{ "cells": [ { "cell_type": "code", "execution_count": 1, "id": "d33cf431-81c3-4b25-a5f5-f6c8ee07d007", "metadata": {}, "outputs": [], "source": [ "import tensorflow\n", "from tensorflow import keras \n", "from tensorflow.keras import Sequential\n", "from tensorflow.keras.layers import Dense, Flatten" ] }, { "cell_type": "raw", "id": "6070758c-585d-4642-a4a7-7ed00a8692cc", "metadata": {}, "source": [] }, { "cell_type": "code", "execution_count": 2, "id": "15acacc2-4304-4ef6-9fd1-fad67b242952", "metadata": {}, "outputs": [], "source": [ "(x_train, y_train),(x_test, y_test) = keras.datasets.mnist.load_data()" ] }, { "cell_type": "code", "execution_count": 3, "id": "c4518e50-b7de-4dcd-aa6a-b04bcc5de863", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "(60000, 28, 28)" ] }, "execution_count": 3, "metadata": {}, "output_type": "execute_result" } ], "source": [ "x_train.shape" ] }, { "cell_type": "code", "execution_count": 4, "id": "dd370503-c2af-4988-871b-dc5cab5d2f01", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "array([[ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n", " 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n", " 0, 0],\n", " [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n", " 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n", " 0, 0],\n", " [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n", " 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n", " 0, 0],\n", " [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n", " 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n", " 0, 0],\n", " [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n", " 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n", " 0, 0],\n", " [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 3,\n", " 18, 18, 18, 126, 136, 175, 26, 166, 255, 247, 127, 0, 0,\n", " 0, 0],\n", " [ 0, 0, 0, 0, 0, 0, 0, 0, 30, 36, 94, 154, 170,\n", " 253, 253, 253, 253, 253, 225, 172, 253, 242, 195, 64, 0, 0,\n", " 0, 0],\n", " [ 0, 0, 0, 0, 0, 0, 0, 49, 238, 253, 253, 253, 253,\n", " 253, 253, 253, 253, 251, 93, 82, 82, 56, 39, 0, 0, 0,\n", " 0, 0],\n", " [ 0, 0, 0, 0, 0, 0, 0, 18, 219, 253, 253, 253, 253,\n", " 253, 198, 182, 247, 241, 0, 0, 0, 0, 0, 0, 0, 0,\n", " 0, 0],\n", " [ 0, 0, 0, 0, 0, 0, 0, 0, 80, 156, 107, 253, 253,\n", " 205, 11, 0, 43, 154, 0, 0, 0, 0, 0, 0, 0, 0,\n", " 0, 0],\n", " [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 14, 1, 154, 253,\n", " 90, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n", " 0, 0],\n", " [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 139, 253,\n", " 190, 2, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n", " 0, 0],\n", " [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 11, 190,\n", " 253, 70, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n", " 0, 0],\n", " [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 35,\n", " 241, 225, 160, 108, 1, 0, 0, 0, 0, 0, 0, 0, 0,\n", " 0, 0],\n", " [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n", " 81, 240, 253, 253, 119, 25, 0, 0, 0, 0, 0, 0, 0,\n", " 0, 0],\n", " [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n", " 0, 45, 186, 253, 253, 150, 27, 0, 0, 0, 0, 0, 0,\n", " 0, 0],\n", " [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n", " 0, 0, 16, 93, 252, 253, 187, 0, 0, 0, 0, 0, 0,\n", " 0, 0],\n", " [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n", " 0, 0, 0, 0, 249, 253, 249, 64, 0, 0, 0, 0, 0,\n", " 0, 0],\n", " [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n", " 0, 46, 130, 183, 253, 253, 207, 2, 0, 0, 0, 