jw5puv6Rd6BrWnahax3Vu0kUtnKyOoYZwZFB56Y60Wb+Gp+a/4H4hz2+KH5P8A4P4FDwT4L8JXGqeLEn8N6TIsGtmOINaoQifZbc7RxwMsTj3NdN/wgXgr/oVdG/8AANP8K5XwT4h1Wy1Txab/AMJam27XCXaxkjuVRvstuMY3K54APC96i8dfFq50OWAaP4YGoIYnkuTqeoDSjAV6DE8eHyMnIPalyVrXV36O/wCQ/a0b2enrp+Z1/wDwgXgr/oVdG/8AANP8KP8AhAvBX/Qq6N/4Bp/hXlmkfH7Vdc07wk+g/D03moeJra8uobOTW4ofJjt3C5Z2THzA5AOD9a9u0ua6uNNtZ76zFldyQo89t5ok8lyAWTcOGwcjI64rLnn3ZryR7Hlln8MvAeueNvFNvqPhiwdLZ7RYREpi8sGAEgFCMZPP1q6fgp4Vtx/xKwsGOiXVpBdp/wCRE3f+PV0XhT/kf/GP/XWz/wDScVS+J/xAl8JatoGgaVoE2va9r8ky2FmLpLWMrCgeRmlfgYBGBgkmqVaa6/fr+ZMqEJO9vu0/Ix2+G32Vvk8K+AtVQf3tOazc/iPMX9BR/wAI74dtR/xM/g3bKB/HYwW90v5Aq/8A47Wbp3xxfXdG8N/8Iv4LvdV8Qa4t240pr6KFbdLWTy5Xec5Urv8AlUgfN7V33wx8Zad498G2fiTToLi2SZpIpba4AEtvLG5SSNscZDA89xg0/ap/FFfl+Wn4E+xkvhm/z/PX8TzTTrX4TD4j6rFqGgaTpsJ0qy8uLUdM+zBZPNud3EigdNvPfHtXfWHgn4Z6hF5th4b8NXcf96G3icfmM1YsFV/inrqOoZToun5BGQf313XMfGSfwj4Us9LlPgq21bWNY1GPTtOgtmSzaWdwWG6fjYMKeeT2Ao/cvuvx/wAg/fLaz+9f5nUf8K58A/8AQn6H/wCASf4Uf8K48Bf9Cdof/gEn+FeO2XxCL6TbRaDY+LbXxXca9c6FFoK61FcRfaLdBJM3nTK6GJVIywHU4x3rtvhd4r8YeLdFvbq1ubBb3Tb+XTtS07VLQxzW1xFjcvmwsVYEEEMEGQelHs4P4ZL53X/A/EPazXxQfys/8n+Bp6L4f0PQfjCiaLpFlpyy+H5DILaFY9+LlMZx1616HXlz6v4itfixDLqHhZ5pF0GQFdNvEmyv2hPmAk8s/hya6j/hO9EhAGpxanpDf9P1hLGv/fe0p+tHsKj2V/TX8g+sU18Tt66fmdTXzvFJ4mGq68NPtdEktv7d1DY1xczLIf8ASXzkKhHX3r3fS9d0XVR/xLdWsLzjpBcK5/IGvHtL/wCPrW/+w7qP/pS9duWwarNPTQ8rO6kXhk1rr+jM/wA3xn/z4+Gv/Ay4/wDjdHm+M/8Anx8Nf+Blx/8AG63aCQCASAT0Gete5y+Z8pzr+VGEZfGeP+PHw1/4GXH/AMbrE8LyeLvtviHy7Lw8T/bEm/ddzjDeTD0xH0xjr713B6VheE/+P3xJ/wBhqT/0TDUSh7y1NI1Fyy0Qeb4z/wCfHw1/4GXH/wAbo83xn/z4+Gv/AAMuP/jdbtAIJIBBwcHB6H0PpV8vmZ86/lRheb4z/wCfHw1/4GXH/wAbrG0WTxd/wkfiHZZeHi/nW3mA3c+Afs64x+79PWu2rE0P/kZ/Ev8A12tf/SZaiUNVqaQmuWWi2/VDfN8Z/wDPj4a/8DLj/wCN0eb4z/58fDX/AIGXH/xut2jI3bcjOM4zzir5fMz51/KjC83xn/z4+Gv/AAMuP/jddR8EG1RvGfin+1YrGKb7Fp20Wkruu3dc9S6g5qpWt8Jf+R68T/8AXhp3/oVzXBmMbUN+p62Szvilp0Z33ieTVYfDmoy6GLI6oltI1n9sYrB5u07PMI5C5xnHavExr37S3/PP4Rf+Blx/8VXt/iDSbDXtDvtF1WD7RYX9u9tcxbiu+N1KsMggjIJ5FeT/APDLvwP/AOhM/wDKjc//AByvnz7E9R8JS6xP4Y02bxCLAas9uhvPsLFrfzcfN5ZPJXPTNeN+F/8AkFP/ANf17/6VTV7R4b0XTfDnh+x0LR7f7Np9hAlvbRb2bYijAGWJJ+pNeL+F/wDkFP8A9f17/wClU1eplX8V+h4PEH8CPr+jLWsajZaRpN3quozrb2dpC008pBIRFGScDk/SsLwj440jxJqMumw2uq6dfpbJdra6laGCSW3Y4WZBk7kJ49R6VX+NGi6h4i+FniDRtKiM17cWo8mIHBkKur7R7kKQPesLwrNc+J/ivbeKLfR9U0/TtO8PGwka/s3t2e4klDGNVYAsEA5YcV6s6klUUVt/X5Hz1KjCVGU3vr8trfeemHpWH4M/49dV/wCw1ff+jjW4elYfgz/j11X/ALDV9/6ONbP4kc8fgl8jV1C7ttPsLi/vZlgtbaJpppG6IiglifoAa5vwj4+0XxJqS6db2urWFzLai9tU1CzMH2q3zjzYuTuXkeh56VY+KGk3uu/DnxDo2nIHvLzT5YoEJxufGQue2cY/GuM8JyXniX4heF9Vi0PVtNttA0Ca2vWv7NoP9IkVE8lNwG/G0ksMjFY1Kko1FFf1/wAMdFGjCVKUpbq/y00+96Hq1Yfhj/kK+Jv+wt/7bQVuVh+GP+Qr4m/7C3/ttBW0t0c8Phl/XVEXi3xfp3hy6s7GWz1TUtQvVd7ey020M8zIg+d8ZACjI5JrKl+J/hs6ZpV7p0Gr6u2q28l1b22n2RlnWGM7ZHdcjaFYFTz1HGa5v43WU154t8PvdweIbHSre1uCdX0C1ea9jmb5RB8mSsbL8x4OSAOOTWB4FXXfB+q+H/EniDwvqEdkfDUmkrFp+nM8sTx3Jki82FMlGkTBPbcTnvXHOvUVRx6enoejSwlKVGM3q+1999Py/pntegatp2v6HaaxpVwtzYXsQkik2kblPqDyDnIIPcGr3wz8OxXPiDxO2mX95os8MtqY2sXCocwZO6Igo+TzyM+hFcZ8EtE1Dw98L9G0vVYDb3qrLNNCesRlleQIfcBgD716d8Hf+Rj8Wf8AXWz/APScVGNqzWHUtm7XNsqo03jZQ3Svb7zeF94x0bjUdMg1+1XrcadiG4A9Whc7W/4C/wCFaWh+KdD1idrW1vQl6v37O4Uw3CfWNwG/HGK2qztc0PSNbgEOradb3aryhkTLIfVW6qfcEV4vPTl8St5r/L/Kx9R7OpD4JX8n/nv99zRorlDoHiDSfm8O+IHmhHSy1bM6fRZR+8X8S/0qEyfEe+JCW/hzRkzjc8kt2/1AARfzNP2Keqkrfd+H+VylVe0otP8Arr/nY7Gobu6trSIzXVxFBGOryuFA/E1yv/CJa3ec6z451mYf887BI7NPzUFv/HqltPh54QhlE82jx384582/ke6Yn1/eE0clJbyv6L/OxXNN7L7/APgXJpfiB4GikaOXxjoEbqcFW1CIH9WqOTx/8P5I2jk8ZeG2RhhlOowkEe43V4j8TreC2+KGuQW0EUMSRWYVI0CqP3R6AVg4HoPyr1KGUKtTVRTtfy/4J5VfNXRqOm43t5/8A9gu5vhbHcPe+H/H2keHLxjuL6dqsKxOf9uEkxt+QPvUa/FKLQ+NT1/wr4jtF63OmalDFcgerQO+G/4A34V5HgegowPQflXZ/ZLek583qv1vc5v7WS1jC3z/AOAfQujfE/wFqlkl1B4o02FWAOy5mELjP+y2PzHFXf8AhPfBP/Q3aF/4Hx/4151+zd/yGfFX+7Y/+gy17RXz+KpKlWlCOyPcw9R1aUZvqc5/wnvgn/obtC/8D4/8aP8AhPfBP/Q3aF/4Hx/410dFYGxzf/CfeB923/hL9B3Yzj7fHnHr1pf+E98E/wDQ3aF/4Hx/41DF/wAlWuP+wHF/6USV1NAHOf8ACe+Cf+hu0L/wPj/xo/4T3wT/ANDdoX/gfH/jXR0UAZOjeJ/Dms3TWmka7pl/cKhkaK3ukkcKCAWwDnGSBn3FFUL7/kqGj/8AYGv/AP0daUUAV/hF/wAiFZf9drn/ANKZazf2g/CWq+NvhVqmhaGYTqZeC5tUmbakjwzJKEJ7btmM+prS+EX/ACIVl/12uf8A0plrrc0AeS/DrSfFOtfGTVPiR4i8Nz+Gof7Bg0a0sbm4illkImaaSQ+WzKFBIVecnk4r1o9KOKQnigDlfhl/yDdY/wCw/qX/AKUvXK/tFeG/Efjiw8PeCdLsJX0TU9Vik8QXiyKqw2cRDlCCwYl2AA25+7z1rqvhl/yDdY/7D+pf+lL11dAHg/jjwz428PePvG2p+FfCR1+x8YaDb6fB5F1FCLC4hjeJfNDsv7ra+7K5PGMCvVPhj4dk8JfDnw94ZmmWebS9NgtZJF6M6IAxHtnOPauk4pCeKAOV8A/8hfxl/wBh8/8ApJbVz37SOleKvEfw4fwn4TsZJp9duorG9uVdFWztGbM0p3EZ+UbcDJ+Y10PgHjV/GXX/AJD5/wDSS2rq6APCPjN8ONHPh6DQ9H+C1t4o8vSms7G+t7mC3ktJdu1N5dlbHCtvG45BGK6z4ZfD/wAQaB4A0PTtT8Z62utWtkkd1JHdC4hMg7BZlbIAwvGM4r0vijNXGpKLumZypRkrNHl/hq28ZWvjbxWtnqmk6g6y2fmG8tWhL/6OMfNGxA4/2TXI/HTw9418Yat4di134ftr3hbT5JZr/T9J1aJZppyuIZFd/LcKuWyqspOec4xXqPhT/kf/ABj/ANdbP/0nFdbx6fpTlU5lZpfl+Wgo0uV3Un+f56/ifIvg7/hMPh5qnhPxPqvhzVLw6XYX+jHSZQIri0snmWS1HnsFhlKhdrNu4BHBr2n9muwTRPhra6feappdxqtzdXN/dw2d2kywPPM0nlgqTnaGAJ9c16hxWPqnhfw5qhLahoenXEh/5aPbLvH/AALGR+dVek+jX4/5fmS1WWzT/D8dfyM7Tf8Akq2uf9gXT/8A0dd1yP7SvhrX/FOg6JYWGhv4g0OPU0n1zS7e4jgubqFRlBHI5AXD4JwysQMAjmrWn+D7KH4mazBpepazpSJpFi6/Zr1yMmW6GNsm4Y4HGMDn1NdL/ZXjK0ybPxTa3yjomo6cMn/gcTJ/6DR7OD2l99/0uDqVFvD7mv1seD+FPh78Q/DR8MeJ7TwxcvY+Gtev5dM8MvfwyXlvp13CEYecWCM4k3MFZyQD9416z8BfDWt6JpniTWPEVkNO1HxJr9zq7WPmrIbVHCqkbMpILbUBOCRk1vjU/GloALvwvZ36jq+n6gAT/wAAlVf/AEKlXxpZw5Gp6Nr+mBerT6c7oP8AgcW9f1o+rze2vo0w+s018WnqmivJ/wAllg/7F6X/ANKY67DFed2XiLQtR+L9tLZatZTKdAkXAmAIb7SnBB5B9q9EBBrOUZRdpKxrGcZq8Xcx9V8L+HNUJbUND065c/xvbrv/AO+sZH514jo2iWsEusRWVzfWax61foiw3LbQBcOBw2RX0N2rw3S/+PrW/wDsO6j/AOlL16mVVZ+1avpb/I8HP6UPq6dtbr8mYPiTV9S8PS2ka/2tqv2piq/Z9GNwI8EDMjRFdg56kdj6Vx2pabd6Z+0LoGpNZS3V5faXqDyeXevICqhAAiyYEarzhR6k5r1yuT1D4ceDL/xEfEN3o7SaoZhN5/2ycEPkHIAfaBwOAMH0r16ylO2ieqfb8j5vDyhTvdtXTXe9/XsbTazDGP8AS7PULT3ktmZf++kyKyvBmo2E994iEN7bsW1mRlHmAEjyYecHnsa6gk8nOCfSub8O2lrdXniQXVrBOP7ak/1kYb/ljD61rJxcloYQUlGWv9XJ/iJe3umeAPEOpaeWW8ttLuJrdgMkOsbFSPoefwry3wVpen+H/GHwxm8PRmI67odxJq7xuW+2AQJIJpOfmbzGPzfhXrb6Dpu1lhSa2DAgiCdlUg9QVztI9sVz3hj4daL4Vv5r/wANLHaXEqGMmeLztqE5KISRsXPOFwKyq0FOaknt39em500MV7KnKMo73263Vtb2236naViaH/yM/iX/AK7Wn/pMtWfN1yL79pY3Q9Ypmib8mBH61jaJqZi8SeI2utOv4czWudsXmhf9HXqUJrSUHdW/rQ54VFyyv2/VHWDgg+nrXmHgjRrfRfjv4sgtTeSebolncSyXM7zSO7yuSSzdugAGAAABXoFvrWlSuFTULdXz92Rtjfk2DWDo/wAOfBmma8niHTtIaPUVcyLcC8nfJOeoLlSOTwRgdqzrUp80XbZ9TbD14KM1fdW0/wCHOsrX+Ev/ACPXif8A68NO/wDQrmsitf4S/wDI9eJ/+vDTv/QrmuTM/wCB80ehkf8Ava9GenUUUV86faAa8G8L/wDIKf8A6/r3/wBKpq95NfN2haPfz2c80XijWLVGv70iKJLcon+lS8DdET+ZNenlbtUfoeHnyToRu7a/ozrKUnPU5rB/sLU/+hy13/v3a/8Axmj+wtT/AOhy13/v3a//ABmvc5n2PlOWP835/wCRunpWH4M/49dV/wCw1ff+jjSHQtTx/wAjjrv/AH7tf/jNYvhHRdRe21Mr4t1qPGsXqkKltyRKfmOYup/KocnzLQ0jGPI/e7d/8jt6Cc9TmsL+wtT/AOhy13/v3a//ABmj+wtT/wChy13/AL92v/xmr5n2M+SP8y/H/I3aw/DH/IV8Tf8AYW/9toKT+wtT/wChy13/AL92v/xmsXw3omotqfiIDxbrSFdUwSqW3zn7PAcnMXXnHGBwKmUndaGkIx5Ze9+fdeR3AODkHH0NIDjocfQ1hf2Fqf8A0OWu/wDfu1/+M0f2Fqf/AEOWu/8Afu1/+M1XM+xnyR/mX4/5G7W38Hf+Rj8Wf9dbP/0nFcP/AGFqf/Q5a7/37tf/AIzXXfAq1mtNa8WRT6hdX7+faHzbgIG/49xx8iqMfhXn5m26O3U9jI4pYnR30f6HqhIAya8lk/aR+CccrRv48tAysVI+yXB5Bx18uvWiMjFfFPjDw/o3wh/af0vSPDGlaT4o0zxZKrXfhy5s0nksd743RllOwDLMv+yrBhgBq8A+vPsPwr4g0jxT4fs9f0G9W90y8QvbzqjKHXJGcMARyD1FadV9NsbLTbGKx06zt7O1hG2KCCMRxoM9Aq8AfSrFABRRRQB82/Ff/kq2v/8AXKz/APRRry/U/EWu6b4z0rS7rTtObTtUunt7cwzu1yoVcmVlxt2+oHT1r1D4r/8AJVte/wCuVn/6KNeXQ+Gddi8bXHiI61p8yysI0jmsWaSC3ByYo234Unu2OT19K+swvP8AVafJf8O58vieT6zU5/17Faw8X6o/ii70i4t9GuUhsp7lm0+5eVrVo84jmJGAze2KtfDnxNe+JrRru5l0EoYY5BFYXTyTRM3O2VWHyke3fNRQeEtWk8UQ69f6tp32i0t54rY2mneUXaQY3TfMd+Ou3ofarfh3w3fWviW48RavfWVxeyWi2aJZWhgiWMNuyQSSzE/kK1pqvzrmva77bGdR0OR2tey77nun7Nv/ACGfFf8Au2P/AKDLXtFeL/s2/wDIZ8V/7tj/AOgy17RXzOP/AN5n6n0OB/3eHoFFFFch1nLRf8lWuP8AsBxf+lEldTXLRf8AJVrj/sBxf+lEldTQAUUUUAc1ff8AJUNH/wCwNf8A/o60oovv+SoaP/2Br/8A9HWlFAHK/DTwV4f1Hwfb3l1BetNLcXRYpqVygz9pl6KsgA/AV0n/AAr3wv8A8++of+Da7/8AjtN+EX/IhWX/AF2uf/SmWtHx94q0rwV4Q1HxPrTSCxsIt7iJdzuSQqoo7szEAD1NAFD/AIV74X/599Q/8G13/wDHaD8PfC+P+PfUP/Btd/8Ax2qHw++IsXibxBf+GtT8Pan4b1+yto7xrC/aJ2kt5DhZVaNmUjIwR1B4ruj0oA8u+Hngbw5c6fqrSwXxKa5qCDGp3Q4Fw4HSTrgde9dN/wAK98L/APPvqH/g2u//AI7R8Mv+QbrH/Yf1L/0petzxHrFh4f0C/wBd1WYQWOn20lzcSYztRFLMcdzgdKAMP/hXvhf/AJ99Q/8ABtd//HaD8PfC+P8Aj31D/wAG13/8drC+H3xYtfE/iK20HUPDWs+HL3UNO/tTS11DyiL21yAWUxu21hkEo2CAa9IPSgDy7wT4F8Nz6r4sWS3viIdcKJjU7ocfZbc84k5OSeTXTf8ACvfC/wDz76h/4Nrv/wCO0eAf+Qv4y/7D5/8ASS2rp7qeG1tpbm4kWOGJC8jscBVAySfoKAOY/wCFe+F/+ffUP/Btd/8Ax2j/AIV74X/599Q/8G13/wDHa5fwT8adL8Sa9othN4c1vSLLxGkz+H9QvBF5WoCIZbAVy0ZK/MocDIr1OgDy3w14H8OS+N/FcDwXxSKW0CY1O6B5tweSJMn8a6f/AIV74X/599Q/8G13/wDHab4U/wCR/wDGP/XWz/8AScV1jsqKWYhVAySTwKAOV/4V74X/AOffUP8AwbXf/wAdo/4V74X/AOffUP8AwbXf/wAdrlPC3xu0fXdc0i3Ph/WbHRdeuZrTRNauBF9nv5YywKhVcugba20so3Yr1agDy/T/AAJ4bb4mazbG3vvLTSLF1/4ml1nJlugefMyfujj/ABNdL/wr3wv/AM++of8Ag2u//jtLpv8AyVbXP+wLp/8A6Ou66qgDlP8AhXvhf/n31D/wbXf/AMdoHw+8MA5EGoj6atd//Ha5M/HDRh4gEDaBrK+HjrX9hDxBiL7Ib3O3Zt3+Zs3fL5m3bn869XoA8wh8GeGbf4tLanSo7qKbQJGdbyR7nJFymD+9LY69q6f/AIQTQYcnTDqGkse9hfSwqP8AgAbZ+lV5P+Sywf8AYvS/+lMddhWka1SCtGTMp0ac3eUUzljoPia1P/Eu8ZTyoOkepWUU4/76Ty2/WvN4fDPxK0+51Pf4e0XUkm1C5uklt9VMBkEsrP8AceM7fvdCx+te40VrDF1IO6tf0Rz1sBRrR5Z3t6s8AubnxzZyst98Ob+2Qf8ALYXyzp+cSMf0otdV1G5cRx2/h9ZTx5U2vrFJ/wB8vED+le/4qvfWNlfxeVe2lvdR/wByaMOPyIrq/tOb3/D/AIK/U4XklFbfjf8Az/Q8kj0XxzLGHj8M6c6EcMutqQf/ACFVDRvCXj+wuNUkfw3pri9v2ulA1kfKDHGuD+66/Ifzr0yTwH4X8wy2mnHTZT/Hp88lqR/37YD9KZ/wjOs2o/4lfjPVox/cvY4rpfzZQ/8A49R9dnLap96/yuCyqjFWdP7pf52OG/sLx5/0K9h/4Ol/+NUf2F48/wChXsP/AAdL/wDGq7nd49szynh/VkX+60tm7fn5i5/KgeKNUtR/xNfButQ/7dp5d2n/AI42/wD8dp/WsS/hkn935bi/s3BL4oNff+exw39hePP+hXsP/B0v/wAaqhp/hPx/a6tqt6fDenMt7JC6qNZGU2RBDn913IzXpkPjzwq8ohn1ZLCU/wDLO/je1bPp+8C1vWl3a3kQltLmG4jPR4nDj8xWc8Xio2ctPkaU8swMrqGvz/4J5FP4d8bzrsn8JaZKvpJq6sP1iqg3gbxPu3ReDbC2f+9b675R/wDHYwK9zopLM8StpDeR4KW8PxZ4Z/wiXxHj/wCPawRR/dn1iOYfrCD+ta/w/wBE+JWia5q+rX2keH5Fu4LaFYRqLq7eUZSTkRkD/Wd69coqamYVqseWdmvT/LU0oZThsPLnpJp+r/W6OW/4SjVbUf8AE08G6zD/ALdoY7tP/HG3/wDjtPh8eeFWlEVxqqWEp/5Z38T2rf8AkQLXTUyaKKaMxzRpIjdVcZB/A1hz0nvG3o/87nZyVVtK/qv8rEdpeWl5CJbO5huIz0eKQOPzFeG+F/8AkFP/ANf17/6VTV6vd+CPClxMJzoVnBMDnzbVTbvn/ejKmvFvC2lyR6QRaarqEAW8u1CtIJlwLqUdHBPb1r0srVP2r5X06o8PPpVPYR5kt+j8n3t+Z0N7dW1jZzXt5PHb20EbSzSyNtWNFGSxPYAVieE/GfhrxVJPFoep/aZYEWSSJ4JIX2N91wsiqSh7MMiud+Nel+Jr/wCFPiKwsZob+SS0yI4rdkmdVdWYKFJDEqDxjmuf8J+II/FHxctPEeiafLd6fp/hr7FdS2nzKsjyhki+YLllAOV/hr1Kk5RqKCt0/r5HgUqUJ0HUlfS/ytbf1voexHpWH4M/49dV/wCw1ff+jjVo65py8XDzWh9LmB4/1Ix+tUPAtxbz2mqGCeKUHWb0jY4OQZTg8VrOElJXRhCcXCVn2N6eWKCCSeeRIoo0LyO5wqqBkknsABmsDwp448LeKbuW00PVlubiKMTGNoZImeMnAkQOo3pn+JcjpUXxasb7Uvhj4m0/TYpJby40yZIYk+85x90epIyMd84rh/B+q6d4q+JXhC98Os01tonhqWDUWETILd3CKlu2QPnBDHb2wTXPUqyjUUV/X/DHVRw8Z0pTfS/ysr6+ux6/WH4Y/wCQr4m/7C3/ALbQVuVh+GP+Qr4m/wCwt/7bQVtLdHPD4Zf11QeLPFvh7wsludc1D7O9yWEEUcLzSybRliqRgsQB1OMCqOpfETwbYaTp2qz62j2upxtLZmCCSZpUX7zBEUsFXoSQMHg1xXxuu1tfHfhqU69L4PaKyuiviLyGmUbvlNrsAK5bh8tyMccmuX+HGrWnhTV/DXiDxJYHQtFfwtPp1tKY5TE8yXTOzYYFlaZfnCtyd3pXHPEyjUcdLf8ADHoUsDCVGM9W+3ffRaeXn6LQ+gNNvbPUtPg1DT7mK6tLiMSQzRNuV1PQg10Xwd/5GPxZ/wBdbP8A9JxXlfwD0690r4R6FaahBJbzFJZhDICGjSSV3RSD0O1hx2r1T4O/8jH4s/662f8A6TiscfJyw0ZPrY6sngoY6UU7pJ/mei3nn/ZJvsuzz9jeXv8Au7scZ9s4r46+Hfw7/aM8HeNdY8a/8In4V1zxHqrMZdQ1PUd7xqx+ZYwsihQcAdOAABgcV9lUV4R9aYfgKfxNc+EdOn8Y2dlZ688ZN7BZtuhR9xwFOTxjHc1uUUUAFBOK57xJ4u0vRrlbACa/1WQZi0+zTzJ39yOiL/tMQKyRoXiPxR+88VXn9maa3TSNPmOXHpPOMFvdUwPc1tGi7c0nZf1sv6XmZupraOrPF/ixq2lD4pa5KdTsgjJaqrfaFwSsZDDr1B4PpXN/21o//QWsP/AhP8a+hPDCaD4d8Q+Ko3Gn6Xp1vLZqgcrFGn+jD14q03jfSrxjH4a0XUPEMnQPaW2yAH3mk2p+Wa9bDZjUhTUKcLpdX+vQ8rEZdCpUc5zs30PnH+2tH/6C1h/4EJ/jSrq+ksQF1SyYk4GJ15P519GCy8d6vzNLo3hq3P8ADbxfbLjH+8wCA/RTU9r8O/D5uFu9YF1r10pyJdTmMoB9o+EH4LXR/bHL8aXy1/4H4sx/shP4W/noeZ/ADxDoGl6v4mbU9c0yxEy2flG4u0j37VlB27iM4yOlet/8Jv4L/wChv8P/APgyh/8AiqoaBaWsXxE8Qwx20KRJYaeFRYwFUZueg7V1X2a3/wCeEX/fArwcRVVarKaVrntUKXsqahfYxP8AhN/Bf/Q3+H//AAZQ/wDxVH/Cb+C/+hv8P/8Agyh/+Krb+zW//PCL/vgUfZrf/nhF/wB8CsTU8+i8Y+Ef+Fn3E/8AwlWh+SdFiUSf2hFt3efIcZ3da6b/AITfwX/0N/h//wAGUP8A8VVKKCH/AIWpcL5MeP7Di42j/n4krqPs1v8A88Iv++BQBif8Jv4L/wChv8P/APgyh/8AiqP+E38F/wDQ3+H/APwZQ/8AxVbf2a3/AOeEX/fAo+zW/wDzwi/74FAHHW2uaJrPxR0saRrGn6iYtGvjJ9luUl2ZmtcZ2k4zg/lRV67ijj+KGj+XGiZ0a+ztUD/ltaUUARfCL/kQrL/rtc/+lMtZH7RvhfWPF/wj1XSNAhS41RZLe6toGcKJmhnSXy9x4BYIQCe+K1/hER/wgVlz/wAtrr/0plrrcj1FAHkHw4tde8S/G3VfiRqPhnVfDenr4fg0W2ttUVEnmk85ppH2qzYVThQT1zXr56Ug2jpigkY6igDlfhl/yDdY/wCw/qX/AKUvTPjP4cvfF3wq8TeGtNaNb3UNOlht/MOFMhGVBPYEgDPbNO+GRH9m6xz/AMx/Uv8A0peusyPUUAeF+ALHxT4p+KPhLxBqvhHVvDVp4V8OzWNwdREYNxdyiNWWIKzbo1CE7+M8DFe6HpSDaOmKCRjqKAOV8A/8hfxl/wBh8/8ApJbVseLdNfWfC2raPHIsT31lNbK7DIUvGygn86x/AJH9r+Muf+Y+f/SS2rq8j1FAHzh8PdA8Z6pqXwp8Par4O1TRIvAMcp1O/ujH9nuHWAwxLblXJkDZ3E4G0V9HjpSfL7UuR6igDkvCn/I/+Mf+utn/AOk4rpdTtvtmnXNoG2edE8e7GcblIz+tcz4UI/4T/wAY/wDXWz/9JxXXZHqKAPmTwJ4W8bXdj8MPAGqeENS0seB9XN9qOrSmM2c6QiUReQwYlzJvXI2jbzX02OlJ8vtS5HqKAOV03/kq2uf9gXT/AP0dd11R6Vyumkf8LW1z/sC6f/6Ou66rI9RQB8vQeDvG3/CN2/wjk8J6kFi8Zf2o+ujy/sBsBdG43ht+7zedvl7evevqEdKT5c54pcj1FAHHyf8AJZYP+xel/wDSmOuwrj5P+Sywf9i9L/6Ux12FABRRRQAUUUUAFFFFABRRRQAyaGKaMxzRpIjdVdQQfwNc/d+BvCdzL5x0K0gl/wCetqpt3/76jKmujoq41Jw+F2InShP4kmcv/wAIlc22TpXizX7P+6ks63SD8JlY/rSfZ/HlngRaloWqoO1xbSWzn/gSM6/+O11NFX7eT+Kz9Uvz3M/q8F8N16N/lscsPEHiK1ydS8GXjKOr6ddxXA/75Yo36Uo8eeHYiF1GW80lz/DqFnLAB/wJl2/rXUUhAIwRkHtRz03vH7n/AJ3D2dVbT+9f5WKem6vpeppv07UbO8X1gnWT+RNXaw9S8IeGNRYveaDp0kh580QKsn/fS4P61T/4Qu3tyP7K13X9MA+6kV+0qD/gE28UctJ7Nr1X9fkHNWW8U/R/5r9TqDXg3hf/AJBT/wDX9e/+lU1eoHTvG1mM2viPTdRX+5f6fsb/AL7iYD/x2vN4vht8TbcyxWPiLw9DbtPLKqy2zSFfMkaQjO0EgFyBnsK7cDKFGbk5Jq39b2PLzWlUxVJQjFpp/wBbXLtFRw/Dn4nEjzvGnh1R3C6Ox/8AZxWnbfDnxjx9o8baafXZog/rJXqfXcP1keD/AGRi+kf6+ZnknaRk49K5fwtpem3VvqrXFjbyN/bV8NxQBh++Pcc16IfhzrjDDeMkHqU0mMfzc1Rt/hJqtrHMlp48vIBNcSXD402A5d23MefftS+v0FJNT/B/5FrJsU4uLh+K/wAzn/7Iij/49L7ULX0CXJZfyfcKXyNaj/1Wp21yPS4ttpP/AAJCP5VszfCPxJJ0+J+qp/u6dAKh/wCFNa8f9Z8TtZk+tog/9BYVX9q0Orv8hf6v4rokvmZn2nWIh++0dZh/etbkH/x1wv8AOsTw3q1vDqniQ3cF5a7tVyfNtmwv+jQcEqCAfx9K60/BXUW/1njy+k/37Un/ANq1DbfAqWGW4k/4S0SmeXzD5mmK2DtC4H7zp8vfPWoeZ4RtXv8Ad/wS45FjYpq618/+AR22o2FyP9HvraUdwso/lT5b20jyZby3T13zKP5mph8DwCT/AG5phJ7t4fhJ/MtUB+AxWTzIPFENq/8Aeh0aEfoWI/Sn/aWEb3f3L/Mn+w8al9n7/wDgFeTW9GTmTWNPH1uk/wAa0Phd4r8N6frviea71uxjSaW08o+aDvxBg4x1weKk/wCFR+JLeAix8c2JcDg3PhyBh/44ymtDwL4E8caG+pT3Xi/Shc3ssbM1tpPy7UTYuAXG09c9frXPisVhq9PlT/T9GduAy/F4StztLbpr+q/M6gfEDwk3+r1Rpv8ArlazSf8AoKGl/wCE50Rv9RDrNx/1y0e6P/tOkGg+KH/13jm8A7iHT7dP5q1B8KX0g/f+NPEj/wC5JBH/AOgxCvO5MMuv4v8A+RR7fPin0/Bf/JMD4zhP+q8O+J5R6jSpF/8AQsVga7rur3sbSarqcHgbRTkbriVP7QuB/sjJWIH23N9K3x4LgP8Ar/EHiaf/AHtWkX/0DFWdG8GeGtJuTd2ulQteMdzXVxmacn18xyW/WhTw8NYrX+u/+TKjGvL49v6/rc5bw5qmnWFs9v4D8HanqPmndJfTqbeOdv7zzTfPJ+APtWsNK8c6vzqniC00SA9YNJh8yXHoZpe/0UV2VFZSxGt0te71f46fgbKlpZv7tDzbwd4R0JfG3iM3tp/ak9pLbCK41FvtEo3QBidz55z+XbAr0hVVVCqAABgAdBXK+Fv+R58Xf9drT/0nWurrKdSU9ZO5pGEY7IKKKKgo5bRf+SleJP8Arw0/+dzXU1y2i/8AJSvEn/Xhp/8AO5rqaACiiigDlov+SrXH/YDi/wDSiSuprlov+SrXH/YDi/8ASiSupoAKKKKAOavv+SoaP/2Br/8A9HWlFF9/yVDR/wDsDX//AKOtKKAKNv8ADvTbVGis9c8T2sJkeQRQ6xKqKXYscDPAyx4qT/hA7f8A6Gbxd/4O5v8AGuvooA5D/hA7f/oZvF3/AIO5v8aP+EDt/wDoZvF3/g7m/wAa6+igDibL4b6bZJIlpr/iuFZZnmcLrUw3O7Fmbr1JJNT/APCB2/8A0M3i7/wdzf4119FAHIf8IHb/APQzeLv/AAdzf40f8IHb/wDQzeLv/B3N/jXX0UAcTa/DfTbWS5kt/EHiuJ7qbzpyutTfO+1V3HnrhVH4VP8A8IHb/wDQzeLv/B3N/jXX0UAch/wgdv8A9DN4u/8AB3N/jR/wgdv/ANDN4u/8Hc3+NdfRQBxMHw302C7ubuHX/FST3JUzONamy5Vdq557Dip/+EDt/wDoZvF3/g7m/wAa6+igDkP+EDt/+hm8Xf8Ag7m/xo/4QO3/AOhm8Xf+Dub/ABrr6KAOJT4cacl/Lfr4g8Vi6liSKSX+2ptzIhYqOvQF2/M1P/wgdv8A9DN4u/8AB3N/jXX0UAch/wAIHb/9DN4u/wDB3N/jR/wgdv8A9DN4u/8AB3N/jXX0UAc54e8Hafo2tPrCX+r3141t9mD31+8+2PcGIAY8cgc10dFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFAHB6Xr2h6T4+8VxaprOnWMjyWjKlzdJGzD7OBkBiOODW9/wmng//AKGrQv8AwYw//FVmeHrO0ufHfi1ri2hmImtAC8YbH+jj1rpf7K0z/oHWn/fhf8KAM3/hNPB//Q1aF/4MYf8A4qj/AITTwf8A9DVoX/gxh/8Aiq0v7K0z/oHWn/fhf8KP7K0z/oHWn/fhf8KAOI0fxb4VX4ieIZm8TaKInsbAK5v4sMQbjIB3dsj866X/AITTwf8A9DVoX/gxh/8AiqytG03Tz8R/EaGxtSosdPIHkrgc3PtXT/2Vpn/QOtP+/C/4UAZv/CaeD/8AoatC/wDBjD/8VR/wmng//oatC/8ABjD/APFVpf2Vpn/QOtP+/C/4Uf2Vpn/QOtP+/C/4UAcRF4t8K/8ACz7if/hJdF8o6LEof7fFtz58nGd3Wul/4TTwf/0NWhf+DGH/AOKrKi07T/8AhaVxH9htdv8AYkXHkrj/AI+JPaun/srTP+gdaf8Afhf8KAM3/hNPB/8A0NWhf+DGH/4qj/hNPB//AENWhf8Agxh/+KrS/srTP+gdaf8Afhf8KP7K0z/oHWn/AH4X/CgDl7fWtH1f4oaWNK1awvzFo18ZBbXKS7MzWuM7ScZwaKszWlrbfFDSPs9tDDu0a+z5cYXP7609KKAOrooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKAOU8Lf8jz4u/67Wn/pOtdXXKeFv+R58Xf9drT/ANJ1rq6ACiiigDltF/5KV4k/68NP/nc11Nctov8AyUrxJ/14af8Azua6mgAooooA5aL/AJKtcf8AYDi/9KJK6muWi/5Ktcf9gOL/ANKJK6mgAooooA5q+/5Kho//AGBr/wD9HWlFF9/yVDR/+wNf/wDo60ooA6WiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooA5Twt/yPPi7/AK7Wn/pOtdXmsLVvB3hbVr99Q1LQNOu7uRVV5pYAXYKMAE98VV/4V74I/wChW0n/AMBxQB0+aM1zH/CvfBH/AEK2k/8AgOKP+Fe+CP8AoVtJ/wDAcUAN0X/kpXiT/rw0/wDnc11Oa5YfDvwMHZx4U0gMwAZhbLkgdMn8TTv+Fe+CP+hW0n/wHFAHT5ozXMf8K98Ef9CtpP8A4Dij/hXvgj/oVtJ/8BxQA2L/AJKtcf8AYDi/9KJK6nNct/wrvwNv3/8ACKaRvxt3fZlzjrjPpTv+Fe+CP+hW0n/wHFAHT5ozXMf8K98Ef9CtpP8A4Dij/hXvgj/oVtJ/8BxQA6+/5Kfo3/YGv/8A0daUVc0Twp4b0S8a90jRLCyuWjMRlhhCsUJBK59MgHHsKKAP/9k="}}},{"metadata":{},"cell_type":"markdown","source":"### **An