diff --git a/contributors.md b/contributors.md new file mode 100644 index 0000000..401933b --- /dev/null +++ b/contributors.md @@ -0,0 +1,6 @@ +# Contributors +Here's a list of people who have made code contributions to this project: +* [@EricAlcaide](https://github.com/EricAlcaide) +* [@McMenemy](https://github.com/McMenemy) +* [@roberCO](https://github.com/roberCO) +* [@pabloAMC](https://github.com/PabloAMC) diff --git a/models/angles/predicting_angles.ipynb b/models/angles/predicting_angles.ipynb index f1fcc70..0b40e8f 100644 --- a/models/angles/predicting_angles.ipynb +++ b/models/angles/predicting_angles.ipynb @@ -2,17 +2,9 @@ "cells": [ { "cell_type": "code", - "execution_count": 1, + "execution_count": 44, "metadata": {}, - "outputs": [ - { - "name": "stderr", - "output_type": "stream", - "text": [ - "Using TensorFlow backend.\n" - ] - } - ], + "outputs": [], "source": [ "# Import libraries\n", "import numpy as np\n", @@ -43,20 +35,18 @@ }, { "cell_type": "code", - "execution_count": 2, + "execution_count": 45, "metadata": { "scrolled": true }, "outputs": [ { + "output_type": "execute_result", "data": { - "text/plain": [ - "(43001, 2)" - ] + "text/plain": "(43001, 2)" }, - "execution_count": 2, "metadata": {}, - "output_type": "execute_result" + "execution_count": 45 } ], "source": [ @@ -68,15 +58,13 @@ }, { "cell_type": "code", - "execution_count": 3, + "execution_count": 46, "metadata": {}, "outputs": [ { - "name": "stdout", "output_type": "stream", - "text": [ - "(43001, 4)\n" - ] + "name": "stdout", + "text": "(43001, 4)\n" } ], "source": [ @@ -92,7 +80,7 @@ }, { "cell_type": "code", - "execution_count": 4, + "execution_count": 47, "metadata": {}, "outputs": [], "source": [ @@ -121,25 +109,21 @@ }, { "cell_type": "code", - "execution_count": 6, + "execution_count": 48, "metadata": {}, "outputs": [ { - "name": "stdout", "output_type": "stream", - "text": [ - "(43001, 34, 22) (43001, 34, 21)\n" - ] + "name": "stdout", + "text": "(43001, 34, 22) (43001, 34, 21)\n" }, { + "output_type": "execute_result", "data": { - "text/plain": [ - "(43001, 34, 42)" - ] + "text/plain": "(43001, 34, 42)" }, - "execution_count": 6, "metadata": {}, - "output_type": "execute_result" + "execution_count": 48 } ], "source": [ @@ -155,20 +139,19 @@ }, { "cell_type": "code", - "execution_count": 7, + "execution_count": 49, "metadata": {}, "outputs": [ { + "output_type": "display_data", "data": { - "image/png": "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\n", - "text/plain": [ - "
" - ] + "text/plain": "
", + "image/svg+xml": "\n\n\n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n\n", + "image/png": "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\n" }, "metadata": { "needs_background": "light" - }, - "output_type": "display_data" + } } ], "source": [ @@ -181,18 +164,16 @@ }, { "cell_type": "code", - "execution_count": 8, + "execution_count": 50, "metadata": {}, "outputs": [ { + "output_type": "execute_result", "data": { - "text/plain": [ - "\" WE DON'T PREPROCESS INPUTS SINCE THEY'RE IN 0-1 RANGE\"" - ] + "text/plain": "\" WE DON'T PREPROCESS INPUTS SINCE THEY'RE IN 0-1 RANGE\"" }, - "execution_count": 8, "metadata": {}, - "output_type": "execute_result" + "execution_count": 50 } ], "source": [ @@ -215,173 +196,19 @@ }, { "cell_type": "code", - "execution_count": 9, + "execution_count": 51, "metadata": {}, "outputs": [ { - "name": "stdout", "output_type": "stream", - "text": [ - "__________________________________________________________________________________________________\n", - "Layer (type) Output Shape Param # Connected to \n", - "==================================================================================================\n", - "input_1 (InputLayer) (None, 34, 42) 0 \n", - "__________________________________________________________________________________________________\n", - "conv1d_1 (Conv1D) (None, 34, 16) 2032 input_1[0][0] \n", - "__________________________________________________________________________________________________\n", - "batch_normalization_1 (BatchNor (None, 34, 16) 64 conv1d_1[0][0] \n", - "__________________________________________________________________________________________________\n", - "activation_1 (Activation) (None, 34, 16) 0 batch_normalization_1[0][0] \n", - "__________________________________________________________________________________________________\n", - "conv1d_2 (Conv1D) (None, 34, 16) 272 activation_1[0][0] \n", - "__________________________________________________________________________________________________\n", - "conv1d_3 (Conv1D) (None, 34, 16) 784 conv1d_2[0][0] \n", - "__________________________________________________________________________________________________\n", - "batch_normalization_2 (BatchNor (None, 34, 16) 64 conv1d_3[0][0] \n", - "__________________________________________________________________________________________________\n", - "activation_2 (Activation) (None, 34, 16) 0 batch_normalization_2[0][0] \n", - "__________________________________________________________________________________________________\n", - "conv1d_4 (Conv1D) (None, 34, 64) 1088 activation_2[0][0] \n", - "__________________________________________________________________________________________________\n", - "batch_normalization_3 (BatchNor (None, 34, 64) 256 conv1d_4[0][0] \n", - "__________________________________________________________________________________________________\n", - "conv1d_5 (Conv1D) (None, 34, 64) 1088 activation_1[0][0] \n", - "__________________________________________________________________________________________________\n", - "activation_3 (Activation) (None, 34, 64) 0 batch_normalization_3[0][0] \n", - "__________________________________________________________________________________________________\n", - "add_1 (Add) (None, 34, 64) 0 conv1d_5[0][0] \n", - " activation_3[0][0] \n", - "__________________________________________________________________________________________________\n", - "conv1d_6 (Conv1D) (None, 34, 16) 1040 add_1[0][0] \n", - "__________________________________________________________________________________________________\n", - "batch_normalization_4 (BatchNor (None, 34, 16) 64 conv1d_6[0][0] \n", - "__________________________________________________________________________________________________\n", - "activation_4 (Activation) (None, 34, 16) 0 batch_normalization_4[0][0] \n", - "__________________________________________________________________________________________________\n", - "conv1d_7 (Conv1D) (None, 34, 16) 784 activation_4[0][0] \n", - "__________________________________________________________________________________________________\n", - "batch_normalization_5 (BatchNor (None, 34, 16) 64 conv1d_7[0][0] \n", - "__________________________________________________________________________________________________\n", - "activation_5 (Activation) (None, 34, 16) 0 batch_normalization_5[0][0] \n", - "__________________________________________________________________________________________________\n", - "conv1d_8 (Conv1D) (None, 34, 64) 1088 activation_5[0][0] \n", - "__________________________________________________________________________________________________\n", - "batch_normalization_6 (BatchNor (None, 34, 64) 256 conv1d_8[0][0] \n", - "__________________________________________________________________________________________________\n", - "activation_6 (Activation) (None, 34, 64) 0 batch_normalization_6[0][0] \n", - "__________________________________________________________________________________________________\n", - "add_2 (Add) (None, 34, 64) 0 add_1[0][0] \n", - " activation_6[0][0] \n", - "__________________________________________________________________________________________________\n", - "conv1d_9 (Conv1D) (None, 17, 64) 4160 add_2[0][0] \n", - "__________________________________________________________________________________________________\n", - "batch_normalization_7 (BatchNor (None, 17, 64) 256 conv1d_9[0][0] \n", - "__________________________________________________________________________________________________\n", - "activation_7 (Activation) (None, 17, 64) 0 batch_normalization_7[0][0] \n", - "__________________________________________________________________________________________________\n", - "conv1d_10 (Conv1D) (None, 17, 64) 12352 activation_7[0][0] \n", - "__________________________________________________________________________________________________\n", - "batch_normalization_8 (BatchNor (None, 17, 64) 256 conv1d_10[0][0] \n", - "__________________________________________________________________________________________________\n", - "activation_8 (Activation) (None, 17, 64) 0 batch_normalization_8[0][0] \n", - "__________________________________________________________________________________________________\n", - "conv1d_11 (Conv1D) (None, 17, 128) 8320 activation_8[0][0] \n", - "__________________________________________________________________________________________________\n", - "batch_normalization_9 (BatchNor (None, 17, 128) 512 conv1d_11[0][0] \n", - "__________________________________________________________________________________________________\n", - "conv1d_12 (Conv1D) (None, 17, 128) 8320 add_2[0][0] \n", - "__________________________________________________________________________________________________\n", - "activation_9 (Activation) (None, 17, 128) 0 batch_normalization_9[0][0] \n", - "__________________________________________________________________________________________________\n", - "add_3 (Add) (None, 17, 128) 0 conv1d_12[0][0] \n", - " activation_9[0][0] \n", - "__________________________________________________________________________________________________\n", - "conv1d_13 (Conv1D) (None, 17, 64) 8256 add_3[0][0] \n", - "__________________________________________________________________________________________________\n", - "batch_normalization_10 (BatchNo (None, 17, 64) 256 conv1d_13[0][0] \n", - "__________________________________________________________________________________________________\n", - "activation_10 (Activation) (None, 17, 64) 0 batch_normalization_10[0][0] \n", - "__________________________________________________________________________________________________\n", - "conv1d_14 (Conv1D) (None, 17, 64) 12352 activation_10[0][0] \n", - "__________________________________________________________________________________________________\n", - "batch_normalization_11 (BatchNo (None, 17, 64) 256 conv1d_14[0][0] \n", - "__________________________________________________________________________________________________\n", - "activation_11 (Activation) (None, 17, 64) 0 batch_normalization_11[0][0] \n", - "__________________________________________________________________________________________________\n", - "conv1d_15 (Conv1D) (None, 17, 128) 8320 activation_11[0][0] \n", - "__________________________________________________________________________________________________\n", - "batch_normalization_12 (BatchNo (None, 17, 128) 512 conv1d_15[0][0] \n", - "__________________________________________________________________________________________________\n", - "activation_12 (Activation) (None, 17, 128) 0 batch_normalization_12[0][0] \n", - "__________________________________________________________________________________________________\n", - "add_4 (Add) (None, 17, 128) 0 add_3[0][0] \n", - " activation_12[0][0] \n", - "__________________________________________________________________________________________________\n", - "conv1d_16 (Conv1D) (None, 9, 128) 16512 add_4[0][0] \n", - "__________________________________________________________________________________________________\n", - "batch_normalization_13 (BatchNo (None, 9, 128) 512 conv1d_16[0][0] \n", - "__________________________________________________________________________________________________\n", - "activation_13 (Activation) (None, 9, 128) 0 batch_normalization_13[0][0] \n", - "__________________________________________________________________________________________________\n", - "conv1d_17 (Conv1D) (None, 9, 128) 49280 activation_13[0][0] \n", - "__________________________________________________________________________________________________\n", - "batch_normalization_14 (BatchNo (None, 9, 128) 512 conv1d_17[0][0] \n", - "__________________________________________________________________________________________________\n", - "activation_14 (Activation) (None, 9, 128) 0 batch_normalization_14[0][0] \n", - "__________________________________________________________________________________________________\n", - "conv1d_18 (Conv1D) (None, 9, 256) 33024 activation_14[0][0] \n", - "__________________________________________________________________________________________________\n", - "batch_normalization_15 (BatchNo (None, 9, 256) 1024 conv1d_18[0][0] \n", - "__________________________________________________________________________________________________\n", - "conv1d_19 (Conv1D) (None, 9, 256) 33024 add_4[0][0] \n", - "__________________________________________________________________________________________________\n", - "activation_15 (Activation) (None, 9, 256) 0 batch_normalization_15[0][0] \n", - "__________________________________________________________________________________________________\n", - "add_5 (Add) (None, 9, 256) 0 conv1d_19[0][0] \n", - " activation_15[0][0] \n", - "__________________________________________________________________________________________________\n", - "conv1d_20 (Conv1D) (None, 9, 128) 32896 add_5[0][0] \n", - "__________________________________________________________________________________________________\n", - "batch_normalization_16 (BatchNo (None, 9, 128) 512 conv1d_20[0][0] \n", - "__________________________________________________________________________________________________\n", - "activation_16 (Activation) (None, 9, 128) 0 batch_normalization_16[0][0] \n", - "__________________________________________________________________________________________________\n", - "conv1d_21 (Conv1D) (None, 9, 128) 49280 activation_16[0][0] \n", - "__________________________________________________________________________________________________\n", - "batch_normalization_17 (BatchNo (None, 9, 128) 512 conv1d_21[0][0] \n", - "__________________________________________________________________________________________________\n", - "activation_17 (Activation) (None, 9, 128) 0 batch_normalization_17[0][0] \n", - "__________________________________________________________________________________________________\n", - "conv1d_22 (Conv1D) (None, 9, 256) 33024 activation_17[0][0] \n", - "__________________________________________________________________________________________________\n", - "batch_normalization_18 (BatchNo (None, 9, 256) 1024 conv1d_22[0][0] \n", - "__________________________________________________________________________________________________\n", - "activation_18 (Activation) (None, 9, 256) 0 batch_normalization_18[0][0] \n", - "__________________________________________________________________________________________________\n", - "add_6 (Add) (None, 9, 256) 0 add_5[0][0] \n", - " activation_18[0][0] \n", - "__________________________________________________________________________________________________\n", - "batch_normalization_19 (BatchNo (None, 9, 256) 1024 add_6[0][0] \n", - "__________________________________________________________________________________________________\n", - "activation_19 (Activation) (None, 9, 256) 0 batch_normalization_19[0][0] \n", - "__________________________________________________________________________________________________\n", - "average_pooling1d_1 (AveragePoo (None, 3, 256) 0 activation_19[0][0] \n", - "__________________________________________________________________________________________________\n", - "flatten_1 (Flatten) (None, 768) 0 average_pooling1d_1[0][0] \n", - "__________________________________________________________________________________________________\n", - "dense_1 (Dense) (None, 4) 3076 flatten_1[0][0] \n", - "==================================================================================================\n", - "Total params: 328,308\n", - "Trainable params: 324,340\n", - "Non-trainable params: 3,968\n", - "__________________________________________________________________________________________________\n" - ] + "name": "stdout", + "text": "Model: \"model_3\"\n__________________________________________________________________________________________________\nLayer (type) Output Shape Param # Connected to \n==================================================================================================\ninput_3 (InputLayer) (None, 34, 42) 0 \n__________________________________________________________________________________________________\nconv1d_45 (Conv1D) (None, 34, 16) 2032 input_3[0][0] \n__________________________________________________________________________________________________\nbatch_normalization_39 (BatchNo (None, 34, 16) 64 conv1d_45[0][0] \n__________________________________________________________________________________________________\nactivation_39 (Activation) (None, 34, 16) 0 batch_normalization_39[0][0] \n__________________________________________________________________________________________________\nconv1d_46 (Conv1D) (None, 34, 16) 272 activation_39[0][0] \n__________________________________________________________________________________________________\nconv1d_47 (Conv1D) (None, 34, 16) 784 conv1d_46[0][0] \n__________________________________________________________________________________________________\nbatch_normalization_40 (BatchNo (None, 34, 16) 64 conv1d_47[0][0] \n__________________________________________________________________________________________________\nactivation_40 (Activation) (None, 34, 16) 0 batch_normalization_40[0][0] \n__________________________________________________________________________________________________\nconv1d_48 (Conv1D) (None, 34, 64) 1088 activation_40[0][0] \n__________________________________________________________________________________________________\nbatch_normalization_41 (BatchNo (None, 34, 64) 256 conv1d_48[0][0] \n__________________________________________________________________________________________________\nconv1d_49 (Conv1D) (None, 34, 64) 1088 activation_39[0][0] \n__________________________________________________________________________________________________\nactivation_41 (Activation) (None, 34, 64) 0 batch_normalization_41[0][0] \n__________________________________________________________________________________________________\nadd_13 (Add) (None, 34, 64) 0 conv1d_49[0][0] \n activation_41[0][0] \n__________________________________________________________________________________________________\nconv1d_50 (Conv1D) (None, 34, 16) 1040 add_13[0][0] \n__________________________________________________________________________________________________\nbatch_normalization_42 (BatchNo (None, 34, 16) 64 conv1d_50[0][0] \n__________________________________________________________________________________________________\nactivation_42 (Activation) (None, 34, 16) 0 batch_normalization_42[0][0] \n__________________________________________________________________________________________________\nconv1d_51 (Conv1D) (None, 34, 16) 784 activation_42[0][0] \n__________________________________________________________________________________________________\nbatch_normalization_43 (BatchNo (None, 34, 16) 64 conv1d_51[0][0] \n__________________________________________________________________________________________________\nactivation_43 (Activation) (None, 34, 16) 0 batch_normalization_43[0][0] \n__________________________________________________________________________________________________\nconv1d_52 (Conv1D) (None, 34, 64) 1088 activation_43[0][0] \n__________________________________________________________________________________________________\nbatch_normalization_44 (BatchNo (None, 34, 64) 256 conv1d_52[0][0] \n__________________________________________________________________________________________________\nactivation_44 (Activation) (None, 34, 64) 0 batch_normalization_44[0][0] \n__________________________________________________________________________________________________\nadd_14 (Add) (None, 34, 64) 0 add_13[0][0] \n activation_44[0][0] \n__________________________________________________________________________________________________\nconv1d_53 (Conv1D) (None, 17, 64) 4160 add_14[0][0] \n__________________________________________________________________________________________________\nbatch_normalization_45 (BatchNo (None, 17, 64) 256 conv1d_53[0][0] \n__________________________________________________________________________________________________\nactivation_45 (Activation) (None, 17, 64) 0 batch_normalization_45[0][0] \n__________________________________________________________________________________________________\nconv1d_54 (Conv1D) (None, 17, 64) 12352 activation_45[0][0] \n__________________________________________________________________________________________________\nbatch_normalization_46 (BatchNo (None, 17, 64) 256 conv1d_54[0][0] \n__________________________________________________________________________________________________\nactivation_46 (Activation) (None, 17, 64) 0 batch_normalization_46[0][0] \n__________________________________________________________________________________________________\nconv1d_55 (Conv1D) (None, 17, 128) 8320 activation_46[0][0] \n__________________________________________________________________________________________________\nbatch_normalization_47 (BatchNo (None, 17, 128) 512 conv1d_55[0][0] \n__________________________________________________________________________________________________\nconv1d_56 (Conv1D) (None, 17, 128) 8320 add_14[0][0] \n__________________________________________________________________________________________________\nactivation_47 (Activation) (None, 17, 128) 0 batch_normalization_47[0][0] \n__________________________________________________________________________________________________\nadd_15 (Add) (None, 17, 128) 0 conv1d_56[0][0] \n activation_47[0][0] \n__________________________________________________________________________________________________\nconv1d_57 (Conv1D) (None, 17, 64) 8256 add_15[0][0] \n__________________________________________________________________________________________________\nbatch_normalization_48 (BatchNo (None, 17, 64) 256 conv1d_57[0][0] \n__________________________________________________________________________________________________\nactivation_48 (Activation) (None, 17, 64) 0 batch_normalization_48[0][0] \n__________________________________________________________________________________________________\nconv1d_58 (Conv1D) (None, 17, 64) 12352 activation_48[0][0] \n__________________________________________________________________________________________________\nbatch_normalization_49 (BatchNo (None, 17, 64) 256 conv1d_58[0][0] \n__________________________________________________________________________________________________\nactivation_49 (Activation) (None, 17, 64) 0 batch_normalization_49[0][0] \n__________________________________________________________________________________________________\nconv1d_59 (Conv1D) (None, 17, 128) 8320 activation_49[0][0] \n__________________________________________________________________________________________________\nbatch_normalization_50 (BatchNo (None, 17, 128) 512 conv1d_59[0][0] \n__________________________________________________________________________________________________\nactivation_50 (Activation) (None, 17, 128) 0 batch_normalization_50[0][0] \n__________________________________________________________________________________________________\nadd_16 (Add) (None, 17, 128) 0 add_15[0][0] \n activation_50[0][0] \n__________________________________________________________________________________________________\nconv1d_60 (Conv1D) (None, 9, 128) 16512 add_16[0][0] \n__________________________________________________________________________________________________\nbatch_normalization_51 (BatchNo (None, 9, 128) 512 conv1d_60[0][0] \n__________________________________________________________________________________________________\nactivation_51 (Activation) (None, 9, 128) 0 batch_normalization_51[0][0] \n__________________________________________________________________________________________________\nconv1d_61 (Conv1D) (None, 9, 128) 49280 activation_51[0][0] \n__________________________________________________________________________________________________\nbatch_normalization_52 (BatchNo (None, 9, 128) 512 conv1d_61[0][0] \n__________________________________________________________________________________________________\nactivation_52 (Activation) (None, 9, 128) 0 batch_normalization_52[0][0] \n__________________________________________________________________________________________________\nconv1d_62 (Conv1D) (None, 9, 256) 33024 activation_52[0][0] \n__________________________________________________________________________________________________\nbatch_normalization_53 (BatchNo (None, 9, 256) 1024 conv1d_62[0][0] \n__________________________________________________________________________________________________\nconv1d_63 (Conv1D) (None, 9, 256) 33024 add_16[0][0] \n__________________________________________________________________________________________________\nactivation_53 (Activation) (None, 9, 256) 0 batch_normalization_53[0][0] \n__________________________________________________________________________________________________\nadd_17 (Add) (None, 9, 256) 0 conv1d_63[0][0] \n activation_53[0][0] \n__________________________________________________________________________________________________\nconv1d_64 (Conv1D) (None, 9, 128) 32896 add_17[0][0] \n__________________________________________________________________________________________________\nbatch_normalization_54 (BatchNo (None, 9, 128) 512 conv1d_64[0][0] \n__________________________________________________________________________________________________\nactivation_54 (Activation) (None, 9, 128) 0 batch_normalization_54[0][0] \n__________________________________________________________________________________________________\nconv1d_65 (Conv1D) (None, 9, 128) 49280 activation_54[0][0] \n__________________________________________________________________________________________________\nbatch_normalization_55 (BatchNo (None, 9, 128) 512 conv1d_65[0][0] \n__________________________________________________________________________________________________\nactivation_55 (Activation) (None, 9, 128) 0 batch_normalization_55[0][0] \n__________________________________________________________________________________________________\nconv1d_66 (Conv1D) (None, 9, 256) 33024 activation_55[0][0] \n__________________________________________________________________________________________________\nbatch_normalization_56 (BatchNo (None, 9, 256) 1024 conv1d_66[0][0] \n__________________________________________________________________________________________________\nactivation_56 (Activation) (None, 9, 256) 0 batch_normalization_56[0][0] \n__________________________________________________________________________________________________\nadd_18 (Add) (None, 9, 256) 0 add_17[0][0] \n activation_56[0][0] \n__________________________________________________________________________________________________\nbatch_normalization_57 (BatchNo (None, 9, 256) 1024 add_18[0][0] \n__________________________________________________________________________________________________\nactivation_57 (Activation) (None, 9, 256) 0 batch_normalization_57[0][0] \n__________________________________________________________________________________________________\naverage_pooling1d_3 (AveragePoo (None, 3, 256) 0 activation_57[0][0] \n__________________________________________________________________________________________________\nflatten_3 (Flatten) (None, 768) 0 average_pooling1d_3[0][0] \n__________________________________________________________________________________________________\ndense_3 (Dense) (None, 4) 3076 flatten_3[0][0] \n==================================================================================================\nTotal params: 328,308\nTrainable params: 324,340\nNon-trainable params: 3,968\n__________________________________________________________________________________________________\n" } ], "source": [ "# Using AMSGrad optimizer for speed \n", "kernel_size, filters = 3, 16\n", - "adam = keras.optimizers.Adam(lr=0.001, beta_1=0.9, beta_2=0.999, epsilon=None, decay=0.0, amsgrad=True)\n", + "adam = keras.optimizers.Adam(lr=0.001, beta_1=0.9, beta_2=0.999, decay=0.0, amsgrad=True)\n", "# Create model\n", "model = resnet_v2(input_shape=(17*2,42), depth=20, num_classes=4, conv_first=True)\n", "model.compile(optimizer=adam, loss=custom_mse_mae,\n", @@ -398,7 +225,7 @@ }, { "cell_type": "code", - "execution_count": 10, + "execution_count": 52, "metadata": {}, "outputs": [], "source": [ @@ -410,31 +237,18 @@ }, { "cell_type": "code", - "execution_count": 11, + "execution_count": 53, "metadata": {}, "outputs": [ { - "name": "stdout", "output_type": "stream", - "text": [ - "Train on 38700 samples, validate on 4301 samples\n", - "Epoch 1/5\n", - "38700/38700 [==============================] - 74s 2ms/step - loss: 1.1764 - mean_absolute_error: 0.4641 - mean_squared_error: 0.3590 - val_loss: 1.1334 - val_mean_absolute_error: 0.4706 - val_mean_squared_error: 0.3994\n", - "Epoch 2/5\n", - "38700/38700 [==============================] - 66s 2ms/step - loss: 0.9392 - mean_absolute_error: 0.4207 - mean_squared_error: 0.3089 - val_loss: 0.9370 - val_mean_absolute_error: 0.4317 - val_mean_squared_error: 0.3372\n", - "Epoch 3/5\n", - "38700/38700 [==============================] - 66s 2ms/step - loss: 0.8221 - mean_absolute_error: 0.3955 - mean_squared_error: 0.2831 - val_loss: 0.8474 - val_mean_absolute_error: 0.4180 - val_mean_squared_error: 0.3059\n", - "Epoch 4/5\n", - "38700/38700 [==============================] - 66s 2ms/step - loss: 0.7630 - mean_absolute_error: 0.3815 - mean_squared_error: 0.2709 - val_loss: 0.7937 - val_mean_absolute_error: 0.4066 - val_mean_squared_error: 0.2880\n", - "Epoch 5/5\n", - "38700/38700 [==============================] - 67s 2ms/step - loss: 0.7271 - mean_absolute_error: 0.3722 - mean_squared_error: 0.2632 - val_loss: 0.7797 - val_mean_absolute_error: 0.4082 - val_mean_squared_error: 0.2865\n" - ] + "name": "stdout", + "text": "Train on 38700 samples, validate on 4301 samples\nEpoch 1/5\n38700/38700 [==============================] - 75s 2ms/step - loss: 1.1865 - mean_absolute_error: 0.4670 - mean_squared_error: 0.3581 - val_loss: 1.0533 - val_mean_absolute_error: 0.4458 - val_mean_squared_error: 0.3290\nEpoch 2/5\n38700/38700 [==============================] - 72s 2ms/step - loss: 0.9451 - mean_absolute_error: 0.4167 - mean_squared_error: 0.3032 - val_loss: 0.9130 - val_mean_absolute_error: 0.4201 - val_mean_squared_error: 0.3101\nEpoch 3/5\n38700/38700 [==============================] - 72s 2ms/step - loss: 0.8288 - mean_absolute_error: 0.3927 - mean_squared_error: 0.2800 - val_loss: 0.8382 - val_mean_absolute_error: 0.4067 - val_mean_squared_error: 0.2971\nEpoch 4/5\n38700/38700 [==============================] - 72s 2ms/step - loss: 0.7676 - mean_absolute_error: 0.3802 - mean_squared_error: 0.2677 - val_loss: 0.8017 - val_mean_absolute_error: 0.3980 - val_mean_squared_error: 0.2966\nEpoch 5/5\n38700/38700 [==============================] - 73s 2ms/step - loss: 0.7311 - mean_absolute_error: 0.3719 - mean_squared_error: 0.2609 - val_loss: 0.7947 - val_mean_absolute_error: 0.4080 - val_mean_squared_error: 0.2960\n" } ], "source": [ "# Resnet (pre-act structure) with 34*42 columns as inputs - leaving a subset for validation\n", - "his = model.fit(x_train, y_train, epochs=5, batch_size=16, verbose=1, shuffle=True,\n", - " validation_data=(x_test, y_test))" + "his = model.fit(x_train, y_train, epochs=5, batch_size=16, verbose=1, shuffle=True, validation_data=(x_test, y_test))" ] }, { @@ -446,7 +260,7 @@ }, { "cell_type": "code", - "execution_count": 12, + "execution_count": 54, "metadata": {}, "outputs": [], "source": [ @@ -455,15 +269,13 @@ }, { "cell_type": "code", - "execution_count": 13, + "execution_count": 55, "metadata": {}, "outputs": [ { - "name": "stdout", "output_type": "stream", - "text": [ - "(4301, 2)\n" - ] + "name": "stdout", + "text": "(4301, 2)\n" } ], "source": [ @@ -472,20 +284,13 @@ "for pred in preds:\n", " angles = []\n", " phi_sin, phi_cos, psi_sin, psi_cos = pred[0], pred[1], pred[2], pred[3]\n", - " # PHI - First and fourth quadrant\n", - " if (phi_sin>=0 and phi_cos>=0) or (phi_cos>=0 and phi_sin<=0):\n", - " angles.append(np.arctan(phi_sin/phi_cos))\n", - " # 2nd and 3rd quadrant\n", - " else:\n", - " angles.append(np.pi + np.arctan(phi_sin/phi_cos))\n", - " \n", - " # PSI - First and fourth quadrant\n", - " if (psi_sin>=0 and psi_cos>=0) or (psi_cos>=0 and psi_sin<=0):\n", - " angles.append(np.arctan(psi_sin/psi_cos))\n", - " # 2nd and 3rd quadrant\n", - " else:\n", - " angles.append(np.pi + np.arctan(psi_sin/psi_cos))\n", " \n", + " #PHI\n", + " angles.append(np.arctan2(phi_sin, phi_cos))\n", + " \n", + " #PSI\n", + " angles.append(np.arctan2(psi_sin, psi_cos))\n", + "\n", " refactor.append(angles)\n", " \n", "refactor = np.array(refactor)\n", @@ -494,7 +299,7 @@ }, { "cell_type": "code", - "execution_count": 14, + "execution_count": 56, "metadata": { "scrolled": true }, @@ -510,7 +315,7 @@ }, { "cell_type": "code", - "execution_count": 15, + "execution_count": 57, "metadata": {}, "outputs": [], "source": [ @@ -521,20 +326,19 @@ }, { "cell_type": "code", - "execution_count": 16, + "execution_count": 58, "metadata": {}, "outputs": [ { + "output_type": "display_data", "data": { - "image/png": "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\n", - "text/plain": [ - "
" - ] + "text/plain": "
", + "image/svg+xml": "\n\n\n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n\n", + "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYAAAAEGCAYAAABsLkJ6AAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADh0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uMy4xLjEsIGh0dHA6Ly9tYXRwbG90bGliLm9yZy8QZhcZAAAgAElEQVR4nOy9e3wU9b3///zM7G4AAxpALkIAMYRwESVBjBdaUWu1pdqCHKvWlp5ae1r7Pe2v/vr9nmJLLW1tT8/XPno5ttXalh4VtAiKUrVWRY1KgCSAhDuEhIQ7IdwhuzPz+f4xO7OzszN7STY32NfjAZud62dmP5/3/SKklOSQQw455HD+QenqAeSQQw455NA1yDGAHHLIIYfzFDkGkEMOOeRwniLHAHLIIYcczlPkGEAOOeSQw3mKQFcPIBPkX9hfjhg5kj4htU3nHzkVZs/RM/Z3AYy+OJ8+IZUjp8IcPNGKbkhCAYXWiI4EhIDRA/M52apx4PhZ+9zB/XoxqG9e2vc+HdY52aoRUASaIcnPC9AnpHI6rFN3+CRSmuPpFVQ5E9F973PwRKvvOE6HdVpOhwEo6BNK+p5Oh3XqDp3EGQN2cX4ep08dZxT7EEiEEDCgCEIXpP2cOZw7sOasNVezfW3nvAfi1pv7fh05lu4O57MDsffm8668UF1dfVhKebF7e49iAJE+AzDueJQn7i+nbGRBRudWN7Rw1xMrGWrEh72WjRnIgAtCvLRuLwM9zlMFfHbqCABeqG5C1w2CAYVn0xhDdUMLS2uaOHSilXe2HkTVJQYQEGAEFJ64v5zKumYee2MrzmFdBCgCQh73qW5o4d6nKolo8eOobmjh7idXkqebF9ICCk981X+Mj6/Ywf/9x9Y4BqAI+Ja6jP9PXUxAGOgobCiezQdDv0j56AEZv/Nk76WyrtnzmtY7k8Cs0uFZu2cOmcGaZwHNsOdqNn+Lx1fssOe9kwGoAh68ZSwPTi/qtLFkA8nmdHuv63z2WaXDWbR6N4b0fld+EEI0eG3vMgYghOgFvAfkRcfxgpTyh6nOi2gGlXXNGb/kyrpmdCMx5+H97Yfxy4QQgKoIXqhuQtMNBHDTuMHcMHYQlXXNAAnE2ZoEAHf/sZKwZiRc15AQjj5H+egBUY3DsMehANcVDeTbNxfbxH1JTRMCmFk6nGejjMM52SrrmonosSex3tPW/Sd4rXYft00cyj1Xj7DHub7xKALint2QsFIfxzfVAEiNCAHmbyhg3Yatvswo00lvTeiwZiRcs7qhJe6dvVDVyKIHrul2i/18QGVdM2HNwJBtX3PJYM37iGagqgpIiW5IggHFXj+dNZb2Itmcbi/czy7Bfm9e7ypTdKUG0ArcKKU8KYQIAu8LIV6TUlYmO0kIQUGfUML2hat2exI6i0AV9AnFEbsLQiqnwrov8Qe47OILGH1xPm9uPmBL6G9uOsA72w6h6fE/tnsSzCodTsSD+FswpGmmKRtZwLwZE/jBSxuw6LdQBLdNHBon2YejOxdXN7Hoq+U8OL2I6oYWHl+xg/LRAygfPYCgKuzjAqpg+4ETvLRuLwAV2w8DMHZI3zgiK6L/WfmANbKYe8NzKVc2U2mMo0YWA9AaMZj/ykbmfWaCPa67nvgQzTAZ1k8+d7n93v1Q3dDCr97cZjM792KurGuOe2cRXXa7xX6+wEmgs0Fo3CgbWRAnyAC+wkRHj6W9yCaDcgtV7mefVTqcWaXDs6ZtdBkDkGYK8sno12D0X9K0ZAEYUjJ/+UbGDulrE6In3t3JG5sOACah2918ihOtGourGonoElUR3FgyCEVgE/JTYd3/RlHsOHSK3UdOx20zwCaeYc3gV29u47aJQ3l+ze44wiYxibBTKnejdu8xAFpOh+NMQLoRe8YlNU02UYfYBAMSpI5Hbp/ID17agCHNF2kRfwu/eWsbN40bHEdkJTCkbx77j7fa22pkMTV6cdy5EljfdIy7nlzJ8w9cwx/e3Yl1GQP4/osb7GfxM+1Y45WYTMO9mMtHDyAYUOz3G1RFt1vs5wvcBLojmHDZyIK461rr2RJqrH3OsRT0CXlq350NJ6FuK4NyWwyW1DTZ1gancOn1O2Tr2bvUByCEUIFqoAh4XEq5yuOYB4AHANR+F8dxWTCJ4NlIvKT9ZEUdUsa4iWZI3tx8wHRqZlj6QtMl+b0CHD+rJewzpMlwLOnaHrMiOHSiFSPFvf5W1cis0uEJ2gmYEvcT7+7krS0H47ZLTM1haU1TgiRt7ZeA7sF49h9vZXFVYwJjchL/VNB0yfxXNiYwUAOYt6wWQ0pPNdgpJSki3sRloWxkAYu+Wp7zAXQTuAl0e5COuTCZKcX67ChTSybwGmemzNJ5jUDUBBbRpU0HnJpENn8HN7qUAUgpdeBKIcRFwItCiIlSylrXMU8CTwL0umSMVEVMcrSISuJ1E1UJQ5Ix8QeTsHkR/6TnGJJ/RjWSZNB1yZKaJhpdWgaY439r8wG8FIg/f7CL+uZTsWeMmsXGDulLQDUlEUURSMN0OjsR0SWD++Uxon8fjpyOsOPgSTLF+qZjqB4BxFpUjWmNmJqR04ex9+gZAoqw7bxu4m+hIyd7Dl2DdG3kqUwp3cUX4DWOB6cXZTQW9zUgRrMEidqxH9rrfO4WUUBSyqNCiHeAW4Fav+MuubA31xYNtO3jEHOIIMwwxvLRA3h94357m+5vhgegb57KidbU5qB04TQzpYIEFlc1ovmYiawQOfdeN9G2TEbzZkxAN0ytwHJ4q8Ikqusaj9oSxv7jrew/3sqwi3oBUCq2Jdj8vbbF3zP5c1VsP8zZupU8eOl+/tAwlFWRIhRFcOO4wfzbxy/zNBF1pLkhh65DuoTby5SSDVNLtpGNcfg5wVVFMHtKITPT0H6z4XwWXVUNVAhxMRCJEv/ewBvAf0opl/ud0+uSMfKSL/0qwfn6h3d38vaWgxiGJC+oMG/GBFpOh9l79IwdMtXRKPJwGLuRCXMACKmCvKDCibP+DMoi1KuMcezqM5Ejp8IJ93zolrGUjx7AQ39bR33z6YTznw09ShANTQS4p3UugL0tQoB7w3M9mUAyOK/rvEZAEcy/Y2Kcr6Ajoyhy6Hr4hS77Heu0i7vnBfg7i7OCxtVQXwGjpkHh1KTP1N5xuJ810+u5Q2nvvnoEj37ucs9jhRDVUsop7u1dqQEMBf4a9QMowN+SEX8wJWJDmiaGpTVN9otaseWgLfGGIwYtp8N2lMySmiZb+kgXXlJ3quPqDp1i9MX5Sa1MmTIiXcqUxD+OyJ6eyxHiCbUVbQRQPLhvAgMoVzYTRCMgDAQa1wY2YxjY25Aa5crmBKewExfnhzh0Mp7xOK/rvIZuSNtXEIhKO4dOtNp+nHAXqvY5dAwycSg7TYCPr9jRblNLRmhcDX+9HfQwqCH40su+TCAbpkovJ3gmKB89gIBiRv5JzDylTP1mXVYKQkr5kZRyspRykpRyopRyfqpznAkji6saWbhqN796c1tcfL+ixCJHrBDLEf37ZDa2NhxnAP/cdCDtc90oujgx29ZtZlEVKBqUb393EtkgJpF1QwArth7kv576H8Zse5JSsS1uf6UxjggBNKkQlgFWywkcG3w1ugigoxAhQKUxLunY3cTffV3rGgLz99EMaeZC6JJnV+22I7ggnmHlcO6gbGRBxsTbMpM4/X4divoKk/hL3fysr+jY+7UTZSMLmD2l0KaLuh4LBkkX3cIHkC4KLgjZUrcWlSR1w+R+VtLW/DsmxpmG3kpiksk22nobAUwcdiE7Dp3yPeaW8YP52scvA+CuJ1ei6dImslbSlhehlsCRLRU8EzQ1hW+q8SYdd9z/OopYsxc2i7lco25m70VTqDk8LONn8sonKBqUT10aTufXavfZYb45nL8oU7bz1tRqVurjuXTy9I6fD6OmmZK/pQGMmtax92sLXCaqmaXDWVLTREQzuCqwg8+eXAuNtyQ1XznRZT6AtmD0uElS+dzPMaREEcIm/gpw3Zj4zFln8lRPgCrwjPgBk0H8/58ca5u1nM+WylkL8A11Gd8JmOUdNKnwS202v9PvSOv8dK6fjWd0QgB5wZwv4LxGBuaYjK6Zwr6/Zc2btGx6m4LxN1Jy1c3tu19bkGyM0Xci9VY0EWTnbQspuepmqhta2LV2BTM3fB3FiHi+r+7oA8gYe4+dYWjUU37/9ZeyYGW97Vi6beJQW/1xl0WwkE1i5nddoE33SEYYJfDu1oMU9Anx/JrdcYzNK2nLjUpjHJpI1BT8HLXO52qvMzjdZ3TCK0s4XeSiic4R1Fcg9VaENJB6GFFf0T4GkAZDqW5o4d6XI0zQL+a6nYsBKBnSLy2ncFaQaoyOdyKMCK++sphTg8pMX8LuXWBE4s1XaYy3RzEAK75fSknf3sG47MD5yzfa0QLzZkxAVUVceGW2iZnXdfWoS0XFyOo9ALSGVTQ1LkA1xkHU0ZvKWW0xpjViPL8Y9At67VkZx5j8HLUWUu3PBhQBihBIaTJ2hLAL7mVq83VGEynCNAemKk+RQ+boDCa7pdcVjDQC5nqVKg29rqCkPRf0su+7CGRlXTMT9C22uZRXl4CigKF5E+Q0I4biju09AM40e5+TbIyNq+FYEzoqSIgQ4EOthDxLSGqj+apHMQALatTRa3nRH1+xw86KtaKAJhdexJr6FvucbBMzi7heIg7HomikRCBRBFklmH7MKxXxd55z356HqYqafSzYPgQiSCE4IvO99yfxMbQXAUXwyO2xsFAgLjTOXRYgGZzx5oY0fUQ5X0J20Vkhu2+dHMXbkblcLTazWo5j+slR7WMAaRDIm/LrmRRYSpAIASGRUoIOIL0JcromqsbV8JdPmRI6AAoE8hLP8Ruj416KUHle3sgS7Xpq1RJ+kl8PFcvMY7/0csbaSo9jAAKYPaUwbtI5SykYQKS+kqsa30MXMWk3W8SsVGxjplrBbPVdVMySyTqKOUcsDUAaGd0jlWkqXebl1AjMc8yJjIzwWfEeU9VNcfeokcX8KHIfPw4uQMHgh8Gn2RYu9HUQZ9NsZsHKHnaWtG1rbkD56AEoQtglOAwjV0wu2+isbNzy0QP4rVrCOq2YYEDhe9mIALrybkDCFfd42tdL/vEFxiqtgESiINQAIGIagJNppKFR2Pjg1w7iD2B4n1M4NZ6IA1Q8Bsea7HspwMeumsyR/M/wk/x6Sv7xhXgmNO2hjF5Jj2MAeUGFmaXD49Sv0L4mHgy8zkp9HELAvzU8SiAQLy3HETOZmPF6RObTX5xMase3pOoQERQkIkpxn9Ons1cOjDv3iMw3wzINkhJOL+neeX+AS8Rhm8kkYyySGIMqYg8qEilBRfJ59W0EJpPaaIzief0GnjNuor84iUCiCklQasxUKyiXsWdPx8fQHhgST0m9LYSmbGQB8++YaOYZGJJQsPtVjuzp6Kxs3KwWo3NL61fck3hMlKALDBAKjL4BbvhebJ9bqral9VazM0vvJO/hxL7EbX5mmsKp5j/nmBUVlIAp3aohhl15Cw8WFpmSfzpMqHE1w/qKIV5D61EMYHC/XqYkqGyPezkzJRiqGeL4kvwYQTRUD2nZImaKiBHKf1HfIYAeJY7CtLEBKjoShR9E5vCccROlYhs/CDxNiDBqtKacLgURAtQao5io1DNTrWCpPo0jMt+WqsMEfX0Bn1fe4oHAcvuayDAz1QpmqRW2T0HBQMVAIvinXsY7xhU2Y4EYs5mo1FPEHqaoW1EdxiGr/p0aZViK1LlS2cmVyk5GaAfoJ87EaTCWZuP2YXSUAx28JXU3oSnoE0rLHHTP1SMYO6RvzhHcQeiMKqHOe2Xl+ulI627zyw3fix3jRVQLp8KtP4dXHwLDgNf/w9zuZd+f/EXYUx37XjIDrvuW+XfFY6n9AQZQ9kUSvH7p2P2jjGRIvvCM5e5RDGBQ3zxzQlQ4f1ADBVCEREFnyogCtN0KINFRqM+fDMcSI3WeDT1KHmEEMSIZEBJFmoXfFAFS6vw0+GdGaAf4SuB1Qpj7pIQIKm/rkwGYH1xA0DQW8i/qOyhIVAyEgDwZ5gF1OR/Jy+KI5+eVt/hZ8E/2s5lEGorYY5t7VBmt2S9Mx/cn1Cqmq+tQ0QGBgUC1DU8xCBG7phXl6yyEav39tcByZNSE9Zw+nYEc4xNqNaqQNvPEIM7klalzOx3GEfAo++wuATx/+UZaI4ad65HMuZsrKNex6HHvNx1CaRH0zctg3B3p2dDPNJvEHwO0syYzkDLRJzBljvlpXXvKnNQ+BOeYlQAtB5vo2/guKhpi3XOx4912f4dlpNoYQ/idlyjX/av99igGYGFLryu4TAQIAEJRsex0ihqisVcxIwAR5ZSTCi/iyOkd/EWJmVmW6NMIokWJfOy6cf1JJVGJWfK1wN+jPXLNfYaEemMI09V1BNFsJgIQkLFewtb1PqlWcQtVaKjMi8xholLP7cr74Dwu+jlGaUKJmm6cMMcCITSbIaiu853PYZ3j3uaEAghhoEiDgRxjurrOvrdAcplo4n+FXoxjlJk4t9ONvDKApTVN9ne3dDn/lY12qQgrATDn3M0hbXgRSjcaV5tSvB6G+vdh/3q44u7kjKD3AGxVHAmGjqfDGEyibzECMPdrZ83jtVZ/f8D6RRg1z9Cv4U3b7Cy1s4j1C2PmosKpULXAHP++j0AaGEqQ/wrPJaJfzDPBgG/ASI9jALFY3e9xXWALn/rUbAA7eWPs/kpUDBRhOmM/c+FOPjMV8qo1FMx6N0DUIRxBRcb1JRXOgm0OJgAOwgoUKXvitAfnPkk8UZbS1CiCUufR4J9w0GUb1vn9RSxT1o+AOxmG828vKV+IWLNt32sBt6hVcc+jIJmpfmAm2jnuZWBGC31DXZYyecwZIZWMcWjRkhCLq5tASjRD2uG8j7xcm5DQZ8icczeHNOAO00xGzOPMRDpU/QXWLUoe3XOm2fQXSAMQpq3e0gBShWGePU7MnGNEv7tQONUcl6GhChmjM0LC2oUxZ3bVAlj+rfhzdSiTG3ncuIP7InM5EP6+xw16IAOwnIPVsph1kWIONw1maU0TYe06Qjsi/Oa6SfR3RPtsDE7i+FmNmWoIjDAChVpjFEv1abb9/DZ1NdcpGwhYtn1U/qjdxlcDr6FEPe8WY9gv+zNYtMT/IFHEiKcJL6nbqS24z/Mi5F7HuLc7P70giGcMnteT8WN2ajDOMe0yhvDD4NNpJY85I6TSiYoKa4bNQM9GDH7z1jbPbO5QN2wLmEM3QxITi2ceg2VysaRyP0neiVHTQM2L3ePWn/vH+Lux/6Pk3+PuEULTzHpbCqbJG0OLjW3zssTz1CDV+gRUAbVqCXtPyL2JB/VABuB2DgqIixZ5es9gnojGD68yxrH+vQCGVFkf+AKPBBYgDZ0fBp/m3vBcuxzCNlnI1NBWkJE4x++bxpSY/Tsa2vkb7XP8MPg0eTLef2DBjxAnM9M496VD0N33cjMPr7H4aQde13OOz/29vzhhO62FjDBTraBG80sei4+QSsdvoCixInhencquGH6h3Zc4hxx84eP49Q0vtk0uC03p2iv00410TEt+GHcH7Hw7/rvPPZQ5r7Bv3RtsPR7ihrrHzJBS59jc1yqZgXLdt/iuMcZmdFN+csaz0FiPYwBezaStYkhWSYj59Wb8sHDUC+onT4A0onHxpjlirW4mU/nFu9fIYmq0YltbsPZtCxfyg8DTXKnsTBifn/09GbFNh9gnOy4TpuE1Hre5SohEJmGZyQaK4/ZxCpLZ6rss1af55ltY+0rFtqRmIwv5eQGOnYnvwGYNNaiKHPHPIT34OH6ThhdbZqIr7kmfqKcyLfnByzGc5B7DCqcyDKDxhsSx+VyrjNQlpntUMbgpU6bIqqqqhO1ulc4qjjTw8Gp+s3OwTYCe6/UzFCNimy7ODC5j8/4TbRpLqdjGotBPCKBjIAgQi9gBb6JvIdm+7gL3tDDANoU5mZwmBb/U/sXWpiAx8qc9ZTiEgJ9+9nJq9x5DQFqdknLIAfAs1bBw1e64PJHzpeDgOVEMLl2UKdspq/0GhtbK1SGT4KyTxfzs4v+kaO8rtlM00o460TWymLvD37cJ3c1KFV8LLEdxOVgttEXi70ikYkJu05YRzUlwm5EkSoJt35081p4yHFOii3NptLHPkpqm82bR5tBOuKTz6oYW5i/faFYTVgTzZvRsbTIbNZl6PAOwObqUMZvebtP+p2A2SrlG3cwmUcKtFx+h9MA7CAxmqRXcd3gukJwQKQIGXJDY8QriCV2NXsybxhQeUJczWLRwVPbhWmUTIaEnSM3Q9VqA3zi8nNoiGlG1UR9JRASYoNSjRCMf3tInUywamamazTOc5iALmZbhuCCkUjQon417j1Hd0MLa3UcxpOzyZuA59Gw4zT8CScvpxDWdNjIpBNcByFZNph7NAKobWpi3rNauJ2O3EyyK2f8UNcilk2/lpWFBSl57FCnMrF9BhKliM1VRBnDVKNN05FYKpowsYLWjqFwy1Mhi/k37DmCaQa5VzQ5dXiGc7r+7Cl73d4e2WtFAE9QGvhf5CujwZfV1LlP2crNaxSfVmFnuX9R3+Hz4B3FMINOaQiP692HCsAv5qOmYXf1VVQQC2aXNwHPo2chaGYuO6FWQIbJVk6lHM4DKuub4dpAimlFaWGR755VR07izcCpUPIY0DDus0XCZLgr6hOz+mhZ6BRX2HDvbprGVK5vtbGBriM54+lRO4mTbOxK+YaLR8fyr+jojlQN2VrT7uKDU4yKDnP6A3+k+kQ4ubN5/gm0HT9hR0hK4//pL6ds7mCvvkEObkbUyFkkijDqrBEm2mFmPZgDloweQF1QIRwwURztIINE7P2oamhJE6GEkCvO0OawXY8GqQ0+sMqUArh8zkNsmDuXhFze0aWxOs4ezSqiw4nhJn8B3BiPwiwRyoxetZvaz41i/MbbH+evsh6wI6Ns7GFcx1Au5ZjA5pEJWylh4RBh1VplsC9liZj2KARw5Fea+P63itolDuefqEZm9hMKp7LxtIa++spgPtRJq1RK+es0onnp/F4aUvL0l1jtYAvuOnuGdrQfT6vPrVVHUbfYAUyvI5xRfDyxPSPjyitH3i9fvCCS7h9OENVQ5kpBYpklQMJu6WKGfkNz5a+VQJPPDB1SBNGJmn2QEvrMXYA7nMTzi/ytX7GiXSSZhbqfhY4hjZm30SfQoBrDn6Bkqth+mYvthAJsJpPuiS666mVODysira+Z7owdQWddsOxfdhGjHoVPsOHQKJQWRcpeI1hFEHBVAndEuzr+/Fvg7UkpkNOv4Y2IDE9SGBIk6HVNRtuC+p9d3JWrW0h32GZ0AT2q3MkFp4DV9ato9GFJFIN81pZBLLuptq7fJCHxn1anP4TyHk9A6au+3xyTjFl5euj2YWOc/GVFvh0+iRzEAJ16r3edfEdKDGzo5rNOUYP1oAFeQWLkyPy/A8bNa4j2isKRcqzSEM9HML9TxF/o9vGlMibvXL4DnmM/V6pYEJ6wTqbJ524N0rqUQK3ehoaBioKJzf+A1FCRTla12U5lkzt/JKaqEBlURF/P/8Isb7K5vXgS+s+rU53CeonF1Ypawg9C2xyTjFl5aNr2dfrMZyKw5jQs9lgHcNnGo9w4PblhtjPGUHp0/2pjWTUxb6dF2MYWYGpNyzcJyWrRHQKpQR69GKzsYxtVssb9HS0zFlZzwyydoCzNI5nx2Xt+L6RgSu+iekBIV3bNaqNdzpvINCOK7vlU3tLC4qtE2x6lqIoHvzDr1OZxnsGiKXScIT0LbVv9CQu+L8TdC45/T7+/bxn7A0MMYwLCLenNd1DnrK/17cMNKrb+vecD+0SqWIRUNIePt1SdadfvSZpcB4vwCTinX7QPIFEv1acxW342WlDbLolmahROpSkt4IdNzvOoIWeUgdEmCI1vKWIOcVMwvVWJYUBXMKh1uf6+sa45z0N9Z5p0N3OPq1OfQM2DRFHvli4wJbTK4hZeSkQUwJIMaQ+2oSdSjGED/C0I8/ZWrkx/kwQ3LjTTMA6OmIdQ8DC1MBDWBiF0x/EIG9+vFG5sOJJyarbaJzuziIzKfHwX/ipCabXZxE2yviqHu/anqBCVjDAklpjHLQYdlgF4iEmeqChNgsf5xz0Qwd2mIuAgpEUx41yMGXBD33S0hOZlDDjl0OOKas6gw+QuJvQLamRiWILxkWmOojTWJuqwWkBCiEPgfYAimteNJKeWvk53jVwvIjS1r3rT7A5RcdTOQZohg42r2rHuDh1b3ZVWkKE7Sv2X8YN7ZdoiwZnifmwW4u5YtCv0kruGM2xRjIRnhzyTU1H0tL9OPWf4h3iwlgbmRr/CccVPCdaf1quNJOd829zzUaz77j5+1M4dfNKZRbSQyz16uOi3VDS0sqWnK1QPKITk6KkM32XV9nLDdKSy5O9YC0oCHpJQ1Qoi+QLUQ4p9Syk3tuajVMMbqD/DsoBabu6b8EaJV9747qYU/vLuTf7qkfU3vOOJ/TWAHf1bju5ZZNnbL/GL5BBSZSJTd4aPpwq/0g/O7E6adP/EcZyObvr1UBIJhF/XmiuYNBJWYuedLF1Qy6eyr9nNaIaNueDl6z8V6QN2JSPR4ZDND16uZjN+1PMzOfn7H7gZ3O9lOg5Ryn5SyJvr3CWAz4Nm4OBN4hQM6Ud3QwuMrdrBw1W4eX7GD6obEMg9lIwu4svAiuwyxAgzsm0dA7bjXNVlutO3iQUfXMk3GqLlOgDV6ief5cRK6459bondHF1kMw52T4C5f4YRTu5DSHKfVJaxUbGNM62a+EFlC7wPVfKiNiz6HgqEEGX1xn7jnLFc2x11bFeY/t6ku1e/aE2GF/z32xlbufarScy7mkAG8omH80LjabMjeuNp7319vh7d/an56HeOEZSISqm127inztVv4AIQQo4DJwCqPfQ8ADwCMGOHfCNxCsnBAa8FZ4YSKwJc7W1nGrREDBPTLC3Bn2XAWrdqdVnJYpnBGE0mE3bXsW4ElXK/UogqJKg12MIzJ7CDg8A1Y8DMRWUjmQ/DKOXBG/EiIq3RqQUfhT9qtdpcwO+vZ0UD+3vBcrg+a7TtLhvTD2LEUTQ/HOYwFkBc020C2nA4nSMTnYpjn+Zi70BXMpwAAACAASURBVKEaT7rRMKk0hUzDKj2csOVGS4+Yr13OAIQQ+cAS4NtSyoS+lVLKJ4EnwfQBpLpesnBAa8FZF0m28MpGFjDnmlH84b06pIQ/vFfHZ6+8BFURGNFwmHZUk05AjSzmR5H7+HFwAQLD7lr2a20WU0NbCToarFgNaiaJnXxCrUJ1+Qecn6nglvzd5h9Lwv9h5EtMVOq5UuxgvNLgaBIvuVbdTJ4IowCKNOx9QkaYFahgU+mP+HjpHEqsXg2X/56i0+v4+eYBrKeIUEDhzrLhzEpi2z8XwzzPRabWpdna6UbDpCLwbQmrdJmI2jRfu6DCaJcyACFEEJP4PyulXJqt6/rZ+60FF44YZoMTh6nBq6nM6xv3x53/8nqzraaiCMYMym9zMxk/9BcnEci4ZLLf6Xd4lpSoNMZRyThuUteiSN0zJyBZPL8nXMdZUNHZJgvZphdyd+jt+LwEYKLYaffyte8FKEJyd+BdlOCfQLmH6gbLLppHKHAN82ZMYJqHtO8H63e1zHg9nRGca0wtFYHvFI0nnWiYVAS+cKrZ39fqsNVGYpxRWHKW/BeZalhdxgCEEAL4E7BZSvnLzrinc8EV9AnZpgaILzMwb8YE5i/faJp/HLAiXmhHLfFhF/XiqlH9eWldYo/mSmMcmkgsnWCFmXolUP1Ru41/CyzHbZdyRwKBd7hnQk0ij+NUKZmv/oWTojcKMi76RwIqNu9IdEhLDaoWwLrn2DXxd4S1vFjG4+lwygJvbpxrNX/OpdyFVAS+22g8qTSFxtXw+n+YxLhhJQwe3/ESeTuyeS20ZW10pQZwHXAfsEEIsS66ba6U8tWOvKnXgnvcVcjptdp9tqlIACMH9OHWCUNYsLLePs6rYXk6OHQyTJ+8gGeNoRpZzLwLH+VbRQd4el8hNXUD4/a7E6hmqhXMUits4uu2/adTT8iv7LNzPwImBBpMHuPY1yz70l+c8Lyvdaiw/tLDXKNuIhQoaxcBOB/t5j0FqQh8VjSebJlJMozq6XAG0I5sXgttWRtdxgCklO8TExy7FO6Je9vEoaypP2J/f+xfrqRsZAGfmDCEX725jfe3H/Z0BKvCNA9F9Pi9RYPy2XnwJBLQddNGHlAVz5yCpYeHcdfMO/nEJKh7dyd1h06iGZL65tO2o1igmZoC2KWZnZE7TjOMRYT9QkTdErt1vqdfIPqfjH6+r0/is+oH9rGrjRKOkc9NSjWqkBhEW0kKgVBDDLvyFp6dNKZdBKDbSJE5JCAdAt8ujScdM0k2GEQWiHHGaEc2r4W2rI0udwJ3Fdy2MvfEHTukb8JELhtZwG0Th7Jyp9mIRhFQ2L8Px89EuGxQPp+bPJzn1+xmfdOxuHvdXDKIppbThDUDIQR98wIYhpGQIQtgGJKlNU0sqWmyo5Usml0ji/mi/jC/uvokTzUOY33jUWar76JKM1LJIvTgkshJJPJuhuDlM3AnflkQACOvZerAa5HVH6IgMVAYPvUzXDikHPnq55EygpCgIXjLmMyVxWMZRPtNHuea3bw7IJuROR1q0kolmTeuhgUzYoR7zvK2MQEXMa42xlDZGT6nNmbzWmjL2jgvGYDbVuYVeug1ka2m0rohTWleQn3zaQCONx5lfePRBOlfYDYzmTdjAvOW1aIbkqfe38Uk6V0QTRECCXHRSs4r1uhjeCl/LHmjItTsrmOx/nHuUd+KS+jwywROliyWLBPYPQahhuDmH5lJG+v/O9p605TwKZwKB+5DVv0FISSKNJgu1qJurYGdS7PSPu9cspt3NXqUTyWVZL5+EehR06zean5v61yLEuMe9X7IfG10WSJYZ8KKGrESbZy2snDEYN6yWjsZJ1mCmDuM1AlNl0R0yWSxzU6IsmLby0cPoOV0GENGGYchucZhz7cSogKK4P7rLzVNRIrw/HFUxWx72bd3EDALyEUIxExAUZs9pOcI9is7HRdOGo320aXgfWMSW25dFJNWbv05jP64+WkttivuRqp5aFJBokS7oBmpk3OSwP0bnk/oyGfvKQlLQEwyv/FhH0HCPZHbH6fdo95PG3DOawBeHNxpKxNC2E1hwprJDAwpPbl9+egBBFTzPK+pVaps45lgTKq/LzKXmTNm2deweg5LYLUYjy6CQASpBhk9+VbmD53II69sJKIZBFTBTeMHs+vQSXYcOmXf44axg+KuV2MU88PIl/j3wFKGiBa7YqlVudMp8aeqERQn/ZPoC9BR+bU2k+knR1EC/tEShVNR5rzCvnVvsPV4iBvqHgMj0mZ7ak+TwrKJjn72HudTKZxqmmR2NFNutMS/iyvugbXPgh4BNWh+byd63PvJEOc8A/Di4A9OL4oLB52/fKPNDCzzjq8XPUoRAwr06xXkyOmIvetqsZmQ0FAxo3Smis3U7jX9AWUjC5g9pZCF0UziKm0M9xrf42plM9ViAt+dPN2udQMQ0SVvbzloJp058M62Q7YkeGPJIJq3VESzcCPRWHwBQuFNfTKXySZGq/tjw/aI808w+Thr/ThMRYaExfrH+UiM5XvWIkhmk43WVRoG0HhDu+yp53PkT0c/e1f7VDL1PyRliIVTYc7fs5pM1dXvp6NxzjOAVBx87JC+9g984kzE7hHsPnbLmjfZ+f5yJhojqaEYKeGyQfkcqY+p5VaUjnTE8TsLHc8sHc7fqhqJRLWAKqOYKqMYVZgL/eCJ+NBS3SPVWNcN20kc1gweDFhMR0Z7CICUOjcoa02zSxR+jWS84DYbgckXao1R3FAS00DSjpZogz3VSRjOdSksGTry2a13XNAnlLVrZnr/TLWblAyxnY5UL5zLPqdzngF4cXA/s9C9T1WiGxJVEcybMcH+0d94/WWmrfwKRWh8JhTgC+G5bFDGJkT71Mhi7mmNZe3WqiU87Kpd75boBWY2ckGfEO9uOxS3zytKSFUV20lsSPhQH8c3A0EUNNNsY+hmhjO6WT3UI87fCXeEj73dI4t4olLP/K0HqW6Iqt4Zhq6lK816/T7nshSWDB0lgTrfsWUuzAt2rnmtLdrN+SwMdATOeQYAiRzcz7FjOXiljGX6Vje08NH7y7lRjSVg3TWogZJRN7No9W7ALCkxon8fdh85TY0sZp1RzHVFA3lk4lD72mUjC6JN6GPjUhXBXVcVMqt0OLvWruCrvM5KYRJ737aJUjLxkgvNkhaaQbVRzN1nv8fs4PtM77Wdwa0N9vUlCrpVUprkSRdeCWLu7QM5hm5Idq1dQdnuXdB7AJxpTov4Vze0sPfoGQKKaWZLtnj9zHbnE+F3oiMkUOc7BpKbPTsIbSHm57pJprNxXjAAN/wmnte2yrpmVhrjeFCNlWiYdP0MLhs0nCU1TfbxD3zsMtuXYCWTzV++MUHLyAuatYgURTD/jolma8vG1Uze8HUMNcw3VZPYX+PTNlE3TOb07P3ldlIawGfFe4TCpj9Cjzps39YnU6ZsY6A47qsBOLOIwTsxzEIzF3JVYAczNzwaDbeLshU16N0lKQqntBlQFe6aWpi08FtOyut42HWxokxAIbEEd0ejrcT8XDbJdDbOSwbgN/G8tpWPHsBv1RK+EDGJ8qTrZ3BLtMtYsuSxVM7nuAlfX4EwwgSEgUBj3uUt7OhzK8qGZUgjgiECVInxcXXyy0YW8O2bi1lTf4RrpMksVCRSKBwKFXJxuJFb1KpYjR5SaAD2f4lZwFbm79Bx5fxG2YqytTV2cLTMg6z6C3r1M7QU38nF1385jhE434WuGwy7qHfSBZyT8joefnWxOvtd54h516LLWkK2Bem2hMw22pIpaUm9Ec1AVQSzpxT6tjK0fAyWuafimj+xPW88N+XXU3J2fSx6xmMM1Q0t7Fq7gpkbvo5iRMyepYaGjJZlTrslJN4F3cA6X8CUL8PaZ6INshPPlTLatSzQC2XOKzYTcL6L4HkWxplDDt0Bfi0hcwygg1Dd0MLSmiYOnmjl3W2H0HTvSIfqhhbuemIlk+RW2+H7kRjrm4vgi8bVsH4h7PsI9lTbm70k/3S0gYT9QoFLJsPetSAdNYyEii5Bkbr5VUTr/9z0fZj2UNxz5iT6HLo1nHWEoNNr83ckumNP4G4FPwLltd3zWMfkcfYDVRyJZl5Otso6s65QDWbJZ0WAdOUiWMelJJ7rngMtPpTUi9A7t3kRe0/mIA3YU2OeIRRQgjD5HhhyJWcq/0yfQ+vt/sUogoNNO3nvpaVcOnm6rebnCH8O3RbOQnNKtMC5obW/t3A3R44B4B+P7LUdSDxW2Y6x4DN2PPyuy39v171HShRFIPCOfHE7hu+//lIWrKy3zSUFfUL+sdJOicVKyjJb3cCwyTB0EhzaBg0f2PezbP2ZNI6PQZrXHn0D3PA9c9Nfbydfa0UKKwnN3Nx/yyI+zWK+VPV9/s9Xv5gj/jl0b8QlNVoaruy8ctBdhHOHAaRRBtZPyveLR04WLurcNuTkGwzWTCeuprVybdMfmRq4lTVaEUGfYnMWvByen5gwJKkzuWxkQWJp3Ft/HkvKUgIwdBJvBG6k8Xg//pUPbKleV/ugaqft+2fMB4SIdUmqeMxmOsJKG5YGSJ2AAKTGFLmRpTVNOQaQQ/eGM6nRrQF0RjnoLsK5wQDSqBOeLOvQL+zQ2UJSCEFBnxBjh/RNOHbl2vF8OtrQXUUy5PBKFoZqWFr2e9sEkgxx5pHG1ZTtrqCsaBoUmt2yPEMi3WUYzjSz5ZPPEKlZyIQDr0DVAm6Uf2WvMcCM8YtS+sDwK5ENH6b0A/hCGmb9H4BjjSazsTLOjJhvQJfCzoYuact9csihM+FOaoRzygfgh3ODAaTRwSdZ1qFf2GHZSLMx/JMVdeiGZP7yjT5ZqdP5cvX3+QaLuU6pRUVi6BGuUTcxbOTM9J/Dg5GVjZxq3++m/HpKdv8ZlGkJZRjqz/Ti1X8uZrBxlHFqhICQCCSFSnx28TZjOG9rn+Fr6iuxgm8QZxZKzhyk6Wf4+3dMZqCoUPYlGHKFXRhOCpXnI9N4QZtGrTI2IRs6h+6DnHPeAXcZiXOY8Fs4NxhAGjVp0mlX51X/36wNZH4P+2Sllo0s4Lv3f5FdawuRH30dTQ8TQeWh1X357qQW34WVsPh8GFnZyALKlO3w1y/EazmWxNJ7AMNe/d/8u4hgqCKxQXs0PBMlxF939WMczZanAIiv/2Z994VQoxc1o34wNPPsKXPYIofTsultCsbfyNhBZdxU18zDOcLSbdHWSqPnDNPIVnvJHoxzgwGkUZOmLclFVoSOBUUI30xJk4HM5AVgV9XrrNTHsZ6ijOrdlCVjZF7MYdpDti0+ICMIYTga1zs+FRWl7ItU7Tf4UeOfUTBzBCzp3/obx3meTGDI5TDhc2Y00Jbl9rGHToRpbGjh3pcjhLXrCO2I8Oz9ZNzwPYfUyCbxbUstHr/AiGRj6pYMI532kucBzg0GAGlVAcw0FNGrdIOXluCc3JdOns73q3sTwVvTsI7fe/RM4uKbnoSRJWMOo6Yh1DykdhaEdDWSEYiyL8IV91Ba9UkEhmerR2claF8NYPhVJtNpXI2x7Q3QI0RQ+fdNYxndq+m8LdncWch2b4C2lNxwM40lNU12GXO/PJdu2cuhKxq/d0OcOwygA5BKa/Cb3M/eX87SmqaEpjELV+22G84EFEFAVdB11+LzY2TJtJzoPrF+EdQ8bTZfsaAEYMiVsOybZnlou/iPN8F3MgTLL2D1CRB5/ez7LZ30RJymcxk+zuocsoZs9wZoi1bsZhqCxKi4dCLsuhxd0fi9GyLHAFIgmdaQbHJb9fqX1jTZavK8ZbVoUZOSZkg+P7WQYRf1Tl81Tqbl2PskVC0gVthHh1cfitrqY3DwgYRyETZTcBSFkwAr/xtKPg2FU21NZ6LYwoOBl/nU8NnMLM3V7+lIdESRvEy1YjfTAOKKInrluXRLwSDDUubnKnIMIAlS2S79Jrdf/oDbn5CsImabccU9US0gSvClEV+6wQGvpDB3TSDrUwjMME+HY/ql24Nc9trPTP/DP5aZUUvTz8+F1Bnwldg7wZnpXgvOeZtMi+jWhf06oHlMT0OOAfggHdul3+T2Ywyp/AnWfdu1WAqnwqcei0r9RlR81z0PdUr5EO0dHN3n3CatowN5capyydn1IDWTwZzHdtTORILE3gnOzFRrIZUWkSsD0n2RYwBRuAlvurZLr8mdSblp9xhSMZ2Fq3bzWu0+bps41Owl4IRTEvzya+bfB7fAhr/5hnlKQIpE2z84ooSEClFHctqO6Rw6B53gzOy2dvwcvJGBRtilDEAI8WdgBnBQSjmxq8bh1yKyPbZLP8aQbOGkWmgLV+1m7osbAKiINoKxmYCXJDhqGqx41DbrGNFGMWaSmGkWEkJBhPpCq9neUtj/RZkDcKT3CHacKaRqR3/KjRYzJ8GaYDk7asbIalhkmky4PffsLDt+RmPMxfB7I0ONsKs1gAXAfwP/k87BB0+0xvrRZhEZNW/pQJSPHsDUwA7K5EaqxQTKR18bt/+12n0J362OYrzzs2gl0Kg5Zv1CaGkAQ4s5eoFqYwwXDJ/A5aMLzQW0p8Ym/hZsP0D0nP6ndjG1dj4t+qu89PaVTA49Y/YesCaYo+xzDsmR9bDINJyZ7b1nZ9jxMxpjLobfHxlqhF3KAKSU7wkhRqV7/IHjZ7n3qcq4ap3ZmJQFfUIo0XhHp4TT2bbLMmU7C0OPRif2MhTlGiD24902cagt+Vvf7cWgncUm3YoKaxfa4aB2yQcJVylbEQd2wn4jzjdgmYjiQkKdUUASblGruIm10WqJ536lxI5Ah5hTUjgzs3FP63hnj+tsIqMxZsHs1S2T07KBDM2yXa0BpIQQ4gHgAQC138VxUTXZkKSqG1qYv3wjRrRs87wZE7I3ITJVU+srTMkawyTeroltmXvifAAVix39eTGp9ZhbYOtr0egfgRACKSUIiYqMyxNwSvv2d59MMLPev45EQQoFkbP7Z4yuCIv0u2cmRLCjE7oyei/t9D112+S0bCDD8NZuzwCklE8CTwLkDR0jrcmRLUnKeR2B2XA9K8hUTW1cHV9d02dijx3Sl5bTYcYO6WtuGDXNbNBihXpKIP/i6AJpNfdd800OHT5E/21/Q5UaIkrt3a0fPbOBHT2Bo90A0CT8zZjO5E99nZKc9J8RuiIs0uuebiKYrGQ5dLwjOKP30s4Y/nPeqZ1BeGu3ZwBODO7XK45bZ0OSyrZEZklVnz35BsPSVVMdzMIQKhuHfJZg6T0JxNV70fZnyri5TNn0UxQpEYE8M1pnyJVmxU5Dw1j5O/498n0i+sP8PPBHipQ9CfV/ALujl1dmsHODIiVNxgCOnBxFSVuccee5A6+tpsX2mC2se1Y3tPDwixtYtesIZyOm0BDWDDtD3U8i7gzNJaP30o4Y/m6bnNYF6FEMYFDfvLhSzdmQpLIpkTkJdEWgLwtDQZQk0rwNh03TMCSvNwb4U1OEZwfFO7ydkks4Elu0hiyhVPyA64Nb+NQnZ5uM44Nf2zZ+YYSZId/l+8ZXWG2UUKTsAWKSP6RXDM4KEdVRqBYTeCS/PrFCaapFmXPgtQnZMFtUN7Rw9x/NazghJWjRyeCs7yMhLllxVunwhG09Ed06Oa2T0dVhoIuAG4CBQogm4IdSyj+le362nLTZuo6TQK/Rilha9nvuHLAraXSGWef/CkrUEIZmlpFeqY8jQqJq6pRchKPXMECNLGZ9pJi8qFQut74GxNv3ATZxaeyLuw60Y3M8FLj8TsSGF5DCQAEeuX0CJQeWx5zP2lkz8igVMc8V4WoTsmG2qKxrJqIlZoU7p4AhYdGq3fa2F6oaeeT2icxfvpGwZhBQzVKDW/efSGoy6u7o0clpWdSguzoK6O6uvH+24VYtw0On8PjpSZQbAyhzHeuU6H4bUHjp9mfou7+Sh1b3ZT1Fvj0LLMmloE/IXpSGNG3z1jl71j3HEMNAjZp0dBSW6tMQwMeGq7A/nvI7pX9niWgbahCO74FoGekAOiW1j0HjGsd1JFT/j2l6mjLH/yXlksfahLaaLZxmo4I+oZTHu+WBiC55rXZfTPPUDBau2g2YJsNzzona3ZFlDbpHmYC6O/wItNcicUt0b50cxYOfuZnvTkpu53VKLmOH9LXv5ZTGXlg7nk8TJCgjSBQe0b/MeorJCyqIUdej7XuKALpN7N1lHxI0AD0CDR/Gb2tYSQK5sArPAZxp9pZQckW42oS2mC2cQkZAVUBKL4UvKVRVcNvEoaypj/kMLJyzTtTujCxr0DkG0A54OeUsAv34ih1JVXYviS5TJ5+fGnvpZLNFpZVQdvtnPsd3ogyisq6ZFdoc5gcWIKSBgWIzA/DrBeBFNnxIiRFlAlL6Syi5IlxtQqZmC7eQ0RZMHzvIDj/+wbLauIKGAlDV89uJ2unIsgadYwBthCVdtUYM1GhxN2dtnnRaULrL6rbJyedhDywbabaorKxr5pH8ekoO/BIzfOduGD2Ge5VPsC1SyNViM58SlUxQG1I0iJfR8FQdX8IP2EloVgXSnI2/S+Gcg2pUA9CMmN8orv6TD5qOnAag5XTYzCWJwooYi4skyKHjkWUNOscA2ojKumZaIwYSs7b/vGW1dmy+RdTnzZhgJ205iblT0rfaJqbSGDyRxB5YNjLaR3jB3eZ+gJqnKSu+hffGX8R7vW+mX6/LGF/5t7Sf+VRBCfuVwQwWLeQ3b3CVmRYwrBQmf9FuDp+z8Xct3ELG1v0nePK9ndQ3m0Q9afe3KDbvP8HCVbsp6BPCIfzbf+uGtBMzncJMLsKmA5FFDTrHANqI8tEDUBVhN3gxpGRpTZPdCCbgkLjW1B9h7JC+ngk4lqTfJidfKntgfYVpv7dgRGDL3xkE3Km+AJPvIbn8F4M0NPoc2cylbCZCAEMNoMgIcU7g/Rtg8Picjb8bwRn/P3/5RlojiaYgVREYhr9/4LXafQnzMaCY2eXBgEJBn5A9pxVFIKNaRl4w5yDu7lBSH5KDF8pGFjD/jokEFGFHQ0ji2+NFdJnQFMZpl22NmB3DrOs9e38537llbPqLZtQ0DCWIgYqhBBOl7VHTzAgeD0i9FQ5tTft5LUlREWYU0N78Caa5xwlDjzEhq2F9Dt0CS2qabI0VzN9TwSTSP75jItePGeh77oALQmw/cCJu27WXDbDnasvpsD2nNV2iS1MsCEdi877T0bgaKh4zP3PwRU4DaAfuuXqEHYljSUhLo+3xVFXBkBJdl6iqKSU9vmIHBX1CBFSFsGYuxsVVjcyMJtZk6uRbuHcIL579HlexiRp9At81xsSHmxZOhTl/N+PzTx7C2PIqwmG2MRo+TFsCsOV8CQqSS46vt7daDWNytYG6J6obWnihOr5HdUAVzJ5SaCd1jR3S1zPSB+Dl9XvjzD8AFTsO862biykbWcDW/ScS9gMoiugaB3Eu2TBt5BhAO+FUsSvrmu2aKgV9Qjzyci06pnnokZfNfsChgMINxRfzz00HbP/Br97cxrejiyldVDe0RHsMj2ENY1B0vP0GDnthyy+upP+pXbEqnxk8p8BsHGP9LTDszOAIKu/IyVx52VgG+V3gPC//0JWorGtG010hnIZk2EW9E+bu82t2s74pvjy4F3GX0hR2Kuua2Xv0TFxOoQA7MKJLzD/nWbJhe0qE5BhAFuBl16+sa0aL2lV1XWLFz0Q0g4F988z2kFG1+f3th1lTfyQje2llXTOGMyojlbTVuJqCM42Aq9F7BnAzDAHoCN7WJ/Nx9SPyttbAzqWJEldOIutSWP6lcMTAwDTjOUOP3fWlavduQE8javT5NbujRRQBAUJCMKpZzOzKchHnUbJhe0uE5BhAO2Bx3j1HzyRE8DijJiQQMH3CBAMKs0qHM6t0OL96cxvvbz9sM4ZkkT9uLm8vas1AETFpy1MaiDaMEVK3pX+ZTghICkgEYYI0cyFBNBS7Gc2ieGn/PJPIuhvcCYq1e4/ZP707V6B277G0JQOv1IJPXT6Un37u8qyNvU04j5IN21siJMcA2gh3lmVAEehGrKFMZV2zrRYrwF1XjeCSi3rHEeZv31zMqrpmIrpE9ZHgqxtaWFLTxAvVTWh6PJd3LuqW02EWrtqdkH18wcFqil79PKrUAIkmTQOOgtG+CAChIMq+xIHQGCbtqkY5EDAJvBKAtc+YDmFna8rzRCLrrnBHA4WjRd/mzZhgCxJCCA6faPU0+YCpOfjts/Dy+r3cd82oro/8OU+SDdtb2TTHANKFy4bt5Ly6bvD5qYkEPi8Y+2H8VGLp+OeGM9nM2u/k8tb17BA8YTIhS6NYUtPE5Wt/z1gRsU0+tXI0f9Nv4JHAAoLoSZUAy1Tku3PIlYx47f+YhF0JmI3jwawJ5JT2pz103khk3R1uibHldJh5MyYwL5rl+87WgwRUQURPnJFjB/dl8/4THleNwYj6BrqcAZwnaG9l0xwDSAceNuzy0WPiOK+bwKfzwyytabIXWkSXCQtnqUfonpvLOxc0mJqElGbk0cY9xxhvSHBEa14yrpxhQ77B0f1nGbT1Wc/HdSZ3+luKJGcqfktQCxMQBoYe4eCJMIOunwPrnouX9htXm2YhLzaXcw5nFakcgl4So+VPkpiJXROHXchHTcfifi1VwJYDyYm/BWdkW2fgnG3vmCbaU9k0xwDSgcuGvWfdG1Tm90/ZRSnVD+Mmh5LYZC7oE2JxVaN9jCLg5nGD+drHL4u75okzZqKXANuJt3HvMRZXNfJR0zHGKaNAjdn8B42ZyoNTiqBxDmz/W1x7SBvCt1J0HELH6tAR0YgiSf+tz8H1c+KlfYAFM6JtK4G1z5qhqYVTc87hLCMdh6CfYOJkCnddNYKtBzbaZqHSERdRs/soMpX9JworOzhdotQeAn5Ot3fsBOQYgAuek9FhwzaUIA+t7stqbWvChMt0Is8qHc4LVY1EdElQFUy85EJ7MgMJqffvbD3I1z5+mX2vJ97dyRubwUgcrQAAIABJREFUDtjHzLlmFPdcPYLHV+ywI5AGiJMYQpi9gFFg/3qoeIwtva6gdtKT3NbwX1zQssl7gE7VwwMKkp1yKGPEHoQAFR0++BUMK4sR/3d+FitFAWZmsuUEzjmHs4p0HYLWNmeDdzdTcOa3VNY1U1XfYp8vRDR7WJd4BQv5+bO80F4Cfk60d+xCLTjHABzwnYyOqIKlzZeyelVewoRry0QuG1nAogeuYUlNEwKo3XvMYc5JRFiXLIlmDt/7VGVC0s7rG/fziQlD4tT8amUCQgmakr6iwtpnkIbGSCPAw5G5RAKX8Hllk68vwNcHgCn1Dxk6DA7siX4Htr5u/lMCmO3DTOezDdWRsRxlrFIPo4kAO3tdQUnSN5ZDMqTrEPSbq24TpvN7XtAMI1Wi8f1jh/RlaU0Tz6/ZHRcNJIDZUwozCmd2Z8ZnQsB7fHvHLtaCcwzAgaTSRDSq4NKGFkLVlQkTrj2SyFJH/aBUkZnCcS836ptPc/eTK1n0wDV2Ibr7hukoa6JXlQYYEoFBEI3PKRXMEu+Yu3zul9QRjKBf4QQ4vD4m5UfbUKLrjuMUGDYZhk4y+xVbE7xwKls++QyvvrKYD7QSNr6c2AYzh/SRrkMw07nqd93KuuaEfAHLH5YMTk25fPSAhMz4+4YfoOTs+rQk4h7f3rGLteAcA3AgHWnCb8K1VRJxRxOVjSygqqHFUwsIqsJeXHZrSEXQr1eAI6dMW35Yl/zna5up2X0UQ0omN/ydT6gRhBVrpChIKYhIlYEcsyOBnE1hIOr89SH8McuQhJMHofzr8OFvY8TfDSHg1p97Tuy3To7ivyO3Y0hQZQ9Q4bu50zodh2Bb5qrzuk4/lbMgogDuLEvu/PXSPu4sG263oZwkt3LZaz8DqaUtEbufuUc5hbs4RDrHABxIV5rwWmTJzk02IZ2LUVEE1Q0tSGlWWywdcRFr6lvsSBynau28l9sXYJ0D8H6khG+qQUJCw1CCvDP6IU4fPcj7ewzuUlfY59iEP3ozN+23xpDQPWzL30EortLQ7pP9992UX09r8GU+1EqoVUu6twp/jjit05nnfnPWTcDvv/5Snnp/F7phRqBNvOTCpPf20j5mlQ63a2hdG9hCQEba3E+ixzmFuzhpLccAXGhPSJWflJSsNaS1GJfWNPHc6t1Y4deGISka3JeP9hyzJbVZDtXausaSmiZWbD1ob3cm65SKbZQrm/lR5D5mj7+ARzcNYPWGIkpFkEWhnxBAA+KJul+JCCfxt8+xO4q4Cbw7hkh6L+TG1ZT84wuMVVv5X4EgO29bSEl3XqznkNM62TxPRkTdBLxv7yDz75ho5xHMX77RLn3uhYI+IZRoOrqlfTgZ0k35sxH/WNZmibhHOoW7MGktxwA6AM4ELrv0AuaEtApoWRPfYhRWMphFtNcwnlml1zKrdLivJHb3HysTfAElQ/pSd/gU47UtPBt6lCAaEQL876afsFozGchMtYIQmj220zJIH2GakNxx/56Sf9JaQgJKPg1bX4uZhJQAHGsyJeiEfgVhhDR9EiVn1wM3t/GtdwLOk4zmZEQ0VR6Bu/S5c95aWciGlCiKYM41o9i1dgVDPtpE2ZW3UDZ9KlAEQ9KUiD3McT3eKdzJyDGADoCzW5hFOBVh9k9dXNVoVwWdN2OCrR0EVIUyZRv/EzCJNmqIgHKtPbGtZjNW+d4n3t3p6QjetO8E//ax0UzevYLgPo2AMEBqXH38HxSqA6k0xjGQ+GqPvUUkIeLTIvxuyd86yDtBTJhRPvmD4NO/NENOTx6A7W9C9V9h3aJ4s0lPI6jnSY2ZZETUbT4C2Hv0jF0KRQh4ce0efvnGVoxocbhFD1wDwPxXNsYi16Sk+oN/8K3ATwmiYaz7LcqcV8x90fdbbYyhcsUObzOVjzmuxzuFOxk5BtABKOgTsiVlMAnldUUDKezfh+dW77Ylq+fX7I61ldQMpgY2E8Qk2lKa8fLVxpg4Sf+FqkYeuX0ib2056Hv/jfuO89myW4gs/wtIDR2F2eq7qBhECPCuPsk+VvhlfDkovNM/kDwqyCx9TdUCUEPmgq6vMMNCvcwmPZGgngc1ZlIRUWddIWc9rNKRps9qx8GTQFSbZTP//Mch/rx7UJzAIhTBVLHJnu+GHjGzxdctAq0VQyi8pM3hWe1Gb1t+EnOcV55DDt7IMYAsw1JzncQ/L6jw7ZuLAUfDGEWwcd/xGO0VsFIfxzfVAEgNDZX6XldQWddMxLFwIrrktdp9cQ263ajZ3cI3j/WmX3gu5cpmLhGH+by6IqoNRBgsWtBQCERt906CnmACcjiFU5WQlkjQIygCdK2VY6/N58LSO5NL+ecBQe2JSMcX5o5gO3Si1d5XKrbZJkh974us1udSQ7G9/8aSQazZNh4dBSElhlBoPnGWgdpZBBIhDeYpf2Ejw1mvFSfa8kdNM/NadMP8dMyrHucI7kLkWkJmGdaisKqAXj9mYFyijdX2cfaUQgxH+NzogRdQI4u5NzyXX2qzuad1Lrcvi1DQJ0QwEPuZgqpgwAWhpGM41aqz4+BJamQxv9PvYKk+jQgBNGlmBE9S6jBQWKWXmH0KpKNENPEZyMIVEeT2D7gL2WmoaFKgIOm7932zQfytP4cbH25/1EyuzV+noLqhhcdX7KC6oSXpPstUpEb7C9w6YYh9XLkS02aD6FwX2GLvCygwfewgrNkkkBhS8quNfdCkYjcrUjAoVzajqvFmKKvDmeGUnhzw8mHk4I2kGoAQokRKuUUIUeq1X0pZ0zHD6jnwq9Nv2U/dnb6c6vOSqDYQDCj86/Wj+cFLG6iRxdTopqQkotUaF33VjBKSwOlWjZfW7c1ojBZj+VZgCdcrtahCIqXBDoZRynazhAOgA+u10UxW6xKuIV1Mwdzo+g68IyfTS7ZyrVJLAAnaWdi/Dmb8yvfd3ZRfnzrxp7NDMLt5vH9HIZn07LXP7Q946oNdaLqk0hhHBFObNZQAF0+8CXW96SdQFIWNe49xFRtRMUz/mDS4UJ7gB5E5/Di4ACENIgSpNMaBIhPG9xX5OoaqoQgJhhZnAso5gtNHKhPQd4AHgMc89kngxvbcXAhxK/BrzHqVT0kpf96e63U2/BZLurkE7nr+X502mj9W1NmhoM4wOTDNR8syJP4WamQxv9ZmMTW0laA0I4PsRLAoAVcllEaJv9OH4RSwvBLFnH6BUSNH83DdBK5WNps9CIRErF0YnwHseHcT9C38a/BRpKIh1Dx/wt6ZIZhOZqMEYPI9CeM/V5EsAqiyrtl24rZGzHLjwxwl0B9fscPWai2ho1zZTKUxjo/W59v7IprBwROtbGcCEV6E6HxcI8azRh/DtnChfR7AV8VL7Fp7lrKRM+0Ai5XCNJcq6Cgu02LOEZw+kjIAKeUD0c/p2b6xEEIFHgc+ATQBa4QQL0spfSqTdT+4F4szxPPB6UX2cX5JNe56/qGAwo8/ezm1e49xOGpPXVLTxD837uep93fZGZdtRa0y1l6UR2Q+84MLgETHrnA4fy113CMQKE4r0CVIJchHA26jekcei/WPc4/6lmljNLSELmHWu7s6aioQqRJ/OjNiKI7Z6KZTe91zvsxp1H/8PXbqzz/dcePqBCSTnq3Ks2DOh+fXNCKltIUfZ5c6Q8JahzarIO15JIG3Nh9AyiLu1edyrboZbcR1tJwYCYdO2VrwFHU7T0ejhJQNy6BsOAV9hiCJMZh5l7dw5bQZCb9Le/J5ziek5QQWQswGXpdSnhBCfB8oBX4spVzbjntPBXZIKeui93gOuAPoMQzAuVjcIZ6WNpDKIeXVoGNW6XDPGH8vqAoYRurSzYowx/vednNxfUNdRsAh/UOM4HuaexywQ0SdWgKC44XTmTisH6FAhJf0acxSK+gldIRHlzCrn8Jq3TQVqEJHJCPsnRkxZDEb7Sw2yfJhTk7ib33vyUwgmfS80mVL1x0SfWVdMw9OL0poPflCdRO6bsRKRrj8TDWymBqtGLVeoBun4q4/s2AXoZMaKoZZTnz9IloueNBOdlxHMR8MHYtuDPAPF80hKdKNAvqBlHKxEOJ64JPA/wX+AFzdjnsPAxod35u8rieEeADTDMWIESPacbvsw7lY9hw9ExfiaanOzpyAcCQxM9EvsSaSgvirAm4aN5i3thzwJf75eSqnWnUk5oI5ueNDvqGaqrVlow1JLeE8L6LvZe5xJocpSPrvfoOLmt7h22N/Q7Uxjb8qv2GmWsGgAxXIo7tNCVAPI+orKJs2NfruxtCQf3l6xb86K2LIYjbrF8Uzru6ep5Al+EnPg/v1AkcOiSISmxS5z7USGfcePcOi1bt976m7tFtVgZeOjmaWqpi9poVEr36ahn7jUZVhiGj71YI+oVzETzuQLgOwqnx9Gvi9lHKZEOKRdt7bK5o8gZZJKZ8EngSYMmVK+2wgHQCnU3epw6lrLYgTZ2JJVgZmjgDEm4Wevb/cLgkNJlMIRlVpPxgS6g6dTKjG6ETRxfmsazIXrDMsL0KAe8Nz+WHkS/yr+jp5tJKHxmDlqC+hjzMLAfjkAwg9TP6WxfxT+wpHlP18JbgIKUwVRQKalLQ07WRQ42rK/l975x4eRXkv/s87u5sEwsUQlIsJlwjhFiQSCEHAS6EUK8WKUsVbab0ebavHc3pqtdKK91/rOa2tnmot6rGKVkWxWquiqIAikAASLuGSEAggmBggBMhe5v39MbuT2d3Zze5mN5vdzOd5eMjuzs68Mzvz/b7v9zq41PuwDiPuGcDtdeL6lM24+VHtZ7zYASu3p6Xz+Obzz2JF1WG9f8V9c4rCNkSC4KCHwBLmoVAlrHMP41XOZ77tI62fheqhb/06XJ6BzBytNUdKydIPnYhIFcB+IcRTaE/po0KITNofQloH5Bte5wGxeTg7AWZL5/LaRp5ZVaNvI4DGE06/UhE2RXDD1KF6SejXK+p48YYyltxYxlOf7ObQsVP07uZg5c56P+3osImwGVmj+vfUhT/4h+Uh3cy1rWSe7RMy8F8BBNX7IVgRmOaOmaQG/1x5GTuq9rbXXGRDklu1BHYvNbWpt1XJMaJKj/GMGGpj1bHnkYt1M9B4sYOl2Y/CR6ldLC4UJYNzePmmyX5RP5GGWBprXr2yfh9uT/CMf2huNru+1sxA57CDMts2KtUhOG0OPXDB5xg+6fLov78V8RM7kSqAHwCzgN9JKY8IIQYAP2/nsdcBw4UQQ4H9wJXAVe3cZ6dCq5feeqP7OiUZoyncquTplVrkjXEWU1aQy8dVh3EaHhSb0B6kYf16ctn4PFZ+9A7Ohk9Zo46iQnpDR/E2ow9YGhjD8lzen93hrQcEbWf4BuadmZmBfH9XqkO4UvmQSbbtQd+XgA0V6W5BfPwwXPBLXUi+9MVevahYpiN4OR9xgk8HF23Tbf4rt2vCv7MUi0tAKKtZFnA0DZBKBucwd3wev1++g1XeSY0Apo/sx8c7vgb8V6tuYed+97X0lsf97vPRnu3s/8cHlBTPDApFfcLyB0RMW3kAWcAtaGv0zUANgJTyIHCwPQeWUrqFED8B3kMLA10spdzSnn22RSLrhJs9EGUFuX6dlG6YOpQ11Q1+0RSgCX67IhC0Vkh8vaLOT/iDJkTPH3GGFmG0by1Fe+/EZnfpJh3PmROZOaY/TSddulLxcaDnWP7Q93fkH6vg9YYhANoKwOsDaEsR+Dt8gx3FeoE4Cd/J2Ew/0Qiq//c+9oylzFaFQ7qwCRW5ewWi9nP44VuUq8NZuKxSj3Qy85csrajT/Slhl/vJqjGUyONGK8wTnDcRieklXPTbHTMKWbfnG33mfnrPTNwelfFiB7fbXycDFzYhQbrJEcfZUXgTm7YfAqkpiDv2P4RjvxvXhsepOfvPlJ2jBSqGU0op1Segg2hrBfA84AJWAhcBo4Hb43VwKeU/gX/Ga3/hSHR6uNkDERgV4Sv8pgjhZ0axe9vsGe2pT32yO/ggotWHsH/j+/T3ClKkmzJlGwf6XsCmfUf4YNuhoBn7V8da+POxvsBM/b35zl/xlOO/6SuOBR3KTBGYhYqaVaQ4y1NNf6XR73MPUGar4j7XtVxkW8sUpRK7kEj3ScTq37Om3yKtjpAXJaCvbHltI6+u36dfs8DsUD+SVWMoUceNRZgneBXUVrJVW89byeAcvWvdRUUDACjGN/N3oSBxS4ELO5+5R5Ht8qB6F7VGc6bb46Jm/b/4VXk3LhufF1IphRpPV1cKbSmA0VLKsQBCiL8CKZuDn2hnUagHwrfsfWLFrtZ+v95yuKoq9R6rV01qjXAqr23Ul8NGpITf/GMLK6oOc3RHT5632XWn7hp1FBURJon5Sk6vUUfxmHseDzv+2qYJyGwsev+AICUgUNBKYfsi/+wCkG76iOP8wX0ZkzO2IqVHW/9vf4eL+0zhj/YCXUEuuqQoKFw2ms5TSasxlIjjxiLME7QaCQxeCGV6MUa/jXFvx/nxSvjW9/Vx+2pmOd0q6/Z8w2Xj8wyCXRP+q9Ui/uC+jErbSH48oBerdtWDDDZnfu4ZhQvtWKGUUqjyEF09gqgtBaDbKrwmmwQPJ3EkOj28rezDwJwB1TudsQkY0b+n37Zrqhtwm4T3SMDpVvlg6yFAS6LxCXKfbdQMo8AH/KKB7nNdqxWGQ20z/l8fR4jEMR/HZHfykXoSmRsbUspWRSULqVH7U6js11dCQw4t58UbFocUKIG/32Vt9J1NK2IR5glYjZjNom+7cJjp+zndM/T+Fn/LeIjMGjc8v1hfvQQKZAmsF/6ZwZ/n38io08dTmmnnL6tq9PszMMt4I4Vk2BW9G5kA5o73nyCECrcOOynsAuVA2lIA44TQ7QMC6OZ9rSWCStkroaOLIx2RHh4u+9AsZ0CixT8HLlV99dXdqkQ1ZOIGRt8Y6waFIjD883XPNL9ooItsa7Xqi4aZvFkIaGAoqA+zlUM/RWtJqQhwS8HfPRdwQPbVhf94sYOhylf69wH29GsNA636qsm0i1qXTe+PVZjHeTXiE5jF7GCy3EbNhpN6eQaz2bUiWs01Cv6Z3qYKffx1PL/yDIYe38DgkpncNXEG5bWNXPHU50F5AhspZIOnELtNMGPEGUi01bHbo90zgY3pQ90/ISeFYcxu6WQ2aqsUhK2jBtIRJDo9vK0bo62cAeNMyqYIxp7Zm8kFueyub6bm6+P0yc5g474jev/VQbnZeu31UBjtpUK66MtR/+Vz5hSmuLcivVnBZgIfgoW8aYcw73s+n4KU4MHGUs80vyilm09bi/2k1oxelbBLPZPX9/Tg+ZVrdBOQR5VBzl7j75dOD2FEdIKy2WUFuZTad/Gs8pBfeQZfVnfg/Rwy03vfWkr2ruTxKcN5YX8/LioaoP+GJYPnA/P1YwZG0vnwddlzeyQfbjukmxohtIk38PkPO6kIYXZLt1LTVj+AOBHJjRHKfmostuWbSakeyZd1R9ly8FhrzPTXzdxyXgE9uzn0h6ytkhFr1FF4ULxVFyXfsm/iGdd3GKPU8q6nlN2eAXwozmGGUq7Va4lwth8uasj3WpWwRz3D77NzxA4uOPG+36rmLOUAdx74T9Z77qZcFiKlNg4hCelgnP/053pC0pKbJqf0Q5gqlAzO4bHSJjLLvTN6VWta1JrV7X8/+zK9D7kyGHJoOYy6RNvR83NQ3S1Mk3aect3Nb2pGUnngqN7tzkhZQW5rGQnjWJQdlIpg82dgZnIk5xRNJFm6JZ5ZCiBOGG8Mp0vl98t3+JWCDmU/NeJbFuvtJCEoYWbLwWO8cH1rxQxfqWhjQ3kjFbKQVz3ebEohsUk3N9rfRUFlirLF27dAoqKFoRozfAMTwdpyAQXWEhJAoXKAJRkP8GvXD+kjjjNQ1GMzOIgBbEIivDXjN7gKvY5yLW9i4ewxQQ+YMUTW6ZG8XlGX0g9hKnFm8UzY9KcgwWgmSEsG51Ci7ITn79e2r/0ciucjPS0oaH2gJ4ltlLsLWfLFXpZ6kyADZ+mLLini3jc36/d3qX0Xf3M8jKK2hkBXyELsClwxcVCQ/d9HVKvGEGa3dCs13WUUQKJNBnolRJeKCqzeVc+6Pd/oN3QoO6lxTMZsyVfX79N6rCrCTwn4QuaM5zPwtG5hi8Et9RZmc0g3EoGCB5tA7yomBChSotKazBtJYpgvCsj4HsA3ag/6KMf1zxzSzYOOxYDmEPagaPXVvMnkDiSKPYOiCRczaHN39jSc8PZTljSecAYdO3BYcQ9N6ALOv5iJ1h8RaEpB4hYOhOpEIvhG9gBaAxwCJ04AV00axIj+PfVyKbfaN+CocCEMIdAVnkKumDiIBy8dazqMmEw3Jma3dPNFdQkF0BF2O9+NsegfW/iy7mjQEjFw5hCqiJUxW9J3k1V91aTHS181aVDQ+SyYPCTs2IxREz1o5t/sbwfZ7aG1wieEN/EYPzdu49vfacpxXNhwSE/rfnXzkoflnhK6iRbe9ZSyQ+ZzuX0VE/L7sHh1Dbkele/atvGFOoot9pF+/hHf9Zg7Po9Xy1t9KIEOv3bR0Y1nUpFo/BGBppRxV7E/Yzhnrr4XBZVfO15gtzufclVb+a3a6T9x8uG3wth3Ejb9CdXtxIWNL9RRZDnC3wfxNN0k2pfYkXQJBdCRdrttXzW1JisZkpkCZw5tjcnoFygryPXLEwg0Nz1jCJHzoQj/1o4+eomTeNDi8o1RP+Bf4z/QFxBuRRDoLFYknJI2vpE9acHOIKXeoGwkF9o2YkOlVNESwy5VPiVjn4u/Ka+hKlo7SY/ioOa7LzEyRNmBJTcmaBaW6DIS8V5ddMbVimFM5epwaoqeZLJtq2Y+yi9lyJ6VSEUipCRLePh9WTN3He6rl4Zo8xn1rkKUPSupzRrHt44P4e427gOfA7tEbqFcjKGs4NzEnHuK0SUUQEfZ7Yzx+wKYNyE/9CyG8EWszGb5Ww4e46KiAX7nI4RAlbLVoXpGDyYN7UPPTDt//lQrB+HXoBsFD3ZNwGlWf80mj7+wl8bXmEcGmeFTIN2Fk+7CGWSaUhCAB7s3zf8i21ot7R+JRGLzHsuGm5GnNlFeW8Lvl+8IKgGRMNtross5xHN10Z79JUpxGMakKg5+67ybte5hZNhLePHs4ZQADJmmdX/zOBG2DM4snskd6nC/0hBt/r7eVchIYGQEwypRdvJSxkPea7UMRZmM1pKka9MlFEBH2e2MgnmifRe32jdoy1WTB6ytMRln+S0uVRfmK3fW89ClY3VfweGmFj6uOozq0ZTA3oZmfjxlKK+sa6297l8JFF72XMgB2ZeBop4rbR+imGXzejWKsS1kTMlhAbkFmrKy4fYmhr3rKeVcZSuKbA1DlQiELYPtWeN0Jag5q/Ezn/mqqQZmUreLRJaRiPfqItb9JdLM5TcmKJFbWCOH+c/qTa5xCST2Gd2zEkV1gSF6qdOsmJJIl1AA0DF2O59Qr9mwgrmbH0KpcGkREyEesHBjMioTzSHa+tkr6/ay8HtjtGgYt+rnBHV7pF9RNfCGggotFhvFwaeZM1h5soCfqi9gM+zba6EJ9g1EMPsPFSkUmCegYuNe1wL6CEN1Rxd6I3APNv5ln063Cdew8/gQnO4qVKmZtKYM68sdMwr9ygy4Ve18R/TvGb/fN1Ex9/FeXcS6v0SauYxjUhyUe8ZgEyahmSEcrKF+w3YHcSSrQGAnJ+0VQEcnDJUMzqFkbw1SdYJU9Q5Y0T5gxhVC00mXvgIA2HrwmC78fZnCNl0AC7+iaqD1Av6k7K/0PLSGpn5lfLraQYvLw2THNu93vMJZ1QStkUirf5gpCLNS0eWe4eyQ+VSorbHbL6vT/RqBV7QUwsfw/eImFKFlDGTYFS4qGqAX1jPGhqtSmkZVdTrivbqIdX+JFIaGMSlDpvFzdXi7f5O4BHEkq0BgJyetFUBHZe0FKpntWeMYrHoLtUkbtVnjQtopwyko44your6Z97ceArTyEQKtiqjTa/pRFMG8CfkUDezNb96qxOWR2Lxx0WMG9uZnb2/B6Z6CUiXwqNrs+ZD0P55P+JuVhIgkB8DsvcAew5Ns21lie4D5zl/5JfCYlbVYtvGA5qNQBGefqZ2Xr+fyDVOH8syqGlRvU/KUaQ0Y79VFLPtLtDA0jKkE2v07hAuYiDq2P07nanbcVMxOT2sF0BHRP2ZKZs3xIXzkuptJYhtr5SguPD7EVAFEo6AuGHGGrgBUCWMG9oYJWhMVCaiq5MzTummF5byzZkVRaG5x8//e2643oJFehzHA057ZfMu2Abv0+DmBte3MZ/TR1gM0294h3TzleIzH3D/gZXV6yO/6xulRJWv3NOrvO10qPbs5eOXmyRFHVUXK9nXLadz6ETmjv8XIiXFuU9mZ6ASlJSIlVBBHIiZ4kQhxs+NC+yqLJkt5pLUC6IjoHzPBU1aQyx9tI9noLsRhV/hliONGI7QaTzj18gmK9/Xc8Xm8HlBTyBeJ5EuseTOgRLQiYByt1UGvdN7LXNtK5ts+0kpBYF7jH6IX/kYC8w36iiYedvyVQe5D/D9PdI3gfL2VI4qqiiLaZfu65Qx+ez7DcOOq/gvbWZLeSqATYhSE0GrSa6t0SjwmeJEqlFBJnbGOJZn1hdJWAfhupIWzx7TZuLo9mCmZcBE+xhvcmD0shNCbvYQ6Tqaj9ThNJ10s+scWzj6zt94i0nccuy10Q/k5uft5qMm/Ofyv3NezRQ7hfsezKFI1XQ1g8l40CsFsWynhZvvb7JX9/J3Cbe0LeLfyoF5G23c935zjaJ29D86JOtqlcetHDDNUSm3c+hFYCqDDMApCu00BKXWTX7jSKcZnrz0z6UgVSqiJZayTzURZKgKVqRlpqQA6UqOGEvZmEQ1m41o4e4zeB3fhskoA05DGcE7hDfuO6PXxSwbnMC6vN+sMJhMjA4+sx2FrFXJlyjY2eApZ4plOlZrPItuzjLHVhuwBHA+MmcOKhIccf9XMWN6BUpeSAAAgAElEQVQIoXBmIdBWQat31fNFdQMIgdujUmrfxUsZD2mhfvsWQ/+3oo52yRn9LVzVf9ErpeaM/lb8TtqiTQIFIRA2MSzw2YP2mWEitRiEeuZjDWNNhKUiUNaIjG7ZZtulpQIIjKFfmuBiYZGGmIZaOvoSudoKafQd59q/fuH3vsvj31MgXHXQzz2j+ImttRz0F3KUbmsvFPsYZdPyB8w7fWnE4gswEhQqimaaUqSH+x3PscOZ3+ZKQJXaeYN27UrkFm+tGUPd+SijXUZOnMF2lnQNH0AnJLBpElLiUWWbwth33xu77sUyk44mXyhk8bsY5Ewi8pQCZY2S0b2n2XYprQBCLffKCnJ1M4gEXl2/L2SFwI4klKZXDKGbakCDGDMuKhrAyp31+mtF4Gc+umLiIDbVbW79HBDeFpSB3ZR8gna82MH9juf8SkL7ML4OLADXXgJLTShS1Yt7AQw7owdFA3vx9pcH8ahSUxTecxFCSxqTqqRcjAHbMi3JxyfsY4h2GTlxhmX2SRJmM/pohGI8ZtLJqvMT7+MGXgvVeaLJbDshQ03zOiETJkyQ69evB9o289z9xmaWeCNkbALunDkiyIaYDMyU1ktf7GXhskpUVZLhiGzp+tIXe1m8qprq+makhMyA7934f+u9rSO187+idBD7vjnhpzhAC7FESv7Nvow7bH/H7m3l6CstEao0dDwwyxMA+KXrel5Wp+OdBJJhV5g1pj9vbTqAlOCwCYrzT6N87xFUb3OcRZcUcdXAr6w47y5OKoZiJgrjtZgwpE+5lHJC4DYpuwJoy3Fy2fg8065bnRFfudtobtyrJg2i8sBRdn/djEQzdfnq4pfXNnJGz0wybFopaSEERQN7c9n4PL6obtBr6TtsgvvmFNF4wsn0Hj+Ad17VS0T7FACYC+pw3cMixUy5uKWgjziudQtTvWWCXSpvbTqgF7dzevzDQlVf2egUCm3sKiQlEbOLC34fkVyLlFUAbS33Oqr+TzSEW7WE+rF87SMl+EX6lNc28lp5nW6/l8Df1++jaGBvvZ+uoggQmm/h3mWV3H9JEUtumqzXVfczi33wAlpHgFbnLPgL+XDCP7C8tFlPYR9m/gUPAqTQG8dLtEQ3rTuYMG0L6EMRolMr+K5KrMEY1iy+40hZBRCJgO9ss4Fow73Kaxv9Wj6+tn6f3v7QWHnUh9sjeWXdXr+2kj48quSeNzfz4PfH8lBA04zt65ZTuPoPusnHTIj7MGYGh2sHGVhKWgL1ak9OV5r8lEKT7MbfPNNZrk4I8kuce1YuEhgzoBd/WVUTUgncMHVop/qdLTRiCW9Mt567sRKtEoxVaaasAoDkCfhYL3a0Tqo11Q16OBz4R/sEto/00a9XFtu+ajKNBJKSoCij8tpGPvnHqxQKGSTcfYJfxetINpnph7LjG1+/55nA057ZVMhCrlQ+1Au/uXCwwPULXeAHloJYuaseAazb8w2FZ/Rg21emfix6dnNYs8ZEEmPp6FicsunWczcWolWC7VGaKa0AkkF7Lna0Zqmyglwc9takLoctuMHM6972kW6PFi538/ln0bdnJi99sdd0n77CacZsytXukdzmsJMh3fp2Lmx85DkHgG/ZNqDg0QS6aO0P4JbQKHuRI5rwfViv9qKvcgykRCB4yn2xX6ZvUOG3MOGevpVDi0vFFWL2n+VIoTpAqUg7SkfHYoZNt567sRCtEmyP0kyKAhBCzAN+A4wCSqWU6+Ox346YBbZ3hhLNqqVkcI7e9D3QB2Dc12WG9pElg3P4YMtXpvsTaBE1xoeqrCCXP4gRzHf+irm2lQwT+8nEySueC9kh87nd/rrexN0jBQ3dh5N7YidSas1b+ogm3Nh41XM+Sz3TqJCFjBc7wgp4s8Jv4ZDA7sPHg96fNry1PHRXnzUmjHaWjo52ld4ZfXcdTbRKsD1KM1krgEpgLvBUvHbYUbbDRM5QzBRYJA+QcZvy2kaeWVUTtI0CzJ80KCgfomRwDvMm5PPiFxI86J3DRivPA3hbuEvcUuDBRp+Te7SeAQhUwCYkUqockH1bTTlRCvhICJz/2xTh1zy8q88aE0YS6uh3Nt9dRxOtEmyP0kyKApBSbgOtdn286KhZYKJmKLHY/cyieZZW1Pk1gwFN+D9w6diQXbN8ReUmq62dw4TXgG8TmvD/TC1CPW0w05r+qb8nUZBIPXKnIzHeOtasMYFYdfSTQiwrp1ju+07vAxBC3ATcBDBoUOi2f/GcmbdlSkrEDCUaBVZe28j8pz/X4/lfXreP+y8pYkT/nry6fp++nSJg+qh+3HL+WUH7CjxHrZPZSZTNy5CqC4/EO/MHt3DwB/dlyHqYlPG+XkjuIfU6pg928PjufhEVcWsPgU3uPQHlL7r6rDGhWPkVaUvCFIAQYjnQ3+Sje6SUyyLdj5TyaeBp0DKBQ20Xr1lgssLQolFga6obvHVwNHyF5H4wMV+f/QvgytJBQSGf4H+OimjtqVsyeC6U5MGml7BXvKiVVRA2nnV9h0lem/59rmu5ptcmDud/h+9PvZE11Q1U7KoKe242bzy/T4D7ylqHwyfwBZqt/+hJF5vqjuqfSwhbPdV3ntaqwMIiNAlTAFLKDi+oEo9ZYLIcitEosLKCXBw2oa8AQKsh5HPy+pSIr0JooCA0nqMqAwrQ5Zdq7fykB5CoUuUG2z8RSDwoANhPqRTVbIHzLoCC4WQEjMWIAL539gDe2XwQ1aPV8rlpWgF/WVlNiK/oKGiC/tOA8hU+Kg8cNX3fd85WZJCFRXg6vQmoo0lmGFqkCqxkcA5LbprMU5/s5sNth7R6OQ6FuePzmBsQEaTXGZKtddXLCnI1/0uoAnRGxx8CIT3YhURIiWb5R48IKZlWqmcX1ze1sKLqsN/qBOAf3kJuoM3qq+ubw5cbxd/cE4pAD5JR0VmRQRYWbZOsMNBLgT8CpwPvCCE2Sim/k4yxBBIPU1KkbeXac4ySwTk8fd2EkJFDvmMsXFapm4Wcho5lwmCEsQcqOmNj71PH4LM/4ZEe3NgAsEkVxeZA8UaEBEYhLa2oo3L/UTbvP4oqCcrgPXTsFKrhPQGMGtCT7QebCF3I2h+HTTDXu8LxHdc44184e4wVGWRh0QbJigJ6A3gjGceOhPaYkiIxPcTTPBFurGuqG/yEb4myk+8f38DnG0ajykxAE76Xl4Qolb2/AqreRZEqHmHj184fskPmM1nZxtBzZnG5iWPQNx7fOfpqu6uqikfVBPcVEwdRdWiLnsUsgR2Hjps6BxQBc8YN9CsHPX1UP24OcGwHzvgbTzityKA4YflS0hfLBBRnIjE9dJR5wtdG0ulSKbHtZEnmw9grXMxVHLxmv5t17mF+vgKdfWvhudngaWktCy1V+ojjVKhajP9DA1qdy6FWIT4BnNM9gy0Hjvols43o35PfL9/Bqp31SIJXCT5UCTX1zdwwdShbDh7joqIBpuGsOd0zULxmJWNrTktgtQ/Ll5LeWAogzkTiQ2hrm3jOuOaOz0MAt9o3YK9wgfSgqPBYaRNv9hhhfgxf9ifoTeI9CD3WXxFaU3rfWMNVOAX/Nn3G1pV3zChk3Z5vcLrUsKafTXVH2VR3FAF8vlvromZUAuW1jSx6e4uuRM4+s3c7rpiFEcuXkt5YCiDOtOVDaKtZfbxmXL5Koj4lc+0lZX4ZnWcWz+S2/BANcrxOYOlpAQkeFBa6F/ClGIEN/xZ9bQmINdUNuqnH6fL/3Hetfr98B6t31bcZJioxb5tpPAbA2j1anoSvcqpF7KR8bZ4YC9l1FSwFYCBeM+9Qpgez+PtEmYeWVtTpReScbpUX6vrxYKQZnfmlsOBtvl71HB9uO8Tr7qlU2kayyERptSUgcrpn6IJZJTh237gS8PkLLi/Jo2hgbyoPHOW18jrcbv8VQmDUUllBLjZF+GVAB/ZJtoiNUBOalPALtKOQXVfBUgBeOsLWGTb+3ku8ZlyBM2gJ0WV05pdyxvxSCmsbubC6gV8GPPxPrNjll0UcShg0nnDqSV1G05GRcPvwFbprOunimVU1ettM43UpGZzDokuKuHdZpW4GMlZOtWgfgROalPELtLOQXVfAUgBeOsLWWVaQ22YD+HhlNF82Po/X1u/D5ZE4bCLY0RshkT78ocYZjb/DrGezMaroWIs7uJOZF19bzVCVUy3iR8r4BZJQyC7VsBSAl46wdfpmqsYG8GbHMQo940w72mMtuWlydIokAntptA9/OIUW6UwycLu5IZSZFfXTMaSMX6ALFLJrrynOUgBeOqqiZKQN4OOxzI5KIO5bC89dDB4X2Byw4B3TByaWhz/UOCJVJikz4+wiJPRZibfTNo0L2cVDRlgKwEBHzSAjOU48hF5Us4NNL+mhn3ic2usQiV7xevgjVSYpM+PsQiTkWbGctlERDxlhKYBOSnuFXvSzg8DKOqF7NcTr4Y9UmXTU6swiyVhO26iIx8TIUgAdQCx2uvYKvahnB+Pmw4YXW2df4+ZHdbxYiVSZWPb9LoDltI2KeEyMLAWQYNrbRD5WoRf17MAb+x+r/TUl4sJjIF3Pq1PSBZy28SYSGVFe24itR65ZbxZLASSaVOgvoBOjwyxl4sKjJF3Pq1OTxk7bZOC7h23ZOWeafW4pgASTCv0F2ku6Rumk63lZdB1893Aol56lABJMV3BgpmuUTrqel0XXwXcPI827L4kQ73dKJkyYINevX5/sYViYkK628nQ9L4uuQ3ltI5OKhu93N9UHZVBaCqCdWAIi+Vi/QRfBquwZM0KIcinlhMD3LRNQO7CchMnH+g26CFaSWEJQkj2AVMbMSWjRsVi/Qfriq4VVXttoniRm0W6sFUA7sJyEycf6DdKTwJXdm3PGMdJKEos7XUIBJMpGnMgIH8uuHRldIcqqKxK4svvw+BBGWklicSftFUCibcSJiLW37NrRYZWJSD9MV3b5wyzBH2fSXgGkYjJPKo7ZwiKeWCu7jiHtFUAq2ohTccwWFvEm1pWdZT6NnC6RB5DIGyJR+7ZuYguL6LHMp+Z0qjwAIcRvge8BTmA38CMp5ZFEHS9RNuJE3mwJs2tbyTQWaYxlPo2OZOUBfAAUSSnPBnYAv0zSONpFR8Wg+8VDtwdfMs1HD2r/71sbnwFaWHQSfOZTm8Ayn0ZAUlYAUsr3DS/XAJcnYxztpSNs9XFdZVgdlyzSHMt5HB2dwQn8Y+CVUB8KIW4CbgIYNGhQR40pIjriZjOuMpztXdJaHZcs4kAi/FPx3KcVFhw5CVMAQojlgFkXmnuklMu829wDuIEXQ+1HSvk08DRoTuBYxpJIh2qib7ac7hmo3rNWpfY6ZqyOSxbtJBF+L8txmzwSpgCklDPCfS6E+CEwG5guExiKlOo3V+MJJwKQaA6bxhPO9u3Q0HHJijRKDi6Xi7q6Ok6dOpXsoUSN55SLP13UD4nWY8TzzT62nfgq5v053Son4rzPrkxWVhZ5eXk4HI6Itk9WFNAs4BfA+VLKE4k8VkdHBcRbqJYV5JLpiL+fIdUVYypTV1dHz549GTJkCEKEaNWURJpb3DS3uMnOtJOdaQ/6rKa+GSklQgiG9s0O2iaa49TUN3OalLrwb+8+uzJSShoaGqirq2Po0KERfSdZV/lPQCbwgfcBWCOlvCURB+rIpKpECNVE+RmscLnkcerUqU4t/MMJ+OxMO0P7ZodUENEeSxqEf3amnX69sizhHyNCCHJzc/n6668j/k6yooCGddSxOjIq4PWKOlpcKpL4CtVE+BmsbOPk0hmEv9lM3yiUkVL/3Eh7Bb9xP0II8CobS/i3n2jvqy5xtTsiKqC8tpHXyuvwOTNsiujUQtUKl+vahJrpBwrlRArkeK4mLGLDaggTJ9ZUN+D2qIC2nJ03Ib/TC9WSwTncduGwTj9Oi/jS0NDApIklXD5zKheOH8H0klFMmlhCcXExDqEyoLc2E/f9b8bSpUvZvn07zS1uDh87xbnnTmHjxo1RjeOaa67hg3ff5oxeWfzklhupqqoKue3ixYv56qvQjuF77rmHFStWAJCXl8eRI5EXFqiurubll1/Wz+Xjlav593//98hPJIWxVG6cCDSpzB0f1H/ZwqJTkJubyxfryqmpb+aJxx4mO7sH9/3qLrIz7TS3uDl4tBlVVTl+ykWWw2aqBJYuXYrTI3H3HICUklNulZNOd8xjevbZZ8N+vnjxYsaPH0///sGR5W63mwcffDDmY1dXV/PiS0somnYRUkr6FhTxwCOTYt5fKmGtAOKEz6Ry58wRMTt/41byoT3sWwsrH7PKRJiQzN8n3sf2mV96ZNrpk51BdqadXbt2UXLOOBbddQc/uOh8Du7fx8B+ffXvvPzyy9xwww2sXLmSf/7zn/zXf/4Hl8+cSt2+vYDkpSUvU1payogRI/jss8+CjqmqKrfeeiujR4/me9/7HvX19fpnU6dOZePGjbjdbq699lrGjh1LUVERjz/+OK+88gobN27kiiuuoLi4GKfTSV5eHvfffz9TpkzhjTfe4JprruHNN9/U9/fII49QWlrKpEmTqK6uBgjapkePHgDcddddfPLJx1w+cyp/W/wUn3+6gssvuxSA+vp65syZw9lnn825555LZWUlAL/61a+4/vrrOf/88ykoKOCJJ56Iy+/S0VgrgDjSHl+DL4KoxaViUwSLLiniqkkdnPlsNd4OSTLDZhN1bJ/dPcPeOg/csX0bv/ntn7j34f/B4/Fg5lKcNm0a3/3ud5l9yaUUnTsDLY1H4LAJ1q5dy1tvvcWiRYv417/+5fe91157jZqaGiorKzlw4ACjR4/mllv8g//Ky8upr69n8+bNABw5coTTTjuNP/7xj/zpT3+iuLi4dfzZ2axevRqAZcuW+e0nJyeHtWvXsnjxYu68804/wR/II488wh8e/yMP/+//IaVkzapPsCvaNbn33nuZNGkSb731Fu+//z4LFizAV5F4x44dfPjhhxw5coRRo0Zxyy23YLPZwl/0Toa1AugkrKlu0COI3Kpk4bLKjp9pWo23Q5LM5vOJPLbTrZl6mls0881ZZ53F92ZMo1+vLIb2zQ773SyHjaF9s+nXK4ssu8IV87SSXiUlJezZsydo+08//ZT58+ejKAp5eXlccMEFQdsMGzaMqqoqbr/9dt577z169+4d8vhXXHFFyM/mz58PwNVXX226GgnEpgj9XAb0ysKmaKpv1apVXHvttQDMnDmTAwcO0NzcDMDs2bPJyMjgjDPOoE+fPlGFX3YWLAXQSSgryNVvOgBVyg4VMkBrrSBhs2oFBZDMKpOJOnZzi5sjJ5w0ndIigk443WRna9FAZ/TKome3DIxJ+r7M5eYWN6dcHk65PPq2iiLIzMwEwGaz4Xab+wPaClPMzc3lyy+/ZOrUqTz++OPcfPPNIbfNzg6toMyOY7fbUVUtUMPj8QSN0XcuWRmts/jAIgXG177zhfDn3JlJGwXQKezn7aBkcA6LLinCrggUARnJiM331Qr61j2W+SeAePh4Otuxm1vcetiylJKTLR6/zxVFIScnh507d6KqKm+88QZuj0pNfTNKRjdqDtTrK4dIOO+883j55ZdRVZX9+/fzySefBG3z9ddfI6Vk3rx53HfffVRUVADQs2dPmpqaIj7WK69o9SWXLFnClClTABgyZAjl5eUAvPHGG3g8njb3fd555/Hii1qpsuXLl5OXlxdW8aQaaeEDSJeyBldNGsSI/j2TG5tvqBVk4U8yq0wm4tjZmXbdxi+EoFtmsP360UcfZdasWQwaNIjRo0dzpOkEUkouuuQy7v/lnbz41yd5+61lQd8z4/LLL2fFihUUFRUxYsQIzjvvvKBt9u3bx/XXX6/nJzz66KMA/OhHP+KGG26gW7durF3bdoDCiRMnKC0tRQjBkiVLALj55pu55JJL+OCDD5g5c6Y+gz/nnHPweDyMGzeO66+/ntGjR+v7WbRoET/60Y84++yz6dGjR5vRSqlGWrSEfGLFLh57vwpVgk3AnTNHcNuFHZZsbGERFdu2bWPUqFEJP064mj7RbBO4fbxqAVkkBrP7q1O1hIw3VlmDGLBaQ4Yl1SulRiqoo83AtbJ3k0u0Crst0uLXs8oamBBOwJuFe4KlELykg0kxkpo+sWIJ/uRgVOoIQZ/uDk7rntGu3yJtfsV07wIU1Yy0rXj+wHDPTUtg4xIr/t9LOlRK7ciaPhYdQ6BSb2h20njC1S4znHVXdBLCCfioZ6Rt9f4NbA2JtHoFG0gHk2KqmmribeKIO85maGmCzJ6Q0bHRQD6lbvTbynau7jrhFe56tCXgo56RttX7N7A1JMDGl61ewV7SxaSYTCEaiyDvSAdzTIrG2Qz1uwAVmg5B32EdqgR8Sr3xhDbzj8fqzlIACSIak01bAj7qGWkkvX8Dwz2tXsF+pLtJMZE0t7ipNgjygggFeSL9FoHHiUnRtDQBqveFqr1OwiogO9NOTvf4rJTSJhGsM+Gb0T/2fhVXP7OmzeS0tjI9Y0oEyi+Faf8RuTCPdnuLlMZms1FcXExRURHz5s3jxInIOrP6SiYbE8A+/vhjZs+eDcBbb73FAw89pJsppJQcMfSxPnLkCE8++aT++sCBA1x+uVZCwmfi8LWGTITw79GjB80tbg4dPMCdN/9QN6EEEjhOQDP7eEWmRFA6fQ7NLW6/84+UN998k61bt+qvFy5cyPLlyyP+vi9rub3XqMsqgERmDkdbuyUSAZ/qtftTPVM73ejWrRsbN26ksrKSjIwM/vznP/t9LqXUyyb48M2cDx07RU19s6ngnDNnDrfd8Z/++zL8HShYBw4cyGuvvQa0mjj6ZGdwWvfImprHQnamnX4DBvLfTz0fUtGYKoCMbOg7jJOZfamWA/jr0vepqW/mpNMT9P22CFQAixYtYsaMGVHvp72ktAKIVahEO0OPdgyx1G5JdQEfjnhe7y5LAst0T5s2jV27drFnzx5GjRrFrbfeyvjx49m3bx/vv/8+kydPZvz48cy/4gc0H29CAis/+oDisWOYOnUqS5cu1ff13HPPcf/d/4kQgoavD/PvN1zDzGmTGHv22Xz22Wfcdddd7N69m+LiYn7+85+zZ88eioqKAK3W0C03Xs8Fkyfy7WllvLLsXZpb3Dz33HPMnTuXWbNmMXz4cP7rv/4L0Or5LFiwgKKiIsaOHcv//M//BJ1bTU0NkydPZuLEidx7772ApgCU418zb+YUhvbNZs+uKkpLSykuLubss89m586dQeP8+OOPufDCC7lqwY0UT5nJCZnJpBF5Wi8El4djx45x6aWX6hVOfcrTV3IatGqoCxYs4LPPPuOtt97i5z//OcXFxezevZsFCxboivDDDz/knHPOYezYsfz4xz+mpaUF0EpZ/PrXv2b8+PGMHTuW7du36/s2W5lFQsr6ANoTqx2v3r2hxtAZnYg+n0RO9wwaTzgjHld5bSM1G1Yw2baVM4tn+pmIIvVzpENYZVJJYJlut9vNu+++y6xZswCoqqri2Wef5cknn6S+vp4HHniA5cuXk52dzf0PPsz//eVJfnTLz7jvF3fw3gcfcPbokUFVOR02hYK+2dz9k7spmTyFa6//G6qqcnqW5JFHHqGyslLvHmasGvrEE0/gViVLl6+metcObrl6LjMu0Orvb9y4kQ0bNpCZmcmIESP46U9/yuHDh9m/f79eo9+sC9jtt9/Ov/3bv3Hdddf51ezvnmnHrmiz/z//+c/cfvvtXH311TidTjweT9A4P/74Y9auXUtlZSVnDMynpl6rCCqEIMthY+3atWzdupXBgwcza9Ysli5dqpu2Ajn33HOZM2cOs2fPDtrm1KlTLFiwgA8//JDCwkKuu+46/vd//5c77rgDgL59+1JRUcGTTz7J7373O5555pkgn4bHrZod1pSUXQHEUiK3vLaRu9/YzKvr98Wld2+4MXSmGb1PUf3uvSrufmMzv3uviiue+pyXvtjb5vd++8z/cfGGm+m3/jHU576nz0CjmdUns5JmWpCAMt0nT56kuLiYCRMmMGjQIK6//noABg8eTFlZGQBr1qxh69atTJkyheLiYpa8+ALH6w9y7KtazioYyrgxoxBCcM011wTtPzvTzucrP+GKa36MRCssZ88K7zBdtWoV11xzLQjB0GGFDMgbxMG9WjOX6dOn07t3b7Kyshg9ejS1tbUUFBRQXV3NT3/6U/71r3/Rq1evoH2uXr2a+fPn09ziZtYl80yPO3nyZB566CEeffRRamtr6datm+l2paWlDB06VDdVCQFD+2bTLcNGaWkpBQUF2Gw25s+fz6pVq8KeayiqqqoYOnQohYWFAPzwhz/k008/1T+fO3cu4F9y2+g8l1LS4o7cJJWyK4BoI2OMDVd8wj/a3r2BM95ExovHsxSBT1HplR9p7Tkwon/PkPtfU91AidyCAzd2oaJ6XHqOQCjlZzbmzrgiSinaCuuNAZ8PIBBjpUspJd/+9rf1Ymo+Nm7ciN0WwdxREOTUDedqDleXzKz0ck5ODps2beK9997jiSee4O9//zuLFy8O+u4Jp4d9R1poajqFKgkyk1x11VVMmjSJd955h+985zs888wzFBQUBO3HeG18hfR8/oPA8tO+18b3feW0w9FWbTazktuBSX+Z9sib0qTsCiDayJhAISiATEfkvXvNZryxROdE4reIt828rCCXUvsubrMtY7zYob+vquF7DpQV5FIuxuDCjlsqYHPowidwVp/TPSPsmDvTiijlSFKZ7rKyMlavXs2uXbsArcLmjh07GDlyJDU1NezevRsgSEH4mDF9OsuXvkC/Xlmc0cPBV19/g5LRre3Sy1Kyp3oXX+3fx8DBZ4UcX319Paqqctlll3H//ffrpaONTJkyhRdfWoKUknfeeBUIVgDV1dUUFBTws5/9jDlz5vDll1+GLBEdyta+du1aampqUFWVV155halTpwLQr18/tm3bppfT9hFq/yNHjtEYOgwAAA5fSURBVGTPnj36NX/hhRc4//zzQ14DaHWe+5r4GDu8tUXKrgAgulht42zdpgguGHEGfXtmtv1FL6Hs2NGMIVK/Rbxt5iXKTl7KeAg8TjyKg6ta7qbcM5wMR/hVS8ngHH5+w3W8syE/yAcQOKu37PwJJglluk8//XSee+455s+frzsiH3jgAQoLC3n66ae5+OKL6du3L1OnTtXt8Eb+8Ic/cNNNN/H8c8/ikYJfPfQYxRMmMansXIqKirjooou47bbb9O1vvfVWbrjxJubOmILNbuP+/36SPr2CzUYeVdLY7GRXTS233nyj7nB9+OGHTcdw5fz5PPnEH5lx0fcAglYir7zyCn/7299wOBz079+f//jF3Xgc2X7jvPjii/Go0s/WbmTy5MncddddbN68mfPOO49LL9V6Cj/yyCPMnj2b/Px8ioqKOH78OABXXnklN954I48//rju/AXIysri2WefZd68ebjdbiZOnBjUNjOepEU56EgxOkIXvb0lKgeyT3j7zD2xFAiLtGx1qGPFahba/48HGFD+GAoqCBv7x9/Jmz2u1Paj7IwuASxEkbl4XJ+uQkeVg+4sHD52ikPHTqF1DoZ+3vj1wEQmX4eyb064QiaRxZrEFWnmb7j9R3oeHU2QE/ibOsaNHeO3TVqWgw4UiG0JSN9s/YkVu6KercbDjh2pz8DsWNFEPRmvA8Bv1/bkWcWOAzeKzcGZxTO5LX9Y9NElYba37PwWoQi0UdsUESRkAWrqm1GNE1KTbOBYs4Wj6XcQav+RnEcylEDgmDu9E1gIcT9wCVpe9WFggZTyQDT7CBSICyYP4ZlVNXhUSaYjvICM1XlrNPfEMhsPJdhDOU5jqQdUXtvI/L9o18WmCKaPPIO17mFczd1Mtm1j6DmzuNwn5NsqGhdIG9tb5RMszAgsTGcmZLU//a0RZklaia5yGm7/kZxHtOOJR/G77Ew7eMdMlE7gZK0AfiulvBdACPEzYCEQlaHLKBBPuVSeWlmN7/5xusLP6sPNVstrG3m9og4BzB2fF1LIxpqDEKhEIt1PWUEudkXg8kiEgANHTuqOaCNLK+pweuOAParkg62HUBTBRlnIVjGSF88pa904ILpke9Y4PlyxS1eIQdcnAdEoXRUzO3IkdPpqmSHwjbe5xY3To4IQiAAhKwxCLKe7gxyTWveJrnLa1v4D32uPMkpE8TtdIRFsCTAjKXeQlPKY4WU2/tnibVJe28iBIydRFIHq8dUcaf1ciSC232y2Wl7byPynP8fp3eer5XUsuTFYKMfL4Rl1QpoQSCRuFZas3cvrFXVBSiPwQko0RWBTBAtnj9Fs/itXasL++BCmf+dvjDy1ie1Z4/j+Wy6c7irsigAhcHsCFFOYInOp3kGrI8nKyqKhoYHc3NyolEBnaccYqxIKamiSnUGWw6bvK1LBnmjlF+n+26uM4lX8rrnFDVIipcR94hjHTsmgyaXI6GaahJG0KYQQ4kHgOuAocGGY7W4CbgIYNGiQ34kFxd6iJXYtuqQoJiG0proBl6dVhJoJZZ/ysSsCjyojzkEIFI7ltY28Vl4XcULamuoG3J7WDL9Qyuey8Xn8fd1eApMBPark2M7VqO/fgfQ4GSztfOS6mz/aRrJw9jze/fIgLa56JHgVoDS/BvmllKvDWbOrgTJVW4E88s9tPL2yGlWC3Xv9r5o0KOw16crk5eVRV1fH119/HdX3mk65OHbSrTshTxy20zMrcTVzzHC6VeqPt/gm6vTtkRlx2GHg+I9n2jjh9ATtq+2Uzs5HJGN2ulVa3B4y7TYy7ErQtVR7ZNIQRQincb/1x1vwSEndMTfZOf1YvHyH3+RSyeje0+y7CVMAQojlQH+Tj+6RUi6TUt4D3COE+CXwE+DXZvuRUj4NPA1aFJBx9q0gsStagwSbIpg3IT+k2cZIqNlqWUEuDpvQVwCBwt2ofOw2hStK87msjeOFMvMsrajD5ZXSgQlpZuPz+S2cLhXV+x0hBDndM/yOVzI4h1duPpfXK+pYW93Arq+b9c/OaFiH6nZiFyoO3EwS29jgKuTeZZV41OBFmGK4BqEiqBZMHsKfP63Wv+NWJfe8uZkVVYe55fyzrNWACQ6Hg6FDh0b9vfLaRn4SEGk1qoOvrxbJtqfNSDYzAsc/d3weL6+ti2lfqUYoOWB81se1w7+oP585Gfza+3xKWp9h1XnCNPkiYQpAShlpabuXgHcIoQACCXTgLpw9hsoDR/1s9u3prjVvQj47DjXhdKtcMXFQkCPWp1XdbpUzT9NSxp/w2s3NBHiojFljOQqHXWHMwN48sWJXyBBVo9+i6aRLd3gventLUDavb/vy2kaueOoz3CrYFTiUOxHXNy+AdOPCzhp1FEJgLvwFTBnWlztmaCnpvmumCIEqpX4+/9ryVdB3pYQPth7ik6rDLLlpsqUE4kRniLRqT/Z7yeAcFs4ew7uVBxkzoBfHWtzYbQoeT3wy6eNlhkyEOTPSPCIz+eT7figZY9yPMcLR+AxPeOBks9m4khUFNFxKudP7cg6wPdz2RowPQU73DLYcOMpr6/fhViWvV9SxcPaYsDH+oX6IwFIRioCqQ/7CNad7hi60VaDppMv0xzK+t3D2mKAHZk11A26D0B2X11sfc6CANZpfjD+y6rUdhvMdVH3VhEQAEkVRONqnmKudd1OmbGONOorcUdOYDry/9ZD+HZvXquawK9wxozDopkJKFEUg0Mxfs8b091sBGHF5ZMokhKWKDyPZkVbtUULltY36fb5yZz0CcNgEV5YOimjl3ta+Yw3MSMR+AolUcQbKp9cr6vTAjlAyxjjGwOP4nuFQJMsH8IgQYgSaHK0lyggg3wkF1vZxuVXerTwYU3etwFIRZt9vPOFEEejadcvBY6aze+N7jSecpg+MXWk1NVXsPYKqtjqDjALW7EaJ5GYqr21kocG04/aobDl4jI0UUuEpRBHwH/mnUVaQy8dVh3F5JA6b4DdzioKqhZqtuozbDMrN5t3Kg+RmZ/CPLw/qx3TYYi+015Ek6qFPV2JVQkbhBq0BCgNP69bu6x2vwIxEZbRHqjgDnzUBbcqYwEliNAo6pTKBhRBfoykMbD1y+9uyc87EO2P1nDiKrVsv1d3UsM/eMzcfzUwuXY0Hdkin//JHZHTLVjK691SdJ5p8n4mMbtmOnIGFIBTvpBmQqvH7rdtoW5gdC8C4jdnxAey9+w1SsnqebjiWXqvN3dSwTyg2u3d83YD6oGthcg5GAq8PUkp3U8Nes2vT1r4iOZ5xO1u3XrkAnpPHGkJs29fsnJKF37WSUnqajxzwHG8Itm2Fp1OdUxyJ23lF8oy1f9/hnzsvIc8pyv0kBOOzBsHyxOy9UHLCwGAp5elBx0olBRAOIcR6s1TnVCcdz8s6p9QhHc/LOqdWUrYaqIWFhYVF+7AUgIWFhUUXJZ0UwNPJHkCCSMfzss4pdUjH87LOyUva+AAsLCwsLKIjnVYAFhYWFhZRYCkACwsLiy5KWikAIcT9QogvhRAbhRDvCyEGJntM8UAI8VshxHbvub0hhDgt2WNqL0KIeUKILUIIVQiR0iF5QohZQogqIcQuIcRdyR5PPBBCLBZCHBZCBPd6TEGEEPlCiBVCiG3e++72ZI8pHgghsoQQa4UQm7zndV9U308nH4AQopev1LS3z8BoKWXiGmp2EEKImcBHUkq3EOJRACnlL5I8rHYhhBiFlgn+FPCfUsrYe30mESGEDdgBfBuoA9YB86WUW5M6sHYihDgPOA78n5SyKNnjaS9CiAHAACllhRCiJ1AOfD8NficBZEspjwshHMAq4HYp5ZpIvp9WK4D29hnorEgp35dSur0v1wB5yRxPPJBSbpNSViV7HHGgFNglpayWUjqBl9G63aU0UspPgW+SPY54IaU8KKWs8P7dBGwDzkzuqNqP1Djufenw/otY7qWVAgCtz4AQYh9wNVqnsXTjx8C7yR6Ehc6ZwD7D6zrSQLCkM0KIIcA5wBfJHUl8EELYhBAb0drrfiCljPi8Uk4BCCGWCyEqTf5dAiClvEdKmQ+8iNZnICVo67y829wDuNHOrdMTyTmlAWYtvdJi5ZmOCCF6AK8DdwRYDFIWKaVHSlmMZhkoFUJEbLJLnaaiXhLVZyDZtHVeQogfArOB6TJFHDdR/FapTB2Qb3idBxxI0lgswuC1kb8OvCilXJrs8cQbKeURIcTHwCwgIud9yq0AwiGEGG54GVWfgc6MEGIW8AtgjpTyRLLHY+HHOmC4EGKoECIDuBJ4K8ljsgjA6yz9K7BNSvnfyR5PvBBCnO6LChRCdANmEIXcS7cooNcBvz4DUsr9yR1V+xFC7AIyaW09uibVo5uEEJcCfwROB44AG6WU30nuqGJDCPFd4PeADVgspXwwyUNqN0KIJcAFaKWTDwG/llL+NamDagdCiKnASmAzmnwAuFtK+c/kjar9CCHOBp5Hu/cU4O9SykURfz+dFICFhYWFReSklQnIwsLCwiJyLAVgYWFh0UWxFICFhYVFF8VSABYWFhZdFEsBWFhYWHRRLAVgYREFQgiPt9pspRDiVSFEdyHEkFBVM4UQi4QQXSEhziIFscJALSyiQAhxXErZw/v3i2hVJZcCb6dD1UyLroW1ArCwiJ2VwDDv3zYhxF+8Ndnf92ZlIoR4TghxefKGaGERGksBWFjEgBDCDlyEllkKMBx4Qko5Bi2z+bJkjc3CIlIsBWBhER3dvKV31wN70erLANRIKTd6/y4HhiRhbBYWUZFy1UAtLJLMSW/pXR2tzhgthrc8QLeOHJSFRSxYKwALCwuLLoqlACwsLCy6KFYYqIWFhUUXxVoBWFhYWHRRLAVgYWFh0UWxFICFhYVFF8VSABYWFhZdFEsBWFhYWHRRLAVgYWFh0UWxFICFhYVFF+X/A01DCb6B1V61AAAAAElFTkSuQmCC\n" }, "metadata": { "needs_background": "light" - }, - "output_type": "display_data" + } } ], "source": [ @@ -557,17 +361,13 @@ }, { "cell_type": "code", - "execution_count": 27, + "execution_count": 59, "metadata": {}, "outputs": [ { - "name": "stdout", "output_type": "stream", - "text": [ - "Correlation coefficients - SOTA is Phi: 0.65 | Psi: 0.7\n", - "Cos Phi: 0.38018721662043725\n", - "Cos Psi: 0.4501908862112098\n" - ] + "name": "stdout", + "text": "Correlation coefficients - SOTA is Phi: 0.65 | Psi: 0.7\nCos Phi: 0.3988181200670821\nCos Psi: 0.4312205139160979\n" } ], "source": [ @@ -582,7 +382,7 @@ }, { "cell_type": "code", - "execution_count": 30, + "execution_count": 60, "metadata": {}, "outputs": [], "source": [ @@ -600,7 +400,7 @@ }, { "cell_type": "code", - "execution_count": 31, + "execution_count": 61, "metadata": {}, "outputs": [], "source": [ @@ -609,7 +409,7 @@ }, { "cell_type": "code", - "execution_count": 32, + "execution_count": 62, "metadata": {}, "outputs": [], "source": [ @@ -619,9 +419,9 @@ ], "metadata": { "kernelspec": { - "display_name": "Python 3", + "display_name": "Python 3.7.4 64-bit (conda)", "language": "python", - "name": "python3" + "name": "python37464bitconda9144c6b387f64ea49bb30359880b7777" }, "language_info": { "codemirror_mode": { @@ -633,9 +433,9 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.6.7" + "version": "3.7.4-final" } }, "nbformat": 4, "nbformat_minor": 2 -} +} \ No newline at end of file diff --git a/models/angles/resnet_1d_angles.h5 b/models/angles/resnet_1d_angles.h5 index 2140d62..a726c87 100644 Binary files a/models/angles/resnet_1d_angles.h5 and b/models/angles/resnet_1d_angles.h5 differ diff --git a/preprocessing/get_proteins_under_200aa.jl b/preprocessing/get_proteins_under_200aa.jl index 81d1b65..9f88a85 100644 --- a/preprocessing/get_proteins_under_200aa.jl +++ b/preprocessing/get_proteins_under_200aa.jl @@ -16,9 +16,10 @@ RAW_DATA_PATH = "../data/training_30.txt" # Path to raw data file DESTIN_PATH = "../data/full_under_200.txt" # Path to destin file # alternatively declare paths from cammand line -if length(ARGS) > 1: +if length(ARGS) > 1 RAW_DATA_PATH = ARGS[1] # Path to raw data file DESTIN_PATH = ARGS[2] # Path to destin file +end # Open the file and read content f = try open(RAW_DATA_PATH) catch @@ -168,4 +169,4 @@ end println("\n\nScript execution went fine. Data is ready at: ", DESTIN_PATH) -exit(0) \ No newline at end of file +exit(0) diff --git a/readme.md b/readme.md index a03db24..3445c5d 100644 --- a/readme.md +++ b/readme.md @@ -112,4 +112,4 @@ By participating in this project, you agree to abide by the thoughtbot [code of * **Author's GitHub Profile**: [Eric Alcaide](https://github.com/EricAlcaide/) * **Twitter**: [@eric_alcaide](https://twitter.com/eric_alcaide) -* **Email**: ericalcaide1@gmail.com \ No newline at end of file +* **Email**: ericalcaide1@gmail.com