From ea7586121c5f5f22d345732c28f8839fcc0404c4 Mon Sep 17 00:00:00 2001 From: rohitkg2003 <87852134+rohitkg2003@users.noreply.github.com> Date: Sun, 5 Jun 2022 16:01:06 +0530 Subject: [PATCH 1/5] Add files via upload --- Assignment 1/A1_200816.ipynb | 290 +++++++++++++++++++++++++++++++++++ 1 file changed, 290 insertions(+) create mode 100644 Assignment 1/A1_200816.ipynb diff --git a/Assignment 1/A1_200816.ipynb b/Assignment 1/A1_200816.ipynb new file mode 100644 index 0000000..826720b --- /dev/null +++ b/Assignment 1/A1_200816.ipynb @@ -0,0 +1,290 @@ +{ + "nbformat": 4, + "nbformat_minor": 0, + "metadata": { + "colab": { + "name": "CV with TF: Assignment 1.ipynb", + "provenance": [], + "collapsed_sections": [] + }, + "kernelspec": { + "name": "python3", + "display_name": "Python 3" + }, + "language_info": { + "name": "python" + } + }, + "cells": [ + { + "cell_type": "markdown", + "source": [ + "### **Aim** \n", + "The motive of this assignment is to make predictions using **Linear Regression**. To make sure you truly understand how the underlying algorithm works, you are to implement it from scratch." + ], + "metadata": { + "id": "RB2d1J1f1CF7" + } + }, + { + "cell_type": "markdown", + "source": [ + "### Generating the dataset \n", + "Run the cell below to create the dataset. It further splits the available data into training and testing. Please do not edit this cell.\n" + ], + "metadata": { + "id": "a_S80lf6H4Xv" + } + }, + { + "cell_type": "code", + "source": [ + "from sklearn import datasets\n", + "from sklearn.model_selection import train_test_split\n", + "\n", + "# Generate the data\n", + "X, y = datasets.make_regression(n_samples=100, n_features=5, noise=20, random_state=4)\n", + "\n", + "# Split the data\n", + "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=1234)" + ], + "metadata": { + "id": "yX0zqXcHIQHP" + }, + "execution_count": 2, + "outputs": [] + }, + { + "cell_type": "markdown", + "source": [ + "### Visualizing the data \n", + "Use `matplotlib` to visualize the given data." + ], + "metadata": { + "id": "Zj4rrRXGJBXy" + } + }, + { + "cell_type": "code", + "source": [ + "import matplotlib.pyplot as plt\n", + "\n", + "# Your code here\n", + "plt.scatter(X[:,0],y)\n", + "plt.scatter(X[:,1],y)\n", + "plt.scatter(X[:,2],y)\n", + "plt.scatter(X[:,3],y)\n", + "plt.scatter(X[:,4],y)" + ], + "metadata": { + "id": "zxfi8dkBJOUi", + "outputId": "40ffcaa7-aed8-4ee5-95d0-efacfaaeee21", + "colab": { + "base_uri": "https://localhost:8080/", + "height": 282 + } + }, + "execution_count": 3, + "outputs": [ + { + "output_type": "execute_result", + "data": { + "text/plain": [ + "" + ] + }, + "metadata": {}, + "execution_count": 3 + }, + { + "output_type": "display_data", + "data": { + "text/plain": [ + "
" + ], + "image/png": "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\n" + }, + "metadata": { + "needs_background": "light" + } + } + ] + }, + { + "cell_type": "markdown", + "source": [ + "You should be able to see the linear relations between `y` and the features in vector `X`." + ], + "metadata": { + "id": "r7vndSBAJceF" + } + }, + { + "cell_type": "markdown", + "source": [ + "### Gradient Descent Review \n", + "1. #### Cost function\n", + "Define the `cost function` to measure the difference between predictions and target outputs. Here, we are working with first degree polynomial, so derivatives are easy to calculate. ( Linear function `y = wx +b` ) \n", + "\n", + "$$Error = \\frac{1}{N}\\sum_{i=1}^N (y_i - \\overline{y}_i)^2 = \\frac{1}{N}\\sum_{i=1}^N (y_i - (x_iw+b))^2 $$ \n", + "\n", + " where `N` is the number of samples \n", + " \n", + "\n", + "\n", + "2. #### Compute the derivative\n", + "$$\\frac{\\delta Error}{\\delta w} = \\frac{2}{N}\\sum_{i=1}^N -x_i(y_i -(m x_i +b )) $$\n", + "$$\\frac{\\delta Error}{\\delta b} = \\frac{2}{N}\\sum_{i=1}^N -(y_i -(m x_i +b )) $$\n", + "3.

Update current parameters

\n", + "$$ w:= w- learning\\_rate \\cdot \\frac{\\delta Error}{\\delta w} $$ \n", + "$$ b:= b- learning\\_rate \\cdot \\frac{\\delta Error}{\\delta b} $$ \n", + "4.

Repeat until it fits good enough

\n" + ], + "metadata": { + "id": "b4I9Z3epNvBM" + } + }, + { + "cell_type": "markdown", + "source": [ + "### Model definition\n", + "\n", + "Complete the functions in the class below. Hints provided at appropriate places." + ], + "metadata": { + "id": "kBtUcOVnJu-I" + } + }, + { + "cell_type": "code", + "source": [ + "import numpy as np\n", + "\n", + "class LinearRegression:\n", + "\n", + " # The __init__ is called when we make any object of our class. Here, you are to specify the default values for \n", + " # Learning Rate, Number of Iterations, Weights and Biases. It doesn't return anything.\n", + " # Hint: Google what a `self pointer` is and figure out how it can be used here.\n", + " def __init__(self, learning_rate=0.001, n_iters=1000, w=np.full(X.shape[1],0),b=0):\n", + " # Your code here\n", + " self.learning_rate=learning_rate\n", + " self.n_iters=n_iters\n", + " self.w=w\n", + " self.b=b\n", + " # pass # Uncomment this when you're done with this function\n", + "\n", + "\n", + " # The following function would be the heart of the model. This is where the training would happen. \n", + " # You're supposed to iterate and keep on updating the weights and biases according to the steps of Gradient Descent.\n", + " def fit(self, X, y):\n", + " # Gradient Descent code goes here\n", + " entries = X.shape[0]\n", + " feature_count = X.shape[1]\n", + "\n", + " for iteration in range(self.n_iters) :\n", + " prediction = np.matmul(X,self.w)+self.b\n", + " w_derivative = np.full(feature_count,0)\n", + " for feature in range(feature_count) :\n", + " w_derivative[feature] = np.sum(np.dot(X[:,feature],y-prediction)) * -2 / entries\n", + " b_derivative = np.sum(y-prediction) * -2 / entries\n", + " self.w = self.w - self.learning_rate * w_derivative\n", + " self.b = self.b - self.learning_rate * b_derivative\n", + "\n", + " # pass # Uncomment this when you're done with this function\n", + " \n", + " \n", + " # This function will be called after our model has been trained and we are predicting on unseen data\n", + " # What is our prediction? Just return that\n", + " def predict(self, X):\n", + " # Code goes here\n", + " return np.matmul(X,self.w)+self.b\n", + " #pass # Uncomment this when you're done with this function" + ], + "metadata": { + "id": "dGnFNPJx3I28" + }, + "execution_count": 15, + "outputs": [] + }, + { + "cell_type": "markdown", + "source": [ + "### Initializing, Training & Predictions" + ], + "metadata": { + "id": "EvyInkTKPn7W" + } + }, + { + "cell_type": "code", + "source": [ + "# Now, we make an object of our custom class.\n", + "regressor = LinearRegression() # You may pass the custom parameters or let the default values take it ahead\n", + "\n", + "# Call the fit method on the object to train (pass appropriate part of dataset)\n", + "regressor.fit(X_train,y_train)\n", + "\n", + "# Now, let's see our what our model predicts\n", + "predictions = regressor.predict(X_test) # pass appropriate part of dataset" + ], + "metadata": { + "id": "nvItUpAkHTiv" + }, + "execution_count": 16, + "outputs": [] + }, + { + "cell_type": "markdown", + "source": [ + "### Evaluate the model \n", + "\n", + "Return [Mean Squared Error](https://en.wikipedia.org/wiki/Mean_squared_error) & [R2 Score](https://www.ncl.ac.uk/webtemplate/ask-assets/external/maths-resources/statistics/regression-and-correlation/coefficient-of-determination-r-squared.html#:~:text=%C2%AFy) from the functions below." + ], + "metadata": { + "id": "tzK6cq8eRD4Q" + } + }, + { + "cell_type": "code", + "source": [ + "def mean_squared_error(y_true, y_pred):\n", + " # return the mean squared error\n", + " return np.sum(np.dot(y_true-y_pred,y_true-y_pred))/y_true.shape[0]\n", + " # pass # Uncomment this when you're done with this function\n", + "\n", + "\n", + "def r2_score(y_true, y_pred):\n", + " # return the r2 score\n", + " sum_square_regression = np.sum(np.dot(y_true-y_pred,y_true-y_pred))\n", + " total_sum_squares = np.sum(np.dot(y_true-np.mean(y_true),y_true-np.mean(y_true)))\n", + " return 1 - sum_square_regression/total_sum_squares\n", + " # pass # Uncomment this when you're done with this function\n", + " \n", + "\n", + "mse = mean_squared_error(y_test,predictions) # Pass appropriate parts of dataset\n", + "print(\"MSE:\", mse)\n", + "\n", + "accu = r2_score(y_test,predictions) # Pass appropriate parts of dataset\n", + "print(\"Accuracy:\", accu)" + ], + "metadata": { + "id": "WqkrvDzcRF5m", + "outputId": "d9736135-b2ed-4198-94c5-0edce7b66bee", + "colab": { + "base_uri": "https://localhost:8080/" + } + }, + "execution_count": 17, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "MSE: 673.3063809304753\n", + "Accuracy: 0.936346427498015\n" + ] + } + ] + } + ] +} \ No newline at end of file From aa2ed23211f7fdc078db4ad63b7ef6fc3403ede1 Mon Sep 17 00:00:00 2001 From: rohitkg2003 <87852134+rohitkg2003@users.noreply.github.com> Date: Fri, 17 Jun 2022 17:18:54 +0530 Subject: [PATCH 2/5] 200816_A2 --- CVusingTF_Assgn2.ipynb | 576 +++++++++++++++++++++++++++++++++++++++++ 1 file changed, 576 insertions(+) create mode 100644 CVusingTF_Assgn2.ipynb diff --git a/CVusingTF_Assgn2.ipynb b/CVusingTF_Assgn2.ipynb new file mode 100644 index 0000000..944408f --- /dev/null +++ b/CVusingTF_Assgn2.ipynb @@ -0,0 +1,576 @@ +{ + "nbformat": 4, + "nbformat_minor": 0, + "metadata": { + "colab": { + "name": "CVusingTF_Assgn2.ipynb", + "provenance": [], + "collapsed_sections": [], + "include_colab_link": true + }, + "kernelspec": { + "name": "python3", + "display_name": "Python 3" + }, + "language_info": { + "name": "python" + } + }, + "cells": [ + { + "cell_type": "markdown", + "metadata": { + "id": "view-in-github", + "colab_type": "text" + }, + "source": [ + "\"Open" + ] + }, + { + "cell_type": "markdown", + "source": [ + "# Assigment 2: Deep Learning" + ], + "metadata": { + "id": "UxcaEbrCy1g_" + } + }, + { + "cell_type": "markdown", + "source": [ + "## Generate Dataset\n", + "\n", + "This is the same code from Assignment 1" + ], + "metadata": { + "id": "h2JON-_Oy79w" + } + }, + { + "cell_type": "code", + "execution_count": 1, + "metadata": { + "id": "hgpG3WDuypfa" + }, + "outputs": [], + "source": [ + "from sklearn import datasets\n", + "from sklearn.model_selection import train_test_split\n", + "\n", + "# Generate the data\n", + "X, y = datasets.make_regression(n_samples=10000, n_features=5, noise=5, random_state=4)\n", + "\n", + "# Split the data\n", + "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=1234)\n" + ] + }, + { + "cell_type": "markdown", + "source": [ + "## Visualize Dataset\n", + "This is the same code from Assignment 1" + ], + "metadata": { + "id": "r6it-Rm7zD1Y" + } + }, + { + "cell_type": "code", + "source": [ + "import matplotlib.pyplot as plt\n", + "import numpy as np\n", + "for i in range (5):\n", + " plt.scatter(X_train[:,i],y_train)\n", + "\n", + "\n", + "# Your code here" + ], + "metadata": { + "id": "UautPVj1yzaQ", + "outputId": "75bcc3b3-0559-45e7-ad6f-f12a75b2f08d", + "colab": { + "base_uri": "https://localhost:8080/", + "height": 265 + } + }, + "execution_count": 2, + "outputs": [ + { + "output_type": "display_data", + "data": { + "text/plain": [ + "
" + ], + "image/png": "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\n" + }, + "metadata": { + "needs_background": "light" + } + } + ] + }, + { + "cell_type": "markdown", + "source": [ + "## Model Definition\n", + "\n", + "Using TensorFlow, build a model with the following definition:\n", + "> Input of shape 5 \\\\\n", + "> Dense of shape 5 \\\\\n", + "> Dense of shape 5 \\\\\n", + "> Dense of shape 1 \\\\\n", + "\n", + "Use Mean Square Error Loss and Stochaistic Gradient Descent (SGD) Optimizer\n", + "\n", + "Use Gradient Decay with appropriate parameters" + ], + "metadata": { + "id": "XMXb9lTyzGHE" + } + }, + { + "cell_type": "code", + "source": [ + "import tensorflow as tf\n", + "from tensorflow import keras\n", + "model = keras.Sequential([keras.layers.Dense(5,input_dim=5,activation='relu'),keras.layers.Dense(5,activation='relu'),keras.layers.Dense(1)])\n", + "model.compile(loss='mean_squared_error',optimizer=tf.keras.optimizers.SGD(0.001))\n", + "history = model.fit(X_train,y_train,epochs=50,validation_split=0.2,verbose=2)\n", + "predictions = model.predict(X_test)\n", + "\n", + "\n", + "# Your code here" + ], + "metadata": { + "id": "r32N1xK2ziOs", + "outputId": "e74b01fe-9f46-4562-fdaf-5b8ad24935c1", + "colab": { + "base_uri": "https://localhost:8080/" + } + }, + "execution_count": 6, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "Epoch 1/50\n", + "200/200 - 1s - loss: 1400.1647 - val_loss: 2141.0627 - 865ms/epoch - 4ms/step\n", + "Epoch 2/50\n", + "200/200 - 0s - loss: 340.9002 - val_loss: 44.8760 - 275ms/epoch - 1ms/step\n", + "Epoch 3/50\n", + "200/200 - 0s - loss: 492.3806 - val_loss: 192.2196 - 289ms/epoch - 1ms/step\n", + "Epoch 4/50\n", + "200/200 - 0s - loss: 147.8546 - val_loss: 525.9345 - 369ms/epoch - 2ms/step\n", + "Epoch 5/50\n", + "200/200 - 0s - loss: 202.5587 - val_loss: 45.8932 - 259ms/epoch - 1ms/step\n", + "Epoch 6/50\n", + "200/200 - 0s - loss: 227.0734 - val_loss: 41.9783 - 270ms/epoch - 1ms/step\n", + "Epoch 7/50\n", + "200/200 - 0s - loss: 159.3960 - val_loss: 59.6942 - 284ms/epoch - 1ms/step\n", + "Epoch 8/50\n", + "200/200 - 0s - loss: 239.3188 - val_loss: 29.9748 - 281ms/epoch - 1ms/step\n", + "Epoch 9/50\n", + "200/200 - 0s - loss: 152.8331 - val_loss: 221.7097 - 298ms/epoch - 1ms/step\n", + "Epoch 10/50\n", + "200/200 - 0s - loss: 338.3758 - val_loss: 64.0810 - 284ms/epoch - 1ms/step\n", + "Epoch 11/50\n", + "200/200 - 0s - loss: 209.4844 - val_loss: 59.8163 - 267ms/epoch - 1ms/step\n", + "Epoch 12/50\n", + "200/200 - 0s - loss: 251.1109 - val_loss: 435.7401 - 262ms/epoch - 1ms/step\n", + "Epoch 13/50\n", + "200/200 - 0s - loss: 622.8074 - val_loss: 39.8785 - 284ms/epoch - 1ms/step\n", + "Epoch 14/50\n", + "200/200 - 0s - loss: 166.6548 - val_loss: 352.9469 - 258ms/epoch - 1ms/step\n", + "Epoch 15/50\n", + "200/200 - 0s - loss: 188.5881 - val_loss: 36.6427 - 275ms/epoch - 1ms/step\n", + "Epoch 16/50\n", + "200/200 - 0s - loss: 178.6596 - val_loss: 62.4603 - 271ms/epoch - 1ms/step\n", + "Epoch 17/50\n", + "200/200 - 0s - loss: 140.6317 - val_loss: 36.7756 - 258ms/epoch - 1ms/step\n", + "Epoch 18/50\n", + "200/200 - 0s - loss: 262.6449 - val_loss: 115.1941 - 284ms/epoch - 1ms/step\n", + "Epoch 19/50\n", + "200/200 - 0s - loss: 174.5533 - val_loss: 50.6086 - 265ms/epoch - 1ms/step\n", + "Epoch 20/50\n", + "200/200 - 0s - loss: 202.2552 - val_loss: 1926.5394 - 279ms/epoch - 1ms/step\n", + "Epoch 21/50\n", + "200/200 - 0s - loss: 229.1364 - val_loss: 124.1915 - 263ms/epoch - 1ms/step\n", + "Epoch 22/50\n", + "200/200 - 0s - loss: 461.1045 - val_loss: 88.1916 - 279ms/epoch - 1ms/step\n", + "Epoch 23/50\n", + "200/200 - 0s - loss: 295.3871 - val_loss: 48.4503 - 262ms/epoch - 1ms/step\n", + "Epoch 24/50\n", + "200/200 - 0s - loss: 95.2892 - val_loss: 51.6104 - 257ms/epoch - 1ms/step\n", + "Epoch 25/50\n", + "200/200 - 0s - loss: 97.4321 - val_loss: 83.4106 - 260ms/epoch - 1ms/step\n", + "Epoch 26/50\n", + "200/200 - 0s - loss: 156.3376 - val_loss: 43.0365 - 290ms/epoch - 1ms/step\n", + "Epoch 27/50\n", + "200/200 - 0s - loss: 382.1672 - val_loss: 33.2760 - 275ms/epoch - 1ms/step\n", + "Epoch 28/50\n", + "200/200 - 0s - loss: 158.5331 - val_loss: 229.5324 - 275ms/epoch - 1ms/step\n", + "Epoch 29/50\n", + "200/200 - 0s - loss: 89.6189 - val_loss: 911.1938 - 266ms/epoch - 1ms/step\n", + "Epoch 30/50\n", + "200/200 - 0s - loss: 149.3119 - val_loss: 808.9080 - 280ms/epoch - 1ms/step\n", + "Epoch 31/50\n", + "200/200 - 0s - loss: 301.7253 - val_loss: 41.8418 - 258ms/epoch - 1ms/step\n", + "Epoch 32/50\n", + "200/200 - 0s - loss: 102.5081 - val_loss: 37.0123 - 273ms/epoch - 1ms/step\n", + "Epoch 33/50\n", + "200/200 - 0s - loss: 130.9274 - val_loss: 163.9801 - 259ms/epoch - 1ms/step\n", + "Epoch 34/50\n", + "200/200 - 0s - loss: 153.3079 - val_loss: 52.8656 - 280ms/epoch - 1ms/step\n", + "Epoch 35/50\n", + "200/200 - 0s - loss: 151.9014 - val_loss: 43.4715 - 284ms/epoch - 1ms/step\n", + "Epoch 36/50\n", + "200/200 - 0s - loss: 168.6933 - val_loss: 32.9337 - 264ms/epoch - 1ms/step\n", + "Epoch 37/50\n", + "200/200 - 0s - loss: 91.0383 - val_loss: 44.8102 - 282ms/epoch - 1ms/step\n", + "Epoch 38/50\n", + "200/200 - 0s - loss: 85.5136 - val_loss: 283.6330 - 266ms/epoch - 1ms/step\n", + "Epoch 39/50\n", + "200/200 - 0s - loss: 147.2607 - val_loss: 513.7488 - 260ms/epoch - 1ms/step\n", + "Epoch 40/50\n", + "200/200 - 0s - loss: 169.6636 - val_loss: 222.6365 - 278ms/epoch - 1ms/step\n", + "Epoch 41/50\n", + "200/200 - 0s - loss: 156.9541 - val_loss: 31.6757 - 272ms/epoch - 1ms/step\n", + "Epoch 42/50\n", + "200/200 - 0s - loss: 231.9851 - val_loss: 77.3350 - 277ms/epoch - 1ms/step\n", + "Epoch 43/50\n", + "200/200 - 0s - loss: 257.5688 - val_loss: 47.2681 - 281ms/epoch - 1ms/step\n", + "Epoch 44/50\n", + "200/200 - 0s - loss: 326.8341 - val_loss: 31.5751 - 264ms/epoch - 1ms/step\n", + "Epoch 45/50\n", + "200/200 - 0s - loss: 94.9101 - val_loss: 70.3932 - 275ms/epoch - 1ms/step\n", + "Epoch 46/50\n", + "200/200 - 0s - loss: 110.4162 - val_loss: 34.9609 - 261ms/epoch - 1ms/step\n", + "Epoch 47/50\n", + "200/200 - 0s - loss: 137.7447 - val_loss: 78.6928 - 275ms/epoch - 1ms/step\n", + "Epoch 48/50\n", + "200/200 - 0s - loss: 75.7320 - val_loss: 1105.6212 - 281ms/epoch - 1ms/step\n", + "Epoch 49/50\n", + "200/200 - 0s - loss: 113.9831 - val_loss: 86.3590 - 273ms/epoch - 1ms/step\n", + "Epoch 50/50\n", + "200/200 - 0s - loss: 121.9195 - val_loss: 33.9616 - 269ms/epoch - 1ms/step\n" + ] + } + ] + }, + { + "cell_type": "markdown", + "source": [ + "## Plot Loss\n", + "\n", + "Using matplotlib visualise how the loss (both validation and training) is changing, use this information to retrain the model with appropriate parameters.