Example of Convolution Operation** <a id=\"113\"></a>\n<mark>[Return Contents](#0)\n    \n![conv2.png](attachment:conv2.png)\n* As you see above we have 5x5 image matrix and 3x3 filter matrix,\n* If we choose the stride (S) parameter as 1 then our output matrix would be 3x3 matrix\n* If we choose the stride (S) parameter as 2 then our output matrix would be 2x2 matrix\n\n\\begin{equation}\nn^{l} = \\frac{5 - 3}{1}+1 = 3\\\\\n\\text{output} =  3 x 3\\\\\n\\text{  }\\\\\nn^{l} = \\frac{5 - 3}{2}+1 = 2\\\\\n\\text{output} =  2 x 2\\\\\n\\end{equation}","attachments":{"conv2.png":{"image/png":"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"}}},{"metadata":{},"cell_type":"markdown","source":"* If the entrance picture is colored (RGB) as below, the 2nd and 3rd dimensions will also be available. (6x6x3)\n* In this case, we will convolute the filter 1 to have three different values from 3 channels and will sum the results to obtain a single number.\n* The important factor in here is filter1 has the same values for all three-channel (demonstrated as different colors) he has.\n* On the example above we use only one filter but in real applications, there will be more filters used at the same time as below.\n* The output matrix width(w) and height(h) sizes are generally the same in applications but it can be different also.\n* So output images are a matrix in $w$x$h$x$c$ dimension.\n* $w$ and $h$ is calculated as above equation and the channel dimension of the matrix is the same as filter number used on convolution. You can imagine that after the convolution operation each filter creates a different layer on the matrix as below."},{"metadata":{},"cell_type":"markdown","source":"![rsz_convolution-with-multiple-filters2.png](attachment:rsz_convolution-with-multiple-filters2.png)","attachments":{"rsz_convolution-with-multiple-filters2.png":{"image/png":"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"}}},{"metadata":{},"cell_type":"markdown","source":"### **Why do we use Filters?** <a id=\"114\"></a>\n<mark>[Return Contents](#0)\n* To answer this question first we should ask another and more general question;\n* What is our main purpose?\n* In this kernel our main purpose is as you know recognition handwrite patterns, but for simplicity, let us think about cats.\n* When you see a cat face picture how do you understand that is a cat? It should have solid patterns on its face right? \n   * Solid patterns like eye shape, nose curve, mustaches, etc.\n   * Our brain recognizes some parts of the face separately and combines them to give a final decision. The same explanation is acceptable for CNN filters.\n* Each filter has a job; some of them detect the edges (Sobel filter as on the example), some of them detect just the horizontal lines. \n* The task of the filter becomes more complex in the deep layers of the evolutionary network. For example, the first layer of the network can detect just __horizontal lines__ while deeper layers of the network __can detect the nose or eye__ and again ongoing deeper layers __can detect even the human face.__\n* To sum up filters are used to extract the features of the image. After feature extraction, we use a fully connected layer for classification according to extracted features.\n\n"},{"metadata":{},"cell_type":"markdown","source":"## **Padding** <a id=\"130\"></a>\n<mark>[Return Contents](#0)\n\n    "},{"metadata":{},"cell_type":"markdown","source":"##### Padding refers to the process of symmetrically adding values to the input matrix. \n\n![padding.png](attachment:padding.png)","attachments":{"padding.png":{"image/png":"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"}}},{"metadata":{},"cell_type":"markdown","source":"### **__Why do we use Padding?__** <a id=\"131\"></a>\n<mark>[Return Contents](#0)    \n1. The information at the edges is convoluted only once, while the information in the middle is convoluted 3 times with a 3x3 filter. This results in the loss of information on the edges. Edge information can be convoluted multiple times thanks to padding.\n2. The output matrix dimension getting smaller whenever we use convolution operation. Padding mostly used in designing the CNN layers when the dimensions of the input volume need to be preserved in the output volume (**Same Padding**).\n    \n### Equation of calculating output dimension changes with using padding process as below <a id=\"132\"></a>\n\n\\begin{equation}\nn^{l} = \\frac{n^{l-1} + 2p - f}{s}+1 \\\\\n\\text{output} =  n^l x n^l\n\\end{equation}\n"},{"metadata":{},"cell_type":"markdown","source":"### **Types of Padding in Keras** <a id=\"133\"></a> \n<mark>[Return Contents](#0)  \n* Valid : No padding\n* Same  : Choosing a $p$ value on above equation to obtain output matrix in same dimension as like input matrix."},{"metadata":{},"cell_type":"markdown","source":"## **Pooling** <a id=\"150\"></a>\n<mark>[Return Contents](#0)"},{"metadata":{},"cell_type":"markdown","source":"* Pooling refers to the process of dividing a matrix into pools and select from every pool only one value as representing that pool.\n* Despite the convolution operation Pooling has not any weight because you don't use any filter to operation.\n* It is about only selecting one value from small groups."},{"metadata":{},"cell_type":"markdown","source":"![pooling.png](attachment:pooling.png)","attachments":{"pooling.png":{"image/png":"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"}}},{"metadata":{},"cell_type":"markdown","source":"### **Hyper Parameters of Pooling Operation** <a id=\"151\"></a>\n1. Pooling Size\n2. Stride"},{"metadata":{},"cell_type":"markdown","source":"* Same as convolution operation, for example in the above pic. there is $2$x$2$ pooling size and stride = 2 (sliding on matrix by 2 cell)"},{"metadata":{},"cell_type":"markdown","source":"### **Why do we use Pooling?** <a id=\"152\"></a>\n<mark>[Return Contents](#0)\n1. To gain robustness on feature extraction;\n    * Pooling prevents the model from over-training by discarding the unnecessary data relative to the selected value.\n2. To speed up the computation;\n    * Reducing the size of the representation for increasing the speed of the computation."},{"metadata":{},"cell_type":"markdown","source":"### **Types of Pooling in Keras** <a id=\"153\"></a>\n<mark>[Return Contents](#0)\n    \n* Max Pooling: The operation of selecting the maximum value from each mini-group (pool) as the picture above\n* Average Pooling: The operation of selecting the average value from each mini-group."},{"metadata":{},"cell_type":"markdown","source":"<a href=\"https://ibb.co/sFVGBpY\"><img src=\"https://i.ibb.co/xM704KT/cnn.jpg\" alt=\"cnn\" border=\"0\"></a>"},{"metadata":{},"cell_type":"markdown","source":"  1. Filter Matrices containing a specific pattern\n  2. In the Conv layer, the filters are shifted over the image by the number of strides and convolution is performed.