{ "cells": [ { "cell_type": "markdown", "metadata": {}, "source": [ "#
cs231n 2019. [A1, part 4](http://cs231n.github.io/assignments2018/assignment1/). Two-layer net\n", "\n", " \n", "####
**Solution by [Yury Kashnitsky](https://www.kaggle.com/kashnitsky) (@yorko)**\n", "\n", "In this exercise we will develop a neural network with fully-connected layers to perform classification, and test it out on the CIFAR-10 dataset." ] }, { "cell_type": "code", "execution_count": 1, "metadata": {}, "outputs": [], "source": [ "# A bit of setup\n", "\n", "import numpy as np\n", "import matplotlib.pyplot as plt\n", "\n", "from cs231n.classifiers.neural_net import TwoLayerNet\n", "\n", "%matplotlib inline\n", "plt.rcParams['figure.figsize'] = (16.0, 12.0) # set default size of plots\n", "plt.rcParams['image.interpolation'] = 'nearest'\n", "plt.rcParams['image.cmap'] = 'gray'\n", "\n", "# for auto-reloading external modules\n", "# see http://stackoverflow.com/questions/1907993/autoreload-of-modules-in-ipython\n", "%load_ext autoreload\n", "%autoreload 2\n", "\n", "def rel_error(x, y):\n", " \"\"\" returns relative error \"\"\"\n", " return np.max(np.abs(x - y) / (np.maximum(1e-8, np.abs(x) + np.abs(y))))" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "We will use the class `TwoLayerNet` in the file `cs231n/classifiers/neural_net.py` to represent instances of our network. The network parameters are stored in the instance variable `self.params` where keys are string parameter names and values are numpy arrays. Below, we initialize toy data and a toy model that we will use to develop your implementation." ] }, { "cell_type": "code", "execution_count": 2, "metadata": {}, "outputs": [], "source": [ "# Create a small net and some toy data to check your implementations.\n", "# Note that we set the random seed for repeatable experiments.\n", "\n", "input_size = 4\n", "hidden_size = 10\n", "num_classes = 3\n", "num_inputs = 5\n", "\n", "def init_toy_model():\n", " np.random.seed(0)\n", " return TwoLayerNet(input_size, hidden_size, num_classes, std=1e-1)\n", "\n", "def init_toy_data():\n", " np.random.seed(1)\n", " X = 10 * np.random.randn(num_inputs, input_size)\n", " y = np.array([0, 1, 2, 2, 1])\n", " return X, y\n", "\n", "net = init_toy_model()\n", "X, y = init_toy_data()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "# Forward pass: compute scores\n", "Open the file `cs231n/classifiers/neural_net.py` and look at the method `TwoLayerNet.loss`. This function is very similar to the loss functions you have written for the SVM and Softmax exercises: It takes the data and weights and computes the class scores, the loss, and the gradients on the parameters. \n", "\n", "Implement the first part of the forward pass which uses the weights and biases to compute the scores for all inputs." ] }, { "cell_type": "code", "execution_count": 3, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Your scores:\n", "[[-0.81233741 -1.27654624 -0.70335995]\n", " [-0.17129677 -1.18803311 -0.47310444]\n", " [-0.51590475 -1.01354314 -0.8504215 ]\n", " [-0.15419291 -0.48629638 -0.52901952]\n", " [-0.00618733 -0.12435261 -0.15226949]]\n", "\n", "correct scores:\n", "[[-0.81233741 -1.27654624 -0.70335995]\n", " [-0.17129677 -1.18803311 -0.47310444]\n", " [-0.51590475 -1.01354314 -0.8504215 ]\n", " [-0.15419291 -0.48629638 -0.52901952]\n", " [-0.00618733 -0.12435261 -0.15226949]]\n", "\n", "Difference between your scores and correct scores:\n", "3.6802720496109664e-08\n" ] } ], "source": [ "scores = net.loss(X)\n", "print('Your scores:')\n", "print(scores)\n", "print()\n", "print('correct scores:')\n", "correct_scores = np.asarray([\n", " [-0.81233741, -1.27654624, -0.70335995],\n", " [-0.17129677, -1.18803311, -0.47310444],\n", " [-0.51590475, -1.01354314, -0.8504215 ],\n", " [-0.15419291, -0.48629638, -0.52901952],\n", " [-0.00618733, -0.12435261, -0.15226949]])\n", "print(correct_scores)\n", "print()\n", "\n", "# The difference should be very small. We get < 1e-7\n", "print('Difference between your scores and correct scores:')\n", "print(np.sum(np.abs(scores - correct_scores)))" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "# Forward pass: compute loss\n", "In the same function, implement the second part that computes the data and regularizaion loss." ] }, { "cell_type": "code", "execution_count": 4, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Difference between your loss and correct loss:\n", "1.794120407794253e-13\n" ] } ], "source": [ "loss, _ = net.loss(X, y, reg=0.05)\n", "correct_loss = 1.30378789133\n", "\n", "# should be very small, we get < 1e-12\n", "print('Difference between your loss and correct loss:')\n", "print(np.sum(np.abs(loss - correct_loss)))" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "# Backward pass\n", "Implement the rest of the function. This will compute the gradient of the loss with respect to the variables `W1`, `b1`, `W2`, and `b2`. Now that you (hopefully!) have a correctly implemented forward pass, you can debug your backward pass using a numeric gradient check:" ] }, { "cell_type": "code", "execution_count": 5, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "W2 max relative error: 3.440708e-09\n", "b2 max relative error: 1.276034e-10\n", "W1 max relative error: 3.561318e-09\n", "b1 max relative error: 3.833134e-09\n" ] } ], "source": [ "from cs231n.gradient_check import eval_numerical_gradient\n", "\n", "# Use numeric gradient checking to check your implementation of the backward pass.\n", "# If your implementation is correct, the difference between the numeric and\n", "# analytic gradients should be less than 1e-8 for each of W1, W2, b1, and b2.\n", "\n", "loss, grads = net.loss(X, y, reg=0.05)\n", "\n", "# these should all be less than 1e-8 or so\n", "for param_name in grads:\n", " f = lambda W: net.loss(X, y, reg=0.05)[0]\n", " param_grad_num = eval_numerical_gradient(f, net.params[param_name], verbose=False)\n", " print('%s max relative error: %e' % (param_name, rel_error(param_grad_num, grads[param_name])))" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "# Train the network\n", "To train the network we will use stochastic gradient descent (SGD), similar to the SVM and Softmax classifiers. Look at the function `TwoLayerNet.train` and fill in the missing sections to implement the training procedure. This should be very similar to the training procedure you used for the SVM and Softmax classifiers. You will also have to implement `TwoLayerNet.predict`, as the training process periodically performs prediction to keep track of accuracy over time while the network trains.