0, 0,\n", " 0, 0],\n", " [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 39,\n", " 148, 229, 253, 253, 253, 250, 182, 0, 0, 0, 0, 0, 0,\n", " 0, 0],\n", " [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 24, 114, 221,\n", " 253, 253, 253, 253, 201, 78, 0, 0, 0, 0, 0, 0, 0,\n", " 0, 0],\n", " [ 0, 0, 0, 0, 0, 0, 0, 0, 23, 66, 213, 253, 253,\n", " 253, 253, 198, 81, 2, 0, 0, 0, 0, 0, 0, 0, 0,\n", " 0, 0],\n", " [ 0, 0, 0, 0, 0, 0, 18, 171, 219, 253, 253, 253, 253,\n", " 195, 80, 9, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n", " 0, 0],\n", " [ 0, 0, 0, 0, 55, 172, 226, 253, 253, 253, 253, 244, 133,\n", " 11, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n", " 0, 0],\n", " [ 0, 0, 0, 0, 136, 253, 253, 253, 212, 135, 132, 16, 0,\n", " 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n", " 0, 0],\n", " [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n", " 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n", " 0, 0],\n", " [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n", " 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n", " 0, 0],\n", " [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n", " 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n", " 0, 0]], dtype=uint8)" ] }, "execution_count": 4, "metadata": {}, "output_type": "execute_result" } ], "source": [ "x_train[0]" ] }, { "cell_type": "code", "execution_count": 5, "id": "fb232de3-23cd-400e-bc3e-2e66face68b8", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "(10000, 28, 28)" ] }, "execution_count": 5, "metadata": {}, "output_type": "execute_result" } ], "source": [ "x_test.shape" ] }, { "cell_type": "code", "execution_count": 6, "id": "80b07cea-bf4a-403f-8e7a-9b679f6f3e5a", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "array([[ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n", " 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n", " 0, 0],\n", " [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n", " 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n", " 0, 0],\n", " [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n", " 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n", " 0, 0],\n", " [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n", " 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n", " 0, 0],\n", " [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n", " 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n", " 0, 0],\n", " [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n", " 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n", " 0, 0],\n", " [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n", " 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n", " 0, 0],\n", " [ 0, 0, 0, 0, 0, 0, 84, 185, 159, 151, 60, 36, 0,\n", " 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n", " 0, 0],\n", " [ 0, 0, 0, 0, 0, 0, 222, 254, 254, 254, 254, 241, 198,\n", " 198, 198, 198, 198, 198, 198, 198, 170, 52, 0, 0, 0, 0,\n", " 0, 0],\n", " [ 0, 0, 0, 0, 0, 0, 67, 114, 72, 114, 163, 227, 254,\n", " 225, 254, 254, 254, 250, 229, 254, 254, 140, 0, 0, 0, 0,\n", " 0, 0],\n", " [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 17, 66,\n", " 14, 67, 67, 67, 59, 21, 236, 254, 106, 0, 0, 0, 0,\n", " 0, 0],\n", " [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n", " 0, 0, 0, 0, 0, 83, 253, 209, 18, 0, 0, 0, 0,\n", " 0, 0],\n", " [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n", " 0, 0, 0, 0, 22, 233, 255, 83, 0, 0, 0, 0, 0,\n", " 0, 0],\n", " [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n", " 