\n  3. The matrix obtained as a result of the 3rd process is called a feature map. Here it can be observed in which regions of the matrix in the previous layer how much data is available for the filter pattern.\n  4. Numerically high values are indicative of pattern compliance.\n  5. A feature map can be considered as the new picture we have for the next CNN layer. We can now detect the patterns in this picture with a new filter. This is the 2nd layer of CNN. We can increase the number of layers with this logic."},{"metadata":{},"cell_type":"markdown","source":"## **Batch Normalization** <a id=\"160\"></a>\n<mark>[Return Contents](#0)"},{"metadata":{},"cell_type":"markdown","source":"#### **What is Batch Norm?** <a id=\"161\"></a>\n<mark>[Return Contents](#0)\n    \n* Batch Normalization is a method used to normalize the input of a hidden layer by adjusting and scaling the activations.\n* The method consists of performing normalization on each neuron of a specific layer on each training mini-batch.\n* Normalized neurons of $l$'th layer will have a specific mean and variance for the problem according to trained $\\gamma$ and $\\beta$ parameters.\n* The algorithm of the batch norm is shown below;\n\n![batch_norm.png](attachment:batch_norm.png)","attachments":{"batch_norm.png":{"image/png":"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"}}},{"metadata":{},"cell_type":"markdown","source":"#### **Why do we use Batch Norm?** <a id=\"161\"></a>\n<mark>[Return Contents](#0)\n    \n* At artificial neural networks distribution of the inputs changes for each layer during training since the weight parameters of the previous layers change. This slows down training by requiring lower learning rates and careful parameter initialization, making it difficult to train models with non-linear saturation.\n* In short terms we use Batch Norm;\n    1. To increase the learning speed of the model.\n    2. To use much higher learning rates and be less careful about initialization\n    3. To regularize the network (side positive effect)"},{"metadata":{},"cell_type":"markdown","source":"#### **Some notes about Batch Norm** <a id=\"162\"></a>\n<mark>[Return Contents](#0)\n    \n* The parameters $\\gamma$ and $\\beta$ are learnable parameters. Therefore, you just initialize them and with backpropagation or other optimization algorithm they will be optimized like weight parameters.\n* Changing the distribution of each layer’s inputs during training, because of the enhancement of parameters of the previous layers calling covariate shifting at the original paper.\n* You can read the original paper written by Sergey Ioffe and Christian Szegedy from [here](https://arxiv.org/pdf/1502.03167.pdf)."},{"metadata":{},"cell_type":"markdown","source":"## **Drop Out** <a id=\"180\"></a>\n<mark>[Return Contents](#0)"},{"metadata":{},"cell_type":"markdown","source":"* Drop out is an effective regularization method.\n* During training, some number of layer outputs are randomly ignored or “dropped out.” This has the effect of making the layer look-like and be treated-like a layer with a different number of nodes and connectivity to the prior layer. In effect, each update to a layer during training is performed with a different “view” of the configured layer.\n* __Why do we use Drop Out?__ The answer is to prevent overfitting...\n* It can be used with most types of layers, such as dense fully connected layers, convolutional layers, and recurrent layers such as the long short-term memory network layer."},{"metadata":{},"cell_type":"markdown","source":"![rsz_images.jpg](attachment:rsz_images.jpg)","attachments":{"rsz_images.jpg":{"image/jpeg":"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"}}},{"metadata":{},"cell_type":"markdown","source":"![CNN.png](https://i.ibb.co/Qcb9y35/Types-of-Learning-in-Machine-Learning.jpg)"},{"metadata":{},"cell_type":"markdown","source":"# ** 3. An Image Classification Application with CNN** <a id=\"200\"></a>\n<mark>[Return Contents](#0)\n<hr>"},{"metadata":{},"cell_type":"markdown","source":"## **Import Modules** <a id=\"210\"></a>"},{"metadata":{"trusted":true},"cell_type":"code","source":"import numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\nimport matplotlib.pyplot as plt # data visualization\nimport seaborn as sns # data visualization\n\nfrom sklearn.model_selection import train_test_split\nfrom keras.utils.np_utils import to_categorical\n\nimport tensorflow as tf\nfrom tensorflow.keras import Sequential\nfrom tensorflow.keras.layers import Conv2D, Dropout, Dense, Flatten, BatchNormalization, MaxPooling2D,LeakyReLU\nfrom tensorflow.keras.optimizers import RMSprop,Nadam,Adadelta\nfrom tensorflow.keras.preprocessing.image import ImageDataGenerator\nfrom tensorflow.keras.callbacks import ReduceLROnPlateau, EarlyStopping\nfrom tensorflow.keras.utils import to_categorical\nfrom tensorflow.keras.regularizers import l2\n\nimport warnings\nwarnings.filterwarnings('ignore')\n\nimport os\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"* With this code below you can check if the kernel use GPU or not."},{"metadata":{"trusted":true},"cell_type":"code","source":"tf.test.gpu_device_name()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## **Understanding the Data** <a id=\"220\"></a>\n<mark>[Return Contents](#0)"},{"metadata":{},"cell_type":"markdown","source":"* We have training and test set CSV files,\n* In order to evaluate the generalization skill of the model we will split our training set into training and validation sets.\n* After training the data, Kaggle will evaluate the final performance of our data with test set predictions."},{"metadata":{},"cell_type":"markdown","source":"* Let's read csv files"},{"metadata":{"_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","trusted":true},"cell_type":"code","source":"raw_train = pd.read_csv('../input/Kannada-MNIST/train.csv')\nraw_test = pd.read_csv('../input/Kannada-MNIST/test.csv')","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"* We have $28$x$28$ dimension handwritten pics.\n* Dataset has been already flattened and has 784-pixel values for each pic.\n* Totaly we have $60000$ pics in training set."},{"metadata":{"scrolled":true,"trusted":true},"cell_type":"code","source":"raw_train.iloc[[0,-1],[1,-1]] # First and last values of dataset","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"* It is important to know the distribution of data according to the labels they have.\n* This data set is __homogeneously__ distributed as you see below."},{"metadata":{"trusted":true},"cell_type":"code","source":"num = raw_train.label.value_counts()\nsns.barplot(num.index,num)\nnumbers = num.index.values","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"* __If the data wasn't homogeneously__ distributed what would we do?\n    1. Then we could use data augmentation techniques to generate new data for low quantity labels,\n    2. Or if we have enough data we can discard some high quantity labels"},{"metadata":{},"cell_type":"markdown","source":"#### **Image of Handwritten Character** <a id=\"2\"></a>\n<mark>[Return Contents](#0)\n<hr>\n    \n * An overview of a picture\n * You can change the $num$ variable to see other numbers."},{"metadata":{"trusted":true},"cell_type":"code","source":"num=6\nnumber = raw_train.iloc[num,1:].values.reshape(28,28)\nprint(\"Picture of \"+ str(num) + \"in Kannada style\")\nplt.imshow(number, cmap=plt.get_cmap('gray'))\nplt.show()\n","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## **Data Preprocessing** <a id=\"230\"></a>\n### **Normalizing Data** <a id=\"231\"></a>\n<mark>[Return Contents](#0)\n<hr>\n* What is normalizing? Normalization means that adjusting values measured on different scales to a notionally common scale.\n* Why should you normalize the data?  With a normalized data weight values reach optimum value faster.\n* On image processing applications generally we normalize data to 0-1 scale with dividing data to 255.