We ideally want the loss to be constant over the last few iterations." + ], + "metadata": { + "id": "jmeP6vt3z0oA" + } + }, + { + "cell_type": "code", + "source": [ + "# Your code here\n", + "plt.plot(history.history['loss'],label='loss')\n", + "plt.plot(history.history['val_loss'],label='val_loss')" + ], + "metadata": { + "id": "RQTNqPHm0mOi", + "outputId": "8e605b93-8215-487c-8882-a755eafc6241", + "colab": { + "base_uri": "https://localhost:8080/", + "height": 282 + } + }, + "execution_count": 7, + "outputs": [ + { + "output_type": "execute_result", + "data": { + "text/plain": [ + "[]" + ] + }, + "metadata": {}, + "execution_count": 7 + }, + { + "output_type": "display_data", + "data": { + "text/plain": [ + "
" + ], + "image/png": "iVBORw0KGgoAAAANSUhEUgAAAX0AAAD4CAYAAAAAczaOAAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADh0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uMy4yLjIsIGh0dHA6Ly9tYXRwbG90bGliLm9yZy+WH4yJAAAgAElEQVR4nO2dd3xb1d3/30eWbHnGdmwnTuzEzp4kIZsZCCMJtEBZZTUUCqVAx1M6aPvrQx9antL2KW0p0Ja9WkZZYUMICTR7kJC9t+MVO96WrXF+f5x7bdmWbMlL1vV5v15+XenoSjrXkj73ez/ne75HSCnRaDQaTf/AFukOaDQajab30KKv0Wg0/Qgt+hqNRtOP0KKv0Wg0/Qgt+hqNRtOPsEe6A+2RkZEh8/LyIt0NjUajiSo2bdp0UkqZGeixPi36eXl5bNy4MdLd0Gg0mqhCCHEk2GPa3tFoNJp+hBZ9jUaj6Udo0ddoNJp+hBZ9jUaj6Udo0ddoNJp+hBZ9jUaj6Udo0ddoNJp+hDVFv6Ealv8vHNc5/hqNRuOPNUXf0wif/Q4KNkW6JxqNRtOnsKbo2+PU1uOKbD80Go2mj2FR0Xeqrachsv3QaDSaPoY1RT/GDja7jvQ1Go2mFdYUfVDRvo70NRqNpgUWFv04HelrNBpNKyws+k5wa9HXaDQafyws+jrS12g0mtZYWPSdWvQ1Go2mFRYW/Tg9kKvRaDSt6FD0hRC5QojlQoidQogdQojvG+3pQoilQoh9xjbNaBdCiIeFEPuFEFuFEKf7vdZiY/99QojFPXdY6Ehfo9FoAhBKpO8B7pFSTgDmAHcJISYA9wLLpJSjgWXGfYCFwGjj73bgb6BOEsB9wGxgFnCfeaLoEXSkr9FoNG3oUPSllIVSyi+M29XALmAocBnwnLHbc8Dlxu3LgOelYi2QKoTIBi4Glkopy6WUp4ClwIJuPRp/7PE60tdoNJpWhOXpCyHygGnAOmCQlLLQeKgIGGTcHgoc83vacaMtWHvr97hdCLFRCLGxtLQ0nO61REf6Go1G04aQRV8IkQS8DvxASlnl/5iUUgKyOzokpXxcSjlDSjkjMzOz8y+kPX2NRqNpQ0iiL4RwoAT/n1LKN4zmYsO2wdiWGO0FQK7f03OMtmDtPYOO9DUajaYNoWTvCOApYJeU8iG/h94GzAycxcASv/ZvGFk8c4BKwwb6CLhICJFmDOBeZLT1DHYneOp77OU1Go0mGrGHsM+ZwE3ANiHEFqPt58CDwKtCiFuBI8A1xmPvA4uA/UAd8E0AKWW5EOLXwAZjv/ullOXdchSB0JG+RqPRtKFD0ZdSrgREkIfnB9hfAncFea2ngafD6WCnMT19KUEE675Go9H0L6w9IxfA2xjZfmi6l0OfqzWQNRpNp7Cw6JurZ+kMHsvgqoTnL4MvX450TzSaqMW6ou/QSyZajoYakD5wVUS6JxpN1GJd0deRvvUwP0u9ToJG02n6gejrSN8yuOtbbjUaTdhYWPSNgVwd6VsH87PU8y80mk5jYdHXkb7l0JG+RtNlLCz6RqSvBcI6NHn6+jPVaDqLhUVfR/qWQ0f6Gk2XsbDoa0/fcmhPX6PpMhYWfZ2yaTmaIn39mWo0ncXCom9G+tresQza09douoyFRT9ebXWkbx1Msdf2jkbTaSws+jrStxw60tdouoyFRV97+pZDZ+9oNF3GwqKvI33LoSN9jabLWFf0hYCYOB3pWwl3ndp66tXiOBqNJmysK/rQvHqWxhr4p2rqKziNplNYXPR1pG8p/LN2zKhfo9GEhcVF36kjQivRItLXJ3ONpjNYXPR1pG8p/D9LPZir0XQKi4u+jvQthb/Qa9HXaDqFtUXfoQdyLYXHBTZH822NRhM21hZ9HelbC3c9JKQbt/VArkbTGSwu+trTtxQeF8Snqdu60qZG0yksLvo60rcU7nqI15G+RtMVLC76OtK3FB5Xs72jP1eNplNYXPSd2gawClIakX6quq8jfY2mU1hc9HWkbxm8jYD0s3f056rRdAaLi7729C2DmZdvDuTqhVQ0mk5hcdHXkb5lMD9H5wBA6MlZGk0nsbjoO8HnBp830j3RdBVT5B3x6k+LvkbTKawv+qAtHitgRvp2pxZ9jaYL9BPR1xZP1OMf6dvj9Weq0XQSi4u+XjLRMpii3xTp65RNjaYzWFz0daRvGTz+nr6ef6HRdBaLi76O9C2D29/TT9ApmxpNJ7G46JuRvhaIqMe8WnPEGzOt9Weq0XSGDkVfCPG0EKJECLHdr+1XQogCIcQW42+R32M/E0LsF0LsEUJc7Ne+wGjbL4S4t/sPJQA60rcObTx9LfoaTWcIJdJ/FlgQoP1PUsqpxt/7AEKICcDXgYnGcx4TQsQIIWKAR4GFwATgOmPfnkV7+tbBP9LXoq/RdBp7RztIKT8XQuSF+HqXAS9LKRuAQ0KI/cAs47H9UsqDAEKIl419d4bd43DQefrWwT/S1ymbGk2n6Yqnf7cQYqth/xgFURgKHPPb57jRFqy9DUKI24UQG4UQG0tLS7vQPfzsHS0QUY+O9DWabqGzov83YCQwFSgE/thdHZJSPi6lnCGlnJGZmdm1F3PEq62O9KMfdz2IGIhxaNHXaLpAh/ZOIKSUxeZtIcQTwLvG3QIg12/XHKONdtp7Dh3pWwePq/kk7ohXGVlSghCR7ZdGE2V0KtIXQmT73b0CMDN73ga+LoSIE0LkA6OB9cAGYLQQIl8IEYsa7H27890OEe3pWwd3fbPo250gfUaNfY1GEw4dRvpCiJeAeUCGEOI4cB8wTwgxFZDAYeDbAFLKHUKIV1EDtB7gLiml13idu4GPgBjgaSnljm4/mtboSN86eFxqABeaxd9d3/wZazSakAgle+e6AM1PtbP/A8ADAdrfB94Pq3ddxYz09ZT96Mddr8ovQEvRN5dP1Gg0IWHtGbk2OwibjvStgMfVfBI3I34901qjCRtri74QxpKJWvSjHn9PvynS15+rRhMulhR9r09yrLyOynq3sWSiHsiNevwjfX97R6PRhIUlRb+stoGzf7+ct788oSN9q9A6ewe0vaPRdAJLin6K0wFAlY70rUOLSD9BbXWkr9GEjSVF3+mIIdZuo8rl1nVarILbf3KWmZWlRV+jCRdLij6oaL+q3qMjfavgrtORvkbTDVhX9OPtRqSvPX1L4F+GQXv6Gk2nsa7oOx3a07cS7voA2Tv6ZK7RhIt1RT/eFH2njgijHa8bpDdAnn5d5Pqk0UQp1hV9p50ql/b0LYH/Air+W23baTRhY13RbxHpa3GIavwXUAFjpnW8jvQ1mk5gXdF3OqhyuZE60o9+Wkf6oNI2taev0YSNdUU/3o7bK/Ha4nSkH+20jvRBpW3qlE2NJmysK/rGrNwGHDrSj3YCRfp6gF6j6RTWFf14JfouYlWkKGWEe6TpNE2Rvr+9E6/tHY2mE1hX9J1qfRiXtKul9XyeCPdI02nMSN+ciQuG6OuBXI0mXKwr+kakX+9TW+3rRzHmZ9fG3tGfqUYTLtYVfcPTr/MZK0JqXz96aYr0Ww/k6khfowkX64p+vBL7Wm+MatCZHtFLoEhfp2xqNJ3CuqJvRPo1Xh3pRz3BIn2dvaPRhI1lRd/piCHObqPaY0T62v+NXoJ5+vrqTaMJG8uKPhilGJpEX0f6UUvASF+nbGo0ncHaou+0U+XWkX7U43EBAmJim9t0yqZG0ymsLfrxDiq06Ec/5qLoQjS32eNVuWWvO3L90miiEGuLvtPBqUbjELW9E734L6BiomvqazSdwtqiH+8v+jrSj1r8l0o0aVocXX+uGk04WFv0nXbKXTrSj3oCRvpGSQadtqnRhIW1RT/eQZmp9TrSj14CRfrmSUCnbWo0YWFt0Xc6qPHq2jtRT7uevhZ9jSYcrC368XZVTx+06EczAT19LfqaKEFKWP8EuKoi3RPA6qLvdNDYJPra049aAkX6dkP0taev6euc3Avv/wh2vRPpngBWF/14Bz5s+GwOHelHMx5XywVUQEf6muih/pTauioi2w8Da4u+sZCKzxarI/1oxl3fHNmbNIm+Pplr+jj1FS23Ecbaom8spKIXR49yAkX6pt2j7R1NX8dVaWy16Pc4Znllty1OR/rRjNvVcqlEaL6v7R1NX8cUe1P8I4ylRT/ZsHfcIlZH+tGMJ1DKps7T10QJpthre6fnMWvqN+LQkX604vOCtzHA5Cw9kKuJEkyxjxZ7RwjxtBCiRAix3a8tXQixVAixz9imGe1CCPGwEGK/EGKrEOJ0v+csNvbfJ4RY3DOH05aUeCNtU0f60UmgBVQAbDaIidOevqbv0+TpR4+98yywoFXbvcAyKeVoYJlxH2AhMNr4ux34G6iTBHAfMBuYBdxnnih6mhSnHRcOneURrZifW+tI32zTn6umr+OKsuwdKeXnQHmr5suA54zbzwGX+7U/LxVrgVQhRDZwMbBUSlkupTwFLKXtiaRHSIl3UC91pB+1mJF860gf9EIqmujAItk7g6SUhcbtImCQcXsocMxvv+NGW7D2NgghbhdCbBRCbCwtLe1k95pJcTqo99m1px+ttBfp2536ZK7p+5gRvsfVJ65MuzyQK6WUgOyGvpiv97iUcoaUckZmZmaXXy8l3kGdz67FIVppN9JP0AO5mr6Pv5ffB3z9zop+sWHbYGxLjPYCINdvvxyjLVh7j5PitFPr1ZF+1BJoUXQTh1OLvqbv46qAxKzm2xGms6L/NmBm4CwGlvi1f8PI4pkDVBo20EfARUKINGMA9yKjrccZEO+gxmNH6kg/OnHrSF8Txfi80FAFacPV/WiI9IUQLwFrgLFCiONCiFuBB4ELhRD7gAuM+wDvAweB/cATwJ0AUspy4NfABuPvfqOtx0mJd1CnB3KjF09Hnr4WfU0fxhT5VEP0+0AGj72jHaSU1wV5aH6AfSVwV5DXeRp4OqzedQMpTgeVenJW9NJupO/sEwNjGk1QTDunKdKPvOhbekYuNC+kIrwNajEDTXTRXqTvSNApm5q+TetIPxrsnWgnxemgQcaqOzrajz7ai/StmLJ5ZA143ZHuhaa7qG8V6fcBe8f6oh/v8FsyUfu/UUeHkb6FPtOT++CZBbDsfyLdE013YUb2CRngSNT2Tm+Q4vRfJ1dH+lFHh56+hUS/4qjarnkUCjZFti+a7sEU+fhU9adFv+dpGelbzAroDwQruAYq0ve5wevp3T71FDXFautIhCXfBU9jZPuj6TpmpO8coP60vdPzJDvtNEgd6Uct7npVTdMW4KtqtdWzqovU9qt/gZIdsOrPke2PpuvUV4CIgdgkcKbqgdzeIM4egy8mTt3RkX70EWipRBOrrZNbUwyxyTDpSph0FXz2eyjZHeleabqCq1JF+EJoe6c3iYk1xEFH+tFHoEXRTZpE3yJpm9VFkGzULlz4O4hLhrfvVrM6NdGJq0KJPRj2jo70ewV7nLGeqo70ow+PK3DmDvjZOxb5XGuKIWmwup2YAQt/D8c3wPrHI9svTedxVSpbBwx7R0f6vYIjzhQHHelHHe764KLftDi6BSN9gMlXweiLYdn9cOpwxLql6QL1FSrCB7VtqIr4lVu/EP1Yp470oxaPK3DmDvgtjm6Rz7WmpDnSB+UDX/qQGgh85/t6Rnk04m/vmNsID+b2C9GPM0XfKuLQn3C3Y++Ykb4VsncaqsFd2zLSBxiQAxf+DxxcAdv+HZGuabqAOZALzTZPhC2efiH6zngd6Uctnvrgkb7ZboUJWtVGjr5/pG8y/ZuQMBAOr+zdPmm6hpSGveM3kAs60u8NnEakr2vqRyHtRvpm9o4FRL/GyNFPymr7mM2mTga1J3u3T5qu4a5XkwdNsTftnQhP0OoXop+QmAiAu8EC4tDfaC/St5LomxOzkgNE+qCyeWq7vma0phfxL8EA2t7pTRLikwBocFkky6M/4a4PPjnLzN+3whWcWYIhaVDgxxMztehHG/4lGPy32t7peZISlTg0atGPPvrL5KzqIlVuIj4t8OOJmdreiTZMG8fZKntH2zs9T0p8LC7p0PZONNJfyjDUFKsoX4jAjydmQGO1Nays/kJTpG+IvSMBbA5t7/QGKfEOXMRq0Y82pDTy9INE+rYY9SOyQspm64lZrUnMVFsd7UcPrT19IZTFo+2dnsesqe9ttEBE2J9oWkAlSKQP1llIxYz0g9Ek+iW90x9N12kd6YM6AWh7p+dJiXfQIB14rSAO/YmmBVSCRPpgnYVUqouCZ+5AcyqnjvSjhyZPP6W5rQ/U3+kfou900EAsstEC4tCfCCnSj49+0Xe7lBAEmphlkpihtjqDJ3pwVao6+jGO5jZt7/QOsXYbbuHQk7OijVAifXt89Hv6pmUTkqevRT9qcPkVWzPR9k7v4bHF6Sqb0UZ/ifTbK8FgEpuoxi+0vRM9+JdgMNH2Tu/htcUitOhHF2YqZruefnz0p2yaJRjai/RBz8qNNvyLrZmY9k4EK6b2G9GXMXHYvFr0owrTtmkv0rc7o9/eMUswtJe9A3pWbrThX1bZJD4VfB5orI1Mn+hvou/Toh9VhBzpR7no1xSDsDX79sHQoh9dBIz0I19/p9+IPg4ndl9jpHuhCYemSN/iol9dpATdFtP+fokZUKNFP2oI6OlHvv5O/xF9ezx2qUW/NZX1bvYUVUe6G4ExI32ri35HE7NMErOg7iT4fD3fJ03X8HpU2YxA2TsQ0QyefiP6NkccsbIRqZeca8HDy/Zx5d9W4/X1wf+LGekHK60M1kjZ7GhilklipvKD+8Di2poOaKhS29aevrZ3eg9bbDyxuKl3R3ZR4r7GtoJKaho8nKjog8IZUqTvtED2TqiRvq6/EzWYoq7tnchhj43HSSNV9Z5Id6XPIKVssnYOl0UumyAooUT6jgTwNoAvSk/mPq8anA0p0tezcqOGphIM2t6JGPbYeOzCR1VdH4xoI0RRlYvKejcAh0/2QdEPJdI3TwjROtu6thSkL8xIX4t+n8eM5FvbO3FGHR5t7/Q8DqcSjpqamgj3pO+wu7B5APfQyT64EIm7TpVObi+rxWEseh+tg7nmilmhevqgRT8acAWJ9G0xEBfZ+jv9RvTj4pTo19Zp0TfZbVg7OWnxHDrZB/8vnnYWRTcxJ25Fq+iHUoLBJGEgILToRwOByiqbxA/Q9k5vEBevFkevre2DEW2E2F1UxdDUeCYPHcDhsj74f3G3syi6SdRH+iGWYACIsUNCuhb9aCCYp2+2aXun54kz7J36uj7oXUeI3YXVjBucTH5GIsfK6/B4+1j+d3tLJZo0efpRKvpmpJ+YFdr+elZudOCqAJtdFcprjTNV2zu9gdOI9OvrwxR9rxvKDvRAjyJLo8fHgdIaxmUnk5eRiMcnOX6qjwlne4uimzTZO1E6kFtTpESgo5ObiV4gPTowSzAEWvM4wuWVuyT6QojDQohtQogtQoiNRlu6EGKpEGKfsU0z2oUQ4mEhxH4hxFYhxOndcQCh4ohTNoCrPkwbY/0T8NjciC980N0cKK3B45OMHZxCfoY6IR7qa2mboUT6TfZOH7SnQiHUiVkmVq202Vgb0cqT3U6gEgwmFrB3zpNSTpVSzjDu3wssk1KOBpYZ9wEWAqONv9uBv3XDe4eOPQ6Ahvowo9lja1UeuMWi/d1Fasbg+MHJ5A00RL+0j4l+KJF+tKdshjoxy8SK9k59BTw0Hr54PtI96T4CFVszsaC9cxnwnHH7OeByv/bnpWItkCqEyO6B9w+MIQ6NDYEjQrfXR4MnwASfE1vU9tShnupZRNhdWE1sjI38jEQykmJJjrP3vQla/SLSLw4z0s9UguGxUB2pg8vVMe1fGumedB+ByiqbxKeq72uEPsOuir4EPhZCbBJC3G60DZJSFhq3iwAzjBkKHPN77nGjrQVCiNuFEBuFEBtLS7sxojEifXcQ0b/n1S+57vG1LRvryqHiiLpdbjHRL6pmVFYS9hgbQgjyMhI51NcmaLld1vb0pVSefliRvgVn5e4zxP7YeutYPK7KduydyNbf6aronyWlPB1l3dwlhDjH/0GpqpuF9SlKKR+XUs6QUs7IzOygvng4GJG+p6GtvXO0rI53tp5gy7EK6hv9ov3CL5tvW070qxiXndx0Py8jsQ9G+vXWjvTrT4G3McxI38jysYro