\n", "\n", "Once you have implemented the method, run the code below to train a two-layer network on toy data. You should achieve a training loss less than 0.2." ] }, { "cell_type": "code", "execution_count": 6, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Final training loss: 0.008116963954598025\n" ] }, { "data": { "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYUAAAEWCAYAAACJ0YulAAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADl0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uIDMuMC4yLCBodHRwOi8vbWF0cGxvdGxpYi5vcmcvOIA7rQAAIABJREFUeJzsvXmcZFV5//95au+u6u7pnu5ZmIVZ2GVQYERwQyUqqAGNUYkxwjf6JXGJ69do8kuMmtUkXxON+aooGo0GMRoVFFFcUEAYHAYYGAZm37feu6q6a39+f9x7bp27Vd3qrtvNVD/v16tfXXXr1K1zt/OcZz3EzBAEQRAEAIgsdAcEQRCEZw4iFARBEAQLEQqCIAiChQgFQRAEwUKEgiAIgmAhQkEQBEGwEKEgPOMhoigR5YhobTvbni4QUYyImIjW+Xx+AxH9aH57JXQqJHkKQrshopz2thtAEUDVfP9HzPyN+e/V3CGivwGwmplvnOffjQEoA1jPzAfmsJ+vA9jDzB9rU9eEDiS20B0QOg9mzqjXRHQAwNuZ+ad+7YkoxsyV+eibMHuIKMrM1eYthdMZMR8J8w4R/Q0R3UZEtxJRFsBbiOgKInqQiCaI6DgRfYaI4mZ7m/mEiL5ufv4jIsoS0QNEtL7Vtubn1xDRLiKaJKJ/I6L7iejGWRzTs4jol2b/HyeiV2ufvYaIdpq/f4SI3m9uX0ZEd5rfGSOiXzX5mVcS0R4iGieiz2j7fzsR3WO+jpjHe8o8pu1EdAERvRPAmwD8uWle+26Afn+diP6diO4iojyAPyWiY0QU0dq8iYi2tnq+hGcuIhSEheJ1AP4LQB+A2wBUALwXwCCAFwC4GsAfNfj+mwH8JYABAIcA/HWrbYloGYBvAfiQ+bv7AVzW6oEQUQLADwD8EMAQgPcDuI2IzjKbfAXA25i5B8BFAH5pbv8QgH3md1aYfWzEqwBcCuBiGIL0tzzaXAPgcgBnA+gHcD2AMWb+fzDO898xc4aZXxeg34Bx7j4OoAfApwBkAVylff4WAP/ZpN/CaYQIBWGhuI+Z72DmGjPPMPNvmHkLM1eYeR+AmwFc2eD732bmrcxcBvANAM+ZRdvXAHiUmb9vfvYvAEZmcSwvAJAA8E/MXDZNZT+CMSADhj/gAiLqYeYxZt6mbT8DwFpmLjHzL117tvP3zDxp+hXugfcxlwH0AjgPAJj5SWY+Mct+A8B3mfkB8zoVAXwNhiAAEQ3CEBC3Num3cBohQkFYKA7rb4joPCL6IRGdIKIpAJ+AMXv3Qx/opgFk/Bo2aHuG3g82oi6OBOi7kzMAHGJ71MZBAKvM168DcC2AQ0R0DxE9z9z+D2a7nxHRXiL6UJPfaXrMzPwTAJ8H8DkAJ4no80TUM8t+A47rBEMreC0RdcMQHr9g5lNN+i2cRohQEBYKZ9jbFwA8AeAsZu4F8FEAFHIfjgNYrd4QEcE+IAblGIA15vcVawEcBQBTA7oWwDIY5ppvmtunmPn9zLwOwGsBfJiIGmlHgWDmf2XmSwBcCOACAB9QH7XSb6/vMPMhAFsBXAfgDyCmo45DhILwTKEHwCSAPBGdj8b+hHbxAwCXENFvm2Gf74VhW29ElIhS2l8SwK9h+EQ+SERxInoZDPv/t4ioi4jeTES9pokqCzM81/zdjeagPGlun1N0DxFdZv7FAOQBlLR9ngSwQWvu2+8mP/M1AH8Gw0T1/bn0V3jmIUJBeKbwQQA3wBg0vwDDKRoqzHwSRkTOpwCMAtgI4BEYeRV+vAXAjPb3tGlr/20Ys+cRAJ8B8GZm3mV+5wYAB02z2NtgzLAB4FwAPweQA3A/gE8z831zPKwlAG4BMAHgAAxt6F/Mz74E4Nlm9NK3A/Tbj+/AEC7fZuaZOfZXeIYhyWuCYEJEURgmld9l5nsXuj/PVEzNZj+AG5n5ngXujtBmRFMQFjVEdDUR9ZlmoL+EYU55aIG79UznjTC0qWbRUsJpiGQ0C4udF8IIU00A2AHgtaZZRfCAiO6DkQPx+yxmho5EzEeCIAiChZiPBEEQBIvTznw0ODjI69atW+huCIIgnFY8/PDDI8zcLOT69BMK69atw9atUn9LEAShFYjoYJB2Yj4SBEEQLEQoCIIgCBYiFARBEAQLEQqCIAiChQgFQRAEwUKEgiAIgmAhQkEQBEGwEKEQkJ/tPIkj49ML3Q1BEIRQEaEQgEK5ipv+82F8/cFDC90VQRCEUBGhEIB9w3lUa4xSpbbQXREEQQgVEQoB2H0qCwCo1kQoCILQ2YhQCMCuk4ZQqNSkzLggCJ2NCIUA7DqZAwBURSgIgtDhiFAIwG7RFARBWCSIUGhCoVzFoTEjFLUmQkEQhA5HhEIT9g7noGSBaAqCIHQ6oQkFIkoR0UNE9BgR7SCij3u0uZGIhonoUfPv7WH1Z7bsNv0J8SiJT0EQhI4nzJXXigBexsw5IooDuI+IfsTMDzra3cbM7w6xH3Ni18ksYhHC2oFuVCQkVRCEDic0ocDMDCBnvo2bf6fdVHvXyRzWD6aRiEVEUxAEoeMJ1adARFEiehTAKQB3M/MWj2avJ6LtRPRtIlrjs5+biGgrEW0dHh4Os8sudp/K4pzlPYhFSHwKgiB0PKEKBWauMvNzAKwGcBkRXehocgeAdcx8EYCfAviqz35uZubNzLx5aGgozC7bmCkZkUdnL88gGhGfgiAInc+8RB8x8wSAewBc7dg+ysxF8+0XAVw6H/0Jyt7hHJiBs5f1IBaJoFIVoSAIQmcTZvTREBEtMV93AfgtAE852qzU3l4LYGdY/ZkNqubROaIpCIKwSAgz+mglgK8SURSG8PkWM/+AiD4BYCsz3w7gPUR0LYAKgDEAN4bYn5bZdTKHeJSwbjCNWJRQrFQXukuCIAihEmb00XYAF3ts/6j2+s8A/FlYfZgru09msX4wjXg0IpqCIAiLAslobsCukzmcvbwHACT6SBCERYEIBR+Gs0UcHp/GuaZQEE1BEITFgAgFH76x5SCYgddcZPjCY5GIaAqCIHQ8IhQ8KFVq+PqDh/DSc4ewYSgDQDQFQRAWByIUPPjh48cwkivixhest7YZPgWpfSQIQmcjQsEBM+Mr9x/AxqE0Xnz2oLU9GiFUJXlNEIQOR4SCg22HxrH9yCRufMF6EJG1PRaV6CNBEDofEQoOvnz/AfSmYnj9Jats28WnIAjCYkCEgsbkTBl3PXECb3ruGnQn7Hl9En0kCMJiQISCxsR0CdUa47wVva7PRFMQBGExIEJBo1gxoouScfdpkegjQRAWAyIUNEqmUEhE3adFNAVBEBYDIhQ0VBXUZDzq+kxqHwmCsBgQoaBRbKgpRMAM1EQwCILQwYhQ0GjoU4gaOQuiLQiC0MmIUNBQPoVkzNunAED8CoIgdDQiFDSKDYRCLKI0BYlAEgShcxGhoFEsm47mmNvRLJqCIAiLgdCEAhGliOghInqMiHYQ0cc92iSJ6DYi2kNEW4hoXVj9CUKpajqaG2oKIhQEQehcwtQUigBexszPBvAcAFcT0eWONm8DMM7MZwH4FwCfDLE/TSmWG/kUjG2iKQiC0MmEJhTYIGe+jZt/zhH1OgBfNV9/G8BVpJcmnWeUpuBlPhJNQRCExUCoPgUiihLRowBOAbibmbc4mqwCcBgAmLkCYBLAUo/93EREW4lo6/DwcGj9VZqCl/nI8inImgqCIHQwoQoFZq4y83MArAZwGRFd6GjipRW4Rl1mvpmZNzPz5qGhoTC6CgAoVauIRcgSADr1PAWJPhIEoXOZl+gjZp4AcA+Aqx0fHQGwBgCIKAagD8DYfPTJi2K55qklABJ9JAjC4iDM6KMhIlpivu4C8FsAnnI0ux3ADebr3wXwc2ZesFG3WKl5OpkB8SkIgrA4iDVvMmtWAvgqEUVhCJ9vMfMPiOgTALYy8+0AbgHwn0S0B4aGcH2I/WlKqVLzdDIDEn0kCMLiIDShwMzbAVzssf2j2usCgDeE1YdWKVaqvuYj0RQEQVgMSEazRqnqbz6q+xTE0SwIQuciQkGjkaPZ0hQkJFUQhA5GhIJGI0ezRB8JgrAYEKGgUao00BRkPQVBEBYBIhQ0ipWqRB8JgrCoEaGgIXkKgiAsdkQoaDQyH0n0kSAIiwERChrFBslroikIgrAYEKGgUQykKYhQEAShcxGhoGE4mv18CsZ2yVMQBKGTEaGgUarUkIz7aApR0RQEQeh8RCiYMLPhU4hK9JEgCIsXEQomZdMslIz75SlI9JEgCJ2PCAWTYqUKAEiIpiAIwiJGhIJJsWJoAL4+BYk+EgRhESBCwaRkCgV/TcGMPhKhIAhCByNCwaSZpmDKBNEUBEHoaMJco3kNEf2CiHYS0Q4ieq9Hm5cQ0SQRPWr+fdRrX/OB0hT8M5olT0EQhM4nzDWaKwA+yMzbiKgHwMNEdDczP+lody8zvybEfgSimaPZdClI9JEgCB1NaJoCMx9n5m3m6yyAnQBWhfV7c6XUxHxERIhFSHwKgiB0NPPiUyCidQAuBrDF4+MriOgxIvoRET1rPvrjRbGJoxkwIpDEpyAIQicTpvkIAEBEGQDfAfA+Zp5yfLwNwJnMnCOiVwH4HoCzPfZxE4CbAGDt2rWh9FOZj/yS1wCIpiAIQscTqqZARHEYAuEbzPw/zs+ZeYqZc+brOwHEiWjQo93NzLyZmTcPDQ2F0te6o1k0BUEQFi9hRh8RgFsA7GTmT/m0WWG2AxFdZvZnNKw+NcIyHzUQCrFoBBVxNAuC0MGEaT56AYA/APA4ET1qbvtzAGsBgJk/D+B3AbyDiCoAZgBcz8wLMhUviqYgCIIQnlBg5vsAUJM2nwXw2bD60AqBNIUISZ6CIAgdjWQ0mzRLXgNEUxAEofNpKhSI6B+JqJeI4kT0MyIaIaK3zEfn5hMr+qiJplBdGOuWIAjCvBBEU3iFGUr6GgBHAJwD4EOh9moBKJaD5SlISKogCJ1MEKEQN/+/CsCtzDwWYn8WjFK1hkQ0gkjE3w0Si0RQFZ+CIAgdTBBH8x1E9BSM6KB3EtEQgEK43Zp/iuVaQyczIJqCIAidT1NNgZk/AuAKAJuZuQwgD+C6sDs235Sq1Yb+BACIRUkK4gmC0NEEcTS/AUCFmatE9BcAvg7gjNB7Ns+IpiAIghDMp/CXzJwlohcCeCWArwL4XLjdmn+KlVpzTUFCUgVB6HCCCIWq+f/VAD7HzN8HkAivSwtDqVJrmKMAiKYgCELnE0QoHCWiLwB4I4A7iSgZ8HunFcVKtan5KBaJiKYgCEJHE2RwfyOAHwO4mpknAAygA/MUStXm5iPRFARB6HSCRB9NA9gL4JVE9G4Ay5j5J6H3bJ4J4mg2fAoSfSQIQucSJProvQC+AWCZ+fd1IvqTsDs23wTWFCR5TRCEDiZI8trbADyPmfMAQESfBPAAgH8Ls2PzTbHc3NFs5CmIUBAEoXMJ4lMg1COQYL5uWBL7dCSIozkqjmZBEDqcIJrCVwBsIaLvmu9fC2NFtY6iFDBPQRzNgiB0Mk2FAjN/iojuAfBCGBrC/2LmR8Lu2HxTrATLaBZNQRCETsZXKBDRgPb2gPlnfdZp1VKDJK8ZmoJEHwmC0Lk00hQeBsCo+w/UFJnM1xsa7ZiI1gD4GoAVAGoAbmbmTzvaEIBPwyjLPQ3gRmbe1uIxtAXRFARBEBoIBWZeP8d9VwB8kJm3EVEPgIeJ6G5mflJrcw2As82/58GoqfS8Of5uyzBzoJBU8SkIgtDphFaugpmPq1k/M2cB7ASwytHsOgBfY4MHASwhopVh9cmPolqfOR4g+kjyFARB6GDmpYYREa0DcDGALY6PVgE4rL0/ArfgABHdRERbiWjr8PBw2/unhEKjpTgBI09BNAVBEDqZ0IUCEWUAfAfA+8y1nm0fe3zFNeoy883MvJmZNw8NDbW9jyVLU2heJVV8CoIgdDJNQ1IdUUiKrLkKW7PvxmEIhG8w8/94NDkCYI32fjWAY832226KFSM3L9lMU5DoI0EQOpwgmsI2AMMAdgHYbb7eT0TbiOhSvy+ZkUW3ANjJzJ/yaXY7gLeSweUAJpn5eEtH0AZKgX0KhBoDNdEWBEHoUIJkNN8F4LvM/GMAIKJXALgawLcA/D/4Rwu9AMAfAHiciB41t/05gLUAwMyfB3AnjHDUPTBCUv/X7A5jbliO5gDRRwBQZUak8yp9CIIgBBIKm5n5j9UbZv4JEf0dM3/AXHDHE2a+D01qJDEzA3hX4N6GhOVoDlD7CACqNUYT94MgCMJpSRChMEZEHwbwTfP9mwCME1EURlLaaY9lPgqQ0QxAIpAEQehYgvgU3gzDAfw9AN+HYf55M4AojFXZTnuUozlIRjMAyVUQBKFjCVIQbwSA36I6e9rbnYWhFNSnEFWaQkcoSIIgCC6ChKSeA+D/AFint2fml4XXrfmlGNB8ZGkKYj4SBKFDCeJT+G8AnwfwJdgX2+kYSgEdzeJTEASh0wkiFCrM/LnQe7KAWMlrLUQfCYIgdCJBHM13ENE7iWglEQ2ov9B7No8EDUkVTUEQhE4niKZwg/n/Q9q2puspnE4EdTTXfQriaBYEoTMJEn0013UVnvGIpiAIgmDQaDnOlzHzz4nod7w+9ylwd1oStHS20hQqkqcgCEKH0khTuBLAzwH8tsdnDKCDhEIVyVgERg0/f1SegjiaBUHoVBotx/lX5v8FKVI3n5QCrM8M1KOPxHwkCEKnEiR5LQng9XAnr30ivG7NL8VKrWniGqBVSRWhIAhChxIk+uj7ACYBPAygGG53FoZiudY08gjQfAoSfSQIQocSRCisZuarQ+/JAlKqtiYURFMQBKFTCZK89msi2hR6TxaQYrka0KcgIamCIHQ2QTSFFwK4kYj2wzAfEYz1cS4KtWfzSFBNISalswVB6HCCCIVrQu/FAmP4FJo7mkVTEASh0/GdHhNRr/ky6/PXECL6MhGdIqInfD5/CRFNEtGj5t9HW+9+eyhWgpmPYlIQTxCEDqeRpvBfAF4DI+qIYV9vOUjto/8A8FkAX2vQ5l5mfk3zboZLqVpDv0QfCYIgNExee435f1a1j5j5V0S0bnbdml+K5WDJa5KnIAhCpxPEpwAi6gdwNoCU2sbMv2rD719BRI8BOAbg/zDzDp/fvwnATQCwdu3aNvysnVZDUsWnIAhCpxIko/ntAN4LYDWARwFcDuABAHNdjnMbgDOZOUdErwLwPRiCxwUz3wzgZgDYvHlz20fkoI5mqX0kCEKnEyRP4b0AngvgIDO/FMDFAIbn+sPMPMXMOfP1nQDiRDQ41/3OhlI1aO0j0RQEQehsggiFAjMXAKMOEjM/BeDcuf4wEa0gsywpEV1m9mV0rvudDcVyNWCeghl9VBVHsyAInUkQn8IRIloCw7xzNxGNw/ABNISIbgXwEgCDRHQEwF8BiAMAM38ewO8CeAcRVQDMALiemRdkCl4MXCVVNAVBEDqbICuvvc58+TEi+gWAPgB3Bfje7zX5/LMwQlYXlGqNUamxVEkVBEFAE6FARBEA25n5QgBg5l/OS6/mEWt95rhoCoIgCA1HQmauAXiMiNofB/oMoRRwKU5ANAVBEDqfID6FlQB2ENFDAPJqIzNfG1qv5pFipQpANAVBEAQgmFD4eOi9WECKLWgKRIRohFCVMheCIHQoQYTCq5j5w/oGIvokgI7wLxQtn0JzRzNgaAuiKQiC0KkEyVN4uce2jimnnS2UAQDdAYVCLEKynoIgCB2Lr6ZARO8A8E4AG4hou/ZRD4D7w+7YfLH7ZA4AcNayTKD2oikIgtDJNCud/SMAfw/gI9r2LDOPhdqreeSpE1l0xaNYO9AdqH0sQhJ9JAhCx9KodPYkgEkADZPQTneePjmFc5ZnEIlQ88YAopGIaAqCIHQsQXwKHc1Tx7M4d0VP4PYxiT4SBKGDWdRCYThbxGi+hPNW9DZvbBLUp3DrQ4fwDz96ai7dEwRBmHcWtVB4+oSx1PR5rWgK0WA+hZ/tPIkfbG9aN9Di+OQMPnHHk6hIBVZBEBaQRSUUDo7mbe+fOjEFAC2Zj6IBHc35YhW5YiXwfv976xF8+f79ODA6Hfg7wsJx1xMncOfjxxe6G4LQdhaNUPj2w0dw5T/dgz2ncta2p05kMZhJYmkmGXg/QaOP8qUKcoUKglYD33pw3PheC4JEWDg+dffTeO83H8ETRycXuiuC0FYWjVB44VmDIIJtdvf0iSzOXxlcSwCCRx/lixVUamxlTDeiWmNsU0KhVHF99v1Hj2K6JMLimUKtxjgwOo1ylfH+2x5FoVxd6C4JQttYNEJhRV8Km8/st4RCtcbYdTKLc5e3JhQCawpFY6DIFpoP5k+fyFqmJvU9xfYjE3jvNx/FjV/+jWgRzxCOTc6gVKnh1ZtWYvepHD55lwQUCJ3DohEKAPDqTSvx1Iks9pzK4sBoHsVKrSV/AhA8+kjN+IMM5A8frOcCOttPzhhlOB46MIYbv/JQS34KIRz2jxi+qbdcfiZufP46fOX+A7h3d/Bly3efzOJPbn3EKtu+WLh39zAOjOSbN2zCT588idf8270Nzx8z4/49I4HNt0Kd0IQCEX2ZiE4R0RM+nxMRfYaI9hDRdiK6JKy+KK7ZtBJEwA+3n9Aij4KHowLB8hSY2RrcgwzivzkwjpRZutvZXr1/71VnY9uhCdz45YdaMiVJ9nX7UUJhw1AaH7nmPKwfTOP//mRX4O/f8dgx3PHYMRybmJlzX54+kcXkdHnO+wkbZsY7vr4NX/jV3jnv697dw3ji6BQOjfkLmMeOTOL3v7QFW/Z3TPGFeSNMTeE/AFzd4PNrAJxt/t0E4HMh9gUAsLw3heeuG8Cdjx/HU8enECHg7OXBah4pohFCpUlBvGKlBjUWBzEfPXxwHJdvWAoArgFfCZc3PncN/vkNF2HrwXHc/eTJQH0tVqq49rP34e/v3BmovRCM/SN5dCeiWNaTRCoexcVrlmA4Wwz8/SePGxMS5wQgX6zg//vu41aRxmaUqzW8/nO/xqfufrphuzseO4b/3nq4YZtqjQP/LmAUknzPrY/gxGQhUPvjkwXkihVL850L+0yhvG/YXyiM5ozrMZYv2bZXqjW859ZHsPP41Jz70amEJhSY+VcAGonp6wB8jQ0eBLCEiFaG1R/FqzetxNMns7jziRNYN5hGKmB1VEWQPAX9YW+mKRybmMHRiRm86Owhs73dp6CESiYZw4vNNkEfrC/+ah92HJvCbi3i6pnA5EwZ5RbyMT52+w688fMPuEwBU4Uyth0ab3f3mrJ/JI/1g2kQGaVRerviLQ2oakBy3hvbDo3jG1sOWZFozdh9ModcsYJthyYatvv6gwfxH78+0LDNV+7fjyv/6R7UAmqW9+8Zxe2PHcNPnjwRqL2K+nPe37NBCYN9DUxR6tzmHJOyk9kibn/sGO7fM9LwN05MFtoiwE5HFtKnsAqAPn05Ym4LlWsuXAEi4yZtJWlNEST6aFq78XPFxjeWGgAuWzeAdCLq8ikox3M6EUUmZZSq8tI+/vWnu/CrXXW79sHRPP7t53vM9u4+DGeLONoG88VseNWn78WrP3Mvdp3MNm07mivivx46hIcOjOGRw/bB72Pf34Hrb34w8EDWLvaP5LFuMG2970nFkC1WAvVjcqZsnXfngKXeO7f78fhR43w8dWLKWkHQi2yh0nRy8stdwxjLl1zRb36oUNygIbmWUGhBeHpRKFdxbNI4f/sbaArqGck6jls9C1NNzvGNX3lo0QYQLKRQ8KpA5/lUEdFNRLSViLYODwd36HmxrDeFy9YNAADOXd6aPwEIFn1k0xSa3HwPHxhDdyKK81f2oDsZcwmFXLGMrngUsWgEyVgUiWjEJRRKlRr+9ae7ceNXHsIt9+0HM+MvvvcE4tEInr26z1OIfOz2HfiT/9rW7HDbTqVaw9GJGew6mcO1n70P33zoUENn4G1bD6NUqSEZi+DWLYes7aemCrhj+zGUKjXk5jFct1Sp4fDYNDZoQqE3FQezO5zYi6c0s4VzoLYGsoBCYfsRY0AuV9nykXmRLZYb7rNWYzxqCtyggQxPHDN++/Gjwcwwe4eVpjC3a3VwdBrqdtk34q8B+2kKQQXviakCTgY0jXUaCykUjgBYo71fDcCzLgQz38zMm5l589DQ0Jx/+NUXGVaqViOPgGDRR7pfwDlTcbL14Dies2YJYtEIMskY8iX7jC9XrCKdrBezzaRiLu1DzX4G0gn89Q+exPU3P4h7d4/gg684BxuHMp4DwsmpAk61YAdvF0rzecdLNmLzmQP4yP88jnff+ggmpkuutpVqDd948BBecNZS/M4lq3HH9mOYMo/16w8eRNn07QQdRNvB4fFp1BhY79AUgOazTwA2W7ZrFmsFJwSbTT9+dBJnLjVKvisB4UWuUGk4CO4ZzrUkkJjZ0hB2n8wGytOoawpzu1b7TUHwrDN6LYe/F9bg73xWApxjZka2UJnX++qZxEIKhdsBvNWMQrocwCQzz0vdgNdfshofePk5eMm5rQuYINFHQTWFXLGCncensNnUXNJJL/NRBZlk3e/Rk4q59qlu3g9ffR7e9dKN2LJ/DBeu6sVbr1hntPcQTH43/Y93nMAHvvVow+ObC2pQXz+Yxtf+8DL86dXn4sdPnMDV/3ov7tttt/P+7KlTODoxg7desQ5vvmwtCuUavvfIURTKVXx9yyGkE1HzWObP9qtMFrpQ6O2KB+7HzuNZZEwhPxfzUbFSxc7jU7j6WSvQ3x3H4z5CQQ1wpWrNd/B+RPPLBBkIT0wVMJIr4YoNS1GpMZ5qoKUolKbQbJLUDOVHuOq8ZRjJlXzt/upa+PnoGh3nTLlqON4Xafh3mCGptwJ4AMC5RHSEiN5GRH9MRH9sNrkTwD4AewB8EcYqb/NCOhnDe646u2UnM+DWFN71jW342x8+aWszXdJ9Cv431iOHxlFjYPOZ/Ua/Eu4BPFesWL4EwHA4+4Wt9nXF8aFXnofbbroct9zwXEQjZGoW7nIb2ULZc/uvdg3je48cDc1Orx7GnmQMkQjhnS85C9995wuQTkbxllu24GO377A0ra89cACrlnThqvOWYdPqPly4qhf/teUQvv/oUYzlS3jr89fZ9jm4ZzQdAAAgAElEQVQfqNmpp6YwE0BTODGFZ6/pQzRCrglAUHs3AOw6kUO5yrho9RJsWr0Ejx3xdjYXyjXrfvW7F7cdrH83iGB7wjQZXX+Zoeg/3sSvMDFdwkiuhK541POea4V9w3ks60li0+olAOCrLdQ1Ah/B2+C5rAsOcTS3FWb+PWZeycxxZl7NzLcw8+eZ+fPm58zM72Lmjcy8iZm3htWXduL0KTx+dBI7jtntquqGi0ao4azvKTM08aLVfQAMYeX2KVSQTtiFgnPQULPvnpQxY33ehqVY3puytlVrjBnHLHGqUEG1xjYBprbXAtrHZ0PW0VcA2LS6Dz/4kxfhxuevw3/8+gCu+fS9uO03h3D/nlH8/uVrEYsat+mbLzsTT53I4pN3PY3zVvTgFRcsBzB3k0Qr7B/No787jiXdCWtbbyqYplCp1ozSKit6Gwr3IHb37aaT+aLVfXj26j7sPpXDTMmtCWQ1M4nfedp2aByrlnQF/u3Hj04iQsDLL1iOJd1xPNHAdAXUtYRNq/vADNc91woq8ksJ5X3D3n6FutZlvybKbNRoIqGuo5iPhEBEIxFbnsJUoWwNyopp88EayiQbqqATMyVEI4Q+0/yQTsZcD0yuULFmokBj85HeTuFlqqjW2Hr4nX2fmgk+W50N6nedfe1KRPGxa5+FW//35WAGPvydx5GIRfCmzXW307XPOQPpRBRj+RL+8IXrLcHiPAYn7axNtH84b9MSAN2n0LgfKov+/JWGUHAOOtbsNsC5f/zIJJZ0x7G6vwubVvWhWmM86RF7r/+G1yA3OVPG7lM5XGmaUoMMhE8cncRZyzLoTsSwaVVfU01B+RMuXmPM7ufibN4/kseGoTTWDnQjGiFfTcFPwAbRArKaNrEYM6JFKLSIrikwM6Zmyi6zgXIWL+9NNnzAp2Yq6E3FrHj3TDLqTmgqVeyOZo8ZprqJe7XZt8LLCap/3zkIqIFtKqQY7UYCDACu2LgUd73vRfjjKzfiw1efZ6tgm0nG8IbNa7CyL4Vrn30GehuE6CqeODqJC//qx66y6bPFmKnaEx7rPoXGg51KWlNCwR0woMIom5/77UcmsWlVH4gIF5mmlMc9TEg2oeCx38fMqCOVAxNEID1xdBIXrjK02wtX9WHXyWzDkNi9w3kkYhErsGO2QmFiuoSxfAnrB9NIxCJY09/lm8CmfsMleFswH3lp2IsBEQotEo3WfQr5UhU1ds8Q88UK4lHCQDrR8OabnClbWgJg+BRc5qNCxZrtA7B8BDp1k4x7oFXb7IKg7Pka0DSF0ISCsd+Mj1AAgO5EDB+55jy87YXrXZ/9xavPx88+eCVS8cZ5G4q9wzlUzKqmjfj13pGmeRvTpQpOTBWwfrDbtr3uU2h8znYen0I8SjhrWcbzOipTR7OBuVCuYtfJrGV2XN6bxFBP0jMCSd+X1363HRoHkSGMiZqbwE6ZUWsXnmH89qZVfajUGofE7jmVw4bBtHWvz9bcV/fnGEJ5w1DGN4HNz3fgF6qq00y76nREKLSIHn2kD6C6mpkvVtCdiCGTijcUClOFsjXLBIBu03ykO3lzRbtQ6EnFfc1HXgNtj4e9W9ds3P6Jiuf2djHVQKsJQiwaQbfpY+mKRxGNUMOBTF2jRtmpk9Nl/P6XtuCl/3wP/vaHT2I87w6PBYADI4ZgcWoKyVgUyZg7f8TJzuNT2DiUQSJmhB+7oo/U7LbJTHrn8SlUaoxNqwwNgYhw0ao+bPcw49gnAF5CYQLnLOtBX1fcMGk1+W2Vn7BpdV0oAI2dzXtO5bBxWaZuypylpqDXnAIMZ//+kZxnUISfo1mdj3yp6ptv1GjStBgQodAievSR0hAMx2xdzcyXqsgkY552Yx2npqBCT6dNlbVcraFYqbnMR6VqzaauZwtGgls86r6cXj6FRgOFGkTDehhyphaVjM391iMi35BbxWQAoTA2XQIzsHEog1vu248X/+Mv8G8/2+06B16RR4qeVLypT2Hn8SlccIaRMOmt8TUPlwTqA7DSFIzXS7B3OOe7T8A9QNZqjEcOjeOSMw3h0tPkfgWAx49MgQi4YKVxHKv7u9DXFffNbC6Uqzg8Po2zhjKBNLtG7B/JIxohrOk3NLUNQ2kUyjWcmHInmenhvfqELUgJGtEUhJbQfQq2Gbc26BiaQtQcsBrMUGfKthmzGvyVCUn9t2sK7gcrW6j4mmP82tdf1/tXrFStRYHCNB/1pOKWH2Wu9KSaC16g8fGoxLkPvfIc3PW+F+PyjUvxf+/ehRf94y/wuXv2WtdBJU6tc5iPAKC3yx0VdnKqgB9uP45CuYrRXBEnp4rWYNrjFX3UIE/hW785jC37RsHMeOzwJAYzCazsS1mfX2RG9uxwDM7ZBoPgvhEjae3itUZItJcW6uTxo5PYMJi27lUiauhs3j+SNwTusgx6knHPfgRl33Aea/q7kDAnFPUIJLsJqVKtYaZcRVc86lroKtdASCqaaVedjr9hV/BEr32kDzRThTLOgBHWly8ZWciZZAyFcg3las1zFj81U7GZj1Toaa5YwXLUb9qMQ1MAjJt70HTCZh0RSjrqQdQHB93hqAs2/QEIy3yUdfhI5kpPsnExuiCawoT5WV9XAucs78EX37oZjx2ewKfu3oVP3vUUvvCrvXjr5Wdi54ksVvSmLPOVrR+puEvwfOneffjivfsxkE7gio1GFdzzTaGQdpiPajVGrlRBNEKYKVdt98zxyRn86Xe2W98fzRUtJ7PiQs2M8zyz4i5QH+DiUXJpMio/4RJTKGRSMZczulyt4aH9Y7h47RJ0J2LYcWwSl60fsLW5cFUfbrlvH4qVKpIxe+6PijzSNYXZ1j/aN2KP/No4ZJjx9o/k8MKzB63tKmt+ZV8K+0byyBYqVk5StmBoquUq+wrAKdEUhFawaQo+dvp8sYJ0MmoNfl4L7ajIpd6u+gCjZl+qoJ4lFFIeQsE2yFdscf86dZXdTxDo271ft5NGAmw2ZFLuGbqOJRQarDmgjnVJd/0cPnvNEnz1Dy/Dd97xfDx33QA+8/M9uPvJk56mIwDo9dBYTmWLWJpO4JK1xop/RHWhoEqaVK2ghQqYgeU9hqDX75nRnKHJvP6S1WBmnMoWcamZ8KgY6klieW/SFZaaLRhaa1+XWwt48vgUMsmYVcfJK9z5JztO4ve/tAXP/Zuf4n3ffATHJwuWH0GxaVUfylXGzuNuZ/Pe4RyIDFNP2jSPzkZTqNUYBxyRX8t6kkgnotjr0BTUc7nC1KScz4rK4fGbTGQLhnBu1KaTEU2hRaKmUFCDusJpPlqa7rbZUPVkJ8BYc6FUrdmjjxwPjRoY0g5Hs9qnIlsoW+GZXv3tTkQ9fQrpRNRXO2hmH58tzryLudKbiuHYhH/hskCagikwlnS5BeulZ/bji2/djD2ncvjPBw7gio2DrjZGP+Ku6KXRXAlnLu3Gl27YjH3DOZyYLGAgbdwH6hzkSxX0agEJK5d04dhkwXbPqP69cfNqXLb+Ijx9Mot1S93CaXlvyrV+gDrfKptYZyRXxFBPEpGIComO4ZAjSkvZ619+wXJrHY+L1y6xtbl47RIkohG86QsP4LcuWI7fuXgVXnT2EBKxCPacymF1f5c1U0/EIrMqH3EyW8BMuYr1Q/XjJiKsH0q7chXUcVpCwRGBtW5VL46Mz/j2I1csY0VvCkcnZlzn7Mc7TmC6VMHrLl7d8jGcLohQaJGY+QBVa+w7iKrcgp5k/cF3ogYp3afg1Cz0tRQU3iGmFZt92YnT4Z0tVJCMRTCQSTTQFMKKPipjzYDbJj9belJxZIv+4ZBqQJ2Y8Y4o0tv0eggFxVnLMvj4dRf6ft7b5dYURnJF61g3DGWwYag+y9XNgL2puPVdNZDp+xo3fR796QSIyHe1wP7uhCtyKlssI5OMocsxAVD77de0I+NcOtrkS4gQ8Kk3PgeFShW7T+bw7DV2oXDGki58913Px7d+cxh3bD+OH24/jr6uOF5+wXI8cmgC5yy3H7dTGzllCp5lvf73sKo5tcGhqa0fzODRw/b1J9SzcUZfl3UOAMMUNlOuYkVfF4BxX/NRtlDB8t4kjk3OuLTQW+7bj8npskso3PP0Kfx67yj+/FXn+x7D6YKYj1okGjWEQqXmrylMF6uG+ShVf/CdTFl2bC0kNWEXIso26uVTcIbNKd+BF84InamCYW4y7PFuwdbrYVtuF9lCxRKW7aCZo7kekurfZmKmhEwy5un3CUqvh09hNF/CYCbh2V7dG84JwBkeJg/lCNfNW14MpBMYc1SbzWrX2nkfjufL6Nc0WONc2o9hfLqEJd0JRCKE7kTMJRAUzzqjDx+/7kJs+fOrcMsNm3HVecvw4ydO4OjEDM5bWRdiGY9SLh/878fwoW9vb3hs+xzhqIoNg2kcGZ+xRePlHAJWPUf5ov0c+9032YLh68skPM5HvuQ6xwBw5+PH8WWzbL0fjx+ZxGV/+1O89csP4Qu/3Isnjk7O+1ogQRBNoUXsmkIZg5kkRnJFV8ZwOhGrD+AeaqqlKXR5aQr2mzitVUnN+GgKjUwyGUe4pDI3OQdUpR2s6u8OTVMwoo/aLxSY2TOiKUj0kTM0eLb9KFZqlrO1VmOM5UtYmk56tnfeG5b5qE/VIKr3d9wyb3kLGIWhKbizpHtSMaTiURwes5uGxqdLVogsYEREOQMjnNpEM+LRCK46fzmuOn85ipUqth2cwLNW2YWC0yRzdHzGMmH5cWhsGolYBMt77NrE2oFuMAPHJgqWvydrnUslYO21jJzbnWQLZawbTHtOOManS5iYLrvut7F8yZgoFiq+99JjRyZwKltEdyJvLYjV1xXH89YP4IqNS/HcdQM4f2Wv5c9YKEQotEiEdE2hgqXpBKZLFWvQqZi5Bd2JWN3U46UpFNyaghr8rdmjqhOUdAsOdbNWqjVMl6q+jmbAmPm7NYUYelJxHBmf1rYbfVq1pAu7TzUvh9wqzEbNpUZ9bZVMsl7wzxkVVK7WrPyRZslrzWbhzdBLXSQzUUzOlFGtMZb6aQqO/BE1I13pMYudmDZMQIkmuR0DacM3oUcBZQtlnLEkhVTM7VNwDvi6Zttv+j6c2kQrJGNRK+pK/w3nQDtqmqgaMZIrYiiTdAmPQdMxP5YvWkLBqSnUz7Hxf1lvCkT+Wc1KkGZS7gix8emyZTrWn91R02w3li/5CgXl7/nJ+6/E+HQJv947ggf2juKBfaP4iemvySRjuPTMfvz1dRdi7dL2mVlbQYRCizg1hd6uGHpn6jNxNQgZ0Uf+cdmTDcxHbkdzXVNIxiKIR8lV8KuhppCM4bi2ilTWzKR2RsxMzZQRjRBW9CXx8MFGy2vPjmmzLEi7NQXAeMCdQkEJ6qXpBEbzJVSqNaviqs5EmzQFwBhQBjNJjOaNBYz02k06To1PDT4rzWqldqFQCiS09IF8RV89aKEnGUcqHrHdhzOlKgrlmvUd4xjq96u1r+kSVve30QeUjNmSzcrVGiZnyiCC7/UBDKe9l4BdavZzJFc36SgNYKXlU7A/K72puGe1YUVWmzTZwrcLZStabNwx+I9ZQqHoG6E2miuiN2UI9+W9Kbzu4tWWb+LoxAy2HhjDA3tH8c3fHMYvnj6FG8zS8PON+BRaJGretJVazRAKqbiRuGSaW9RaAOlkrIlPQd2g9YEsGiF0xesL7eSKFaTiEduDYmTxxl2zn0YDrTPUUN30vV1Os5JRoK+vK46pQvsrRDYqxzFbGq16pgSvcvb6DQKTM23QFFTFVvM31SA1mA6mKeQc9m59ADdm9M1n6wNmGz0CSZ/1ZrVrajmvtf2qPun3xPh0CQPpNmp2Dq1V9YO5bibzYixfsiK3dFSuzqguFAoVEAH93XFjAmWd43rdrV6fEjSFchWlag29qbjLfKSfV6dfoS4U/I/B8DF5TxJWLenCdc9Zhb993SZEyNCMFgoRCi1i0xTM5LNezWavh5F2x6NGkbGAPgX1PaVtOOseKYxoIlXi2r8YXr29PcFLOaaVA7qm5V2o4/Faa2GueK2lMFcarWWgzvFaUyj4mZAmpsvoa2Kvb4azjLcaJPw0BWd2rxJYSzNJVz2n8YDmLX12D9RNi5lUzDKzFco1W5t+27oQdkHFbJhLZms+8sIZfWQbaH1qTgHGLNvLP6MExag2iGbN54aIjCRBj2g+rygowK55OzO8xzVBoEd5lSo1a99jef/BfDTnLdh0ohHCQDopQuF0QjmBKlXTfOSYcSsncToRRSRCyCS8b76pmTK6E+56RRltSc58A6HgNDs0Gmh7UvZEqakZpR7HbAvOT80ozSfYOgWtkg1g6mqVRvV0gggFZsbkTDDzTCNUEqLqhxqk/AYBZ06KqoYbjZBrwJowI4CaoX5LDa7qXuwxZ71APTxTOaS9fArqGKZLVZQqdhPTXDGypjWhoM3wR30GQmbGaN7bfJSIRdCbilk2fcDMzTCfG/1c1kvMxzyzt/U2PamYy8SkayP67+nCYrSBYBvzOQYng5kEhrP++wkbEQotojQFFZKqbPPKHORMOEt71M0H/CNe9NXXcgX7WgoK3VkX1HwEGIO/itXu7Yq7EuGmChX0dsVs9vF2oj+U7aJRX4MIhelSFeUqt8Gn4DYfKROGF7FoxGbnzxXrUVnOaqXGbD2AptBt1xR0LdJ5nlQbXWg5s+Xr2kT7NLueZAylSg0lsx6RPoj6Daj5klGTa6mPcFIRgAq9Fph+LvUKAV7Z28Z3zXOWVD43uynNeu2j4ehCzslovogBn2i0Rscz34QqFIjoaiJ6moj2ENFHPD6/kYiGiehR8+/tYfanHShNYWqmjBrDmlm7HM2m09OrGibgLoan0Ndp9jMf6cXU1GynmaYAGA9LThMizoHC0hQcA1y7sNZSaJBT0Sp156i7r1MOn4KXUFDbvLKZW8G54M9ovoj+7oSv4xRQZr26cFfXWrdlq4CGIJqC0nbUIKWvh+30YYxbuQ9uR7O6Tiqpr53mI2fRR31A9dMU1EDrp3UNpBN2n0LRfi71CC/lt/MrE551PB9FTYApf0GE7D6FRr4GhYpc8stb0RnMJDpTKBBRFMC/A7gGwAUAfo+ILvBoehszP8f8+1JY/WkXsYhxytTF7+2KWYlLzOyKGPIrnz1V8NMUopYt39enkHLbSZv5FABjQKi3r2sKU5p/IlTzUYC+tkoQTWHNgBGFMunxwFolLuY4G04nYiCqn7PRXMl3ZqvQkwqNUF33QDY5UwZzsNl6PGqYUtQstm4fj0OPLALq5qMltoxme+6EGuzaaj5yaCOjeUOjipC/T2HEtNP7OWmXZhJ253qxgox5vE5Tq/I1+CU96otAeWlOyVgEy3pSNk1BaThd8ajvMagQ5WY+BXWcow00jrAJU1O4DMAeZt7HzCUA3wRwXYi/Ny8oTUHdFCr6SK2pkNeijwB3NrFicqZiK4an0M1HRmE979XUWo0+MtqWfUwKKsGrYgq5mPW+neRCEAqZhH/00cR0Gal4BENmLLuXpqDKXzQqcRGESIRs6xH4hVDa+p6MWRVDDZNHfSBTGuCEh0O4EUZWs9pn/Vo7M+HHp0voSdmzuFW4s9PE1FbzkUOIj+WLWNIVR393AiM+A+poE01hqRYCDBhVWC1TnBZllLVpEN5lwvVFoJyakxL0A+mEw2Rk/PZZyzK+QqFZiLLOYE8SM+WqZyHN+SBMobAKwGHt/RFzm5PXE9F2Ivo2Ea3x+BxEdBMRbSWircPDw2H0NTDKp6AuvorWAQxzhdOn4BfloPwRTlzmI48BVDc7TBXKSMQirpLFtvbaDLBeyiKuRe5UUKqYvoZQNQUjHj3tUXp6tkRMx6xf9NGSrgSSsShS8YinULAqpM4x+giwl88eyRebDgBGyQdDKzQiwtwD1niLmsxAul7/SA8B9vIpOAUNkd3JrfbT3ugju8aiQk0NE5CP+cgaUH18CuYgrQIpjNwMzadQqGsKut9mplxFpVqz7ctpPtK3jU+X0O8lFKbLViVYvxm+2t5MewTqGtFCmZDCFApeOYrOwPc7AKxj5osA/BTAV712xMw3M/NmZt48NDTU5m62hqp9pGZRzkFUPeTd8br5yEtTmPLzKZhLcgINfAqp+uprKregEbq9W7/pLY2gULEGVcMBrTSF9gqFqUIFmUSsaUmDVvFzGurO/L6uuLem0CbzEQDTt1TXFPxyFBR6JI5uPtLNg7PSFJRQKLoHuLoppOxpFupJxTVtwp1gOVfqSXv67DvpMgHpjFgDqp/5KIka18+Vvq55Typmqy+lCwWjH/b7pu73inmGGQ+kE+hPJ2w5FUrbGcokbc5oHWViCmY+Ugl5nScUjgDQZ/6rARzTGzDzKDOrI/8igEtD7E9bqGsKahCNaZpCBdMlo369VY7YY8Cq1hjZoneNlEwyakUJFco135BUoO4jaBb37+VTcKrHurBQM+t2L7TT7rUUFH724UBCwWMthbn0Y6pQtrJ0g2gKanC0DWRaKGSrmkJ/d8IamLKaVphOOma9ee+aRvokZmLayNpt5CxvFWeZFjXQLm1gRx/Ll9CdiKIr4a0NKw1i1NQW8mZuhvo9pRE4HdB6PxRGZnwUsWjEVaZGaVcD3XFXfkW/KSymS1UUyu78HiUUgoWkGvfNQoWlhikUfgPgbCJaT0QJANcDuF1vQEQrtbfXAtgZYn/agp9PATBm1rmivQZPTzKGXKliq4aoz8qdpJNG7oCaJXiGpGqzHN1+6oe+0I6a/RtF0iKIRQwbsm5WMj5vvKLZbDDCLts361Q4yxEoJjUTXSNNIR41IlLmiiqBPR5wAFCmGudA1pMywjaLlapWIbU1TYGZkS1UEIuQ6Suwh8COT5esDGgdQ7CZA3bAUNhWcGosY/kSBjIJqxSJF6O5YsNzqTSIkVzR8ullknaNIF+smuZYdX/7aQp2h7/aZvU1ncBAOonJGUP4q+1L0wnLNOR1HMo0FkTjUz6wjtMUmLkC4N0AfgxjsP8WM+8gok8Q0bVms/cQ0Q4iegzAewDcGFZ/2oUz+qgnpWkKhTKmSxVkHFVNmYFpbfagHLhemkK3eROfMGsVeZWZ1pOMgixvmU4YmdW5YsVmZ1ZRGFMz5XrZDbNPeu5FuwhLU/CN8HJpCn7aRKIta0b3mueymbnD6rdpJnImIOoD2fh0CdEIBc7t6E8nUDT9Q8qGro6tR1u3YTzvnRCnm+ImTBt6O9G1XCNMUw2o9oFWZzRfahjfr8wto7mSK5ih7k8r2yr0+tUly2oTF12TVlnLhlAwtivTo+4XAbxzFcbyRoJkkPLsaj8LJRRCLYjHzHcCuNOx7aPa6z8D8Gdh9qHd6JpC2lQzLZ+C6WjWNQXddKMeiPoCO15agCFQTk75awo9DqHgtZC8jnIgqpmjnkmtBgpLUzC1HmddpHaQLVQCqc+t0pOK4ZCjLDTgNB8lPJeLbEc2s6K3y9CuRps4RhWZZAzlKlvtLeeoNhiNT5expCseWGjp9Y+MQVALOTUd8sVKFflS1bOmkb5o0Vi+ZC1d2S66tQnKhJnrM5Cu53OM50uuxXZGc6WGi0jppS7q65qbA7umVetreXgtU2u8d/sdsoVK3beTTlja0/h0CUM9SYzlS7j0zIG6UPDwKwQpcaGIRyNY0h3vPE2hU1E+hfHpkiUM9KJs+WLVviiOw7FmtPN34KnInFNZQ1PQK6Qq9Lo5zgffD2XacM7WjRXD6mYlpfV4LRozV4L2tVX0GbBClc0O4miea+JavR+G43g4awqFAHkKQF0rzHiYLVot661XSnVqkUozqTvX3f3To48m2lBS3AmRWfqlWLGiigbSCcspP+Izy240oC7pTiBChkah5xno/8fyJRQrtaY+BbUAFQAzqs8wuamBfmk6YQne0VzJSkobSMe1MiPuwXw0X8RggGxmxWAmiZEO9Cl0JJamMF2PHopHI+hORA1NoVRBtzaQ12cqdfORXzE8oD47OWmWF/Yyt+iCJqhJRoVtZovO2aNTU4hb/9vtaNYjbNqJsxwBoK9sFzP/G/HqTvOEUQyvTZpCKg5mWFpLEEczAKusuWXL1ma3QSukKtTsf2y6hKzjfCuHvFeJC2cboxiet99hrqjgi1HNzOas26Qw6h41Du81isglTKHg7VM40eAc6+ihwUZ74zmwEvm6E7bCg6qc9kA6aZkLvRzmrWgKgGESG21QXC9MRCi0SCxar5KqJ5+pSqnOhDOv8tleaykoui2h0NzRPDVTQa4UbNEalUSniuHp27MFY3uEDP+DcTyxUEJSw4o+0ssRANo57laagneY7eRM2WrTjn4AwP6RPOLR5n6AtCUUZgBoA5k2izUqpAYfTKz6R+YAqd8bSgvwyma22qRi1gJS06Vq230KVj+K9YFWRR8BcA2E2WIF5So31bqWppM285HTBHTc0sZMv42PpuDSpM0Jh62vmgCzoorSCfR2GQUNvUJrgxbDUxj1j0RTOC2IaTH2ep6BWlMhX6xaAyugRwpp5qMGQqHuUyjYvq9jmR2mCmAOVmBOFdHLFuz5ESrKSJXN1p2SU4Vy29ZUKFaMipvtXJ9Z4bVudb2mkfEgqoHfaUJSCW7tQGlZB0byWJpONvUD9PhpClo9p4kWl8PUZ9zOpU8zybilfQDekTDqt5W2087ENasf5gRFD9P0WiwH0JK+mgyoSzMJm6PZKWAtE525vSseRTRCrnBx1zkz+2ol8qXjlpAez5dswoKIbCHBimqNMTbdvOyJjmE+Ek3htCAaqZ8y+4zC1BRKDk0h6Z6RTJornHV7xF2r754yNQUvoZCMGaGkxydmXP3wo8dM93fOhFQIojOZrrfLcIIWK+5okNmg11xqN85qr0A9/0APSQXsQqFsxq63y26uzuu+kXygWaFzwHJGH+VMU08r/etNxa06Qk5zncqjaGg+Mn+7LhTaf71U0INukunripuzbPtA2KwEucIodZXXFRQAABSzSURBVFFqoCkYz4qaQFnZ25r5SOUG2cyrKdXXenHARCyCnqRRrttZgmOpozgfYERxMQcrcaEY6kkiW6x45jyEjQiFFrFpCl1x2+tJM/pIL+PgFQ+tiuF5zSRV5JJastDLfKRCSY9N2AeTRiifwpTDpKDWb56YKbvMYUD7sprDqHuk8DzHDm3MSyg00thmg142JMgA4DJtOJygw9kiCuVaS+ajSMSYrY5a5iP7vZgrVqyQSS9ho9ofNtfuDsN8ZPUjb9RfSsQiiCi/gFNTMAWHXzE8xdK0UVlUTQzUM6j+H3c48wGY6yXU7weve7THXKBqfLqE3lS9VpSR1VxyCVhnCQz9GFr1KQALE5YqQqFFon7mo1QMw9kiamwfyNParE8xOeNfmkKZniZnylbSkReZVAzHp4JrCmo9ZrUwkLXdHBCPTxQcmkJ76x/Nh6Yw5WE+aiQU2pnNbPSjfl6blbgANE1hqoAIwdIcVWG6w+PG9W3VhNOfTuDYxAyqNbaVKc+YiZHHJmeQTkQ962VlXJpCSD6FgmE+0k0qXglsgc1H6YSlfWSS9VIqqjaW03wEuMujeN2jyuw66oiAUoP/WD6AUAh4DDr1+kfz71cQodAidk3BPrgOW1nI9YfNmUkK2JOqXPs32wPepiNFJhl3mR0akUnWnbHO2SNgLBzudLAB8Ez4mg16xc524xVeOOmo26Pnkigm2lzbR9ccgwwAKrRYDWRKc1SmjcOzNOEMdCes79qvdd1f4Kd9qDbWb7dxfWaF8m2M5Yu2gdbwC9hnxnrYaiOUZnZwbNr13GSS9ZXZnKYhpwavttvamFnq/Q6hMD5tmI/SiShSZka8UaXWqSmoEOXWQlIBLIhfQYRCi/hrCkY4IuCuAppJxm0LeujlF7xwOsm86DETn4CgPgW3dmBsr+c8hKkpTDkcgO3EUyjMlNEVjyIRM25xL01hcqa1EhJB+wEg0ApbqXgE6nZyCvaeVNwy4bTav/50HEfG3Vqkup8OjU37DrI9Kbum0C4nvE4mFUO+VDHDNOvnaSCddM2yR3Il9CRjDasAA3UhfHA073puMh6TIMCdCe9Vhr4nFUeuVMFIrmjTavq7ExjLlazKqfVjSGBiumyrvjqWb11TWCrmo9OHmOZotvsUdJOR/QbOJKM2NVVF+vjR7bCHemG70QMMtBnHDMnrte142u1TKNYL8bUbS7A5zEe6BuBVPrtRaPBsSMaiSJpCKMgAoDQCwC0sM8mYFZbc6mx9IJ1AyRyUejzuk2MTBV+TmaU5js8gk4xZQrWdZJJRMBvaiMt85DCXqNpIzVA2+CNmv+2/Z7xXdaAUKvhCoRcQVPSaZWqOjM/YTGkD6TjGpktuE1hG5TDU77P60qyzMR+JUHjGo0pnA25NQeF0DjuX5PQrm+38fiNNwW4bDZanYL1OujUFwP0wAN6L18yGeTcfeZjonFnNVmZvG0tDq/MZZNlFvb3zvOjXvmWfgscSm/pvNFoBTN17lRqHYjoC6iUo8qWqbcBfmk4gW6ygWKlH3Izmi4FCOZVpplpj17nUC9zpwR36WueAt6agF5+0+xSSKJRrODpu17r6tTIjClVaO9pCyfhUPIqeZEx8CqcDjXwKim6X+aju0GI2EoMazU4z2lKefqgbNxYhywfRiJ6kt3bgLHlRf12vv9MO9EJ87Ub5bZwmuqBCYa6rrumocxjUfuxnKtSDAVrVZPRByst8BPgLmrjm0wrDyezsh32WbZwz+7rNjYvh1b9b34+fpuA8x6oWlEJfS8FqowlVu5nI2H5wdNrWPz2xTT+GVsJRFYM9SdEUTgca+RQU7puy7lMolGsoVWueS3Eq0j4mBds+fWY/zdoD3mYi5+tkLIJENNK2SqnZgrE0ZpAqkbMhk7SX+vbKVO7riluCQLXpTcVamsE1Qw0iQe3Het1/23YtySrVYllvfTC31T5KNhcKQP0YwhIK+gTFGdED2MtEjOZLgbQu3dTlKxSScdd2PRNeX9Pa6mvKu6/q3FRqbCssqDQfm1BoUrvJj8FMQoTC6UCU/PIU6jePMynNiHIwBqMgdmwrxrqRpmDFtAebRfrd6H4+BSIysrTbpCkYiVThmCMAsyxHoXGEl1NTaGeJC70fQOuagvPcKGExm+Qxu6bgbSpsZBpS91YYiWuAfYKi99UqgW0OqLUaYzzggEpE1izdz9HsZ1bSV2ZLxiI2P4qtr91uAWa8Trra6El4o7liYHOizkKVuhCh0CKRCGkRI+5kL8A9U1nRl8LxiQIOjU67FrPxQjmqG9nfnYlOzfBTiVPxKBLm7N2ZO9HOSqlh1T1SOGPOJzyFQsIRklpqe3RNbyqOdINVwpz4XUd1jWYTGaUPWH6aQqP9qr6Ekbjm7MdSW/RRvQQ2YARkVGoc2PSitDNn4IU1gXL5+uyZ8M7ETsD+TOjno9/hIHduH7X5FGarKYj56LQhFonY1iQAHD4FR/TRjc9fh1iU8E8/eTqYppAMEn3k7aD0w8t55vzMaVvvaWOl1CDLhs4FfaW4crWGaa1stsLlU5hpf2noS87sxwvOGgzcvlH0ETC7PAE1AGWSdtOYXlqlUfXTupYSvlCwOZodPoV6NnOwfigB46d1uTQIVYLG1OKzjsRO576ckVLWMWiv49EIelMx6xgq1RrGp8st5SgoBjNJTEx7LzwUJiIUZoGxEpYzrty4meJRcsVUL+9N4X+/aAPueOwY7t09AqCxc7NuPvKfbfqZHfxQWbLOgULvu7NP7ayU6ixJ3G70dZr9BG9fVxz5UtV6yLyc0XPlbS9cj5vfujlw+2amjdloCv2aUHBS328j85HyKYQjxPVj1QdXo4wEWSYTZ12hZihNwT34e0+glABQGqZXGfoeH01B1Zhybjf6Uc+3UKGps1lcarDH7WOZD0QozIJYhFyOYrWmgjPySPFHV27E0nQCn//lXgDBNIVGWkCvz2Dih1EvKe5ZXkMJFk/zUbt8CiGbj/REJH+hYIbZmp9PtnEthdnipylYJpxZDMzphGES9FyLw/ydRgOtpSmEZD5S93d3wu5EJyKzTIRhMlFmpKCzbBXb7zyXaSuaz1uDyFpCwb0IlKqm6lwSVdWYMvpnP0/93XFN22k9m1mhrz09n4QqFIjoaiJ6moj2ENFHPD5PEtFt5udbiGhdmP1pF9GoW1MAjEHUL2Iok4zhfb91thXpECQktZGjWd3QrSSDZZIxT82itysGIre5yliVrZ3mozA1hbr5yFcoaOWzmTkU81GrOBeJV2Ss2XrrAzMRoT8d9xYKASKL6gIpHKEQjxormnkJJmNdBLv5KOgs28/R7H+OTU2h6K8pqATD/m73Ot5KaDqT6/TM7LEWtR2dIVNTGO4UoUBEUQD/DuAaABcA+D0iusDR7G0Axpn5LAD/AuCTYfWnnRiagvfg6lUOW3H9ZWuxfjANoPEMP1BIaoA2TnpSMc/f7UnG0aMVEVP0pgwb/MmpgrWuAjNjYrqE/SP5hustVKo1jOSKVunfsJbitI4hFUO+VMWR8Wmrbo/zGikhcWKqgJFcCdUah1LGoRXSPmZAdZ1mq8kMZpKepqfeVAypeKShI7wefRTeuelJxTyT0pZmEnji2CS+8/AR7B3OtdQP5ZNwOZR9zEfqnI9Pl7DrZNaq2hq0rwPpBOJRcv2eKuyXL1bw5PEpAMH9IjpK83lo/xge3DeKhw+O4ahZLj9Mwpu6AZcB2MPM+wCAiL4J4DoAT2ptrgPwMfP1twF8loiI27WyS0hEI+R58/Sm4ijX/Lsej0bwz2+4CL98erhhvH6reQpBecOlq5H0iHk/Z3nGc+m/Zb0plCo1PO/vfoaueBQDZnlifY2FdCKKoZ6ktfC6sWZtyZbmn05EkS9VWxJgraJmky/85C/q29LuGRwAvPmLW6xtYZlIgtLU0TzLgfnvXrfJM79BzXobYeUphJTRrPrhNXt+7XNW4R/uegof/O/HABhCLGipjeesWYJzlmewYSjj+i39v0I9Ox+/oz4krenvdu3Xz+w60J3w1SCGs0U8669+DMCYRC7rTQU6Bp1lPSkkYhF87p69+Nw9htn5j6/ciI9cc17L+2qFMIXCKgCHtfdHADzPrw0zV4hoEsBSACN6IyK6CcBNALB27dqw+huYD778XGwYSru2/9GVG1FtIBQA4NIzB3DpmQMN2zx/41L80Ys3YNPqPt82Q5kkPvjyc/CqTSuDdRrAjS9Y77n9A68413P7W684E2cvy+DgaB4HRqcxmitiqCeJFX1dWNIVx2i+iOOTBQxni1YxQJBhUx3MJNHfnUCuaBQTm5wpt9TXVnn9JavR1xVHoVxFpcbo64rjzKX2B/yiVX345Os3YWqmgiozYhHCK561PLQ+BeHF5wzhnS/ZiAvO6LVtP29FD975ko142XnLZrXfZ69Z4rn9huevw8ubzDav2bQCM+UqVsxiIAvK+19+jucaCa+/dDVed/Eq7Dg2hZ8/dcpytgbhrGUZ/OT9V7q2n7M8g3e9dCNeeq79XKbiUXzg5ecgX6rgvBU9OHd5L85b0eP6/rtfepanBeCG56/DVee7r89rLz4DkzMlrO7vxobBNC5c1Tcrja8rEcVP338lTkwVUKnWUK4xVvd3tbyfVqGwJuVE9AYAr2Tmt5vv/wDAZcz8J1qbHWabI+b7vWabUb/9bt68mbdu3RpKnwVBEDoVInqYmZuGxoXpaD4CYI32fjWAY35tiCgGoA/AWIh9EgRBEBoQplD4DYCziWg9ESUAXA/gdkeb2wHcYL7+XQA/f6b7EwRBEDqZ0HwKpo/g3QB+DCAK4MvMvIOIPgFgKzPfDuAWAP9JRHtgaAjXh9UfQRAEoTlhOprBzHcCuNOx7aPa6wKAN4TZB0EQBCE4ktEsCIIgWIhQEARBECxEKAiCIAgWIhQEQRAEi9CS18KCiIYBHJzl1wfhyJZeJCzG416MxwwszuNejMcMtH7cZzLzULNGp51QmAtEtDVIRl+nsRiPezEeM7A4j3sxHjMQ3nGL+UgQBEGwEKEgCIIgWCw2oXDzQndggViMx70YjxlYnMe9GI8ZCOm4F5VPQRAEQWjMYtMUBEEQhAaIUBAEQRAsFo1QIKKriehpItpDRB9Z6P6EARGtIaJfENFOItpBRO81tw8Q0d1EtNv837/QfQ0DIooS0SNE9APz/Xoi2mIe921mCfeOgYiWENG3iegp85pfsRiuNRG937y/nyCiW4ko1YnXmoi+TESniOgJbZvn9SWDz5jj23YiumS2v