\n* Because each pixel in every sample of training set has integer values from 0 to 255.\n* In order to normalize training set data, we need to convert x to float type."},{"metadata":{"trusted":true},"cell_type":"code","source":"x = raw_train.iloc[:, 1:].values.astype('float32') / 255\ny = raw_train.iloc[:, 0] # labels","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"### **Cross Validation - Training- Validation Set Split** <a id=\"232\"></a>\n<mark>[Return Contents](#0)\n    \n* In order to measure the generalization ability of the model, we train the data with the training set and make the model arrangement according to the error value in the validation set. In addition, we determine the final performance of the model with the test set. \n* The reason for using the test set on the final evaluation is the model would have a bias on the validation set because we developed the model according to the validation set performance. So a kind of overfitting on the validation set is formed.\n* This Kernel is prepared on a Kaggle competition dataset. They give us a training set for training the model and a test set without labels for prediction. As we don't have the labels we don't know the final performance of the test set until we submit our predictions.\n* To evaluate the model we need to split our training set into training and validation set.\n    \n* For I prefer to split\n    * Training set - $\\%80$\n    * Validation set - $\\%20$\n"},{"metadata":{"trusted":true},"cell_type":"code","source":"x_train, x_val, y_train, y_val = train_test_split(x, y, test_size = 0.2, random_state=42) ","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"### **Reshape Data to Fit Model** <a id=\"233\"></a>\n<mark>[Return Contents](#0)"},{"metadata":{},"cell_type":"markdown","source":"> * In order to feed the CNN model we need to reshape our $54000$x$784$ flatten image data to $54000$x$28$x$28$x$1$ dimensions.;"},{"metadata":{"trusted":true},"cell_type":"code","source":"x_train.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"x_train = x_train.reshape(-1, 28, 28,1)\nx_val = x_val.reshape(-1, 28, 28,1)\ny_train = to_categorical(y_train)\ny_val = to_categorical(y_val)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"* You can leave one unknown dimension as -1.\n* Whenever numpy has -1 value on reshape method it will calculate the dimension which denoted with -1 automatically."},{"metadata":{},"cell_type":"markdown","source":"## **Building and Training a CNN Model** <a id=\"250\"></a>\n<mark>[Return Contents](#0)\n<hr>\n* On Keras Sequential Networks there is three-stage for training building, compiling and fitting the model.\n    \n#### **Model - Build** <a id=\"251\"></a>\n\n    \n* On building stage you specify the architecture of the model mainly.\n* You can decide the [Filter](#110) size and [Padding](#150) type you will use on [Convolution](#110) operations and add [Pooling](#150), Batch Normalization, Dropout, activation function layers with build section."},{"metadata":{"trusted":true},"cell_type":"code","source":"model = tf.keras.models.Sequential([\n    tf.keras.layers.Conv2D(64, (3,3), padding='same', input_shape=(28, 28, 1)),\n    tf.keras.layers.BatchNormalization(momentum=0.9, epsilon=1e-5, gamma_initializer=\"uniform\"),\n    tf.keras.layers.LeakyReLU(alpha=0.1),\n    tf.keras.layers.Conv2D(64,  (3,3), padding='same'),\n    tf.keras.layers.BatchNormalization(momentum=0.9, epsilon=1e-5, gamma_initializer=\"uniform\"),\n    tf.keras.layers.LeakyReLU(alpha=0.1),\n    tf.keras.layers.Conv2D(64,  (3,3), padding='same'),\n    tf.keras.layers.BatchNormalization(momentum=0.9, epsilon=1e-5, gamma_initializer=\"uniform\"),\n    tf.keras.layers.LeakyReLU(alpha=0.1),\n\n    tf.keras.layers.MaxPooling2D(2, 2),\n    tf.keras.layers.Dropout(0.25),\n    \n    tf.keras.layers.Conv2D(128, (3,3), padding='same'),\n    tf.keras.layers.BatchNormalization(momentum=0.9, epsilon=1e-5, gamma_initializer=\"uniform\"),\n    tf.keras.layers.LeakyReLU(alpha=0.1),\n    tf.keras.layers.Conv2D(128, (3,3), padding='same'),\n    tf.keras.layers.BatchNormalization(momentum=0.9, epsilon=1e-5, gamma_initializer=\"uniform\"),\n    tf.keras.layers.LeakyReLU(alpha=0.1),\n    tf.keras.layers.Conv2D(128, (3,3), padding='same'),\n    tf.keras.layers.BatchNormalization(momentum=0.9, epsilon=1e-5, gamma_initializer=\"uniform\"),\n    tf.keras.layers.LeakyReLU(alpha=0.1),\n    \n    tf.keras.layers.MaxPooling2D(2,2),\n    tf.keras.layers.Dropout(0.25),    \n    \n    tf.keras.layers.Conv2D(256, (3,3), padding='same'),\n    tf.keras.layers.BatchNormalization(momentum=0.9, epsilon=1e-5, gamma_initializer=\"uniform\"),\n    tf.keras.layers.LeakyReLU(alpha=0.1),\n    tf.keras.layers.Conv2D(256, (3,3), padding='same'),\n    tf.keras.layers.BatchNormalization(momentum=0.9, epsilon=1e-5, gamma_initializer=\"uniform\"),##\n    tf.keras.layers.LeakyReLU(alpha=0.1),\n\n    tf.keras.layers.MaxPooling2D(2,2),\n    tf.keras.layers.Dropout(0.25),\n    \n    \n    tf.keras.layers.Flatten(),\n    tf.keras.layers.Dense(256),\n    tf.keras.layers.LeakyReLU(alpha=0.1),\n \n    tf.keras.layers.BatchNormalization(),\n    tf.keras.layers.Dense(10, activation='softmax')\n])","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"### **Model - Compile** <a id=\"252\"></a>\n<mark>[Return Contents](#0)\n    \n* On Compile Section we specify the loss function, optimizer algorithm and metric to use for evaluating the model."},{"metadata":{"trusted":true},"cell_type":"code","source":"optimizer = RMSprop(learning_rate=0.002,###########optimizer = RMSprop(learning_rate=0.0025,###########\n    rho=0.9,\n    momentum=0.1,\n    epsilon=1e-07,\n    centered=True,\n    name='RMSprop')\nmodel.compile(loss='categorical_crossentropy',\n              optimizer=optimizer,\n              metrics=['accuracy'])","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"#### **Compile ->Loss Function ->Categorical Crossentropy** <a id=\"253\"></a>\n<mark>[Return Contents](#0)\n    \n* The Categorical Crossentropy Loss Function computes between network predictions and target values for multiclass classification problems.\n\n* The loss is calculated using the following formula;\n\\begin{equation}\nLoss = -\\frac{1}{m}\\sum_{i=1}^{m}\\sum_{k=1}^{K} Y^i_klog(\\hat{Y^i_k})(1-Y^i_k)log(1-\\hat{Y^i_k}) \\\\\n\\end{equation}\n\nwhere $k$ demonstrates class, $i$ demonstrates sample number, $\\hat{Y_c}$ is the predicted value, $Y_c$ is the ground truth value, $m$ is the sample number in a batch and $K$ is the total number of classes.\n\n* Why do we use log? Because cross-entropy function penalize bigger difference more and smaller difference less as mentioned below.\n\n![cross_entropy.png](attachment:cross_entropy.png)","attachments":{"cross_entropy.png":{"image/png":"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"}}},{"metadata":{},"cell_type":"markdown","source":"#### **Compile -> Optimizer** <a id=\"255\"></a>\n<mark>[Return Contents](#0)\n* To optimize the weight values of the network we should choose an optimizer algorithm. \n* In the first lessons of artificial learning, the gradient descent algorithm is taught as the optimization algorithm used in backpropagation. \n* Over time, the gradient descent algorithm was developed and the algorithms that achieved faster and more accurate results were obtained. \n* Some of them are ADAGRAD, ADAM, ADAMAX, NADAM and RMSPROP. \n* These algorithms use techniques such as adaptive learning rate and momentum to achieve the global minimum.\n* If you want to take a more detailed look at Gradient Descent algorithms, [here](https://ruder.io/optimizing-gradient-descent/) is a very nice overview article written by [Sebastian Ruder](https://ruder.io/optimizing-gradient-descent/).\n\n* __As you see below__ while Stochastic Gradient Descent (SGD) which is a basic gradient descent algorithm cannot escape the saddle point, more advanced algorithms escape the saddle point __at different speeds.