0, 0, 0, 0, 129, 254, 238, 44, 0, 0, 0, 0, 0,\n", " 0, 0],\n", " [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n", " 0, 0, 0, 59, 249, 254, 62, 0, 0, 0, 0, 0, 0,\n", " 0, 0],\n", " [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n", " 0, 0, 0, 133, 254, 187, 5, 0, 0, 0, 0, 0, 0,\n", " 0, 0],\n", " [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n", " 0, 0, 9, 205, 248, 58, 0, 0, 0, 0, 0, 0, 0,\n", " 0, 0],\n", " [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n", " 0, 0, 126, 254, 182, 0, 0, 0, 0, 0, 0, 0, 0,\n", " 0, 0],\n", " [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n", " 0, 75, 251, 240, 57, 0, 0, 0, 0, 0, 0, 0, 0,\n", " 0, 0],\n", " [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n", " 19, 221, 254, 166, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n", " 0, 0],\n", " [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 3,\n", " 203, 254, 219, 35, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n", " 0, 0],\n", " [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 38,\n", " 254, 254, 77, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n", " 0, 0],\n", " [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 31, 224,\n", " 254, 115, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n", " 0, 0],\n", " [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 133, 254,\n", " 254, 52, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n", " 0, 0],\n", " [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 61, 242, 254,\n", " 254, 52, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n", " 0, 0],\n", " [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 121, 254, 254,\n", " 219, 40, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n", " 0, 0],\n", " [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 121, 254, 207,\n", " 18, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n", " 0, 0],\n", " [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n", " 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n", " 0, 0]], dtype=uint8)" ] }, "execution_count": 6, "metadata": {}, "output_type": "execute_result" } ], "source": [ "x_test[0]" ] }, { "cell_type": "code", "execution_count": 7, "id": "dc96ccf4-034b-4e1c-85ba-5f9958184b28", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "array([[ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n", " 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n", " 0, 0],\n", " [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n", " 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n", " 0, 0],\n", " [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n", " 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n", " 0, 0],\n", " [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n", " 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n", " 0, 0],\n", " [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n", " 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n", " 0, 0],\n", " [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n", " 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n", " 0, 0],\n", " [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n", " 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n", " 0, 0],\n", " [ 0, 0, 0, 0, 0, 0, 84, 185, 159, 151, 60, 36, 0,\n", " 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n", " 0, 0],\n", " [ 0, 0, 0, 0, 0, 0, 222, 254, 254, 254, 254, 241, 198,\n", " 198, 198, 198, 198, 198, 198, 198, 170, 52, 0, 0, 0, 0,\n", " 0, 0],\n", " [ 0, 0, 0, 0, 0, 0, 67, 114, 72, 114, 163, 227, 254,\n", " 