+3xK9O1OZXWZQVa0Ux9gfVyTJtGPjMXTJdGXUhYY2xLgTWAWUGzaNsbWWPWZAiDX7+k5RlvvYET63sa2ov/cmsNICT4JuwyvG4BCw9rJHGcpe+dUbSPFVQ2MH5zS1JY/MIGCU/WBLa5IEUqk34GnX9/opbLO3c0d6ybM2bjhevpgnQyeoq1qYfiZ31L3j66LbH+6AymVoLdn70DEMng6LfpCiEQhRLJ5G7gI2A68DSw2dlsMLDFuvw18w8jimQNU+tlAPY8hDt5WNkC1y80rG44xY3gaADtO+In+iS2QOhyGnG6pSN+ciTt2cHOkn5+ZiE/CsfI+FDGHFOkbJ4Ug9s4v3trGVx5Z2TdLR5vLJIabvQPWifRNa+eM70JsMhyzgOi768DnbifSNyttRpnoo7z6lUKIL4H1wHtSyg+BB4ELhRD7gAuM+wDvAweB/cATwJ1deO/wMURful0taur/e+Nxaho8/OKS8aQmONh5wu+Sq3ALDJkK6flQfSJ6Z322wszcaWHvmBk8fakGTyiRfoxDTYIJYO94vD4+2VnM0fI6VuwpCfDkCFNj9CmUEgwmVqu/s+9jFVQlD4acGdYQ/fZKMPi3R8jesXf2iVLKg8CUAO1lwPwA7RK4q7Pv12UMe8chG6lr9JIYZ8frkzy7+jCnD0tl2rA0Jg5JaY7060/BqcNw+jdgwDDVduowZI2PSPe7zKqH1TqsZ9zN7sJqBibGkpkU1/SwmavfZ6ptSmlE+h2IPhgLqbSN9Dcfq6DKpUppv7T+KPPHh2Gj9AbhlGAwiUuGmDhriH5dORzfAOf+VN0fNgdWPAiuKnCmtP/cvkx7JRjAz9451Tv9aUW/mZFrRvpxuKlyKY932S4VBd5yVj4AE4cMYHdhNW6vr3kQN3sqpI9Qt8sP9nq3u40NT8DGpwHYXVzN2MHJCL/ZgqkJsaQmOPrOBC2vW5UcDmWmqiM+YKS/Yk8JMTbBTXOG8+nukr63UEx1MTgSlZCHihDWmZV74FNAwuiL1P3cWep+wcZI9qrrBCurbBLF9k50EWPHJ+zECXfTQipPrzrEkAFOFkxUl9cTh6TQ6PWxv6SmWfSHTFP2DkSvr99QDRVH4dQhvI317C2qZtzgtpFU3sDEvjNBq2kBlRAi/SCrZ63YU8r0YWncfs4IJPDqxmNtnxtJaoogKcSaO/5YZVbuvo9V5dAh09T9oTMAEf2DucHKKpvY49T3Ohqzd6INX0xcU6S/40Qlaw+Ws/iMPOwx6t8wcYj6kHacqFKDuAOGqaqG8WmqBna0ZvCU7FJb6aPowFbq3d4Wfr7JiL6Uttm0gEoIkb69baRfUuVix4kqzh2bSW56AmePzuSVDcf6VlG5cCdmmSRlqYyXaMbnhf2fwKgLwGbIkDMFBk2Mfl+/I08fIlp/p1+JPnZD9OvdPLPqMPGOGL4+c1jTw/kZicQ7YtheUGkM4hpDFkKoaD9a7Z3iHU03Tx5SVzDjBrcV/byMRAorXS3nKkSKsCL9tp7+ir0qEp43Vg18Xj8rl8JKF5/t7UMRcrgTs0ysYO+c2Ax1Zc3WjknubDi+MXqXvwQ/T78d0Y9g/Z1+J/pOGjlYWsvbW05w1fQcBiQ4mh6OsQnGZydz6HihEvjsqc3PTc+PXnuneAfEJoHNTsOJHdgEjM4KLPoAR8r7QLQfTqTviG+TWfXZnlKykuOYkK1srPnjB5GZHMe/1h3t7p4G5f1thdy3ZHvwHTob6Zv2TjTPXt33sUosGHl+y/bc2dBYDSU7I9Ov7qAjewciWn+nX4m+sDuJE26eWnmIRq+Pm8/Ma7PPpKEDsBWbfr6/6I+AymNqgDHaKNkJWRMgfSSx5XvJy0gkPrbtEoT5fanwmmnXhBrp+4m+x+vjP/tKmTc2s2mw2hFj49oZuSzf03sDuo9/fpDn1hyhIND7NdYqcetspO9thIaqjvftq+xbCjkzlX3qT+4stY1mi8dVqeYcxLSTHKntnd7B5nASh5uiKhfnjc1kZGZSm30mDklhlGe/uuMf6aflg8+jhD+akFJF+oMmQNY4MusPBrR2APIyVEmDPpHB4wnT0/ezd8xUzXljWw6SXjszFwm8sqHnP8Oymga+PK5+1J/uDuC/d2Zilkm0z8qtKYETX8CoC9s+lpanToTH1vd6t7qN9kowmGh7p3cQDicJNhWpm2marZk4ZACTbYeoj89unv0I0ZvBU12ovlxZE2lMH0u2r5iJmbEBd012OshIilO5+odXwQPZUHm8lzts4A7T0/cbyDVTNc8cldFit9z0BM7ppQHdFXtKkRISY2P4dFdx2x06U4LBJNpn5e5fprajA4i+ECraP7q27WPRQnslGEy0vdNL2J0k2DyMGZTEWa0EwWT0oCQm2w5xzDmm5QNmrn4fyOCpafBw7+tbOX4qhNmzxYY3OmgiBY7h2ITk9ITgYpGfkcDhk3WqzK27Do6s7qZeh0k4kX6rlM3lu1Wq5oB4R5tdr5s1jKIqFyv29Kxgfrq7hKzkOK6ZmcuqA2XUNXpa7tAtkX6Uiv6+j9XJbvBpgR/Pna0Kr5n/o2jDFWqkX6UKzvUy/Uz04xiV7uCPV09tMTHJnzhPDfmiiK2+VlcCSYPVBK8+EOm/++UJXt5wjN99uKfjnYuNgcRBE9jlUZWsR4vg0XvewERl7xRsUg3mtrcJJ9K3xzdl+5RUudhZqFI1AzF/fBZZyXH8a33PDei6vT4+31vKeWOzuGD8IBo9PlbvL2u5U1Ok3wXRr4nCtE2vR03KGnVhc6pma3LnqG0vWDwer4+/f3ZAzc3pLtorq2wSnwpIaOj9aL+fib6TVIeXyTntnIWLtgHwWfWQFjV6sNmU39gHRP/Nzao46btbTzTV0QlKyU5IHgLxaWysScctYxhYFzz1ND8zkZPV9ciCL1RDpEQ/rEi/eSDXTNU8b2zgSU+OGBvXzMhlxQ6LGo8AACAASURBVJ6SwAOs3cDGw6eobvBw3rgsZualkxRnZ1lrX7+mGGyOtgOZoZBg2jtR6OkXbFSRcCBrxyT7NFVqoocHc30+yY9f28qDH+zmL8v2dd8Lh+TpR67+Tr8TfTwN7e9jrJS1ui6X4qpW+6aPiHiufkFFPesOlXPrWfkkxdr509K97T+heKcaxAV2FNVRaM9BlO4Ounv+wERGiEJEY426BC/cGpmMpXA9fY8LfD4+21PKoJQ4xgeYfGbS0wO6y/eU4IgRnDU6g1i7jXPGZPDp7uKWQUS1sUxikCvOdrHHKtGoLeVkTQMl1VG0gMy+j0HEwIh5wfexx6lZuj0o+lJKfvHWdt7cXMCglDj+s6+0+yqxhuTpGyeFCGTw9EPR7+AHUriFxoRsyhjAjhOtzsJp+aroWgTzo9/ecgKAxXPz+NbZI/hoRzHbjgeJFrxuOLkHsiYgpWR3UTUVSSOhdFfQ18/LSGSazchemv5NtT6w3+SuXiPcSB/wNNbx+b5Szh2TGdS+g+YB3Vd7aEB32a5i5owYSFKcStk7f9wgiqsaWpbtrikKr9BaaxIzkbWl3PTUem55dkMXe9yL7PtYFVbrSBSHzVYBWA+siCal5Nfv7uKl9Ue5c95I/t8lE6ioc7PlWDcIsNejUnE7ivTN449ABk8/E/24kCJ929ApCAHbC1pZJ+n5yjuO4ADTki0FTB+exrCBCdxyVh6pCQ7+uDSIt192QOVzD5pIcVUDlfVufBlj4dQRaAw8CJw3MJEp4gCNMYkw5VrVGAmLx/yxh+rpA1sPFVMdIFUzENfOzKWoysX6Q+Vd6WUbjpbVcaC0toW9pOYLtErdNCP9zpKYSdXJQnYVVrG9oIqDpd3oSfcUVYXKPm3P2jHJna1q0p/Y3O3d+OPHe3l61SFuPiOPH188lnNGZ2ITdE/5bXPuREeevrZ3egm7s3l6fyAaqqFsP/ahp5M/MLFtpN+UthkZi2dXYRW7i6q5fOoQQKVY3nHuSFbsKWXTkQDi1TSIO7FpRbDEnImAVFcAAYiPjWGG4xCH48aqK5v4dJVT3dt46tWMzZi2GThtMK4G1u09HjBVMxDnjc0i3hHDe9u6dx2fT3erAdrzxzWLfkZSHFNyUlv6+p0twWCSmEHtqUKSnepq4v1uPo4e4YCRqhkoP781OT0zSevR5ft5ZPl+rpuVy31fmYAQggEJDk4fltY9GV1mueRQsndA2zs9TkeRfuFWQMKQqUzwr61vkmaIfoTSNt/aUoDdJrjktCFNbd+YO5yMpFj++HEAb79kp/JPM8awu1CtljV41OnGY0F8fbeL0fIw2xip/Oah06GgZ0R/f0kNj39+AF8gL9VcQCUUz9tYJ/eLA4VBUzVbEx8bw/njsvhoR1G3rqr16Z5SRmQkNpW0MJk/Losvj1VQWt0AnkZVd6Yz6ZoG1fY0nI3lLJ6bx/Thaby3LQrSG/cvU9lKgyZ2vG9SphpD68YMnqdWHuIPH+3h8qlD+M3lk1tYgPPGZrKtoFJ9Pl2ho7LKJtre6SVMTz+YJ2+uiZs9lUlDB1BQUU9FXWPz46nDlIhGIIPH55Ms2XyCc8dkkp7YPLkqIdbOnfNGsfpAGav3t8rmKN4JGaORMbFsPnqKIQOcJA8Zo7JGgvn6RVux42VlfZ66P3S6qtLZUN2txyOl5J5Xt/C/7+/msRX72+4QylKJJsZaCcdLy5k3LnCqZiAWTc7mZE1jt1k8tQ0e1h4o47xxbe2l88ertuV7SporZHYh0t90MoZ0UcNNs4awaHI2uwr7uMXj88LB5arWTqiD17lzVKTfhTG0yno3L6w5zFf+upJfv7uTBRMH839XTyHG1rIPpiX4eVcL8jXV3elA9GOTlJZoe6eHMVbPwtsY+PETWyA5G5IHMXGIKtTVItqPcUBqbrfbO8fK61h3sKzdfdYeKqOoysXl04a2eez62cMYnOLkj0v3tswQKdlBTeoYbnhyHR/vLFZiFOOAjNFQGmQcwPDvV9XnqRPe0OmAbF5foJt4b1shXx6vZERGIg8t3cuaA62OP5SlEk2MSD+eBuaNCb0+/XnjMnE6bN1mjazaf5JGr4/5AUR/QnYKg1OcfLqrRPn50OlIv9rl5j8n1E93kL2WRZPV6/Rpi+fEZmV9jGqzqF5wcmdB3cmwf28+n2T1gZP84OXNzHrgE365ZAdur49ffWUCD183ramUuj8TslPISIprSvntNB2tmmUihNpH2zs9jBERBs3gKdzSVG+nubZ+oAye4JG+zyfZcqwi5PLEJVUurv77Gq57Ym1b4fNjyeYTJMbGcEGAJf+cjhi+O38Um46cavrSNtZWQMVRHt8dz7aCSh64YhK/vmySekLmuOYa+60p2IQrfhAlpHHoZC0MNeygbrR4Gj0+fv/hHsYNTuatu88kLyOR7728ueWldahLJQIulJ0zOJF2UzVbkxBr5/xxWXywvXssnuV7SkiKszMjr23uvRCC88dn8Z99pbgrVQZWZyP9f288ToHbqBtVW0r2gHhOH5baty2e/csA0baqZnvkzlbbMEoyrD9Uzrz/W8H1T6xj2e4Srp6Rwzt3n8UH3z+bm8/MJ9YeWPJsNsG8sZl8vre0axldodo75j7a3ulhzEg/kK/fUAMn9zVV1kxPjGXIAGdbXz99REB750BpDX/4aDdn/e5TLn90FTc9tY7aBk+b/fxxub3c9sImKuvd5KYn8N2XNlNS5XdCKtoOry7GVVvF+9sKWTApO2B1TICrp+eSkxbPQx/vZf2hcn706MsAJOROZtkPz+WG2cOxmZe0WePVNPfGAIXVCjbhGaxWMjpcVqvqvKQO69YMnn+tO8LR8jp+unAcKU4Hj15/OlX1bv7rlS3N4ut2dWjv7C2u5ldv7+Dmf6oB6/NHJrebqhmIhZOyOVnTwIbDXbN4pJQs313K2UZufiDmj8uittFL4a61apA6LS/s9/H6JM+tOczALGNcxyjFYFo8h/rKGsetObBM5d6HMxktc5xavOjompB231NUza3PbcAm4E/XTmH9zy/gN5dPZnLOgJC+F/PGZlJZ724qlNcpQimrbBKh+jv9TPTbifSLtgESspvXep8wZIBaUMWf9Hz1wdaVU1HXyAtrj3D5o6uY/8fP+NuKA4wZnMwPLhjN5mMVfPPZDW1rrhhIKfnp61v58lgFf7p2Kk98Ywa1DR7ufmlzc6Sx9jHY+Rb7P3ma6gYPl08bEvC1AGLtNr4/fzTbCiq55h9ryGlUJ6Y7rv4qWSmtxDNznNq2tnjqyqH8IM782dgEHDpppHV242ButcvNw5/uZ+6Igcwbo/z38dkp3H/ZRFbuP8kjnxr+vqc+oL3jcnt5c/Nxrv77ai760+f8a91RpuYre+PKyQPD7s/547KIs3fd4tlZWKWqtwawdkzOGJlBnF2QsO9tGH5mp2bjfrq7hCNldVww07hqM2blLpqcDfRRi6e+Qi2MEo61A2oW/MjzYM8HKv+9HYoqXdz8zHriHTG8+K3ZXDEtJ2iAFIyzR5mpm12weFyVaszMsBzbRds7vYBpFwSK9P0GcU0mDknh4MnalsJtFF5bumots/93Gb98azsut5dfLBrP2p/N59lvzuIHF4zhz9dOZePhcr713MaAVs9jKw6wZMsJfnzxWBZMGsyYQcn89muTWX+onD98vEdFurveASB1x7NkJsVyxsj2UxGvmDaUhZMG8+1zR/BfU9yqpnfqsLY7Zo1X29Yzcw1ht+fOYEhqvKq2CTDkdKg8CjVdT2l7/PODlNc28rNF41pEX9fMyOVr04by52V71YB0q0j/WHkdv31/F3N/u4z/euVLSqsb1P/85/O59yvqykS0l44bhMQ4O+eN7brFs9xIx5wXpOYPqIyhrw+rIqPhKHLi1zr1Ps+sOkT2ACdnTTE+QyPSH5KqLJ53t/ZB0T/0GUgvjAxT9AEmX6V8/UMrgu5S5XJz8zPr1Yp435xJTloIghuAbkndNEswhHLFGSF7p50q/xakyd4JEOkfXas81pTspqaJQ1KQEnYVVjN9eJp66oDh2IG3l69i5oiv8rNF45iQndLm8vErU4bg8fn44atfcvsLG3niGzNwOlTk8dGOIv7w0R6+OmUId84b2fScy6cNZcPhcv7x2UEWxGxiWkMVjWMvI2fPEu4aW9om46DN4cXY+NuN09WdZ3YrcQ/05UvLh5jYtr5+wSZAQPZU8jN2Na+XO1S9Zt3h9Xzsnsrne0tJiXcwMjOR/Iwk8jMTyU5xNttHQSiucvHEfw5y6WnZnJbT0vMUQvDryyfx5fEKvvfyFtak12F3DmDFnhJeWHOE5XtKsAnBheMHcdPc4cwdMbD5/XzGj9zduVo6i07L5sMdRWw8XM7sEeFfLQAs213ClJwBZCW3b0ld7VyPR9o4mjWfEWG+x+6iKlYfKOOnC8bhSEwDm71Fpc1Fk7P5zXu7OHSylvxWKaMRZf8yiEuBnBnhP3fUheq5215X6+m2otHj444XNrG/pIZnvjmzaSyus8wbm8n/fbyXkmpXh59lQEIpwWCi7Z1eoMneaRXpVxbA7nehVfQ1aaj6Au00BnMr6918+1012HpFXgPPGl+yYH7hFdNy+P2Vp7Fy/0nueHETDR4vO09U8V+vbGFKzgB+f9VpbZ7731+ZwGk5Ayhe/SJeZzpv5d5LhUzkCvd7oR+n/8IpgYixw8DRASL9TZA5Fpwp5Gckcqi0lsp6N0tKMvBh4+lXXucHr2zhs72l/HvjMX65ZAc3PrWOMx/8lAn3fciCP3/Ow8v2BR3E/vMne/H6JD++eGzAxxPj7Dx2w3RqGtwUnizns4PVfPOZDWw9Xsl3zxvFyp+ex99vms6ZozJanmA6GqDvgPldtHjKahrYcqyiXWsHACkZV7aM1b6JfHKkfbsiEM+sPIzTYeO6WbnqZJ6Y2eLqq09aPFKqqpr554Q20a41DieMu1T9PluVZJBS8pPXvmT1gTJ+d+VpnD069HTdYDSnbnaymF0oZZVNTHunl8u69M9Iv3VEuP4fIH0w544WzdkDnKQlOJqmuX/ruY0cO1VHXVIW52fVQYDUr9ZcPSMXj0/ysze2cccLm9hbXEOK09Ei8vcnzh7DY1eNZeDfN/GBvICXtp6C2Au5+vC7UHUCUoL7+k1UnWhaOCUoWePgmF/NFilVBcQxCwFVjqG6wcOM3yzF7ZVMis/h4rQTzL1yLtNy0xACSqobOFhay8GTNRwqrWVnYRUPLd3Ly+uP8tOF4/jqlCFNJ7X9JdW8suEY35ibx/CBwaPQsYOT+c3lk7G97ULEx/PwddNYMHFw0MFRoNk/dYewvkAAEuPszBubyQfbi7jvKxM7vGJpzWd71YIp53ck+oVbsFce5ouku1mzq4TbzxnZ/v5+lNc28taWAq6cnkNqgjFPIzGzRaQ/JDWeacNSeW9rIXedNyrwC3k9cHw9DJvbqWJvXp9k54kq1hw8ydqD5Qwe4OTXl00KfhV6cp9abe7sH4b1PodO1vLe1hN8sL2IqQ1jeaDhXyx750WSpl7BhCEpJDsd/P6jPby15QQ/umgMV07PCftYAjFxSAqZyXGs2FPCVZ15zVDKKpvEp6pSE+46iO29K7N+JvoBIv2Gatj4LEy4rE02hRCCiUMGsGJvCe9vL8QRY+Of35pDwvJRYeUOXzdrGB6vj18u2YHTYePf3z6j7eCqHzklK4BGnquawebKCq44+2bEhiWw6Vk47+cdv2FJ88IpQckcD9tfV1lLcUkqm6eurClF85wxGUzJGcDMvHQWnZbNiC/OQex5H4alNYnFoBQng1KczB3ZbImsO1jG/e/u5Psvb+H5NUf470snMCU3ld99uIeEWDvfPT+IGPlx1fQcfMsEOeNzYUoIJ7kYh8qG6UJxrkWTs/loRzGbjp5iZoCUy2BIKXlvayEZSXFM6sha2PEm2OzETPwqG1eXcaC0JuCSnYF4af1RGjw+vnlGXnNjK9EHuKQji