__\n"},{"metadata":{},"cell_type":"markdown","source":"![CNN.jpg](https://ruder.io/content/images/2016/09/saddle_point_evaluation_optimizers.gif)\n![CNN.jpg](https://ruder.io/content/images/2016/09/contours_evaluation_optimizers.gif)"},{"metadata":{"trusted":true},"cell_type":"code","source":"batch_size = 1024\nnum_classes = 10\nepochs = 40\n","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"#### **On-the-Fly Data Augmentation** <a id=\"257\"></a>\n<mark>[Return Contents](#0)\n* On classification tasks on image datasets data augmentation is a common way to increase the generalization of the model. \n\n\n\n* With the ImageDataGenerator on Keras, we can handle this objective easily.\n* [Here](https://www.pyimagesearch.com/2019/07/08/keras-imagedatagenerator-and-data-augmentation/) is a comprehensive and inspiring article about data augmentation and ImageDataGenerator written by [Adrian Rosebrock](https://www.pyimagesearch.com/2019/07/08/keras-imagedatagenerator-and-data-augmentation/) who is the author of PyImageSearch a very instructive web-site about computer vision.\n* __By changing__ some of the properties of the image from the code below, __you can observe what changes are happening in the dataset__. \n* With this observation, you can roughly specify the range you should choose."},{"metadata":{"trusted":true},"cell_type":"code","source":"# An observation code for our dataset\ndatagen_try = ImageDataGenerator(rotation_range=15,\n                             width_shift_range = 0.15,\n                             height_shift_range = 0.15,\n                             shear_range = 0.15,\n                             zoom_range = 0.4,)\n# fit parameters from data\ndatagen_try.fit(x_train)\n# configure batch size and retrieve one batch of images\nfor x_batch, y_batch in datagen_try.flow(x_train, y_train, batch_size=9):\n\t# create a grid of 3x3 images\n\tfor i in range(0, 9):\n\t\tplt.subplot(330 + 1 + i)\n\t\tplt.imshow(x_batch[i].reshape(28, 28), cmap=plt.get_cmap('gray'))\n\t# show the plot\n\tplt.show()\n\tbreak","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"datagen_train = ImageDataGenerator(rotation_range = 10,\n                                   width_shift_range = 0.25,\n                                   height_shift_range = 0.25,\n                                   shear_range = 0.1,\n                                   zoom_range = 0.4,\n                                   horizontal_flip = False)\n\ndatagen_val = ImageDataGenerator() \n\n\nstep_train = x_train.shape[0] // batch_size\nstep_val = x_val.shape[0] // batch_size\n\nlearning_rate_reduction = tf.keras.callbacks.ReduceLROnPlateau( \n    monitor='loss',    # Quantity to be monitored.\n    factor=0.25,       # Factor by which the learning rate will be reduced. new_lr = lr * factor\n    patience=2,        # The number of epochs with no improvement after which learning rate will be reduced.\n    verbose=1,         # 0: quiet - 1: update messages.\n    mode=\"auto\",       # {auto, min, max}. In min mode, lr will be reduced when the quantity monitored has stopped decreasing; \n                       # in the max mode it will be reduced when the quantity monitored has stopped increasing; \n                       # in auto mode, the direction is automatically inferred from the name of the monitored quantity.\n    min_delta=0.0001,  # threshold for measuring the new optimum, to only focus on significant changes.\n    cooldown=0,        # number of epochs to wait before resuming normal operation after learning rate (lr) has been reduced.\n    min_lr=0.00001     # lower bound on the learning rate.\n    )\n\nes = EarlyStopping(monitor='val_loss', mode='min', verbose=1, patience=300, restore_best_weights=True)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"### **Model - Fit** <a id=\"259\"></a>\n<mark>[Return Contents](#0)"},{"metadata":{"trusted":true},"cell_type":"code","source":"history = model.fit_generator(datagen_train.flow(x_train, y_train, batch_size=batch_size),\n                              steps_per_epoch=len(x_train)//batch_size,\n                              epochs=epochs,\n                              validation_data=(x_val, y_val),\n                              validation_steps=50,\n                              callbacks=[learning_rate_reduction, es],\n                              verbose=2)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## **Evaluation of the Model** <a id=\"270\"></a>\n### **Accuracy and Loss Curves** <a id=\"271\"></a>\n<mark>[Return Contents](#0)"},{"metadata":{},"cell_type":"markdown","source":"* On classification, accuracy metric is calculated as below;\n\n\\begin{equation}\nclassification~accuracy = \\frac{correct~predictions}{total~predictions} * 100 \\\\\n\\end{equation}"},{"metadata":{"trusted":true},"cell_type":"code","source":"tf.keras.utils.plot_model(model, to_file=\"model.png\", show_shapes=True)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"plt.plot(history.history['accuracy'])\nplt.plot(history.history['val_accuracy'])\nplt.title('Model accuracy')\nplt.ylabel('Accuracy')\nplt.xlabel('Epoch')\nplt.legend(['Train', 'Validation'], loc='upper left')\nplt.show()\n\n# Plot training & validation loss values\nplt.plot(history.history['loss'])\nplt.plot(history.history['val_loss'])\nplt.title('Model loss')\nplt.ylabel('Loss')\nplt.xlabel('Epoch')\nplt.legend(['Train', 'Validation'], loc='upper left')\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"### **Test Set Accuracy Score** <a id=\"272\"></a>\n<mark>[Return Contents](#0)"},{"metadata":{"trusted":true},"cell_type":"code","source":"model.evaluate(x_val, y_val, verbose=2);","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"### **Confusion Matrix** <a id=\"273\"></a>\n<mark>[Return Contents](#0)"},{"metadata":{"trusted":true},"cell_type":"code","source":"y_predicted = model.predict(x_val)\ny_grand_truth = y_val\ny_predicted = np.argmax(y_predicted,axis=1)\ny_grand_truth = np.argmax(y_grand_truth,axis=1)\nfrom sklearn.metrics import confusion_matrix\ncm = confusion_matrix(y_grand_truth, y_predicted)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"* If 90% of the data set is cat image and 10% is dog image, your accuracy will be 90% even if you estimate the entire test set as a cat.\n* But in another aspect, the model's success in predicting dogs is 0%.\n* In this context, accuracy may not always give us realistic information about the actual performance of the model.\n* The confusion matrix shows how confused your classification model is for which classes by detailing the relationship between actual class and predicted class.\n* If there is an anomaly something like above mentioned, you can specify the problem with confusion matrix and improve accuracy by various methods like adding more data for a specific class, etc."},{"metadata":{"trusted":true},"cell_type":"code","source":"f, ax = plt.subplots(figsize=(10,10))\nsns.heatmap(cm,fmt=\".0f\", annot=True,linewidths=0.1, linecolor=\"purple\", ax=ax)\nplt.xlabel(\"Predicted\")\nplt.ylabel(\"Grand Truth\")\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"### **F1 Score Calculation** <a id=\"274\"></a>\n<mark>[Return Contents](#0)"},{"metadata":{},"cell_type":"markdown","source":"* As mentioned above, [accuracy](#271) gives a general idea about the performance of the model but does not provide any information about the model's trends.\n* In classification algorithms, it is important to analyze the false predictions of the model.\n* There are 2 kinds of false predictions; \n  * __Predicted as \"1\" but Ground Truth is \"0\" (False Positive)__\n  * __Predicted as \"0\" but Ground Truth is \"1\" (False Negative)__\n\n<a href=\"https://imgbb.com/\"><img src=\"https://i.ibb.co/q99h0R6/f1.png\" alt=\"f1\" border=\"0\"></a>\n* The F1 score creates a success performance metric, taking into account both of these incorrect prediction performances as well as the true positive predictions\n* Since our problem has more than 2 classes, we calculated the F1 score for each class on a one-to-all basis.