7sohAIRRQH8O4BrAFwA4PeI6IKF7VUoVAB8kJnPB3A5gHeZx/kRAD9j5rMB/Mx834m8F8BO7f0nAfyLedzjAN62IL0Kj08DuIuZzwPwbBjH3tHXmohWAXgPgM3MfCGMsvzXozOv9X8AuNqxze/6XgPgbPPvJgCfm+2PLgqhAOAyAHuYeR8zlwB8E8B1C9yntsPMx5l5m/k6C2OQWAXjWL9qNvsqgNcuTA/Dg4hWA3g1gC+Z7wnAywB822zSUcdNRL0AXgxjTRIwc4mZJ7AIrjWMkv9d5mqN3QCOowOvNTP/Cu6VKP2u73UAvsYGDwJYQkSzWhR9sQiFVQAOa++PmNs6FiJaB+BiAFsALGfm44AhOADMbjX4Zzb/CuBPAdTM90sBTDBzxXzfadd8A4BhAF8xTWZfIqI0OvxaM/NRAP8M4BAMYTAJ4GF09rXW8bu+bRvjFotQII9tHRuLS0QZAN8B8D5mnlro/oQNEb0GwClmfljf7NG0k655DMAlAD7HzBcDyKPDTEVemDb06wCsB3AGgDQM04mTTrrWQWjb/b5YhMIRAGu096sBHFugvoQKEcVhCIRvMPP/mJtPKlXS/H9qofoXEi8AcC3R/9/e3YRYVcZxHP/+mLAXiqKXXcQQWEEtpoWhYTCUtIhWUQxUJEb0AtYqxNxEi0AQWrUKijYmRC82q2xRZhnllI4jFG0ycBaKi5BMCJt+LZ7nnk7XGXXiNDfu/X02c8/7OTxz7/88z3PO/9HPlKbBeyk1h2tqEwMMX5nPA/O2v6nT71GCxLCX9QbgqO2Tts8CHwB3M9xl3bZU+Xb2GzcqQWEGWF2fUFhF6ZiaHvA5da62o78J/GD7tdaiaWBj/bwR+Gilz+2/ZPsl2zfaHqeU7ae2HwM+Ax6uqw3Vdds+DhyTdGuddR/wPUNe1pRmo7WSrqj/773rHtqy7rNU+U4DT9SnkNYCp3rNTMs1Mm80S3qAcvc4Brxl+9UBn1LnJK0HvgCO8Hfb+jZKv8K7wE2UL9Ujtvs7sIaCpEngRdsPSrqZUnO4FjgEPG7790GeX5ckTVA61lcBPwGbKDd6Q13Wkl4BpihP2x0CnqK0nw9VWUvaBUxSUmSfAF4GdrNI+dYA+TrlaaUzwCbb3/6r445KUIiIiAsbleajiIi4CAkKERHRSFCIiIhGgkJERDQSFCIiopGgECNL0lf177ikRzve97bFjhXxf5dHUmPktd9tWMY2Y7YXzrP8tO0ruzi/iJWUmkKMLEmn68ftwD2SZmuu/jFJOyTN1Nz0z9T1J+t4Fe9QXhBE0m5J39X8/k/XedspWTxnJe1sH6u+cbqjjgVwRNJUa997W+Mj7KwvJEWsqEsuvErE0NtKq6ZQf9xP2V4j6VJgv6RP6rp3AXfYPlqnn6xvlF4OzEh63/ZWSZttTyxyrIeACcr4B9fXbfbVZXcCt1Ny1uyn5HT6svvLjVhaagoR57qfkkdmlpIi5DrK4CUAB1oBAeAFSYeBrykJyVZzfuuBXbYXbJ8APgfWtPY9b/tPYBYY7+RqIpYhNYWIcwl43vaef8wsfQ+/9U1vANbZPiNpL3DZRex7Ke1cPQvk+xkDkJpCBPwKXNWa3gM8V9OQI+mWOoBNv6uBX2pAuI0yBGrP2d72ffYBU7Xf4gbK6GkHOrmKiA7kTiQC5oA/ajPQ25Sxj8eBg7Wz9ySLD+/4MfCspDngR0oTUs8bwJykgzWNd8+HwDrgMGUQlC22j9egEjFweSQ1IiIaaT6KiIhGgkJERDQSFCIiopGgEBERjQSFiIhoJChEREQjQSEiIhp/AV3KKrBOKEGqAAAAAElFTkSuQmCC\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "net = init_toy_model()\n", "stats = net.train(X, y, X, y,\n", " learning_rate=1e-1, reg=5e-6, batch_size=1,\n", " num_iters=100, verbose=False)\n", "\n", "print('Final training loss: ', stats['loss_history'][-1])\n", "\n", "# plot the loss history\n", "plt.plot(stats['loss_history'])\n", "plt.xlabel('iteration')\n", "plt.ylabel('training loss')\n", "plt.title('Training Loss history')\n", "plt.show()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "# Load the data\n", "Now that you have implemented a two-layer network that passes gradient checks and works on toy data, it's time to load up our favorite CIFAR-10 data so we can use it to train a classifier on a real dataset." ] }, { "cell_type": "code", "execution_count": 7, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Train data shape: (49000, 3072)\n", "Train labels shape: (49000,)\n", "Validation data shape: (1000, 3072)\n", "Validation labels shape: (1000,)\n", "Test data shape: (1000, 3072)\n", "Test labels shape: (1000,)\n" ] } ], "source": [ "from cs231n.data_utils import load_CIFAR10\n", "\n", "PATH_TO_CIFAR = '/home/yorko/data/cifar-10-batches-py/'\n", "\n", "def get_CIFAR10_data(num_training=49000, num_validation=1000, num_test=1000):\n", " \"\"\"\n", " Load the CIFAR-10 dataset from disk and perform preprocessing to prepare\n", " it for the two-layer neural net classifier. These are the same steps as\n", " we used for the SVM, but condensed to a single function. \n", " \"\"\"\n", " # Load the raw CIFAR-10 data\n", " X_train, y_train, X_test, y_test = load_CIFAR10(PATH_TO_CIFAR)\n", " \n", " # Subsample the data\n", " mask = list(range(num_training, num_training + num_validation))\n", " X_val = X_train[mask]\n", " y_val = y_train[mask]\n", " mask = list(range(num_training))\n", " X_train = X_train[mask]\n", " y_train = y_train[mask]\n", " mask = list(range(num_test))\n", " X_test = X_test[mask]\n", " y_test = y_test[mask]\n", "\n", " # Normalize the data: subtract the mean image\n", " mean_image = np.mean(X_train, axis=0)\n", " X_train -= mean_image\n", " X_val -= mean_image\n", " X_test -= mean_image\n", "\n", " # Reshape data to rows\n", " X_train = X_train.reshape(num_training, -1)\n", " X_val = X_val.reshape(num_validation, -1)\n", " X_test = X_test.reshape(num_test, -1)\n", "\n", " return X_train, y_train, X_val, y_val, X_test, y_test\n", "\n", "\n", "# Invoke the above function to get our data.\n", "X_train, y_train, X_val, y_val, X_test, y_test = get_CIFAR10_data()\n", "print('Train data shape: ', X_train.shape)\n", "print('Train labels shape: ', y_train.shape)\n", "print('Validation data shape: ', X_val.shape)\n", "print('Validation labels shape: ', y_val.shape)\n", "print('Test data shape: ', X_test.shape)\n", "print('Test labels shape: ', y_test.shape)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "# Train a network\n", "To train our network we will use SGD with momentum. In addition, we will adjust the learning rate with an exponential learning rate schedule as optimization proceeds; after each epoch, we will reduce the learning rate by multiplying it by a decay rate." ] }, { "cell_type": "code", "execution_count": 8, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "iteration 0 / 1000: loss 2.302944\n", "iteration 100 / 1000: loss 1.860528\n", "iteration 200 / 1000: loss 1.804372\n", "iteration 300 / 1000: loss 1.635850\n", "iteration 400 / 1000: loss 1.614847\n", "iteration 500 / 1000: loss 1.557273\n", "iteration 600 / 1000: loss 1.599602\n", "iteration 700 / 1000: loss 1.540287\n", "iteration 800 / 1000: loss 1.544831\n", "iteration 900 / 1000: loss 1.585729\n", "Validation accuracy: 0.474\n" ] } ], "source": [ "input_size = 32 * 32 * 3\n", "hidden_size = 50\n", "num_classes = 10\n", "net = TwoLayerNet(input_size, hidden_size, num_classes)\n", "\n", "# Train the network\n", "stats = net.train(X_train, y_train, X_val, y_val,\n", " num_iters=1000, batch_size=256,\n", " learning_rate=1e-3, learning_rate_decay=0.95,\n", " reg=0.25, verbose=True)\n", "\n", "# Predict on the validation set\n", "val_acc = (net.predict(X_val) == y_val).mean()\n", "print('Validation accuracy: ', val_acc)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "# Debug the training\n", "With the default parameters we provided above, you should get a validation accuracy of about 0.29 on the validation set. This isn't very good.\n", "\n", "One strategy for getting insight into what's wrong is to plot the loss function and the accuracies on the training and validation sets during optimization.