2fVn+DT38BXHobpi5uaK+vc/Gd/KQ1uH/YYQWyMDXuMDXuMwG4T7CmqZu3BMtYdKqfapa5ShqbG8+lulab680XjA3fcLL0Qgp9/tKyOd7ed4L2thU1Zc9OHp1GYNJvy2hRcm1/h1vXZTe9dUFHP9bOHBT/BdQIhBOeOyWTpzmI8Xl/AnP52qa+A1OGh7etff0eLfg8RyNPf/KJayGDudwM+ZeLQFFbuP8m4wck88Y0Z5KYnwJf5zUu+hchNc/PITFZXDu3W8wfY/hqkDGXupEvYsfIw582dDRUXKdE/+0eqtG57mFUxg9k7oCJ9UBk8OdObUzIN/35UVjJL7j6ref+S6bDlRVVl1KxBFIDZIwby9t1n8fqm4/z+oz1c9ugq5o/LYtnuEn500RgGJsW133cDmyeMyVlCqGi/k54+wPzxg4i123hva2HIou/2+rj39W0s213C9+ePbv8KQUol+iPmcfkZk3luyypueGId/75jrvpOtcPe4mqeWnmIs0dnMHqQ3zyExEwVSfth+vrvbwsQ7defglV/Vbc/+RVVIxay9GAj720rVPMHvO3bDHkDE7hkcjZzRw5kzoiBDEpxct+S7Tz++UHyBiZy/ewASQP7P1FWYlpwISyucvHdf21mvZE2OzU3lf93yXgWTc5mSKrxHXjvGhZtfpHnrx3PtlIfO05UsnDSYO5dOC7sNN2OmDc2k9c2HWfLsYqAcy7aJSxP36/+TihX8N1EPxP9Vt6v16PSIofNVcIXgJvmDCfBYedbZ+eTaJTKJT1fFcxqrA3rDL1gUggzMOvK1Qll9rf54UXj+Pa5o9T7zroN/nkV7HpbZTS0h9/CKUHJ9MvgyTFSMu3O4FcHQ8xJWpvaFX2AGJvgmpm5LJw8mEeXH+DplYcYlBIXdF3igIRThgE6LqbXAUlxds4dk8kH2wv570sndGjx1DR4+M6Lm/jPvpP88MIxHV/BFHwBFUfh3HvJTU/ghVtnc90Ta7nuibW8+u25zeLWig2Hy7n12Q3EOWL45aWtTuKJGSrSl7Lp6qtdi2fVw8iGKr6Y/iDTNv2cdx66i1+4b2ZoajzfPDOfBZMGMzAxFrdX4vb68Hglbp8Pt8dHbnpCwD7+8tIJHCmv45dLtpOTFs85Y/x8dbdLrbXsd0XRmiNltdzw5DpO1TZy78JxXDI5O/BJcNJViA1Pco53A+ecd23Q1+sOzh6VSYxNsGJPacii/+WxCl5cc5jf1p3iZKOTkOZaR6j+Tj8byG01OWvX2+qHOPfuoE/JSUvg+xeMbhZ88Cu8drj7+7jrHeXzGcLe9L4j56v3Xf9Ex6/ht3BKUNLz1epEZg2egk1qjkKwwbZBE9X+YZS6TXY6uHfhOFb8eB5v3HkmCbEhxhheD/g8oUf6oNJxTx3uuHR2O1wyOZviqga+OHqq3f1Kql1c+481rD5Qxu+vOo3vzR/dcbS54w2Vvz1uEaDmJrxwy2wq69zc8OS6gAuhfLSjiBufXEdGUhxvfOcMxgxqNds4MVOd6FpNsrtkcjY7W03UKio4QuPqx/iAM7ly1TBesy3guphP+ODaFFb+9Dx+vmg8pw9LY/jAREZlJTE+O4XJOQM4fVgas0cMDHpSssfYeOT60xmdlcRd//yCPUV+NZqOrlb9C2Lt7Cqs4qq/r6G2wcNLt8/hjnNHBr/qyZ0NKTnqKriHUambqazY236p5fpGL69uOMZX/rqSyx5dxafbD2PHy4tbKli5L4SB4FbllV1uLwdLa/jPvlJe2XCUJVsKunooAelnou8X6UsJax6B9JEwdmF4r2Mukt4Thde2v65e32++AKAmqsy6DY6tNaqBBsHrVtF7Vgeib1PVNynZrZ5zYkuTtROQGIc6KXRiZu6Q1HiGBhKNnW/DKze2XfbPjNjDifTHLFBZIo/MhG2vdWrB6fnjs5TF0072y4HSGr722GoOnazlycUzuGZGbscv7PPBjrfU5CS/q6/JOQN49paZFFe5uPHJdZTXNteE+ue6I3znxU2My07hte+cEVgMgyyQvtAvi2fdwTK+8+ImPvr7j7F5G1k97Hb+9a3ZXPWjx7AlpDN+0/2ILmaPJMXZefrmmThjY7jl2Q3N5TT2L1OpwXlntnnOpiOnuPYfa4gRgn/fMbdNCm8bbDaY9DX1Gdd17xoIgZg3NovtBVVtTsYNHi+bjpRz/zs7mf2/n/CT17fS4PFy/2UT+exuNV/EnpjOLc9u4MPt7ZfFKPWo38Sf31nPjN8sZdwvP+T8P37GTU+t56evb+Pxz3umhHs/E32/SP/oWiVgc+9UAhgOpr3R3SWWq4vh8H9g0lWBMyumXq+i3w3tRPtl+9WVQijlazPHqhNEyS4ltO2JPqhB3hNbOpwdGRJH18Lrt6orm2cvbS5CBuEtoGKy6A9w4+sqp/v1W+GJeXBgeVhdSnY6OGd0Jh9sK8Lnk3i8PmobPJTVNHCiop7P9pZy5d9W43J7efn2OUHX4W3D8Q1QdRwmXtHmoenD03ly8QyOlNVx45PrqKxz86ele/nFm9s5d0wmL902u0VV1RY0iX7Lk+ZQw+J5aOlern18LYcP7OZG+zJck6/jN7dcxhmjMrAlpMGF/6Myeb58KZx/U0CGpMbz1OIZlNU2cNvzG3G5vUqgh81tY4F+vreUG59cR3piLK99Zy6jskKslzT5KnUFuPOtLve3I841bKp3vyzk093F/O7D3Vz999VM/tXHXPm3Nbyw9jDnjs3ildvn8NEPzuEbc/NIkqrK6W0XTmPS0BTu/Ocm/r2x7ZKcLreXRz7dx1efVOVDBtrruWD8IO65cAwPXTOFl2+fw39+ch5v3dX2ZNkd9DNP35yR61JRfnw6TLk+/NeJT1OXZt29mMqON1Xq6KQrg7/vadfA1lfhgv8JPI2/aRA3BNHPGqculw99pu6bxdWCMXQ6rPu7OlEMntTx6wej/BC8fD0MyIUL7oM374BnL4HFb6sBrc5E+kKoyTsjzodtr6oMlRcuVwW+LrwfBk8O6WUuOW0wn+wqZtQv3ifQBN38jESe++Yshg0MY9bnjjeVNTZ2UcCHzxiZwT9ums7tz2/i/D+uoKy2kaum5/Dbr03G0V72SJIp+m1tiNvOHsHTKw9x1fQcrip4kJjtMSRd2Crza8r1Kjlg6X/DuEtCH4AMwmk5qfzl69O448VN/OjpD3ikZCdbx99D2e4S0hNjGZgUyxdHK7jn1S2Mykrm+VtmkZkc2sA+AINPU4PC216HGbd0qa8dYaZu3v+uyoSz2wSTcwaweO5wZuSlMysvnbTWJ2PDpkkcMJAXbp3Nt1/YxI9f20q1y8MtZ+UjpeSD7UU88N4uCirqWTRhOByEm6amwrzTevR4/Olnom98wUp2wu734JwfQWznpmwHK7zWJba/DoMmNWfWBGLWbfDFc7Dln3BGgIwjv4VTOsQczN3yL3UCTOtgoNW8EijY1HnRd1XCS19X9dWvfxUyRqmI9Z9XwzOLYPE7nYv0TWw2mPJ1mHA5bHgSPv8D/OMcmHErnP+L9ge3UQXYjpTV4fb6cNpjiHPYiIsRjCpbzqjjbzBg1FycKbND74/PpyLTUReAMyXobvPGZvHI9dP43subuXPeSH588diOxwmC2DugsngWTc5W2T0fvASzvwMDWuWd22yw6P/g8Xmw4rew8HehH1cQLp44mPsuncDej/4ONvjJlkx2b265hu+M4Wk8dfPMkBa7aYEQKtpf8WDwOSueBrUcaMbozi063/RWgt9eMZndRVXMyEtnSk5qx7V8/MoqJ8bZeermGXz/pS3c/+5Ojp2qY8eJKtYfKmfc4GT+ddtsVVbld+lKi6bf3KVFdcKhf4m+ECri2v6G8qhn3d7510rP7961Y08dUZfa8+9rf7/Bk9Ul84YnYc5d6ofrj7FwStMJrj3MGjwlO9V0945+JOkjVJpZwaZ2MzKC4vXAv29WFtRNbyrBBxh+Btz0Frx4JTy7CC56QLWHE+m3xuGEM+6GaTfA8v9V/68dbypLY8r1bf9vBk5HDD+4wDhhet1qfGDlQ3ByryrTsXol7Po3LPwDjLmo434cWwvVhcqP7oCLJg5m268ubj+69yfBqMUUQPSbWP6AOnme9V+BHx8yVUXN6x+HaTd17QrO4OYz85EnSvAdGcQ/7r6Jsjo35TWNlNU24PFJvtaJYmhNTLpKnaC2v6E+X38Kv4Q3vq2SEwZNUkHRxK91nOIcCE8DF9S8zQXJAnJvhAATKVuw50N474dq3NCodxVnj+GR66dx7xvbeGbVYdISHDxwxSS+PnNY82S2r/xZXen+41y45nm1IHwP0788fVAfivTCaddCUugLbrQhLR8qjilh6Ai3Cw6ugGW/hnX/CLwK1Y431DYEcWDWbSpT5YFB8IfR8NcZ8OQFSjSPrOp4ELfpGPKaB7c78vNBnRSGnN52zdz6CiWqT12sBmb3ftTW95cSPvyp8nkv/ZOalu9P7kxYvARcVfDGbaqtM5F+a+LTlN9/+2cwcBQsuQuevkiNTQTD7VLH89fT4a071GDkVU/DD3epK5GYWPjX1fDyDeo70B7b31D/4zELQupuyIIP6sQWl9J2INyk8Et1opt7Z7MVFIjz/5+yK9//UfeUBPB5EQeXYxt1AcMzkjh9WBoXTBjEtTOHccPs4Z0XfFCBQvaUllk8Xg98/n/wxHw1F+H8X6oryTe/DX+ZAqv+El6Nm70fwWNz1P/jvXvgkRmw+Z/qNVtTVw6v3wYvXauulm/5UKXSGthjbPz+ytN45uaZrPjRedwwe3jL2csTLoNbl6rss2cXqey8Hi7L0L8ifVARcAPtpmmGRPoIdfLY8abKAHKmqB+gM0VdTRRtVUJ/cIWqB+5xKdtFepXfPH0xzL6j+ZJ72+uQMzO0GusTLoeFZWpw0FWpRNdVqb6ASYNg4uWhHYMtRl0VFG0LTfRB7bfyTypN8MQWLI/K0AAACHtJREFU+OJ52LlE+fBZE1QUv+sdNU9g6vUw7UZ1VbTuH0pIz/genP6NwK89ZBrc/C48f5n6f3Ul0m9N9mnqB/nly7D0l8rSmHi5OrE01qjjMf+qjivxyJlpRPQXN18F5Z8Dd6xSY0Kf/R4enQXn/kRddbWOKH1e9b8ZfZGa9dwTmLn6gfj0N0rMO/quJ6TDBb+Cd74HfzlNnRzTR7T8S8sPLWKWEg6vVP+/cBZMCYdJV6pxiLID6v6b31aD5ROvgEseUsdz9j0qe2j1w2rfz/4Ap9+kMvWGzghs657cDx/9DPZ9rMYObnhd/UY++RUsuRNW/xXm/7d6DSFU9tl790B9OZx7r3rPAP8jm020X5dp8CS4fTm8cbs60RR8AZc+FPIiQuEiZC8X+wmHGTNmyI0bN3bviz42V11+Xf9K117nxBZ4/NzAjwmbGpAFJYQj5sGI85SNcXIPrH5EiYEQ6os6diG8dgsseBDmfKdr/QqX129TA58/PtAiQgnK7vfh5evUAtc1RepEN/kqJeTZU9WVz94P4IsX1BR86VNrnR5fr+r6XPtCx9lSJbtg5Z+Vx9zFwcWA1Fcoi2DbayoKj0tSGSaxiWrt0vg0dSWYf077llfFUfjgXtjznsrBT89XAcDAkUo4vY3wwU/g6mcDZu50C09drOZOpA1X/Y5PV1t7HGx6Rol5MGvHH59P1aA6vhHKD0DZQTVT3UTEqOPLGKP+MseqrbCp5IGSnVC8Xd2uK1MVQO/ZC4mdq1raLhXH4M+TIO9sZTXGOJTYB5u0WPil+s1tf10FXTaHsrWGzYFhZyjR3fAkrHlMfR/m3ausX1PApVTjMst+rf43uXOUS7DrbTW4fPljIScKtIvPB5/9Dj57UL3utS+2O5O5PYQQm6SUAcua9j/RrzqhftjtDKqFTNkBqClWlkRDlYq2G6pUPZvMcTDi3OCDMxVHVfS76TlorAYE3LO71wZzmji8Ulku8/87tP1ry+DRmZAxVgn9hMuCD4ZXFqhB4i0vQsJAZY30Yo2RXuPAp3Doc3WVU3ZAZXWZs74difDjfT133AdXqDkA9adUxFl/CupOqW3yILhjZefeW0r1GuUH1TGV7VMlO07uVfd9rWxNe7yaEDhoovLTc2c3rULXIzy9QF1BjzwfLns0tDIG9afg2Hr1vCNrlE3pv1721BvV7yA5yDKWXrcq27LiQSO6/ymc+f3OVQ9tjz0fqqg/eTDcuTbo+FN79CnRF0IsAP4CxABPSikfDLZvj4h+X8NVqaJiW0zvR/m9iV+pAMvj80FVgToJxKf1rPi1R0/9z70eNaZ0co/Kmx80SdmS4c536Qolu1Xq8ITLOn+MbpcS/oIvYPjc0C1Otwu8DaGXUO4MZQfUWE0nB3b7jOgLIWKAvcCFwHFgA3CdlHJnoP37hehrNBpNN9Oe6Pd29s4sYL+U8qCUshF4Gbisl/ug0Wg0/ZbeFv2hgH+O23GjrQkhxO1CiI1CiI2lpV1fk1Wj0Wg0zfS5PH0p5eNSyhlSyhmZmV1f/kyj0Wg0zfS26BcA/mUJc4w2jUaj0fQCvS36G4DRQoh8IUQs8HXg7V7ug0aj0fRbenVGrpTSI4S4G/gIlbL5tJRyR2/2QaPRaPozvV6GQUr5PvB+b7+vRqPRaPrgQK5Go9Foeo4+XYZBCFEKHOnCS2QAISxWaTn0cfcv9HH3L0I57uFSyoDpj31a9LuKEGJjsFlpVkYfd/9CH3f/oqvHre0djUaj6Udo0ddoNJp+hNVF//FIdyBC6OPuX+jj7l906bgt7elrNBqNpiVWj/Q1Go1G44cWfY1Go+lHWFL0hRALhBB7hBD7hRD3Rro/PYkQ4mkhRIkQYrtfW7oQYqkQYp+xTYtkH7sbIUSuEGK5EGKnEGKHEOL7RrvVj9sphFgvhPjSOO7/MdrzhRDrjO/7K0ZdK8shhIgRQmwWQrxr3O8vx31YCLFNCLFFCLHRaOv0d91yom+szvUosBCYAFwnhJgQ2V71KM8CC1q13Qssk1KOBpYZ962EB7hHSjkBmAPcZXzGVj/uBuB8KeUUYCqwQAgxB/gd8Ccp5SjgFHBrBPvYk3wf2OV3v78cN8B5Usqpfvn5nf6uW0706Werc0kpPwfKWzVfBjxn3H4OuLxXO9XDSCkLpZRfGLerUUIwFOsft5RS1hh3HcafBM4HXjPaLXfcAEKIHOAS4EnjvqAfHHc7dPq7bkXR73B1rn7AIClloXG7CBgUyc70JEKIPGAasI5+cNyGxbEFKAGWAgeACimlx9jFqt/3PwM/AXzG/YH0j+MGdWL/WAixSQhxu9HW6e96r1fZ1PQuUkophLBkXq4QIgl4HfiBlLJKBX8Kqx63lNILTBVCpAJvAuMi3KUeRwhxKVAipdwkhJgX6f5EgLOklAVCiCxgqRBit/+D4X7XrRjp69W5oFgIkQ1gbEsi3J9uRwjhQAn+P6WUbxjNlj9uEyllBbAcmAukCiHMAM6K3/czga8KIQ6j7Nrzgb9g/eMGQEpZYGxLUCf6WXThu25F0derc6njXWzcXgwsiWBfuh3Dz30K2CWlfMjvIasfd6YR4SOEiAcuRI1nLAeuMnaz3HFLKX8mpcyRUuahfs+fSilvwOLHDSCESBRCJJu3gYuA7XThu27JGblCiEUoD9BcneuBCHepxxBCvATMQ5VbLQbuA94CXgWGoUpTXyOlbD3YG7UIIc4C/gNso9nj/TnK17fycZ+GGrSLQQVsr0op7xdCjEBFwOnAZuBGKWVD5Hracxj2zo+klJf2h+M2jvFN464d+JeU8gEhxEA6+V23pOhrNBqNJjBWtHc0Go1GEwQt+hqNRtOP0KKv0Wg0/Qgt+hqNRtOP0KKv0Wg0/Qgt+hqNRtOP0KKv0Wg0/Yj/D7qsegrfUyZnAAAAAElFTkSuQmCC\n" + }, + "metadata": { + "needs_background": "light" + } + } + ] + }, + { + "cell_type": "markdown", + "source": [ + "## Evaluation Metrics\n", + "Use the R2 Score function implemented in the first assignment to evaluate the performance of the model." + ], + "metadata": { + "id": "IVrR_vXA7kOt" + } + }, + { + "cell_type": "code", + "source": [ + "# Insert the function for R2 Score\n", + "def r2_score(y_true,y_pred):\n", + " \n", + " y_mean = y_true.mean()\n", + " return 1 - (((y_true-y_pred)**2).mean())/(((y_true-y_mean)**2).mean())\n", + "acuu = r2_score(y_test,predictions.flatten()) \n", + "print('Accuracy :', acuu)\n", + "\n" + ], + "metadata": { + "id": "-lOHpD8-7ggm", + "outputId": "38a20e3b-f988-42ab-f639-25b9f7ee6efa", + "colab": { + "base_uri": "https://localhost:8080/" + } + }, + "execution_count": 13, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "Accuracy : 0.9976567220172706\n" + ] + } + ] + }, + { + "cell_type": "markdown", + "source": [ + "## Your own custom model\n", + "Build a custom model of your own choice.