\n* [Here](https://towardsdatascience.com/multi-class-metrics-made-simple-part-ii-the-f1-score-ebe8b2c2ca1) is a nice article on how to calculate the F1 score in multiple classes, supported by examples."},{"metadata":{"trusted":true},"cell_type":"code","source":"scores = np.zeros((10,3))\ndef calc_F1(num):\n  TP = cm[num,num]\n  FN = np.sum(cm[num,:])-cm[num,num]\n  FP = np.sum(cm[:,num])-cm[num,num]\n  precision = TP/(TP+FP)\n  recall = TP/(TP+FN)\n  F1_score = 2*(recall * precision) / (recall + precision)\n  return precision, recall, F1_score\nfor i in range(10):\n   precision, recall, F1_score = calc_F1(i)\n   scores[i,:] = precision, recall, F1_score\nscores_frame = pd.DataFrame(scores,columns=[\"Precision\", \"Recall\", \"F1 Score\"], index=[list(range(0, 10))])","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"![rsz_1form%C3%BCl.jpg](attachment:rsz_1form%C3%BCl.jpg)","attachments":{"rsz_1form%C3%BCl.jpg":{"image/jpeg":"/9j/4AAQSkZJRgABAQEAYABgAAD/4RDcRXhpZgAATU0AKgAAAAgABAE7AAIAAAAGAAAISodpAAQAAAABAAAIUJydAAEAAAAMAAAQyOocAAcAAAgMAAAAPgAAAAAc6gAAAAgAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAGJub25lAAAFkAMAAgAAABQAABCekAQAAgAAABQAABCykpEAAgAAAAM3NgAAkpIAAgAAAAM3NgAA6hwABwAACAwAAAiSAAAAABzqAAAACAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAMjAxOToxMjowNyAwMzoxNjo0OAAyMDE5OjEyOjA3IDAzOjE2OjQ4AAAAYgBuAG8AbgBlAAAA/+ELGGh0dHA6Ly9ucy5hZG9iZS5jb20veGFwLzEuMC8APD94cGFja2V0IGJlZ2luPSfvu78nIGlkPSdXNU0wTXBDZWhpSHpyZVN6TlRjemtjOWQnPz4NCjx4OnhtcG1ldGEgeG1sbnM6eD0iYWRvYmU6bnM6bWV0YS8iPjxyZGY6UkRGIHhtbG5zOnJkZj0iaHR0cDovL3d3dy53My5vcmcvMTk5OS8wMi8yMi1yZGYtc3ludGF4LW5zIyI+PHJkZjpEZXNjcmlwdGlvbiByZGY6YWJvdXQ9InV1aWQ6ZmFmNWJkZDUtYmEzZC0xMWRhLWFkMzEtZDMzZDc1MTgyZjFiIiB4bWxuczpkYz0iaHR0cDovL3B1cmwub3JnL2RjL2VsZW1lbnRzLzEuMS8iLz48cmRmOkRlc2NyaXB0aW9uIHJkZjphYm91dD0idXVpZDpmYWY1YmRkNS1iYTNkLTExZGEtYWQzMS1kMzNkNzUxODJmMWIiIHhtbG5zOnhtcD0iaHR0cDovL25zLmFkb2JlLmNvbS94YXAvMS4wLyI+PHhtcDpDcmVhdGVEYXRlPjIwMTktMTItMDdUMDM6MTY6NDguNzU1PC94bXA6Q3JlYXRlRGF0ZT48L3JkZjpEZXNjcmlwdGlvbj48cmRmOkRlc2NyaXB0aW9uIHJkZjphYm91dD0idXVpZDpmYWY1YmRkNS1iYTNkLTExZGEtYWQzMS1kMzNkNzUxODJmMWIiIHhtbG5zOmRjPSJodHRwOi8vcHVybC5vcmcvZGMvZWxlbWVudHMvMS4xLyI+PGRjOmNyZWF0b3I+PHJkZjpTZXEgeG1sbnM6cmRmPSJodHRwOi8vd3d3LnczLm9yZy8xOTk5LzAyLzIyLXJkZi1zeW50YXgtbnMjIj48cmRmOmxpPmJub25lPC9yZGY6bGk+PC9yZGY6U2VxPg0KCQkJPC9kYzpjcmVhdG9yPjwvcmRmOkRlc2NyaXB0aW9uPjwvcmRmOlJERj48L3g6eG1wbWV0YT4NCiAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAKICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgIAogICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgCiAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAKICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgIAogICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgCiAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAKICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgIAogICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgCiAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAKICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgIAogICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgCiAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAKICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgIAogICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgCiAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAKICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgIAogICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgCiAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAKICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgIAogICAgICAgICAgICAgICAgICAgICAgICAgICAgPD94cGFja2V0IGVuZD0ndyc/Pv/bAEMABQMEBAQDBQQEBAUFBQYHDAgHBwcHDwsLCQwRDxISEQ8RERMWHBcTFBoVEREYIRgaHR0fHx8TFyIkIh4kHB4fHv/AAAsIAMMAugEBEQD/xAAfAAABBQEBAQEBAQAAAAAAAAAAAQIDBAUGBwgJCgv/xAC1EAACAQMDAgQDBQUEBAAAAX0BAgMABBEFEiExQQYTUWEHInEUMoGRoQgjQrHBFVLR8CQzYnKCCQoWFxgZGiUmJygpKjQ1Njc4OTpDREVGR0hJSlNUVVZXWFlaY2RlZmdoaWpzdHV2d3h5eoOEhYaHiImKkpOUlZaXmJmaoqOkpaanqKmqsrO0tba3uLm6wsPExcbHyMnK0tPU1dbX2Nna4eLj5OXm5+jp6vHy8/T19vf4+fr/2gAIAQEAAD8A+y80ZozRmjNGaM0ZozRmjNGaM0hYDqaTevqKdmjNIWUHBNAYHoaXNGaM0UUlFFFFFFFFFFFFVtThmnsZoba4a2meNljmVQTGSMBgDwSOteZ+ArTXNc1jxBOPF+vf2bpetpY2IkkjYzLboguC/wAmGDyl19tvGK9QuriC0tZbm5mjhhiUvJJI4VUUdSSeAK5zQvG+g6rrmoaVBqumNJbTxwwbL6Nzcbolf5QD2JIwM9K5z4mnWE8WeG7DS/EupWlxreqRwfZoHRUitIEaW5fBUkswUJknjeuMHr3Hh3TrnTLE29zqd3qTGaR1luipdUZsqmQBkKOBxn1rToooHWlpKyfFuv6Z4W8O3uvazci3sbKIyTPjJwOgA7sTgAdyRWlbyebBHLtZd6hsN1GR0NPpaM0ZFGc9KSilooqC9Wd7d1tpEimKnY7JuCnsSMjP0ritHsZvhv8ADOKwS6i1O4t5vlmnXyPPlnn3Mz4JwS0jEkcV0mgXc+saIJtRsVh85pV8p1yHjDsEYhum5QGwfWoNG8L6Vp2s6lqUVrbGS8mjmUC2RfJKxqmFIHfbn8aqXXhm4uPiRZeLJ9TVobKwlsoLI2/C+ayM8u/d98+Wq9MbeKd4M8Q6jrl3drd6clpBEiPEwL7mDPIBkMABlEVsDpvGa6iiik706o24j+grxX41z3/ifwBqd7pxn+wNMmn2tp9glaaYmdFmnA4Kjy9+0lSNoLfxCugl3+IPHXiXR9fbVre3At4dGW2SRF8ho1eS5SUDAfzCykk5QRgDG7JreGZptS0/UNV12DW38RafqN1dvaRLLEIkhMggt1PRomTYflJ8xmyenHK+G5PEGn6Bo6/Y9cuo9H8G3OoCBo583uoXLY8tt3J2Heqq3zAODjHNdBceH7nwrYeDdNll1iZ78W2m65fwyTz/ALuCKSRYwAT5YklOwyAAlTy3Q1leHZ9ViOmXGqW2s6fout+IdRn1CLyZmNukQ8u0tTtGUiYJuO0BSRtzhueg1LRpLDx3o9ppcOpSWms6PqkFytxNIUjLSwyJuAOI1UPIFxggYUH07DXtNv4vDVnp+jR3Fy9v5ca51N7Vyirty0oVix4GQevXNVfBtlr9rqEz6taTRQmLCl9ce8BbI/gaNQvHfNSSaT40MrGPxjZqhY7V/sVTtGeBnzecU3+yPG//AEOdn/4JF/8AjtL/AGR43/6HOz/8Ei//AB2k/snxt/0Odn/4JF/+O1XvfDfiy9MP2vxXYTeRMs8W/RB8si/dYYmHIzVn+yPG4HPjOy/8Ei//AB2k/sjxv/0Odn/4JF/+O0f2T43/AOhzs/8AwSL/APHaX+yPG3/Q52X/AIJF/wDjtB0jxuOvjOz/APBIv/x2k/snxt/0Odn/AOCRf/jtA0nxt/0Odn/4JF/+O1r+HbTWrVJhrGsQ6mWI8ox2Qt9mOoOHbP6Vr000gX3NJsGMUu3jB5o2jnk80BOnNIEwc7jmqWlaTb6c08kUlxLLPK0jyTzNKw3MW2gseEBJwo4A6VfGQKG6Hk15Z8SNJivfiL4U0yG81FLrVb1rq8Md7NGFsbSPc0YVWCgPI8Stxlgxz0r0Pw9pNvoumCwtnuHiEjuPOneVhuYtt3MScDOAM8AAVznjnx7pXhu5tbJ7lVumvbaKZGt5WCxSNgsCq4zjkc1c1u50TXPBkup3F9cpo0SNdTyQvJblo4sswJ+VgvynPTIGOlc58FvDb/8ACI+H/E2qXOpf2vdW0t3Kkl7KyBblvMWNkLFT5aFVXjjFdh4t8R6d4dsPtF/OYTIriH9zJIGZVJwdgOP0qn8PvFun+KtCtru2nD3RtYZrlFhkRUZ0zgb1GRnPrXCWtxJrfxP8UX7aXq+qaZHf2mg23kXjJbQSRoXuJ2UOCCGkCEhT/qx749S0HTING0e1023muZYraPy0e4maWQj/AGmYkk+5Oa5bxV8RNG0bxFpulPdANJeNBeBrWZjGBCzjaQuCchemeDV/xt4ns9J+G2q+K0PnW0OmyXMQKsvmnYdi4IDDcxUevNct8M/DMiafpOnaxZeIbbUtEt7OWfULrUXY31wUYyDh2DoDkEN7ccV6klOpKKKKKKKKKQ9K51vC9v8A8J2PGLX9894tgbBICU8hIi4c7V27txYAk5ycAdKoaBq+var4oumgaNtDhuriIO0QAYIERQrA5Y+aJiT0AGDziui1jS7fVI7ZJ2lUW91FdJsbGXjbcufbI5qj408PQeKvDF94eu728tbW+iMFw1qyrI0Z+8oLK2ARweOmRWf4jn8SaaNOsPD9us0SQhZppLcMAfMiRBhSoHymRjjgBa6i6hWe3lgYsFkVkO04OCMVW0uwi07R7bTLWSURWsCQROx3MAqhQT2J4HbrWd4J8MWnhXSJNNtLy7u0ku5rt5btlaVpJpC7klVXPzMeo4GB0FUPBmta3rOoS3EqRHSGE/kyiEoWxOVi2nJ3fu1JYgYyVx3rf1LS7a+vtPu5mkElhOZ4djYG4oyHPqMMePWs7xx4YtvFejx6VfXt7bWy3MNy4tmUGVopFkRW3KcruVSR3xjpTfGV3rtlYQtoNsLi4Z38wmEybUWJ26AjLFwgA9Wra0xrlrG3a7KfaDEpl2DA3bRuwO3OatUlFFFFFFFFFIaZFFHCm2KJI1yTtUADPrxTiyg4zzSgg9KWiimsAwIYAgjGD3plrBDbQJBbwxwxRjaiRqFVR6ADgVLRRQOtLSUUUUUUUUUUUV5h8QbfUX+IPhnSrHxDrMEusXzS3EUFzsihsbaEtKAo7u7RKW5PzYGMV33h3TX0nTFs5NQvb8rI7Ca7k8yTDMWC7u4UEAewrRooooooooHWlpmeOtcx4j8WvpXizS/Ddro13qV7qNtPcx+TLGixpCUDFy7DGTIoHXJPbFXvBfiTT/Fnh2DW9NEywSvLE0cybZI5I5GjkRgMjKujDgkHGQSK2sjPWo7iXy4ncKzlFJ2qMseOgHr7VDpd79u022vTbXFqZ4lk8i4TZLHkZ2uvZh3FR2Gofarq8g+y3UItZRH5k0e1JsqG3Rn+JecZ45BFXdwpRyKWiiuWHheRviL/AMJlLqbSGPTm0+CzMChIkaQSMytnduYquT0wo471HoXiLVdU8S3VnFZQNp0E9zC9wu8FfLKKmcjBLOZRgdkznnFdYvIpaKKKKKKB1pahhDLCoc5cKNx9TivNNJ0mXxP8VvFOsX8esWFtaWVtpGnSKJbXzovmlnkRuNys7KuRz+7+lJH4GsL3xtJo7aM9n4T0vw+NOhgj3xJcPcS75AGUgkKsaZOc7nPPJzz2mW3iu+8MX2tyWWqDxnpgv7qCzezaOP7XtljgjWV/llhVCuxI/lY4LEmrvirSLe8+Gkg0Sw8Q3F/f2lvpM88sEwmZZ5o/PnkjbBMiAMxfHykYGBmtUaZc3HxTs9Qh029m0hoTDPDcoyNYS2bN5E0L5w0codlK87sK3Y1z/g6z1uOw8KzazpmrWuk3Umpazq1sIH3tePIGgt5EHzbArthSMM0a57AxaboPiuC40aTUtLvzDpkOsa69mpL7Gndha6cjqcEqjPlRwOAOMV3XgbQtQ0/4M6PoscTm/XTYg0c08lsRI2HdSy5eMAkgAcgADipPDmieIrTWoLi9treO3XdvZdfu7gj5SB+7dQrc46njrWpqGl+Jpr2WS08UpawM2Y4f7MSTYMdNxbJqD+x/F3/Q5J/4KI//AIql/sbxeOf+Ezj/APBTH/8AFVW0/wAM+JNPtFtLLxXb28CFisaaRHgFmLMfvdySfqTVj+xvF3/Q5J/4J4//AIqprDSvE0d5FJdeK0uYEcGSEaZGm8dxuDZH1rolBFOoooooHWlpuOKRVxn3oKgnPfvQVyOtGwdO1IUBpQg655pAmO9OAwMUp5GK8v8Aj9pdte6PY28bTjV9WvbfRrCRJWH2cTShppVUEfMIkc7uo2jGOc9v4f8ADul6FLevpkTQreSLJInmMVBVQowCTjgc46nmsz4k+LofC/h6+uFWc3iWsk0AFlNPHlf7xjUhR9SK2ND1ez1m0aeyNxtV9jefaywHdgHhZFUkcjkDFeSeBbKLxXe6zqd/4cu73TvEusXogv8A7TtjtbOFPIQqobchkaNmBUAEtuz0r2iygjtbSG1i3eXDGsabmJOFGBknknjrU9FFFFFA60tJRRRRRRRRSE4rA13wxaax4h0bW7q7vlm0eV5bSKN1EQd0KMzKVO47WYdeMnGM1nXWra5c+NpNM0homs7NrVbrdGCqbt7ygtnrs8sBeuWB6V0et6bbavo91pd5v+z3URik2NtO09cHtT761N3p81p581uJYynmxMA6gjGVJBwffFZnh/StM8GeDbXS7eaVdN0i02I9w4ZlijU/ebAzgDqefWqfw+vPEeoWX2zW9gilt4Hh/c+UxdlLSfLk4UbkUZ5JVj0IrqqKKKKKB1paSiiiiiiiikJx1pNwJxn2pkcMSO7xxIrSHc5VQCx9T61LRTJo0ljaORFkRhhlYZBHuKVFVFCqoVRwAOgFOooooooHWlpKKKKKKKKKyfFFrBdaLMl1qF1YWqYlnmtpmikEaHewDqcqDjnHOMjvXE/BbSb2/wDCeieLdT1XWWur4XF8tvNqEskX2e4ZmgjKMSCEjKYyM5zzXpY6UtFFFFFFFFFA60tNOdvHWuM8V+N59H8SnQrPQ5dTmj0mXVZWjuY4wkUbhCMN/ESfl7HB5GM10HhvXLDXvDmm69ZSMLPUraK5tzKuxikihlyD0OD0rRMiBwm5dx6DPJ9aQyJv2B13ZA25GRXD2fxBkvLXSJ4NGLjVfEE+k2wW5B3RRNKHuR8vK4hc7fTHNd2PXBpaKw/HGhN4m8Kaj4f/ALRuNPj1GB7aae3CmRY3G1gpbIBIJGcHrWZr+o3fhrTNF0vTVjnncNCqi3LFkigY/Iing7hGAOnPbium0x7qTTbZ76KOK7aJDOkZyqvgbgD3AOas0UUUUUUUUUDrS0w/dOK8J8Y6FrmvX/jHxONG1iY2+oafaQaa0bp/amlwczxhSQHWQzTnaeuxfXnavtFvfEfjXW9G13TtVi0KaK0h0r7PaFYRZeWrSqJMgQOZMhxgPtVQuKdpdnrNx4Z1nUdQ0HU7nxlaXl7e2/nI0cRljMotEicEK8OwphQSCSSwDE1k21lrttfQ61ZeHNZkm0bwhcT2c1zCwuL7U7gjzDICc+YPKACnkCU4wuK3vBnh67svFnhLTpdNvF03w94ZIiuJIsK15MypIS2fvhI2yOv70+9dL4y0LV9T1GKawt9PkjSIKTcahdQNnJ7QnaRz1PP5CrOh6Tq9p4cuLF7i30+8kdmjnt5ZLoR5x837/JJ4PB4qt/YHi3/ofLr/AMFNv/8AE0v/AAj/AIt/6H24/wDBVbf4VC3hXxI93Hdv41drmJGSOU6Pal0VsbgDtyAcDPrgVKPD/i3/AKH25/8ABVbf4Uf8I/4uOQPHtyD76Tbf4V1VqkkduiTSmaRVAeQqF3nHJwOBn2qWiiiiiiigdaWm44xmk2ijbzmjaKQoPb8qXaM+lOpr5xxXj+m+EPDmtfFnxFp50yKTTNJ0lbS4Dcma8vGM0rsTyXWMRYbqPMOMV63bQR21tFbwriOJAiAknAAwOevauGk+IMK+M4tN+wa39jNg8zL/AGJc7/MEyICPk+7gnnp0qj+0DY2t34OLJCJdXvXj0jSWdd3ky3cixNIo/vKhZs9QE7V2nhvwxonh6Sd9HsUtftEcUcuwnDiJSqkj1weT1PfNbVFFFFFFFFA60tJRRRRRRTXGRjNcxYaPpHgqz1/Wo7i72XckmpX0lxcb90gQAsCfu/KigDoABgCjwBJ4muLA3HiGYMJIYDErQqkgfywZSQvABc4A6/KT3AG22m2h1ldXKN9rS3a2DbjjyywYjHTqo5rO8S+F9P1/UdJvr6S8EmkXX2y0SKcqizBWUOy9GO1mHPqarW7+KH8aMGYx6GruFXy0+ZRCmDu+8MyM2P8AcOeorqKKKKKKKKKB1paSiiiiiiikZVYEMAQeoPNKFAGBwOwpCQOpxRmkDAnFOoooopNw9z+FAINLRQOtLSUlLRRRSE4Ga4XxT8RotDu/EsC6HeXqeHdPh1C9ljmjVPKfeSoLEfvAsbNt75HrVlPHcc2t6hp9ro15PFp09sl5debGkUEUsPnGV9zAgIm3cOvzDAIzimnxQ0fZ9rls7xNMaw+2rdBQ3ytIiQoyDlXmLgxr95hnIFO8X+KbuLT2sJ9L1rS7m7vbTT7e4tXhL77g/ejZ8qTGAd4wQBnBPadPiBaPfa/DHp1wYdAedL+V5EQwmOFZgWQncEdW+RuQdpPAqlofjWODRbWCKLVNV1BdH/tq7W6aNZLeCTc6JK6gJvIDKqgc7CTgDJg1P4u6Tb6dPf2elXt7bxeHrfXwVkjjJhmJ2IQx+VyFY4PU4AyTXcPrNhHqNnps9xHDfXkLzQWztiR1Tbv4/wBncM/Wuek8cqNe1bTYdFu5odIvIYL+8E0SwwRvD5zTMSw+VF2gj72W4BAJqrH8TtJ2G6lsrxLE2S3aTqodv3kiJBEyDlZZd4KJ1IzkLWjJ4weHUY9KutCvYNSuJlis4GdStxmPzHYMDjbGOHboCQBuJFcvq3ihvGNn4Ws9MivdP/tTxC6E+aVd7Wyd2mcMh+45iVBnqJBxzW58NZ7jU9c8Xa89xcPaXGrNZWUbyMY1jtUETsoJwN0olzjrgV2560UDrS0wHKhgQQRnIrzXx/4zn0v4h2OijxFb6Nplvo82o6pNJbLIeZEjgVCc4LN5hIxyFGK7Xw3DrFtayrrGpLqEjTs8MgthCyxEDajAHBYc5PGfSq114z8L2txJb3Gu2UUsTFJFZ+VI6g8VP4gGq6jo6L4e1SCwknKkXjQCYxoRnKIcKWPAG7gZzg9Kx/hXrGu6p4du38RSW01xZalc2Ud9BH5Ud7FFIVWcLkhc4IIBIypxxXXsflJ549BmvMvC3hG61631y+8TxXcEOsa7JeT6bLEFMkMO2O2SQ85QpEjlRwS2CcZB6a28GaWmh+ItKma4ni8Qz3Ut/IzbXbz12FQQOAqbVX0Cis3/AIV+ZPBkHh268Q380trLbzWd4kEUbwyW7q0TlFXa5yg3bh8w9K0dU8LNqd1oN5faveST6RePeArGirK7QvFyuPlADkjHPvWTq/w3tNU0/VYbzV79r3U9ITSbi+RUWR4VdmywxhmO4jJ4wSABk5t6l4Bsby61p1v72CHXLaC11NI2CtMkSsoCsBlNyMVbb26bTzUGpfDXR7uLVkS5uLddSu7GZxFGgCQ2hTyrdRjHl/ITg/32ruPLU4JXJAxk9feuXh8EaSPDfiHQp5LieHxBNdzX8pIWRzcDacEDjam1V9AoqhJ4Ae58JWmiXviC+nuLG4trq0vVt4Y2ilt2DRsUVdjHI+bI59qt6j4Plvtc03WZNd1CO9tLS5tJWiRAs0UxQsAMfuyGjQgrzwRnnNV/C3w+s9AuPDktvqV5KugaVJpkEbRoA6uyM0jYHDfu1HHXvmtrwJ4ei8K+GLTQYLu4vEtg376cKHcs7MSdoAySx579TW71paB1paijjCQLGmcKoA/DiuQ8N+F7+18XeK9d1o2FwustbxW8ce4+VbwxlVjYMMH5mdsju2O1a3hfU7jUJ9ZjneNxZ6nJbR7BjCBEYBvU/Maq3vhFrm6nn/4SfxND5rl9kOobUTPZRt4Ap/jCx8TSeHksvC15YR3hKpLNqJkbMWPmwY8NvPTd2yT1xVbRfD1/e+EJ9B8Z2egXNtMvkfY7CCRbYQADCEOSScg56Dp75v694S8O65drd6vpUF1LHH5au5bIXOQOCPU1n/8ACufA4/5l+0H4v/8AFUf8K68Ef9AC0/N//iqP+FdeB/8AoAWn5v8A/FVV/wCEL+HP9rHSP7K077eLcXJt/Mbf5RYqHxu6bgRn1pNQ8FfDqwEDXuladbi5nS3hMkjL5krnCoPm5YnoKt/8K68Ef9C/a/m//wAVS/8ACufBB/5l+0/N/wD4qj/hXPgj/oX7T83/APiqT/hXPgjv4ftPzf8A+KoPw78DBcnQLTH1f/4qj/hXPgf/AKF+0/N//iqP+FdeCDx/wj9p+b//ABVc6mnfCiSGKRdHjKy6u2jJ/o8+TdqxUp9AVb5vu8HmvTYUSKJI4wFRAFUDsB0p9A60tIOlIRmoobaCFpGhijjMr75NqAbm9TjqfepqKKwvH+tReHvBOta3MzKtjYyz/K2CSqnaAfUnA/GvJtT1zxdoOkzSNr9/qlxp3hTy9UlXYY21aYxrapFhcCTcz7sZ+VkJHIrf8Q6prnhbVvDuj3/iKWeXWwRcXFzLFDFCba3BeKJiow8zsCWYkgK5UDjEPh/VNavNY1TwrqXi4W82n2Ec8NyirvuJbppWjZM4MkUICIO7sCW7Co5Nd1y+TxumkeI4jqEV8mmaPDcOiB5bWFJLpQQMoZD5i55243AYFLF4uuZdQ8JPZXurSxTaTe+IrqyuQv2iWAKPJtiMcsryYBHOIuSc1Vs/GOtW8HhnXLvVTdpLo93rfiOOIDyLW1NvvhRP7jCQqikkswWQnPa38LtS8U3PirRdL17W7qe7t/C0d7q1tK0eDcXEuYhgKPmRUlBI4xtHudnxLeeMU+IGhR29hopjK33kq2pTKJFCR4LgQnBHXA3dfxq5421LWD4k8G6Fpt09pe3t491f+SwZBawREyg7hkqZHiUdDz2rl01PXrvxBrPge38WyW91pS21rDe3ksa3UzzL5rXRRVHmgBgiIAEJV9x4q1pniy61Pw3qfjCbW5LZ9MvL2U6RAEL/AGa0MimCRTyJJNgcuem5QoHU5Vp46urbVbfU7rxGt3bad4Un8Q6wkDr9mlZ8CGKI8/Im2XkHn5Sxyal8EWiDXvAPhye6jln0rR7jxBencG828uCUDD1G6S6Oen3favZl+7TqB1paTBowaMGjBowaMGue8b+Hh4o0aPSZ7pre2+1QTzqIlcTrFIsgjYH+Fioz3IyO9bMVrbrF5SwRKm7ftVABuznOPXPP1pbuytbuMR3VtDOgYOFlQOAw6HB7iiSztpLqO6e3ha4jBCSsgLqD1APUfhTWsLNgwa0gIZzIwManLHgseOvvUn2aHzVl8pPMRdivtG4L6A9ccDimJZWscbxpbQqkn31WMAN9R3qQQRCVpRGgkZQrNtGSB0BPpyacY1LhyoLLnBI5GaQwxmQSFF3gFQ2BkA9Rn04qJrG1a7W8a2hNyqbFmKDeF9A3UCljsrWOeWeO2hSWb/WusYDP/vHqfxpkem2Mcflx2VuqGPytoiUDZ/dxj7vJ46VItrAsgkWGNXCCMMFAIUdFz6e1SgYGBS4NA60tFFFFFFFFFFFFFFFFFFFFFFFFf//Z"}}},{"metadata":{"trusted":true},"cell_type":"code","source":"f, ax = plt.subplots(figsize = (4,6))\nax.set_title('Number Scores')\nsns.heatmap(scores_frame, annot=True, fmt=\".3f\", linewidths=0.5, cmap=\"PuBu\", cbar=True, ax=ax)\nbottom, top = ax.get_ylim()\nplt.ylabel(\"\")\nax.set_ylim(bottom + 0.5, top - 0.5)\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"### **Evaluate with Another Dataset** <a id=\"275\"></a>\n<mark>[Return Contents](#0)"},{"metadata":{"trusted":true},"cell_type":"code","source":"raw_dig = pd.read_csv(\"../input/Kannada-MNIST/Dig-MNIST.csv\")\nraw_dig.head()\nx_dig = raw_dig.iloc[:, 1:].values.astype('float32') / 255\ny_dig = raw_dig.iloc[:, 0].values\n\nx_dig = x_dig.reshape(-1,28,28,1)\ny_dig = to_categorical(y_dig)\nmodel.evaluate(x_dig, y_dig, verbose=2)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"### **Submit for Competition** <a id=\"276\"></a>\n<mark>[Return Contents](#0)"},{"metadata":{"trusted":true},"cell_type":"code","source":"sample_sub=pd.read_csv('../input/Kannada-MNIST/sample_submission.csv')\nraw_test_id=raw_test.id\nraw_test=raw_test.drop(\"id\",axis=\"columns\")\nraw_test=raw_test / 255\ntest=raw_test.values.reshape(-1,28,28,1)\ntest.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sub=model.predict(test)     ##making prediction\nsub=np.argmax(sub,axis=1) ##changing the prediction intro labels\n\nsample_sub['label']=sub\nsample_sub.to_csv('submission.csv',index=False)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# **Conclusion** <a id=\"276\"></a>\n<mark>[Return Contents](#0)\n<font color='green'>\n* Please do not hesitate to comment and ask questions.\n* If you found it useful, I would appreciate it if you upvote    \n    \n ![rsz_1smile.jpg](attachment:rsz_1smile.jpg)\n","attachments":{"rsz_1smile.jpg":{"image/jpeg":"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"}}}],"metadata":{"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"language_info":{"codemirror_mode":{"name":"ipython","version":3},"file_extension":".py","mimetype":"text/x-python","name":"python","nbconvert_exporter":"python","pygments_lexer":"ipython3","version":"3.6.5"}},"nbformat":4,"nbformat_minor":1}