\n", "\n", "Another strategy is to visualize the weights that were learned in the first layer of the network. In most neural networks trained on visual data, the first layer weights typically show some visible structure when visualized." ] }, { "cell_type": "code", "execution_count": 9, "metadata": {}, "outputs": [ { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "# Plot the loss function and train / validation accuracies\n", "plt.subplot(2, 1, 1)\n", "plt.plot(stats['loss_history'])\n", "plt.title('Loss history')\n", "plt.xlabel('Iteration')\n", "plt.ylabel('Loss')\n", "\n", "plt.subplot(2, 1, 2)\n", "plt.plot(stats['train_acc_history'], label='train')\n", "plt.plot(stats['val_acc_history'], label='val')\n", "plt.title('Classification accuracy history')\n", "plt.xlabel('Epoch')\n", "plt.ylabel('Clasification accuracy')\n", "plt.legend()\n", "plt.show()" ] }, { "cell_type": "code", "execution_count": 10, "metadata": {}, "outputs": [ { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "from cs231n.vis_utils import visualize_grid\n", "\n", "# Visualize the weights of the network\n", "\n", "def show_net_weights(net):\n", " W1 = net.params['W1']\n", " W1 = W1.reshape(32, 32, 3, -1).transpose(3, 0, 1, 2)\n", " plt.imshow(visualize_grid(W1, padding=3).astype('uint8'))\n", " plt.gca().axis('off')\n", " plt.show()\n", "\n", "show_net_weights(net)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "# Tune your hyperparameters\n", "\n", "**What's wrong?**. Looking at the visualizations above, we see that the loss is decreasing more or less linearly, which seems to suggest that the learning rate may be too low. Moreover, there is no gap between the training and validation accuracy, suggesting that the model we used has low capacity, and that we should increase its size. On the other hand, with a very large model we would expect to see more overfitting, which would manifest itself as a very large gap between the training and validation accuracy.\n", "\n", "**Tuning**. Tuning the hyperparameters and developing intuition for how they affect the final performance is a large part of using Neural Networks, so we want you to get a lot of practice. Below, you should experiment with different values of the various hyperparameters, including hidden layer size, learning rate, numer of training epochs, and regularization strength. You might also consider tuning the learning rate decay, but you should be able to get good performance using the default value.\n", "\n", "**Approximate results**. You should be aim to achieve a classification accuracy of greater than 48% on the validation set. Our best network gets over 52% on the validation set.\n", "\n", "**Experiment**: You goal in this exercise is to get as good of a result on CIFAR-10 as you can, with a fully-connected Neural Network. For every 1% above 52% on the Test set we will award you with one extra bonus point. Feel free implement your own techniques (e.g. PCA to reduce dimensionality, or adding dropout, or adding features to the solver, etc.).\n", "\n", "**Explain your hyperparameter tuning process below.**\n", "\n", "$\\color{blue}{\\textit Your Answer:}$ *Typically you start with a wide range of hyperparameters, and then narrow down the search space around good values. You need to make sure that you don't get optimal loss (or accuracy) values with extreme values of hyperparameters, otherwise you need to change the range of values to try.\n", "That's how I first defined good hidden size and a range of learning rate values. Then learning rate decay and reqularization strength. Not all history of experiments is shown in this notebook. Below we iterate over the final grid of hyperparameters.*" ] }, { "cell_type": "code", "execution_count": 11, "metadata": {}, "outputs": [], "source": [ "from tqdm import tqdm_notebook" ] }, { "cell_type": "code", "execution_count": 12, "metadata": {}, "outputs": [ { "data": { "application/vnd.jupyter.widget-view+json": { "model_id": "7907b29e3aaf43b0bf9d0f37427ccd77", "version_major": 2, "version_minor": 0 }, "text/plain": [ "HBox(children=(IntProgress(value=0, max=5), HTML(value='')))" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "application/vnd.jupyter.widget-view+json": { "model_id": "ab41d9fd9c0c4af88586871cf91dc9c3", "version_major": 2, "version_minor": 0 }, "text/plain": [ "HBox(children=(IntProgress(value=0, max=5), HTML(value='')))" ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "lr: 0.0001, reg: 1e-06\n", "Validation accuracy: 0.366\n", "lr: 0.0001, reg: 2.5750000000000002e-05\n", "Validation accuracy: 0.366\n", "lr: 0.0001, reg: 5.05e-05\n", "Validation accuracy: 0.37\n", "lr: 0.0001, reg: 7.525e-05\n", "Validation accuracy: 0.364\n", "lr: 0.0001, reg: 0.0001\n", "Validation accuracy: 0.366\n" ] }, { "data": { "application/vnd.jupyter.widget-view+json": { "model_id": "f844ad8651684773bb2b3b1caf5b3b55", "version_major": 2, "version_minor": 0 }, "text/plain": [ "HBox(children=(IntProgress(value=0, max=5), HTML(value='')))" ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "lr: 0.000325, reg: 1e-06\n", "Validation accuracy: 0.47\n", "lr: 0.000325, reg: 2.5750000000000002e-05\n", "Validation accuracy: 0.467\n", "lr: 0.000325, reg: 5.05e-05\n", "Validation accuracy: 0.481\n", "lr: 0.000325, reg: 7.525e-05\n", "Validation accuracy: 0.465\n", "lr: 0.000325, reg: 0.0001\n", "Validation accuracy: 0.469\n" ] }, { "data": { "application/vnd.jupyter.widget-view+json": { "model_id": "a2bce59882dc409188be024d6fbd87be", "version_major": 2, "version_minor": 0 }, "text/plain": [ "HBox(children=(IntProgress(value=0, max=5), HTML(value='')))" ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "lr: 0.00055, reg: 1e-06\n", "Validation accuracy: 0.509\n", "lr: 0.00055, reg: 2.5750000000000002e-05\n", "Validation accuracy: 0.505\n", "lr: 0.00055, reg: 5.05e-05\n", "Validation accuracy: 0.504\n", "lr: 0.00055, reg: 7.525e-05\n", "Validation accuracy: 0.497\n", "lr: 0.00055, reg: 0.0001\n", "Validation accuracy: 0.507\n" ] }, { "data": { "application/vnd.jupyter.widget-view+json": { "model_id": "94241fdb1ffa44ee8f435ca73d7a0441", "version_major": 2, "version_minor": 0 }, "text/plain": [ "HBox(children=(IntProgress(value=0, max=5), HTML(value='')))" ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "lr: 0.0007750000000000001, reg: 1e-06\n", "Validation accuracy: 0.51\n", "lr: 0.0007750000000000001, reg: 2.5750000000000002e-05\n", "Validation accuracy: 0.515\n", "lr: 0.0007750000000000001, reg: 5.05e-05\n", "Validation accuracy: 0.498\n", "lr: 0.0007750000000000001, reg: 7.525e-05\n", "Validation accuracy: 0.522\n", "lr: 0.0007750000000000001, reg: 0.0001\n", "Validation accuracy: 0.499\n" ] }, { "data": { "application/vnd.jupyter.widget-view+json": { "model_id": "dd96c7b9527344b09751a357024495e3", "version_major": 2, "version_minor": 0 }, "text/plain": [ "HBox(children=(IntProgress(value=0, max=5), HTML(value='')))" ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "lr: 0.001, reg: 1e-06\n", "Validation accuracy: 0.515\n", "lr: 0.001, reg: 2.5750000000000002e-05\n", "Validation accuracy: 0.521\n", "lr: 0.001, reg: 5.05e-05\n", "Validation accuracy: 0.52\n", "lr: 0.001, reg: 7.525e-05\n", "Validation accuracy: 0.52\n", "lr: 0.001, reg: 0.0001\n", "Validation accuracy: 0.523\n", "\n", "CPU