\n", + "Describe it in detail in Markdown/Latex in the cell below.
\n", + "Visualise the loss, as before." + ], + "metadata": { + "id": "CHqzF1OU0pBg" + } + }, + { + "cell_type": "markdown", + "source": [ + "Your text here" + ], + "metadata": { + "id": "jF8oTUqq0y0g" + } + }, + { + "cell_type": "code", + "source": [ + "# Your code here\n", + "model_custom = keras.Sequential([keras.layers.Dense(64,input_dim=5,activation='relu'),\n", + " keras.layers.Dense(15,activation='relu'),\n", + " keras.layers.Dense(10,activation='relu'),\n", + " keras.layers.Dense(1)])\n", + "model_custom.compile(optimizer=tf.optimizers.Adam(learning_rate=0.001),\n", + " loss='mean_absolute_error')\n", + "history_custom = model_custom.fit(\n", + " X_train,y_train,\n", + " validation_split =0.2,\n", + " verbose=2,epochs=50\n", + ")" + ], + "metadata": { + "id": "1XOk5hJu0oSQ", + "outputId": "8b428952-6a1c-4143-8034-a50d1b89a255", + "colab": { + "base_uri": "https://localhost:8080/" + } + }, + "execution_count": 32, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "Epoch 1/50\n", + "200/200 - 1s - loss: 86.9274 - val_loss: 62.6012 - 799ms/epoch - 4ms/step\n", + "Epoch 2/50\n", + "200/200 - 0s - loss: 19.8114 - val_loss: 9.6341 - 335ms/epoch - 2ms/step\n", + "Epoch 3/50\n", + "200/200 - 0s - loss: 8.5663 - val_loss: 8.0135 - 349ms/epoch - 2ms/step\n", + "Epoch 4/50\n", + "200/200 - 0s - loss: 7.0574 - val_loss: 6.5489 - 324ms/epoch - 2ms/step\n", + "Epoch 5/50\n", + "200/200 - 0s - loss: 5.6996 - val_loss: 5.2579 - 324ms/epoch - 2ms/step\n", + "Epoch 6/50\n", + "200/200 - 0s - loss: 4.8941 - val_loss: 4.7478 - 324ms/epoch - 2ms/step\n", + "Epoch 7/50\n", + "200/200 - 0s - loss: 4.5774 - val_loss: 4.4956 - 310ms/epoch - 2ms/step\n", + "Epoch 8/50\n", + "200/200 - 0s - loss: 4.4216 - val_loss: 4.5247 - 332ms/epoch - 2ms/step\n", + "Epoch 9/50\n", + "200/200 - 0s - loss: 4.3259 - val_loss: 4.4404 - 340ms/epoch - 2ms/step\n", + "Epoch 10/50\n", + "200/200 - 0s - loss: 4.2725 - val_loss: 4.3309 - 317ms/epoch - 2ms/step\n", + "Epoch 11/50\n", + "200/200 - 0s - loss: 4.2383 - val_loss: 4.4178 - 323ms/epoch - 2ms/step\n", + "Epoch 12/50\n", + "200/200 - 0s - loss: 4.1996 - val_loss: 4.5615 - 314ms/epoch - 2ms/step\n", + "Epoch 13/50\n", + "200/200 - 0s - loss: 4.2129 - val_loss: 4.5135 - 337ms/epoch - 2ms/step\n", + "Epoch 14/50\n", + "200/200 - 0s - loss: 4.1564 - val_loss: 4.2678 - 327ms/epoch - 2ms/step\n", + "Epoch 15/50\n", + "200/200 - 0s - loss: 4.1129 - val_loss: 4.3327 - 348ms/epoch - 2ms/step\n", + "Epoch 16/50\n", + "200/200 - 0s - loss: 4.1318 - val_loss: 4.2996 - 416ms/epoch - 2ms/step\n", + "Epoch 17/50\n", + "200/200 - 1s - loss: 4.1150 - val_loss: 4.5790 - 541ms/epoch - 3ms/step\n", + "Epoch 18/50\n", + "200/200 - 1s - loss: 4.0718 - val_loss: 4.3515 - 563ms/epoch - 3ms/step\n", + "Epoch 19/50\n", + "200/200 - 1s - loss: 4.1166 - val_loss: 4.1774 - 562ms/epoch - 3ms/step\n", + "Epoch 20/50\n", + "200/200 - 0s - loss: 4.0774 - val_loss: 4.5272 - 363ms/epoch - 2ms/step\n", + "Epoch 21/50\n", + "200/200 - 0s - loss: 4.0964 - val_loss: 4.3456 - 333ms/epoch - 2ms/step\n", + "Epoch 22/50\n", + "200/200 - 0s - loss: 4.0463 - val_loss: 4.2782 - 317ms/epoch - 2ms/step\n", + "Epoch 23/50\n", + "200/200 - 0s - loss: 4.0313 - val_loss: 4.1738 - 307ms/epoch - 2ms/step\n", + "Epoch 24/50\n", + "200/200 - 0s - loss: 4.0393 - val_loss: 4.3118 - 324ms/epoch - 2ms/step\n", + "Epoch 25/50\n", + "200/200 - 0s - loss: 4.0653 - val_loss: 4.2462 - 330ms/epoch - 2ms/step\n", + "Epoch 26/50\n", + "200/200 - 0s - loss: 4.0408 - val_loss: 4.2241 - 312ms/epoch - 2ms/step\n", + "Epoch 27/50\n", + "200/200 - 0s - loss: 4.0641 - val_loss: 4.1905 - 321ms/epoch - 2ms/step\n", + "Epoch 28/50\n", + "200/200 - 0s - loss: 4.0306 - val_loss: 4.2208 - 322ms/epoch - 2ms/step\n", + "Epoch 29/50\n", + "200/200 - 0s - loss: 4.0128 - val_loss: 4.4978 - 316ms/epoch - 2ms/step\n", + "Epoch 30/50\n", + "200/200 - 0s - loss: 4.0218 - val_loss: 4.1599 - 328ms/epoch - 2ms/step\n", + "Epoch 31/50\n", + "200/200 - 0s - loss: 4.0020 - val_loss: 4.1927 - 320ms/epoch - 2ms/step\n", + "Epoch 32/50\n", + "200/200 - 0s - loss: 4.0253 - val_loss: 4.1439 - 327ms/epoch - 2ms/step\n", + "Epoch 33/50\n", + "200/200 - 0s - loss: 4.0297 - val_loss: 4.2742 - 315ms/epoch - 2ms/step\n", + "Epoch 34/50\n", + "200/200 - 0s - loss: 4.0132 - val_loss: 4.3917 - 313ms/epoch - 2ms/step\n", + "Epoch 35/50\n", + "200/200 - 0s - loss: 3.9896 - val_loss: 4.2615 - 322ms/epoch - 2ms/step\n", + "Epoch 36/50\n", + "200/200 - 0s - loss: 3.9916 - val_loss: 4.1592 - 333ms/epoch - 2ms/step\n", + "Epoch 37/50\n", + "200/200 - 0s - loss: 4.0609 - val_loss: 4.1600 - 332ms/epoch - 2ms/step\n", + "Epoch 38/50\n", + "200/200 - 0s - loss: 4.0511 - val_loss: 4.3256 - 317ms/epoch - 2ms/step\n", + "Epoch 39/50\n", + "200/200 - 0s - loss: 4.0149 - val_loss: 4.2721 - 337ms/epoch - 2ms/step\n", + "Epoch 40/50\n", + "200/200 - 0s - loss: 4.0123 - val_loss: 4.2894 - 335ms/epoch - 2ms/step\n", + "Epoch 41/50\n", + "200/200 - 0s - loss: 3.9865 - val_loss: 4.2675 - 332ms/epoch - 2ms/step\n", + "Epoch 42/50\n", + "200/200 - 0s - loss: 3.9872 - val_loss: 4.1983 - 317ms/epoch - 2ms/step\n", + "Epoch 43/50\n", + "200/200 - 0s - loss: 3.9874 - val_loss: 4.2046 - 324ms/epoch - 2ms/step\n", + "Epoch 44/50\n", + "200/200 - 0s - loss: 3.9847 - val_loss: 4.2214 - 323ms/epoch - 2ms/step\n", + "Epoch 45/50\n", + "200/200 - 0s - loss: 3.9833 - val_loss: 4.2228 - 305ms/epoch - 2ms/step\n", + "Epoch 46/50\n", + "200/200 - 0s - loss: 3.9758 - val_loss: 4.4382 - 316ms/epoch - 2ms/step\n", + "Epoch 47/50\n", + "200/200 - 0s - loss: 3.9682 - val_loss: 4.1712 - 295ms/epoch - 1ms/step\n", + "Epoch 48/50\n", + "200/200 - 0s - loss: 3.9963 - val_loss: 4.1989 - 319ms/epoch - 2ms/step\n", + "Epoch 49/50\n", + "200/200 - 0s - loss: 3.9923 - val_loss: 4.1604 - 318ms/epoch - 2ms/step\n", + "Epoch 50/50\n", + "200/200 - 0s - loss: 3.9805 - val_loss: 4.2202 - 333ms/epoch - 2ms/step\n" + ] + } + ] + }, + { + "cell_type": "code", + "source": [ + "plt.plot(history.history['loss'],label='loss')\n", + "plt.plot(history.history['val_loss'],label='val_loss')\n" + ], + "metadata": { + "id": "aS0ROZa402Lo", + "outputId": "fa91ceb9-10ee-4dc1-f1d6-34ade0308e15", + "colab": { + "base_uri": "https://localhost:8080/", + "height": 282 + } + }, + "execution_count": 33, + "outputs": [ + { + "output_type": "execute_result", + "data": { + "text/plain": [ + "[]" + ] + }, + "metadata": {}, + "execution_count": 33 + }, + { + "output_type": "display_data", + "data": { + "text/plain": [ + "
" + ], + "image/png": "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\n" + }, + "metadata": { + "needs_background": "light" + } + } + ] + }, + { + "cell_type": "code", + "source": [ + "prediction_custom = model_custom.predict(X_test)\n", + "r2_score(y_test,prediction_custom.flatten())" + ], + "metadata": { + "id": "fAAqr7VbcWDS", + "outputId": "34a8a602-7eba-4823-9b28-c22e2ae1b59c", + "colab": { + "base_uri": "https://localhost:8080/" + } + }, + "execution_count": 34, + "outputs": [ + { + "output_type": "execute_result", + "data": { + "text/plain": [ + "0.9980862492729278" + ] + }, + "metadata": {}, + "execution_count": 34 + } + ] + } + ] +} \ No newline at end of file From 87e63b809e6f063194c9b4e21f8e55b228669812 Mon Sep 17 00:00:00 2001 From: rohitkg2003 <87852134+rohitkg2003@users.noreply.github.com> Date: Fri, 17 Jun 2022 17:21:56 +0530 Subject: [PATCH 3/5] Delete CVusingTF_Assgn2.ipynb --- CVusingTF_Assgn2.ipynb | 576 ----------------------------------------- 1 file changed, 576 deletions(-) delete mode 100644 CVusingTF_Assgn2.ipynb diff --git a/CVusingTF_Assgn2.ipynb b/CVusingTF_Assgn2.ipynb deleted file mode 100644 index 944408f..0000000 --- a/CVusingTF_Assgn2.ipynb +++ /dev/null @@ -1,576 +0,0 @@ -{ - "nbformat": 4, - "nbformat_minor": 0, - "metadata": { - "colab": { - "name": "CVusingTF_Assgn2.ipynb", - "provenance": [], - "collapsed_sections": [], - "include_colab_link": true - }, - "kernelspec": { - "name": "python3", - "display_name": "Python 3" - }, - "language_info": { - "name": "python" - } - }, - "cells": [ - { - "cell_type": "markdown", - "metadata": { - "id": "view-in-github", - "colab_type": "text" - }, - "source": [ - "\"Open" - ] - }, - { - "cell_type": "markdown", - "source": [ - "# Assigment 2: Deep Learning" - ], - "metadata": { - "id": "UxcaEbrCy1g_" - } - }, - { - "cell_type": "markdown", - "source": [ - "## Generate Dataset\n", - "\n", - "This is the same code from Assignment 1" - ], - "metadata": { - "id": "h2JON-_Oy79w" - } - }, - { - "cell_type": "code", - "execution_count": 1, - "metadata": { - "id": "hgpG3WDuypfa" - }, - "outputs": [], - "source": [ - "from sklearn import datasets\n", - "from sklearn.model_selection import train_test_split\n", - "\n", - "# Generate the data\n", - "X, y = datasets.make_regression(n_samples=10000, n_features=5, noise=5, random_state=4)\n", - "\n", - "# Split the data\n", - "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=1234)\n" - ] - }, - { - "cell_type": "markdown", - "source": [ - "## Visualize Dataset\n", - "This is the same code from Assignment 1" - ], - "metadata": { - "id": "r6it-Rm7zD1Y" - } - }, - { - "cell_type": "code", - "source": [ - "import matplotlib.pyplot as plt\n", - "import numpy as np\n", - "for i in range (5):\n", - " plt.scatter(X_train[:,i],y_train)\n", - "\n", - "\n", - "# Your code here" - ], - "metadata": { - "id": "UautPVj1yzaQ", - "outputId": "75bcc3b3-0559-45e7-ad6f-f12a75b2f08d", - "colab": { - "base_uri": "https://localhost:8080/", - "height": 265 - } - }, - "execution_count": 2, - "outputs": [ - { - "output_type": "display_data", - "data": { - "text/plain": [ - "
" - ], - "image/png": "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\n" - }, - "metadata": { - "needs_background": "light" - } - } - ] - }, - { - "cell_type": "markdown", - "source": [ - "## Model Definition\n", - "\n", - "Using TensorFlow, build a model with the following definition:\n", - "> Input of shape 5 \\\\\n", - "> Dense of shape 5 \\\\\n", - "> Dense of shape 5 \\\\\n", - "> Dense of shape 1 \\\\\n", - "\n", - "Use Mean Square Error Loss and Stochaistic Gradient Descent (SGD) Optimizer\n", - "\n", - "Use Gradient Decay with appropriate parameters" - ], - "metadata": { - "id": "XMXb9lTyzGHE" - } - }, - { - "cell_type": "code", - "source": [ - "import tensorflow as tf\n", - "from tensorflow import keras\n", - "model = keras.Sequential([keras.layers.Dense(5,input_dim=5,activation='relu'),keras.layers.Dense(5,activation='relu'),keras.layers.Dense(1)])\n", - "model.compile(loss='mean_squared_error',optimizer=tf.keras.optimizers.SGD(0.001))\n", - "history = model.fit(X_train,y_train,epochs=50,validation_split=0.2,verbose=2)\n", - "predictions = model.predict(X_test)\n", - "\n", - "\n", - "# Your code here" - ], - "metadata": { - "id": "r32N1xK2ziOs", - "outputId": "e74b01fe-9f46-4562-fdaf-5b8ad24935c1", - "colab": { - "base_uri": "https://localhost:8080/" - } - }, - "execution_count": 6, - "outputs": [ - { - "output_type": "stream", - "name": "stdout", - "text": [ - "Epoch 1/50\n", - "200/200 - 1s - loss: 1400.1647 - val_loss: 2141.0627 - 865ms/epoch - 4ms/step\n", - "Epoch 2/50\n", - "200/200 - 0s - loss: 340.9002 - val_loss: 44.8760 - 275ms/epoch - 1ms/step\n", - "Epoch 3/50\n", - "200/200 - 0s - loss: 492.3806 - val_loss: 192.2196 - 289ms/epoch - 1ms/step\n", - "Epoch 4/50\n", - "200/200 - 0s - loss: 147.8546 - val_loss: 525.9345 - 369ms/epoch - 2ms/step\n", - "Epoch 5/50\n", - "200/200 - 0s - loss: 202.5587 - val_loss: 45.8932 - 259ms/epoch - 1ms/step\n", - "Epoch 6/50\n", - "200/200 - 0s - loss: 227.0734 - val_loss: 41.9783 - 270ms/epoch - 1ms/step\n", - "Epoch 7/50\n", - "200/200 - 0s - loss: 159.3960 - val_loss: 59.6942 - 284ms/epoch - 1ms/step\n", - "Epoch 8/50\n", - "200/200 - 0s - loss: 239.3188 - val_loss: 29.9748 - 281ms/epoch - 1ms/step\n", - "Epoch 9/50\n", - "200/200 - 0s - loss: 152.8331 - val_loss: 221.7097 - 298ms/epoch - 1ms/step\n", - "Epoch 10/50\n", - "200/200 - 0s - loss: 338.3758 - val_loss: 64.0810 - 284ms/epoch - 1ms/step\n", - "Epoch 11/50\n", - "200/200 - 0s - loss: 209.4844 - val_loss: 59.8163 - 267ms/epoch - 1ms/step\n", - "Epoch 12/50\n", - "200/200 - 0s - loss: 251.1109 - val_loss: 435.7401 - 262ms/epoch - 1ms/step\n", - "Epoch 13/50\n", - "200/200 - 0s - loss: 622.8074 - val_loss: 39.8785 - 284ms/epoch - 1ms/step\n", - "Epoch 14/50\n", - "200/200 - 0s - loss: 166.6548 - val_loss: 352.9469 - 258ms/epoch - 1ms/step\n", - "Epoch 15/50\n", - "200/200 - 0s - loss: 188.5881 - val_loss: 36.6427 - 275ms/epoch - 1ms/step\n", - "Epoch 16/50\n", - "200/200 - 0s - loss: 178.6596 - val_loss: 62.4603 - 271ms/epoch - 1ms/step\n", - "Epoch 17/50\n", - "200/200 - 0s - loss: 140.6317 - val_loss: 36.7756 - 258ms/epoch - 1ms/step\n", - "Epoch 18/50\n", - "200/200 - 0s - loss: 262.6449 - val_loss: 115.1941 - 284ms/epoch - 1ms/step\n", - "Epoch 19/50\n", - "200/200 - 0s - loss: 174.5533 - val_loss: 50.6086 - 265ms/epoch - 1ms/step\n", - "Epoch 20/50\n", - "200/200 - 0s - loss: 202.2552 - val_loss: 1926.5394 - 279ms/epoch - 1ms/step\n", - "Epoch 21/50\n", - "200/200 - 0s - loss: 229.1364 - val_loss: 124.1915 - 263ms/epoch - 1ms/step\n", - "Epoch 22/50\n", - "200/200 - 0s - loss: 461.1045 - val_loss: 88.1916 - 279ms/epoch - 1ms/step\n", - "Epoch 23/50\n", - "200/200 - 0s - loss: 295.3871 - val_loss: 48.4503 - 262ms/epoch - 1ms/step\n", - "Epoch 24/50\n", - "200/200 - 0s - loss: 95.2892 - val_loss: 51.6104 - 257ms/epoch - 1ms/step\n", - "Epoch 25/50\n", - "200/200 - 0s - loss: 97.4321 - val_loss: 83.4106 - 260ms/epoch - 1ms/step\n", - "Epoch 26/50\n", - "200/200 - 0s - loss: 156.3376 - val_loss: 43.0365 - 290ms/epoch - 1ms/step\n", - "Epoch 27/50\n", - "200/200 - 0s - loss: 382.1672 - val_loss: 33.2760 - 275ms/epoch - 1ms/step\n", - "Epoch 28/50\n", - "200/200 - 0s - loss: 158.5331 - val_loss: 229.5324 - 275ms/epoch - 1ms/step\n", - "Epoch 29/50\n", - "200/200 - 0s - loss: 89.6189 - val_loss: 911.1938 - 266ms/epoch - 1ms/step\n", - "Epoch 30/50\n", - "200/200 - 0s - loss: 149.3119 - val_loss: 808.9080 - 280ms/epoch - 1ms/step\n", - "Epoch 31/50\n", - "200/200 - 0s - loss: 301.7253 - val_loss: 41.8418 - 258ms/epoch - 1ms/step\n", - "Epoch 32/50\n", - "200/200 - 0s - loss: 102.5081 - val_loss: 37.0123 - 273ms/epoch - 1ms/step\n", - "Epoch 33/50\n", - "200/200 - 0s - loss: 130.9274 - val_loss: 163.9801 - 259ms/epoch - 1ms/step\n", - "Epoch 34/50\n", - "200/200 - 0s - loss: 153.3079 - val_loss: 52.8656 - 280ms/epoch - 1ms/step\n", - "Epoch 35/50\n", - "200/200 - 0s - loss: 151.9014 - val_loss: 43.4715 - 284ms/epoch - 1ms/step\n", - "Epoch 36/50\n", - "200/200 - 0s - loss: 168.6933 - val_loss: 32.9337 - 264ms/epoch - 1ms/step\n", - "Epoch 37/50\n", - "200/200 - 0s - loss: 91.0383 - val_loss: 44.8102 - 282ms/epoch - 1ms/step\n", - "Epoch 38/50\n", - "200/200 - 0s - loss: 85.5136 - val_loss: 283.6330 - 266ms/epoch - 1ms/step\n", - "Epoch 39/50\n", - "200/200 - 0s - loss: 147.2607 - val_loss: 513.7488 - 260ms/epoch - 1ms/step\n", - "Epoch 40/50\n", - "200/200 - 0s - loss: 169.6636 - val_loss: 222.6365 - 278ms/epoch - 1ms/step\n", - "Epoch 41/50\n", - "200/200 - 0s - loss: 156.9541 - val_loss: 31.6757 - 272ms/epoch - 1ms/step\n", - "Epoch 42/50\n", - "200/200 - 0s - loss: 231.9851 - val_loss: 77.3350 - 277ms/epoch - 1ms/step\n", - "Epoch 43/50\n", - "200/200 - 0s - loss: 257.5688 - val_loss: 47.2681 - 281ms/epoch - 1ms/step\n", - "Epoch 44/50\n", - "200/200 - 0s - loss: 326.8341 - val_loss: 31.5751 - 264ms/epoch - 1ms/step\n", - "Epoch 45/50\n", - "200/200 - 0s - loss: 94.9101 - val_loss: 70.3932 - 275ms/epoch - 1ms/step\n", - "Epoch 46/50\n", - "200/200 - 0s - loss: 110.4162 - val_loss: 34.9609 - 261ms/epoch - 1ms/step\n", - "Epoch 47/50\n", - "200/200 - 0s - loss: 137.7447 - val_loss: 78.6928 - 275ms/epoch - 1ms/step\n", - "Epoch 48/50\n", - "200/200 - 0s - loss: 75.7320 - val_loss: 1105.6212 - 281ms/epoch - 1ms/step\n", - "Epoch 49/50\n", - "200/200 - 0s - loss: 113.9831 - val_loss: 86.3590 - 273ms/epoch - 1ms/step\n", - "Epoch 50/50\n", - "200/200 - 0s - loss: 121.9195 - val_loss: 33.9616 - 269ms/epoch - 1ms/step\n" - ] - } - ] - }, - { - "cell_type": "markdown", - "source": [ - "## Plot Loss\n", - "\n", - "Using matplotlib visualise how the loss (both validation and training) is changing, use this information to retrain the model with appropriate parameters.
We ideally want the loss to be constant over the last few iterations." - ], - "metadata": { - "id": "jmeP6vt3z0oA" - } - }, - { - "cell_type": "code", - "source": [ - "# Your code here\n", - "plt.plot(history.history['loss'],label='loss')\n", - "plt.plot(history.history['val_loss'],label='val_loss')" - ], - "metadata": { - "id": "RQTNqPHm0mOi", - "outputId": "8e605b93-8215-487c-8882-a755eafc6241", - "colab": { - "base_uri": "https://localhost:8080/", - "height": 282 - } - }, - "execution_count": 7, - "outputs": [ - { - "output_type": "execute_result", - "data": { - "text/plain": [ - "[]" - ] - }, - "metadata": {}, - "execution_count": 7 - }, - { - "output_type": "display_data", - "data": { - "text/plain": [ - "
" - ], - "image/png": "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\n" - }, - "metadata": { - "needs_background": "light" - } - } - ] - }, - { - "cell_type": "markdown", - "source": [ - "## Evaluation Metrics\n", - "Use the R2 Score function implemented in the first assignment to evaluate the performance of the model." - ], - "metadata": { - "id": "IVrR_vXA7kOt" - } - }, - { - "cell_type": "code", - "source": [ - "# Insert the function for R2 Score\n", - "def r2_score(y_true,y_pred):\n", - " \n", - " y_mean = y_true.mean()\n", - " return 1 - (((y_true-y_pred)**2).mean())/(((y_true-y_mean)**2).mean())\n", - "acuu = r2_score(y_test,predictions.flatten()) \n", - "print('Accuracy :', acuu)\n", - "\n" - ], - "metadata": { - "id": "-lOHpD8-7ggm", - "outputId": "38a20e3b-f988-42ab-f639-25b9f7ee6efa", - "colab": { - "base_uri": "https://localhost:8080/" - } - }, - "execution_count": 13, - "outputs": [ - { - "output_type": "stream", - "name": "stdout", - "text": [ - "Accuracy : 0.9976567220172706\n" - ] - } - ] - }, - { - "cell_type": "markdown", - "source": [ - "## Your own custom model\n", - "Build a custom model of your own choice.
\n", - "Describe it in detail in Markdown/Latex in the cell below.
\n", - "Visualise the loss, as before." - ], - "metadata": { - "id": "CHqzF1OU0pBg" - } - }, - { - "cell_type": "markdown", - "source": [ - "Your text here" - ], - "metadata": { - "id": "jF8oTUqq0y0g" - } - }, - { - "cell_type": "code", - "source": [ - "# Your code here\n", - "model_custom = keras.Sequential([keras.layers.Dense(64,input_dim=5,activation='relu'),\n", - " keras.layers.Dense(15,activation='relu'),\n", - " keras.layers.Dense(10,activation='relu'),\n", - " keras.layers.Dense(1)])\n", - "model_custom.compile(optimizer=tf.optimizers.Adam(learning_rate=0.001),\n", - " loss='mean_absolute_error')\n", - "history_custom = model_custom.fit(\n", - " X_train,y_train,\n", - " validation_split =0.2,\n", - " verbose=2,epochs=50\n", - ")" - ], - "metadata": { - "id": "1XOk5hJu0oSQ", - "outputId": "8b428952-6a1c-4143-8034-a50d1b89a255", - "colab": { - "base_uri": "https://localhost:8080/" - } - }, - "execution_count": 32, - "outputs": [ - { - "output_type": "stream", - "name": "stdout", - "text": [ - "Epoch 1/50\n", - "200/200 - 1s - loss: 86.9274 - val_loss: 62.6012 - 799ms/epoch - 4ms/step\n", - "Epoch 2/50\n", - "200/200 - 0s - loss: 19.8114 - val_loss: 9.6341 - 335ms/epoch - 2ms/step\n", - "Epoch 3/50\n", - "200/200 - 0s - loss: 8.5663 - val_loss: 8.0135 - 349ms/epoch - 2ms/step\n", - "Epoch 4/50\n", - "200/200 - 0s - loss: 7.0574 - val_loss: 6.5489 - 324ms/epoch - 2ms/step\n", - "Epoch 5/50\n", - "200/200 - 0s - loss: 5.6996 - val_loss: 5.2579 - 324ms/epoch - 2ms/step\n", - "Epoch 6/50\n", - "200/200 - 0s - loss: 4.8941 - val_loss: 4.7478 - 324ms/epoch - 2ms/step\n", - "Epoch 7/50\n", - "200/200 - 0s - loss: 4.5774 - val_loss: 4.4956 - 310ms/epoch - 2ms/step\n", - "Epoch 8/50\n", - "200/200 - 0s - loss: 4.4216 - val_loss: 4.5247 - 332ms/epoch - 2ms/step\n", - "Epoch 9/50\n", - "200/200 - 0s - loss: 4.3259 - val_loss: 4.4404 - 340ms/epoch - 2ms/step\n", - "Epoch 10/50\n", - "200/200 - 0s - loss: 4.2725 - val_loss: 4.3309 - 317ms/epoch - 2ms/step\n", - "Epoch 11/50\n", - "200/200 - 0s - loss: 4.2383 - val_loss: 4.4178 - 323ms/epoch - 2ms/step\n", - "Epoch 12/50\n", - "200/200 - 0s - loss: 4.1996 - val_loss: 4.5615 - 314ms/epoch - 2ms/step\n", - "Epoch 13/50\n", - "200/200 - 0s - loss: 4.2129 - val_loss: 4.5135 - 337ms/epoch - 2ms/step\n", - "Epoch 14/50\n", - "200/200 - 0s - loss: 4.1564 - val_loss: 4.2678 - 327ms/epoch - 2ms/step\n", - "Epoch 15/50\n", - "200/200 - 0s - loss: 4.1129 - val_loss: 4.3327 - 348ms/epoch - 2ms/step\n", - "Epoch 16/50\n", - "200/200 - 0s - loss: 4.1318 - val_loss: 4.2996 - 416ms/epoch - 2ms/step\n", - "Epoch 17/50\n", - "200/200 - 1s - loss: 4.1150 - val_loss: 4.5790 - 541ms/epoch - 3ms/step\n", - "Epoch 18/50\n", - "200/200 - 1s - loss: 4.0718 - val_loss: 4.3515 - 563ms/epoch - 3ms/step\n", - "Epoch 19/50\n", - "200/200 - 1s - loss: 4.1166 - val_loss: 4.1774 - 562ms/epoch - 3ms/step\n", - "Epoch 20/50\n", - "200/200 - 0s - loss: 4.0774 - val_loss: 4.5272 - 363ms/epoch - 2ms/step\n", - "Epoch 21/50\n", - "200/200 - 0s - loss: 4.0964 - val_loss: 4.3456 - 333ms/epoch - 2ms/step\n", - "Epoch 22/50\n", - "200/200 - 0s - loss: 4.0463 - val_loss: 4.2782 - 317ms/epoch - 2ms/step\n", - "Epoch 23/50\n", - "200/200 - 0s - loss: 4.0313 - val_loss: 4.1738 - 307ms/epoch - 2ms/step\n", - "Epoch 24/50\n", - "200/200 - 0s - loss: 4.0393 - val_loss: 4.3118 - 324ms/epoch - 2ms/step\n", - "Epoch 25/50\n", - "200/200 - 0s - loss: 4.0653 - val_loss: 4.2462 - 330ms/epoch - 2ms/step\n", - "Epoch 26/50\n", - "200/200 - 0s - loss: 4.0408 - val_loss: 4.2241 - 312ms/epoch - 2ms/step\n", - "Epoch 27/50\n", - "200/200 - 0s - loss: 4.0641 - val_loss: 4.1905 - 321ms/epoch - 2ms/step\n", - "Epoch 28/50\n", - "200/200 - 0s - loss: 4.0306 - val_loss: 4.2208 - 322ms/epoch - 2ms/step\n", - "Epoch 29/50\n", - "200/200 - 0s - loss: 4.0128 - val_loss: 4.4978 - 316ms/epoch - 2ms/step\n", - "Epoch 30/50\n", - "200/200 - 0s - loss: 4.0218 - val_loss: 4.1599 - 328ms/epoch - 2ms/step\n", - "Epoch 31/50\n", - "200/200 - 0s - loss: 4.0020 - val_loss: 4.1927 - 320ms/epoch - 2ms/step\n", - "Epoch 32/50\n", - "200/200 - 0s - loss: 4.0253 - val_loss: 4.1439 - 327ms/epoch - 2ms/step\n", - "Epoch 33/50\n", - "200/200 - 0s - loss: 4.0297 - val_loss: 4.2742 - 315ms/epoch - 2ms/step\n", - "Epoch 34/50\n", - "200/200 - 0s - loss: 4.0132 - val_loss: 4.3917 - 313ms/epoch - 2ms/step\n", - "Epoch 35/50\n", - "200/200 - 0s - loss: 3.9896 - val_loss: 4.2615 - 322ms/epoch - 2ms/step\n", - "Epoch 36/50\n", - "200/200 - 0s - loss: 3.9916 - val_loss: 4.1592 - 333ms/epoch - 2ms/step\n", - "Epoch 37/50\n", - "200/200 - 0s - loss: 4.0609 - val_loss: 4.1600 - 332ms/epoch - 2ms/step\n", - "Epoch 38/50\n", - "200/200 - 0s - loss: 4.0511 - val_loss: 4.3256 - 317ms/epoch - 2ms/step\n", - "Epoch 39/50\n", - "200/200 - 0s - loss: 4.0149 - val_loss: 4.2721 - 337ms/epoch - 2ms/step\n", - "Epoch 40/50\n", - "200/200 - 0s - loss: 4.0123 - val_loss: 4.2894 - 335ms/epoch - 2ms/step\n", - "Epoch 41/50\n", - "200/200 - 0s - loss: 3.9865 - val_loss: 4.2675 - 332ms/epoch - 2ms/step\n", - "Epoch 42/50\n", - "200/200 - 0s - loss: 3.9872 - val_loss: 4.1983 - 317ms/epoch - 2ms/step\n", - "Epoch 43/50\n", - "200/200 - 0s - loss: 3.9874 - val_loss: 4.2046 - 324ms/epoch - 2ms/step\n", - "Epoch 44/50\n", - "200/200 - 0s - loss: 3.9847 - val_loss: 4.2214 - 323ms/epoch - 2ms/step\n", - "Epoch 45/50\n", - "200/200 - 0s - loss: 3.9833 - val_loss: 4.2228 - 305ms/epoch - 2ms/step\n", - "Epoch 46/50\n", - "200/200 - 0s - loss: 3.9758 - val_loss: 4.4382 - 316ms/epoch - 2ms/step\n", - "Epoch 47/50\n", - "200/200 - 0s - loss: 3.9682 - val_loss: 4.1712 - 295ms/epoch - 1ms/step\n", - "Epoch 48/50\n", - "200/200 - 0s - loss: 3.9963 - val_loss: 4.1989 - 319ms/epoch - 2ms/step\n", - "Epoch 49/50\n", - "200/200 - 0s - loss: 3.9923 - val_loss: 4.1604 - 318ms/epoch - 2ms/step\n", - "Epoch 50/50\n", - "200/200 - 0s - loss: 3.9805 - val_loss: 4.2202 - 333ms/epoch - 2ms/step\n" - ] - } - ] - }, - { - "cell_type": "code", - "source": [ - "plt.plot(history.history['loss'],label='loss')\n", - "plt.plot(history.history['val_loss'],label='val_loss')\n" - ], - "metadata": { - "id": "aS0ROZa402Lo", - "outputId": "fa91ceb9-10ee-4dc1-f1d6-34ade0308e15", - "colab": { - "base_uri": "https://localhost:8080/", - "height": 282 - } - }, - "execution_count": 33, - "outputs": [ - { - "output_type": "execute_result", - "data": { - "text/plain": [ - "[]" - ] - }, - "metadata": {}, - "execution_count": 33 - }, - { - "output_type": "display_data", - "data": { - "text/plain": [ - "