times: user 37min 25s, sys: 4.09 s, total: 37min 29s\n", "Wall time: 6min 14s\n" ] } ], "source": [ "%%time\n", "best_net = None # store the best model into this \n", "results = {}\n", "best_val_acc = -1\n", "# some params are fixed, others are varied \n", "num_iters = 2000\n", "hidden_size = 150\n", "batch_size = 256\n", "learning_rate_decay = 0.95\n", "learning_rates = np.linspace(1e-4, 1e-3, 5)\n", "regularization_strengths = np.linspace(1e-6, 1e-4, 5)\n", "\n", "\n", "#################################################################################\n", "# TODO: Tune hyperparameters using the validation set. Store your best trained #\n", "# model in best_net. #\n", "# #\n", "# To help debug your network, it may help to use visualizations similar to the #\n", "# ones we used above; these visualizations will have significant qualitative #\n", "# differences from the ones we saw above for the poorly tuned network. #\n", "# #\n", "# Tweaking hyperparameters by hand can be fun, but you might find it useful to #\n", "# write code to sweep through possible combinations of hyperparameters #\n", "# automatically like we did on the previous exercises. #\n", "#################################################################################\n", "best_params = None\n", "for lr in tqdm_notebook(learning_rates):\n", " for reg in tqdm_notebook(regularization_strengths):\n", " print('lr: {}, reg: {}'.format(lr, reg))\n", " net = TwoLayerNet(input_size, hidden_size, num_classes)\n", " stats = net.train(X_train, y_train, X_val, y_val,\n", " num_iters=num_iters, batch_size=batch_size,\n", " learning_rate=lr, learning_rate_decay=learning_rate_decay,\n", " reg=reg, verbose=False)\n", " y_train_pred = net.predict(X_train)\n", " train_acc = np.mean(y_train == y_train_pred)\n", "\n", " val_acc = (net.predict(X_val) == y_val).mean()\n", " print('Validation accuracy: ', val_acc)\n", " results[(lr, reg)] = val_acc\n", " if val_acc > best_val_acc:\n", " best_val_acc = val_acc\n", " best_net = net \n", " best_params = (lr, reg)\n", "#################################################################################\n", "# END OF YOUR CODE #\n", "#################################################################################" ] }, { "cell_type": "code", "execution_count": 13, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "((0.001, 0.0001), 0.523)" ] }, "execution_count": 13, "metadata": {}, "output_type": "execute_result" } ], "source": [ "best_params, best_val_acc" ] }, { "cell_type": "code", "execution_count": 14, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "iteration 0 / 3000: loss 2.302631\n", "iteration 100 / 3000: loss 1.942662\n", "iteration 200 / 3000: loss 1.694240\n", "iteration 300 / 3000: loss 1.642821\n", "iteration 400 / 3000: loss 1.634989\n", "iteration 500 / 3000: loss 1.581651\n", "iteration 600 / 3000: loss 1.482083\n", "iteration 700 / 3000: loss 1.443788\n", "iteration 800 / 3000: loss 1.483015\n", "iteration 900 / 3000: loss 1.384776\n", "iteration 1000 / 3000: loss 1.511768\n", "iteration 1100 / 3000: loss 1.275055\n", "iteration 1200 / 3000: loss 1.365429\n", "iteration 1300 / 3000: loss 1.305279\n", "iteration 1400 / 3000: loss 1.355764\n", "iteration 1500 / 3000: loss 1.278184\n", "iteration 1600 / 3000: loss 1.154499\n", "iteration 1700 / 3000: loss 1.172329\n", "iteration 1800 / 3000: loss 1.322811\n", "iteration 1900 / 3000: loss 1.401773\n", "iteration 2000 / 3000: loss 1.238886\n", "iteration 2100 / 3000: loss 1.155777\n", "iteration 2200 / 3000: loss 1.236830\n", "iteration 2300 / 3000: loss 1.149130\n", "iteration 2400 / 3000: loss 1.168785\n", "iteration 2500 / 3000: loss 1.139603\n", "iteration 2600 / 3000: loss 1.160867\n", "iteration 2700 / 3000: loss 1.064185\n", "iteration 2800 / 3000: loss 1.009131\n", "iteration 2900 / 3000: loss 1.114445\n", "CPU times: user 2min 5s, sys: 160 ms, total: 2min 5s\n", "Wall time: 21 s\n" ] } ], "source": [ "%%time\n", "best_net = TwoLayerNet(input_size, hidden_size, num_classes)\n", "stats = best_net.train(X_train, y_train, X_val, y_val,\n", " num_iters=3000, batch_size=batch_size,\n", " learning_rate=best_params[0], learning_rate_decay=learning_rate_decay,\n", " reg=best_params[1], verbose=True)" ] }, { "cell_type": "code", "execution_count": 15, "metadata": {}, "outputs": [ { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "# Plot the loss function and train / validation accuracies\n", "plt.subplot(2, 1, 1)\n", "plt.plot(stats['loss_history'])\n", "plt.title('Loss history')\n", "plt.xlabel('Iteration')\n", "plt.ylabel('Loss')\n", "\n", "plt.subplot(2, 1, 2)\n", "plt.plot(stats['train_acc_history'], label='train')\n", "plt.plot(stats['val_acc_history'], label='val')\n", "plt.title('Classification accuracy history')\n", "plt.xlabel('Epoch')\n", "plt.ylabel('Clasification accuracy')\n", "plt.legend()\n", "plt.show()" ] }, { "cell_type": "code", "execution_count": 16, "metadata": {}, "outputs": [ { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "# visualize the weights of the best network\n", "show_net_weights(best_net)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "# Run on the test set\n", "When you are done experimenting, you should evaluate your final trained network on the test set; you should get above 48%.\n", "\n", "**We will give you extra bonus point for every 1% of accuracy above 52%.**" ] }, { "cell_type": "code", "execution_count": 17, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Test accuracy: 0.525\n" ] } ], "source": [ "test_acc = (best_net.predict(X_test) == y_test).mean()\n", "print('Test accuracy: ', test_acc)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "**Inline Question**\n", "\n", "Now that you have trained a Neural Network classifier, you may find that your testing accuracy is much lower than the training accuracy. In what ways can we decrease this gap? Select all that apply.\n", "\n", "1. Train on a larger dataset.\n", "2. Add more hidden units.\n", "3. Increase the regularization strength.\n", "4. None of the above.\n", "\n", "$\\color{blue}{\\textit Your Answer:}$ *2*\n", "\n", "$\\color{blue}{\\textit Your Explanation:}$ *With validation curves, we see that validation accuracy goes on increasing, thus the algorithm is underfitted.*\n", "\n", "- 1 is incorrect - *Training on a larger dataset with **the same model** wouldn't help - the model will still be underfitting. However, with appropriate changes to model complexity, adding more labeled data is almost always a nice thing to do*\n", "- 2 is correct - increasing model complexity is going to help\n", "- 3 is incorrect - decreasing model complexity would only further cause underfitting" ] } ], "metadata": { "kernelspec": { "display_name": "Python 3", "language": "python", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.7.1" } }, "nbformat": 4, "nbformat_minor": 1 }