" - ], - "image/png": "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\n" - }, - "metadata": { - "needs_background": "light" - } - } - ] - }, - { - "cell_type": "code", - "source": [ - "prediction_custom = model_custom.predict(X_test)\n", - "r2_score(y_test,prediction_custom.flatten())" - ], - "metadata": { - "id": "fAAqr7VbcWDS", - "outputId": "34a8a602-7eba-4823-9b28-c22e2ae1b59c", - "colab": { - "base_uri": "https://localhost:8080/" - } - }, - "execution_count": 34, - "outputs": [ - { - "output_type": "execute_result", - "data": { - "text/plain": [ - "0.9980862492729278" - ] - }, - "metadata": {}, - "execution_count": 34 - } - ] - } - ] -} \ No newline at end of file From c9334d9709e90935bb19090b000e41101d4c984f Mon Sep 17 00:00:00 2001 From: rohitkg2003 <87852134+rohitkg2003@users.noreply.github.com> Date: Fri, 17 Jun 2022 17:22:47 +0530 Subject: [PATCH 4/5] 200816_A2 --- Assignment 2/200816_A2.ipynb | 565 +++++++++++++++++++++++++++++++++++ 1 file changed, 565 insertions(+) create mode 100644 Assignment 2/200816_A2.ipynb diff --git a/Assignment 2/200816_A2.ipynb b/Assignment 2/200816_A2.ipynb new file mode 100644 index 0000000..e1a426c --- /dev/null +++ b/Assignment 2/200816_A2.ipynb @@ -0,0 +1,565 @@ +{ + "nbformat": 4, + "nbformat_minor": 0, + "metadata": { + "colab": { + "name": "CVusingTF_Assgn2.ipynb", + "provenance": [], + "collapsed_sections": [] + }, + "kernelspec": { + "name": "python3", + "display_name": "Python 3" + }, + "language_info": { + "name": "python" + } + }, + "cells": [ + { + "cell_type": "markdown", + "source": [ + "# Assigment 2: Deep Learning" + ], + "metadata": { + "id": "UxcaEbrCy1g_" + } + }, + { + "cell_type": "markdown", + "source": [ + "## Generate Dataset\n", + "\n", + "This is the same code from Assignment 1" + ], + "metadata": { + "id": "h2JON-_Oy79w" + } + }, + { + "cell_type": "code", + "execution_count": 1, + "metadata": { + "id": "hgpG3WDuypfa" + }, + "outputs": [], + "source": [ + "from sklearn import datasets\n", + "from sklearn.model_selection import train_test_split\n", + "\n", + "# Generate the data\n", + "X, y = datasets.make_regression(n_samples=10000, n_features=5, noise=5, random_state=4)\n", + "\n", + "# Split the data\n", + "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=1234)\n" + ] + }, + { + "cell_type": "markdown", + "source": [ + "## Visualize Dataset\n", + "This is the same code from Assignment 1" + ], + "metadata": { + "id": "r6it-Rm7zD1Y" + } + }, + { + "cell_type": "code", + "source": [ + "import matplotlib.pyplot as plt\n", + "import numpy as np\n", + "for i in range (5):\n", + " plt.scatter(X_train[:,i],y_train)\n", + "\n", + "\n", + "# Your code here" + ], + "metadata": { + "id": "UautPVj1yzaQ", + "colab": { + "base_uri": "https://localhost:8080/", + "height": 265 + }, + "outputId": "75bcc3b3-0559-45e7-ad6f-f12a75b2f08d" + }, + "execution_count": 2, + "outputs": [ + { + "output_type": "display_data", + "data": { + "text/plain": [ + "
" + ], + "image/png": "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\n" + }, + "metadata": { + "needs_background": "light" + } + } + ] + }, + { + "cell_type": "markdown", + "source": [ + "## Model Definition\n", + "\n", + "Using TensorFlow, build a model with the following definition:\n", + "> Input of shape 5 \\\\\n", + "> Dense of shape 5 \\\\\n", + "> Dense of shape 5 \\\\\n", + "> Dense of shape 1 \\\\\n", + "\n", + "Use Mean Square Error Loss and Stochaistic Gradient Descent (SGD) Optimizer\n", + "\n", + "Use Gradient Decay with appropriate parameters" + ], + "metadata": { + "id": "XMXb9lTyzGHE" + } + }, + { + "cell_type": "code", + "source": [ + "import tensorflow as tf\n", + "from tensorflow import keras\n", + "model = keras.Sequential([keras.layers.Dense(5,input_dim=5,activation='relu'),keras.layers.Dense(5,activation='relu'),keras.layers.Dense(1)])\n", + "model.compile(loss='mean_squared_error',optimizer=tf.keras.optimizers.SGD(0.001))\n", + "history = model.fit(X_train,y_train,epochs=50,validation_split=0.2,verbose=2)\n", + "predictions = model.predict(X_test)\n", + "\n", + "\n", + "# Your code here" + ], + "metadata": { + "id": "r32N1xK2ziOs", + "colab": { + "base_uri": "https://localhost:8080/" + }, + "outputId": "e74b01fe-9f46-4562-fdaf-5b8ad24935c1" + }, + "execution_count": 6, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "Epoch 1/50\n", + "200/200 - 1s - loss: 1400.1647 - val_loss: 2141.0627 - 865ms/epoch - 4ms/step\n", + "Epoch 2/50\n", + "200/200 - 0s - loss: 340.9002 - val_loss: 44.8760 - 275ms/epoch - 1ms/step\n", + "Epoch 3/50\n", + "200/200 - 0s - loss: 492.3806 - val_loss: 192.2196 - 289ms/epoch - 1ms/step\n", + "Epoch 4/50\n", + "200/200 - 0s - loss: 147.8546 - val_loss: 525.9345 - 369ms/epoch - 2ms/step\n", + "Epoch 5/50\n", + "200/200 - 0s - loss: 202.5587 - val_loss: 45.8932 - 259ms/epoch - 1ms/step\n", + "Epoch 6/50\n", + "200/200 - 0s - loss: 227.0734 - val_loss: 41.9783 - 270ms/epoch - 1ms/step\n", + "Epoch 7/50\n", + "200/200 - 0s - loss: 159.3960 - val_loss: 59.6942 - 284ms/epoch - 1ms/step\n", + "Epoch 8/50\n", + "200/200 - 0s - loss: 239.3188 - val_loss: 29.9748 - 281ms/epoch - 1ms/step\n", + "Epoch 9/50\n", + "200/200 - 0s - loss: 152.8331 - val_loss: 221.7097 - 298ms/epoch - 1ms/step\n", + "Epoch 10/50\n", + "200/200 - 0s - loss: 338.3758 - val_loss: 64.0810 - 284ms/epoch - 1ms/step\n", + "Epoch 11/50\n", + "200/200 - 0s - loss: 209.4844 - val_loss: 59.8163 - 267ms/epoch - 1ms/step\n", + "Epoch 12/50\n", + "200/200 - 0s - loss: 251.1109 - val_loss: 435.7401 - 262ms/epoch - 1ms/step\n", + "Epoch 13/50\n", + "200/200 - 0s - loss: 622.8074 - val_loss: 39.8785 - 284ms/epoch - 1ms/step\n", + "Epoch 14/50\n", + "200/200 - 0s - loss: 166.6548 - val_loss: 352.9469 - 258ms/epoch - 1ms/step\n", + "Epoch 15/50\n", + "200/200 - 0s - loss: 188.5881 - val_loss: 36.6427 - 275ms/epoch - 1ms/step\n", + "Epoch 16/50\n", + "200/200 - 0s - loss: 178.6596 - val_loss: 62.4603 - 271ms/epoch - 1ms/step\n", + "Epoch 17/50\n", + "200/200 - 0s - loss: 140.6317 - val_loss: 36.7756 - 258ms/epoch - 1ms/step\n", + "Epoch 18/50\n", + "200/200 - 0s - loss: 262.6449 - val_loss: 115.1941 - 284ms/epoch - 1ms/step\n", + "Epoch 19/50\n", + "200/200 - 0s - loss: 174.5533 - val_loss: 50.6086 - 265ms/epoch - 1ms/step\n", + "Epoch 20/50\n", + "200/200 - 0s - loss: 202.2552 - val_loss: 1926.5394 - 279ms/epoch - 1ms/step\n", + "Epoch 21/50\n", + "200/200 - 0s - loss: 229.1364 - val_loss: 124.1915 - 263ms/epoch - 1ms/step\n", + "Epoch 22/50\n", + "200/200 - 0s - loss: 461.1045 - val_loss: 88.1916 - 279ms/epoch - 1ms/step\n", + "Epoch 23/50\n", + "200/200 - 0s - loss: 295.3871 - val_loss: 48.4503 - 262ms/epoch - 1ms/step\n", + "Epoch 24/50\n", + "200/200 - 0s - loss: 95.2892 - val_loss: 51.6104 - 257ms/epoch - 1ms/step\n", + "Epoch 25/50\n", + "200/200 - 0s - loss: 97.4321 - val_loss: 83.4106 - 260ms/epoch - 1ms/step\n", + "Epoch 26/50\n", + "200/200 - 0s - loss: 156.3376 - val_loss: 43.0365 - 290ms/epoch - 1ms/step\n", + "Epoch 27/50\n", + "200/200 - 0s - loss: 382.1672 - val_loss: 33.2760 - 275ms/epoch - 1ms/step\n", + "Epoch 28/50\n", + "200/200 - 0s - loss: 158.5331 - val_loss: 229.5324 - 275ms/epoch - 1ms/step\n", + "Epoch 29/50\n", + "200/200 - 0s - loss: 89.6189 - val_loss: 911.1938 - 266ms/epoch - 1ms/step\n", + "Epoch 30/50\n", + "200/200 - 0s - loss: 149.3119 - val_loss: 808.9080 - 280ms/epoch - 1ms/step\n", + "Epoch 31/50\n", + "200/200 - 0s - loss: 301.7253 - val_loss: 41.8418 - 258ms/epoch - 1ms/step\n", + "Epoch 32/50\n", + "200/200 - 0s - loss: 102.5081 - val_loss: 37.0123 - 273ms/epoch - 1ms/step\n", + "Epoch 33/50\n", + "200/200 - 0s - loss: 130.9274 - val_loss: 163.9801 - 259ms/epoch - 1ms/step\n", + "Epoch 34/50\n", + "200/200 - 0s - loss: 153.3079 - val_loss: 52.8656 - 280ms/epoch - 1ms/step\n", + "Epoch 35/50\n", + "200/200 - 0s - loss: 151.9014 - val_loss: 43.4715 - 284ms/epoch - 1ms/step\n", + "Epoch 36/50\n", + "200/200 - 0s - loss: 168.6933 - val_loss: 32.9337 - 264ms/epoch - 1ms/step\n", + "Epoch 37/50\n", + "200/200 - 0s - loss: 91.0383 - val_loss: 44.8102 - 282ms/epoch - 1ms/step\n", + "Epoch 38/50\n", + "200/200 - 0s - loss: 85.5136 - val_loss: 283.6330 - 266ms/epoch - 1ms/step\n", + "Epoch 39/50\n", + "200/200 - 0s - loss: 147.2607 - val_loss: 513.7488 - 260ms/epoch - 1ms/step\n", + "Epoch 40/50\n", + "200/200 - 0s - loss: 169.6636 - val_loss: 222.6365 - 278ms/epoch - 1ms/step\n", + "Epoch 41/50\n", + "200/200 - 0s - loss: 156.9541 - val_loss: 31.6757 - 272ms/epoch - 1ms/step\n", + "Epoch 42/50\n", + "200/200 - 0s - loss: 231.9851 - val_loss: 77.3350 - 277ms/epoch - 1ms/step\n", + "Epoch 43/50\n", + "200/200 - 0s - loss: 257.5688 - val_loss: 47.2681 - 281ms/epoch - 1ms/step\n", + "Epoch 44/50\n", + "200/200 - 0s - loss: 326.8341 - val_loss: 31.5751 - 264ms/epoch - 1ms/step\n", + "Epoch 45/50\n", + "200/200 - 0s - loss: 94.9101 - val_loss: 70.3932 - 275ms/epoch - 1ms/step\n", + "Epoch 46/50\n", + "200/200 - 0s - loss: 110.4162 - val_loss: 34.9609 - 261ms/epoch - 1ms/step\n", + "Epoch 47/50\n", + "200/200 - 0s - loss: 137.7447 - val_loss: 78.6928 - 275ms/epoch - 1ms/step\n", + "Epoch 48/50\n", + "200/200 - 0s - loss: 75.7320 - val_loss: 1105.6212 - 281ms/epoch - 1ms/step\n", + "Epoch 49/50\n", + "200/200 - 0s - loss: 113.9831 - val_loss: 86.3590 - 273ms/epoch - 1ms/step\n", + "Epoch 50/50\n", + "200/200 - 0s - loss: 121.9195 - val_loss: 33.9616 - 269ms/epoch - 1ms/step\n" + ] + } + ] + }, + { + "cell_type": "markdown", + "source": [ + "## Plot Loss\n", + "\n", + "Using matplotlib visualise how the loss (both validation and training) is changing, use this information to retrain the model with appropriate parameters.
We ideally want the loss to be constant over the last few iterations." + ], + "metadata": { + "id": "jmeP6vt3z0oA" + } + }, + { + "cell_type": "code", + "source": [ + "# Your code here\n", + "plt.plot(history.history['loss'],label='loss')\n", + "plt.plot(history.history['val_loss'],label='val_loss')" + ], + "metadata": { + "id": "RQTNqPHm0mOi", + "colab": { + "base_uri": "https://localhost:8080/", + "height": 282 + }, + "outputId": "8e605b93-8215-487c-8882-a755eafc6241" + }, + "execution_count": 7, + "outputs": [ + { + "output_type": "execute_result", + "data": { + "text/plain": [ + "[]" + ] + }, + "metadata": {}, + "execution_count": 7 + }, + { + "output_type": "display_data", + "data": { + "text/plain": [ + "
" + ], + "image/png": "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\n" + }, + "metadata": { + "needs_background": "light" + } + } + ] + }, + { + "cell_type": "markdown", + "source": [ + "## Evaluation Metrics\n", + "Use the R2 Score function implemented in the first assignment to evaluate the performance of the model." + ], + "metadata": { + "id": "IVrR_vXA7kOt" + } + }, + { + "cell_type": "code", + "source": [ + "# Insert the function for R2 Score\n", + "def r2_score(y_true,y_pred):\n", + " \n", + " y_mean = y_true.mean()\n", + " return 1 - (((y_true-y_pred)**2).mean())/(((y_true-y_mean)**2).mean())\n", + "acuu = r2_score(y_test,predictions.flatten()) \n", + "print('Accuracy :', acuu)\n", + "\n" + ], + "metadata": { + "id": "-lOHpD8-7ggm", + "colab": { + "base_uri": "https://localhost:8080/" + }, + "outputId": "38a20e3b-f988-42ab-f639-25b9f7ee6efa" + }, + "execution_count": 13, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "Accuracy : 0.9976567220172706\n" + ] + } + ] + }, + { + "cell_type": "markdown", + "source": [ + "## Your own custom model\n", + "Build a custom model of your own choice.
\n", + "Describe it in detail in Markdown/Latex in the cell below.
\n", + "Visualise the loss, as before." + ], + "metadata": { + "id": "CHqzF1OU0pBg" + } + }, + { + "cell_type": "markdown", + "source": [ + "Your text here" + ], + "metadata": { + "id": "jF8oTUqq0y0g" + } + }, + { + "cell_type": "code", + "source": [ + "# Your code here\n", + "model_custom = keras.Sequential([keras.layers.Dense(64,input_dim=5,activation='relu'),\n", + " keras.layers.Dense(15,activation='relu'),\n", + " keras.layers.Dense(10,activation='relu'),\n", + " keras.layers.Dense(1)])\n", + "model_custom.compile(optimizer=tf.optimizers.Adam(learning_rate=0.001),\n", + " loss='mean_absolute_error')\n", + "history_custom = model_custom.fit(\n", + " X_train,y_train,\n", + " validation_split =0.2,\n", + " verbose=2,epochs=50\n", + ")" + ], + "metadata": { + "id": "1XOk5hJu0oSQ", + "colab": { + "base_uri": "https://localhost:8080/" + }, + "outputId": "8b428952-6a1c-4143-8034-a50d1b89a255" + }, + "execution_count": 32, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "Epoch 1/50\n", + "200/200 - 1s - loss: 86.9274 - val_loss: 62.6012 - 799ms/epoch - 4ms/step\n", + "Epoch 2/50\n", + "200/200 - 0s - loss: 19.8114 - val_loss: 9.6341 - 335ms/epoch - 2ms/step\n", + "Epoch 3/50\n", + "200/200 - 0s - loss: 8.5663 - val_loss: 8.0135 - 349ms/epoch - 2ms/step\n", + "Epoch 4/50\n", + "200/200 - 0s - loss: 7.0574 - val_loss: 6.5489 - 324ms/epoch - 2ms/step\n", + "Epoch 5/50\n", + "200/200 - 0s - loss: 5.6996 - val_loss: 5.2579 - 324ms/epoch - 2ms/step\n", + "Epoch 6/50\n", + "200/200 - 0s - loss: 4.8941 - val_loss: 4.7478 - 324ms/epoch - 2ms/step\n", + "Epoch 7/50\n", + "200/200 - 0s - loss: 4.5774 - val_loss: 4.4956 - 310ms/epoch - 2ms/step\n", + "Epoch 8/50\n", + "200/200 - 0s - loss: 4.4216 - val_loss: 4.5247 - 332ms/epoch - 2ms/step\n", + "Epoch 9/50\n", + "200/200 - 0s - loss: 4.3259 - val_loss: 4.4404 - 340ms/epoch - 2ms/step\n", + "Epoch 10/50\n", + "200/200 - 0s - loss: 4.2725 - val_loss: 4.3309 - 317ms/epoch - 2ms/step\n", + "Epoch 11/50\n", + "200/200 - 0s - loss: 4.2383 - val_loss: 4.4178 - 323ms/epoch - 2ms/step\n", + "Epoch 12/50\n", + "200/200 - 0s - loss: 4.1996 - val_loss: 4.5615 - 314ms/epoch - 2ms/step\n", + "Epoch 13/50\n", + "200/200 - 0s - loss: 4.2129 - val_loss: 4.5135 - 337ms/epoch - 2ms/step\n", + "Epoch 14/50\n", + "200/200 - 0s - loss: 4.1564 - val_loss: 4.2678 - 327ms/epoch - 2ms/step\n", + "Epoch 15/50\n", + "200/200 - 0s - loss: 4.1129 - val_loss: 4.3327 - 348ms/epoch - 2ms/step\n", + "Epoch 16/50\n", + "200/200 - 0s - loss: 4.1318 - val_loss: 4.2996 - 416ms/epoch - 2ms/step\n", + "Epoch 17/50\n", + "200/200 - 1s - loss: 4.1150 - val_loss: 4.5790 - 541ms/epoch - 3ms/step\n", + "Epoch 18/50\n", + "200/200 - 1s - loss: 4.0718 - val_loss: 4.3515 - 563ms/epoch - 3ms/step\n", + "Epoch 19/50\n", + "200/200 - 1s - loss: 4.1166 - val_loss: 4.1774 - 562ms/epoch - 3ms/step\n", + "Epoch 20/50\n", + "200/200 - 0s - loss: 4.0774 - val_loss: 4.5272 - 363ms/epoch - 2ms/step\n", + "Epoch 21/50\n", + "200/200 - 0s - loss: 4.0964 - val_loss: 4.3456 - 333ms/epoch - 2ms/step\n", + "Epoch 22/50\n", + "200/200 - 0s - loss: 4.0463 - val_loss: 4.2782 - 317ms/epoch - 2ms/step\n", + "Epoch 23/50\n", + "200/200 - 0s - loss: 4.0313 - val_loss: 4.1738 - 307ms/epoch - 2ms/step\n", + "Epoch 24/50\n", + "200/200 - 0s - loss: 4.0393 - val_loss: 4.3118 - 324ms/epoch - 2ms/step\n", + "Epoch 25/50\n", + "200/200 - 0s - loss: 4.0653 - val_loss: 4.2462 - 330ms/epoch - 2ms/step\n", + "Epoch 26/50\n", + "200/200 - 0s - loss: 4.0408 - val_loss: 4.2241 - 312ms/epoch - 2ms/step\n", + "Epoch 27/50\n", + "200/200 - 0s - loss: 4.0641 - val_loss: 4.1905 - 321ms/epoch - 2ms/step\n", + "Epoch 28/50\n", + "200/200 - 0s - loss: 4.0306 - val_loss: 4.2208 - 322ms/epoch - 2ms/step\n", + "Epoch 29/50\n", + "200/200 - 0s - loss: 4.0128 - val_loss: 4.4978 - 316ms/epoch - 2ms/step\n", + "Epoch 30/50\n", + "200/200 - 0s - loss: 4.0218 - val_loss: 4.1599 - 328ms/epoch - 2ms/step\n", + "Epoch 31/50\n", + "200/200 - 0s - loss: 4.0020 - val_loss: 4.1927 - 320ms/epoch - 2ms/step\n", + "Epoch 32/50\n", + "200/200 - 0s - loss: 4.0253 - val_loss: 4.1439 - 327ms/epoch - 2ms/step\n", + "Epoch 33/50\n", + "200/200 - 0s - loss: 4.0297 - val_loss: 4.2742 - 315ms/epoch - 2ms/step\n", + "Epoch 34/50\n", + "200/200 - 0s - loss: 4.0132 - val_loss: 4.3917 - 313ms/epoch - 2ms/step\n", + "Epoch 35/50\n", + "200/200 - 0s - loss: 3.9896 - val_loss: 4.2615 - 322ms/epoch - 2ms/step\n", + "Epoch 36/50\n", + "200/200 - 0s - loss: 3.9916 - val_loss: 4.1592 - 333ms/epoch - 2ms/step\n", + "Epoch 37/50\n", + "200/200 - 0s - loss: 4.0609 - val_loss: 4.1600 - 332ms/epoch - 2ms/step\n", + "Epoch 38/50\n", + "200/200 - 0s - loss: 4.0511 - val_loss: 4.3256 - 317ms/epoch - 2ms/step\n", + "Epoch 39/50\n", + "200/200 - 0s - loss: 4.0149 - val_loss: 4.2721 - 337ms/epoch - 2ms/step\n", + "Epoch 40/50\n", + "200/200 - 0s - loss: 4.0123 - val_loss: 4.2894 - 335ms/epoch - 2ms/step\n", + "Epoch 41/50\n", + "200/200 - 0s - loss: 3.9865 - val_loss: 4.2675 - 332ms/epoch - 2ms/step\n", + "Epoch 42/50\n", + "200/200 - 0s - loss: 3.9872 - val_loss: 4.1983 - 317ms/epoch - 2ms/step\n", + "Epoch 43/50\n", + "200/200 - 0s - loss: 3.9874 - val_loss: 4.2046 - 324ms/epoch - 2ms/step\n", + "Epoch 44/50\n", + "200/200 - 0s - loss: 3.9847 - val_loss: 4.2214 - 323ms/epoch - 2ms/step\n", + "Epoch 45/50\n", + "200/200 - 0s - loss: 3.9833 - val_loss: 4.2228 - 305ms/epoch - 2ms/step\n", + "Epoch 46/50\n", + "200/200 - 0s - loss: 3.9758 - val_loss: 4.4382 - 316ms/epoch - 2ms/step\n", + "Epoch 47/50\n", + "200/200 - 0s - loss: 3.9682 - val_loss: 4.1712 - 295ms/epoch - 1ms/step\n", + "Epoch 48/50\n", + "200/200 - 0s - loss: 3.9963 - val_loss: 4.1989 - 319ms/epoch - 2ms/step\n", + "Epoch 49/50\n", + "200/200 - 0s - loss: 3.9923 - val_loss: 4.1604 - 318ms/epoch - 2ms/step\n", + "Epoch 50/50\n", + "200/200 - 0s - loss: 3.9805 - val_loss: 4.2202 - 333ms/epoch - 2ms/step\n" + ] + } + ] + }, + { + "cell_type": "code", + "source": [ + "plt.plot(history.history['loss'],label='loss')\n", + "plt.plot(history.history['val_loss'],label='val_loss')\n" + ], + "metadata": { + "id": "aS0ROZa402Lo", + "colab": { + "base_uri": "https://localhost:8080/", + "height": 282 + }, + "outputId": "fa91ceb9-10ee-4dc1-f1d6-34ade0308e15" + }, + "execution_count": 33, + "outputs": [ + { + "output_type": "execute_result", + "data": { + "text/plain": [ + "[]" + ] + }, + "metadata": {}, + "execution_count": 33 + }, + { + "output_type": "display_data", + "data": { + "text/plain": [ + "
" + ], + "image/png": "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\n" + }, + "metadata": { + "needs_background": "light" + } + } + ] + }, + { + "cell_type": "code", + "source": [ + "prediction_custom = model_custom.predict(X_test)\n", + "r2_score(y_test,prediction_custom.flatten())" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "fAAqr7VbcWDS", + "outputId": "34a8a602-7eba-4823-9b28-c22e2ae1b59c" + }, + "execution_count": 34, + "outputs": [ + { + "output_type": "execute_result", + "data": { + "text/plain": [ + "0.9980862492729278" + ] + }, + "metadata": {}, + "execution_count": 34 + } + ] + } + ] +} \ No newline at end of file From b61beae7ba1011d53a5dcb81b68c6591d2ee3844 Mon Sep 17 00:00:00 2001 From: rohitkg2003 <87852134+rohitkg2003@users.noreply.github.com> Date: Wed, 13 Jul 2022 12:54:17 +0530 Subject: [PATCH 5/5] 200816_A3 --- Assignment 3/200816_A3.ipynb | 1 + 1 file changed, 1 insertion(+) create mode 100644 Assignment 3/200816_A3.ipynb diff --git a/Assignment 3/200816_A3.ipynb b/Assignment 3/200816_A3.ipynb new file mode 100644 index 0000000..d977d41 --- /dev/null +++ b/Assignment 3/200816_A3.ipynb @@ -0,0 +1 @@ +{"nbformat":4,"nbformat_minor":0,"metadata":{"colab":{"name":"Copy of CV_with_TF-Assignment-3.ipynb","provenance":[{"file_id":"1asGptVW1kSOD-sm44G3PJr-Ad9lPwQFR","timestamp":1657696905259},{"file_id":"1D6ydyPPCMxckA2UNfQAfoDNQMednmPXO","timestamp":1655269145670},{"file_id":"1SOXxLRZADUvtLiTygZYTHBTZP2l0W_jT","timestamp":1655267663630},{"file_id":"1nTfv0Eyv59_cvAq13soX2DgTp0t4G6M3","timestamp":1655196024245}]},"kernelspec":{"name":"python3","display_name":"Python 3"},"language_info":{"name":"python"},"accelerator":"GPU","gpuClass":"standard"},"cells":[{"cell_type":"markdown","source":["# Assignment 3\n","\n"," In this Assignment, we will use CNN to classify digits. \n","The `MNIST` database is a large database of handwritten digits that is commonly used for training various image processing systems.\n","\n"],"metadata":{"id":"VGHh_5UYzKpV"}},{"cell_type":"markdown","source":["## Importing TensorFlow"],"metadata":{"id":"JnsMbCPNzPAr"}},{"cell_type":"code","execution_count":21,"metadata":{"id":"HRLTw3cMwvi7","executionInfo":{"status":"ok","timestamp":1657696485418,"user_tz":-330,"elapsed":7,"user":{"displayName":"Rohit Kumar gupta","userId":"03710792288665421186"}}},"outputs":[],"source":["import tensorflow as tf"]},{"cell_type":"markdown","source":["## Get the dataset"],"metadata":{"id":"6Ji7HGpgzSPi"}},{"cell_type":"code","source":["# Import the dataset\n","\n","(x_train, y_train), (x_test, y_test) = tf.keras.datasets.mnist.load_data()"],"metadata":{"id":"oEW3KDEvzIHL","executionInfo":{"status":"ok","timestamp":1657696486164,"user_tz":-330,"elapsed":4,"user":{"displayName":"Rohit Kumar gupta","userId":"03710792288665421186"}}},"execution_count":22,"outputs":[]},{"cell_type":"code","source":["# Split the dataset\n","\n","from sklearn.model_selection import train_test_split\n","X_val,X_test,Y_val,Y_test=train_test_split(x_test,y_test,test_size=0.2)"],"metadata":{"id":"F_sRU9dx_mYQ","executionInfo":{"status":"ok","timestamp":1657696546445,"user_tz":-330,"elapsed":492,"user":{"displayName":"Rohit Kumar gupta","userId":"03710792288665421186"}}},"execution_count":30,"outputs":[]},{"cell_type":"markdown","source":["## Visualize the dataset\n","Print some images with labels."],"metadata":{"id":"EVpQheoVqoEG"}},{"cell_type":"code","source":["# Pre processing \n","import numpy as np\n","\n","def process(dataset):\n"," return np.expand_dims((dataset.astype('float32')/255.),axis=3)\n","\n","x_train_norm = process(x_train)\n","X_val_norm = process(X_val)\n","X_test_norm = process(X_test)"],"metadata":{"id":"yF1Nj63Bz9m7","executionInfo":{"status":"ok","timestamp":1657696549452,"user_tz":-330,"elapsed":576,"user":{"displayName":"Rohit Kumar gupta","userId":"03710792288665421186"}}},"execution_count":31,"outputs":[]},{"cell_type":"markdown","source":["Plot statistics of the training and testing dataset \n","(`x axis`: digits, `y axis`: number of samples corresponding to the digits)"],"metadata":{"id":"Rx8muKSIrKhe"}},{"cell_type":"code","source":["import numpy as np\n","\n","# Your code\n","digits = np.arange(10)\n","\n","plt.figure(figsize=(10,6))\n","\n","n_digits_train = np.zeros(10)\n","for i in y_train:\n"," n_digits_train[i]+=1\n","\n","plt.bar(digits,n_digits_train) \n","\n","n_digits_test = np.zeros(10)\n","for i in y_test:\n"," n_digits_test[i]+=1\n","\n","plt.bar(digits,n_digits_test) \n","\n","plt.legend([\"Training dataset\", \"Testing dataset\"])\n","# plt.grid(True)"],"metadata":{"id":"37kehTG_6Pi4","executionInfo":{"status":"ok","timestamp":1657696553253,"user_tz":-330,"elapsed":512,"user":{"displayName":"Rohit Kumar gupta","userId":"03710792288665421186"}},"outputId":"47aa6e6f-3a24-4001-f891-2d3ddc6f7f04","colab":{"base_uri":"https://localhost:8080/","height":391}},"execution_count":32,"outputs":[{"output_type":"execute_result","data":{"text/plain":[""]},"metadata":{},"execution_count":32},{"output_type":"display_data","data":{"text/plain":["
"],"image/png":"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\n"},"metadata":{"needs_background":"light"}}]},{"cell_type":"code","source":["# model building\n","\n","# You are supposed to look at some CNN architectures and add convolutional layers along with MaxPooling, specifying the kernel size, pooling size, activation \n","\n","model = tf.keras.models.Sequential([\n"," tf.keras.layers.Conv2D(32,(3,3), input_shape=(28,28,1)),\n"," tf.keras.layers.Activation('relu'),\n"," tf.keras.layers.MaxPool2D(pool_size=(2,2)),\n"," tf.keras.layers.Flatten(),\n"," tf.keras.layers.Dense(10, activation='softmax')\n","])\n","\n","model.summary()"],"metadata":{"id":"f-bteMURYaJf","executionInfo":{"status":"ok","timestamp":1657696557836,"user_tz":-330,"elapsed":515,"user":{"displayName":"Rohit Kumar gupta","userId":"03710792288665421186"}},"outputId":"aad65636-bfe5-4857-9505-e148586a72b8","colab":{"base_uri":"https://localhost:8080/"}},"execution_count":33,"outputs":[{"output_type":"stream","name":"stdout","text":["Model: \"sequential_3\"\n","_________________________________________________________________\n"," Layer (type) Output Shape Param # \n","=================================================================\n"," conv2d_1 (Conv2D) (None, 26, 26, 32) 320 \n"," \n"," activation_1 (Activation) (None, 26, 26, 32) 0 \n"," \n"," max_pooling2d_1 (MaxPooling (None, 13, 13, 32) 0 \n"," 2D) \n"," \n"," flatten_3 (Flatten) (None, 5408) 0 \n"," \n"," dense_7 (Dense) (None, 10) 54090 \n"," \n","=================================================================\n","Total params: 54,410\n","Trainable params: 54,410\n","Non-trainable params: 0\n","_________________________________________________________________\n"]}]},{"cell_type":"code","source":["# Compile the model (add optimizers and metrics)\n","model.compile(\n"," optimizer=tf.keras.optimizers.Adam(0.001),\n"," loss=tf.keras.losses.SparseCategoricalCrossentropy(),\n"," metrics=[tf.keras.metrics.SparseCategoricalAccuracy()],\n",")\n","\n","# Fit the model on the training data (specify validation_split, read about validation if new to you)\n","\n","model.fit(\n"," x_train_norm,\n"," y_train,\n"," epochs=10,\n"," validation_data=(X_val_norm,Y_val),\n",")"],"metadata":{"id":"dvoiYzsUYmFb","executionInfo":{"status":"ok","timestamp":1657696644079,"user_tz":-330,"elapsed":82759,"user":{"displayName":"Rohit Kumar gupta","userId":"03710792288665421186"}},"outputId":"831bf75c-a8bc-42dd-bad1-bb0a729a0fb3","colab":{"base_uri":"https://localhost:8080/"}},"execution_count":34,"outputs":[{"output_type":"stream","name":"stdout","text":["Epoch 1/10\n","1875/1875 [==============================] - 14s 3ms/step - loss: 0.2077 - sparse_categorical_accuracy: 0.9411 - val_loss: 0.0826 - val_sparse_categorical_accuracy: 0.9755\n","Epoch 2/10\n","1875/1875 [==============================] - 5s 3ms/step - loss: 0.0788 - sparse_categorical_accuracy: 0.9771 - val_loss: 0.0719 - val_sparse_categorical_accuracy: 0.9784\n","Epoch 3/10\n","1875/1875 [==============================] - 5s 3ms/step - loss: 0.0602 - sparse_categorical_accuracy: 0.9821 - val_loss: 0.0591 - val_sparse_categorical_accuracy: 0.9812\n","Epoch 4/10\n","1875/1875 [==============================] - 5s 3ms/step - loss: 0.0495 - sparse_categorical_accuracy: 0.9851 - val_loss: 0.0574 - val_sparse_categorical_accuracy: 0.9799\n","Epoch 5/10\n","1875/1875 [==============================] - 5s 3ms/step - loss: 0.0425 - sparse_categorical_accuracy: 0.9872 - val_loss: 0.0533 - val_sparse_categorical_accuracy: 0.9831\n","Epoch 6/10\n","1875/1875 [==============================] - 5s 3ms/step - loss: 0.0365 - sparse_categorical_accuracy: 0.9893 - val_loss: 0.0585 - val_sparse_categorical_accuracy: 0.9816\n","Epoch 7/10\n","1875/1875 [==============================] - 5s 3ms/step - loss: 0.0303 - sparse_categorical_accuracy: 0.9911 - val_loss: 0.0586 - val_sparse_categorical_accuracy: 0.9825\n","Epoch 8/10\n","1875/1875 [==============================] - 5s 3ms/step - loss: 0.0262 - sparse_categorical_accuracy: 0.9921 - val_loss: 0.0621 - val_sparse_categorical_accuracy: 0.9822\n","Epoch 9/10\n","1875/1875 [==============================] - 5s 3ms/step - loss: 0.0228 - sparse_categorical_accuracy: 0.9932 - val_loss: 0.0552 - val_sparse_categorical_accuracy: 0.9829\n","Epoch 10/10\n","1875/1875 [==============================] - 5s 3ms/step - loss: 0.0192 - sparse_categorical_accuracy: 0.9941 - val_loss: 0.0556 - val_sparse_categorical_accuracy: 0.9844\n"]},{"output_type":"execute_result","data":{"text/plain":[""]},"metadata":{},"execution_count":34}]},{"cell_type":"markdown","source":["## Model"],"metadata":{"id":"kWlpCWdAr8d3"}},{"cell_type":"code","source":["# Your code\n","p = model.predict(X_test_norm)\n","pred = np.argmax(p,axis=1)\n","\n","fig, axis = plt.subplots(1,15,figsize=(25,5))\n","\n","\n","for i in range(0,15):\n"," axis[i].imshow(X_test[i], cmap='Greys')\n"," \n","for i, ax in enumerate(axis.flat):\n"," ax.set(xlabel= \"Pred: {}\".format(pred[i]))"],"metadata":{"id":"1L07EyQ0Yion","executionInfo":{"status":"ok","timestamp":1657696645853,"user_tz":-330,"elapsed":1787,"user":{"displayName":"Rohit Kumar gupta","userId":"03710792288665421186"}},"outputId":"81dbe438-ef70-46eb-dce2-1967f8123c1c","colab":{"base_uri":"https://localhost:8080/","height":142}},"execution_count":35,"outputs":[{"output_type":"display_data","data":{"text/plain":["
"],"image/png":"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\n"},"metadata":{"needs_background":"light"}}]},{"cell_type":"code","source":["from sklearn.metrics import r2_score\n","\n","accu = r2_score(Y_test,pred)\n","print(\"R2 score: {:.2f}%\".format(accu*100))"],"metadata":{"id":"xv8xM5sPZAwV","executionInfo":{"status":"ok","timestamp":1657696650478,"user_tz":-330,"elapsed":484,"user":{"displayName":"Rohit Kumar gupta","userId":"03710792288665421186"}},"outputId":"824a0f11-3a13-46ab-a445-0e172b186084","colab":{"base_uri":"https://localhost:8080/"}},"execution_count":36,"outputs":[{"output_type":"stream","name":"stdout","text":["R2 score: 95.79%\n"]}]},{"cell_type":"markdown","source":["## Predict some images\n","Print the image along with its label (true value) and predicted value."],"metadata":{"id":"ml1Kna_DuJrL"}},{"cell_type":"code","source":["loss, acc = model.evaluate(X_test_norm,Y_test)\n","print(\"Loss: {:.3f}, Accuracy: {:.2f}%\".format(loss,acc*100))"],"metadata":{"id":"qioZul7_uiYq","executionInfo":{"status":"ok","timestamp":1657696654107,"user_tz":-330,"elapsed":833,"user":{"displayName":"Rohit Kumar gupta","userId":"03710792288665421186"}},"outputId":"58e64d0f-6b99-4a2d-8a78-102e5170c548","colab":{"base_uri":"https://localhost:8080/"}},"execution_count":37,"outputs":[{"output_type":"stream","name":"stdout","text":["63/63 [==============================] - 0s 3ms/step - loss: 0.0572 - sparse_categorical_accuracy: 0.9845\n","Loss: 0.057, Accuracy: 98.45%\n"]}]}]} \ No newline at end of file