225, 254, 254, 254, 250, 229, 254, 254, 140, 0, 0, 0, 0,\n", " 0, 0],\n", " [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 17, 66,\n", " 14, 67, 67, 67, 59, 21, 236, 254, 106, 0, 0, 0, 0,\n", " 0, 0],\n", " [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n", " 0, 0, 0, 0, 0, 83, 253, 209, 18, 0, 0, 0, 0,\n", " 0, 0],\n", " [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n", " 0, 0, 0, 0, 22, 233, 255, 83, 0, 0, 0, 0, 0,\n", " 0, 0],\n", " [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n", " 0, 0, 0, 0, 129, 254, 238, 44, 0, 0, 0, 0, 0,\n", " 0, 0],\n", " [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n", " 0, 0, 0, 59, 249, 254, 62, 0, 0, 0, 0, 0, 0,\n", " 0, 0],\n", " [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n", " 0, 0, 0, 133, 254, 187, 5, 0, 0, 0, 0, 0, 0,\n", " 0, 0],\n", " [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n", " 0, 0, 9, 205, 248, 58, 0, 0, 0, 0, 0, 0, 0,\n", " 0, 0],\n", " [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n", " 0, 0, 126, 254, 182, 0, 0, 0, 0, 0, 0, 0, 0,\n", " 0, 0],\n", " [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n", " 0, 75, 251, 240, 57, 0, 0, 0, 0, 0, 0, 0, 0,\n", " 0, 0],\n", " [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n", " 19, 221, 254, 166, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n", " 0, 0],\n", " [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 3,\n", " 203, 254, 219, 35, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n", " 0, 0],\n", " [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 38,\n", " 254, 254, 77, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n", " 0, 0],\n", " [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 31, 224,\n", " 254, 115, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n", " 0, 0],\n", " [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 133, 254,\n", " 254, 52, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n", " 0, 0],\n", " [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 61, 242, 254,\n", " 254, 52, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n", " 0, 0],\n", " [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 121, 254, 254,\n", " 219, 40, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n", " 0, 0],\n", " [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 121, 254, 207,\n", " 18, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n", " 0, 0],\n", " [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n", " 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n", " 0, 0]], dtype=uint8)" ] }, "execution_count": 7, "metadata": {}, "output_type": "execute_result" } ], "source": [ "x_test[0]" ] }, { "cell_type": "code", "execution_count": 8, "id": "de0c49ca-1de8-4e35-9c20-bdfda733374e", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "array([5, 0, 4, ..., 5, 6, 8], dtype=uint8)" ] }, "execution_count": 8, "metadata": {}, "output_type": "execute_result" } ], "source": [ "y_train" ] }, { "cell_type": "code", "execution_count": 9, "id": "ea8eb490-2fcd-4aee-9d86-25b579510b1c", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "" ] }, "execution_count": 9, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "iVBORw0KGgoAAAANSUhEUgAAAaEAAAGdCAYAAAC7EMwUAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjguNCwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8fJSN1AAAACXBIWXMAAA9hAAAPYQGoP6dpAAAa9klEQVR4nO3df3DU953f8deaH2vgVnunYmlXQVZUB2oPoqQBwo/DIGhQ0Y0ZY5wctm8ykCYe/xDcUOH6gukUXSaHfOTMkIts0nhyGCYQmNxgTAtnrBxI2INxZQ7HlLhEPkRQDskqstkVMl6Q+PQPytYLWOSz3uWtlZ6PmZ1Bu9833w9ff+2nv+zqq4BzzgkAAAO3WS8AADB4ESEAgBkiBAAwQ4QAAGaIEADADBECAJghQgAAM0QIAGBmqPUCrnX58mWdOXNGoVBIgUDAejkAAE/OOXV1damoqEi33db3tU6/i9CZM2dUXFxsvQwAwOfU2tqqMWPG9LlNv4tQKBSSJM3Un2iohhmvBgDgq0eX9Ib2Jv973pesReiFF17QD37wA7W1tWn8+PHasGGD7r333pvOXf0ruKEapqEBIgQAOef/3ZH093lLJSsfTNixY4dWrFih1atX6+jRo7r33ntVWVmp06dPZ2N3AIAclZUIrV+/Xt/+9rf1ne98R/fcc482bNig4uJibdy4MRu7AwDkqIxH6OLFizpy5IgqKipSnq+oqNChQ4eu2z6RSCgej6c8AACDQ8YjdPbsWfX29qqwsDDl+cLCQrW3t1+3fW1trcLhcPLBJ+MAYPDI2jerXvuGlHPuhm9SrVq1SrFYLPlobW3N1pIAAP1Mxj8dN3r0aA0ZMuS6q56Ojo7rro4kKRgMKhgMZnoZAIAckPEroeHDh2vSpEmqr69Peb6+vl4zZszI9O4AADksK98nVF1drW9+85uaPHmypk+frp/85Cc6ffq0Hn/88WzsDgCQo7ISocWLF6uzs1Pf+9731NbWprKyMu3du1clJSXZ2B0AIEcFnHPOehGfFo/HFQ6HVa77uWMCAOSgHndJDXpFsVhMeXl5fW7Lj3IAAJghQgAAM0QIAGCGCAEAzBAhAIAZIgQAMEOEAABmiBAAwAwRAgCYIUIAADNECABghggBAMwQIQCAGSIEADBDhAAAZogQAMAMEQIAmCFCAAAzRAgAYIYIAQDMECEAgBkiBAAwQ4QAAGaIEADADBECAJghQgAAM0QIAGCGCAEAzBAhAIAZIgQAMEOEAABmiBAAwAwRAgCYIUIAADNECABghggBAMwQIQCAGSIEADBDhAAAZogQAMAMEQIAmCFCAAAzRAgAYIYIAQDMECEAgBkiBAAwQ4QAAGaIEADADBECAJghQgAAM0QIAGCGCAEAzAy1XgDQnwSG+v8rMeSO0VlYSWaceOqLac31jrzsPVNyV4f3zMgnA94z7euHe8/80+Qd3jOSdLa323tm6i9Wes98qfqw98xAwZUQAMAMEQIAmMl4hGpqahQIBFIekUgk07sBAAwAWXlPaPz48frlL3+Z/HrIkCHZ2A0AIMdlJUJDhw7l6gcAcFNZeU+oublZRUVFKi0t1UMPPaSTJ09+5raJRELxeDzlAQAYHDIeoalTp2rLli3at2+fXnzxRbW3t2vGjBnq7Oy84fa1tbUKh8PJR3FxcaaXBADopzIeocrKSj344IOaMGGCvva1r2nPnj2SpM2bN99w+1WrVikWiyUfra2tmV4SAKCfyvo3q44aNUoTJkxQc3PzDV8PBoMKBoPZXgYAoB/K+vcJJRIJvffee4pGo9neFQAgx2Q8Qk899ZQaGxvV0tKit956S1//+tcVj8e1ZMmSTO8KAJDjMv7Xcb/73e/08MMP6+zZs7rjjjs0bdo0HT58WCUlJZneFQAgx2U8Qtu3b8/0b4l+asg9Y71nXHCY98yZ2X/oPXNhmv+NJyUpP+w/9/rE9G6OOdD8w8ch75m/rpvvPfPWhG3eMy2XLnjPSNKzH8zznil63aW1r8GKe8cBAMwQIQCAGSIEADBDhAAAZogQAMAMEQIAmCFCAAAzRAgAYIYIAQDMECEAgBkiBAAwQ4QAAGay/kPt0P/1ln8lrbn1Lz3vPTNu2PC09oVb65Lr9Z75rz9a6j0ztNv/Zp/Tf7HMeyb0Lz3eM5IUPOt/49ORb7+V1r4GK66EAABmiBAAwAwRAgCYIUIAADNECABghggBAMwQIQCAGSIEADBDhAAAZogQAMAMEQIAmCFCAAAzRAgAYIa7aEPBE2fSmjvySbH3zLhhH6S1r4FmZds075mT50d7z7x01997z0hS7LL/3a0L//ZQWvvqz/yPAnxxJQQAMEOEAABmiBAAwAwRAgCYIUIAADNECABghggBAMwQIQCAGSIEADBDhAAAZogQAMAMEQIAmOEGplBPW3tacz/66294z/zV/G7vmSHv/oH3zK+e/JH3TLq+f/bfes+8/7WR3jO959q8Zx6Z/qT3jCSd+nP/mVL9Kq19YXDjSggAYIYIAQDMECEAgBkiBAAwQ4QAAGaIEADADBECAJghQgAAM0QIAGCGCAEAzBAhAIAZIgQAMMMNTJG2/E1ves/c8d//lfdMb+eH3jPjy/6j94wkHZ/1d94zu38y23um4Nwh75l0BN5M76aipf7/aIG0cCUEADBDhAAAZrwjdPDgQS1YsEBFRUUKBALatWtXyuvOOdXU1KioqEgjRoxQeXm5jh8/nqn1AgAGEO8IdXd3a+LEiaqrq7vh6+vWrdP69etVV1enpqYmRSIRzZs3T11dXZ97sQCAgcX7gwmVlZWqrKy84WvOOW3YsEGrV6/WokWLJEmbN29WYWGhtm3bpscee+zzrRYAMKBk9D2hlpYWtbe3q6KiIvlcMBjU7NmzdejQjT8NlEgkFI/HUx4AgMEhoxFqb2+XJBUWFqY8X1hYmHztWrW1tQqHw8lHcXFxJpcEAOjHsvLpuEAgkPK1c+66565atWqVYrFY8tHa2pqNJQEA+qGMfrNqJBKRdOWKKBqNJp/v6Oi47uroqmAwqGAwmMllAAByREavhEpLSxWJRFRfX5987uLFi2psbNSMGTMyuSsAwADgfSV0/vx5vf/++8mvW1pa9M477yg/P1933nmnVqxYobVr12rs2LEaO3as1q5dq5EjR+qRRx7J6MIBALnPO0Jvv/225syZk/y6urpakrRkyRK99NJLevrpp3XhwgU9+eST+uijjzR16lS99tprCoVCmVs1AGBACDjnnPUiPi0ejyscDqtc92toYJj1cpCjfvPfpqQ3d9+PvWe+9dt/7z3zf2am8c3bl3v9ZwADPe6SGvSKYrGY8vLy+tyWe8cBAMwQIQCAGSIEADBDhAAAZogQAMAMEQIAmCFCAAAzRAgAYIYIAQDMECEAgBkiBAAwQ4QAAGaIEADATEZ/sirQX9zzF79Ja+5bE/zviL2p5B+9Z2Z/o8p7JrTjsPcM0N9xJQQAMEOEAABmiBAAwAwRAgCYIUIAADNECABghggBAMwQIQCAGSIEADBDhAAAZogQAMAMEQIAmOEGphiQes/F0prrfOIe75nTuy94z3z3+1u8Z1b96QPeM+5o2HtGkor/6k3/IefS2hcGN66EAABmiBAAwAwRAgCYIUIAADNECABghggBAMwQIQCAGSIEADBDhAAAZogQAMAMEQIAmCFCAAAz3MAU+JTLv3rPe+ahv/zP3jNb1/yN98w70/xveqpp/iOSNH7UMu+ZsS+2ec/0nDzlPYOBhSshAIAZIgQAMEOEAABmiBAAwAwRAgCYIUIAADNECABghggBAMwQIQCAGSIEADBDhAAAZogQAMBMwDnnrBfxafF4XOFwWOW6X0MDw6yXA2SF++Mve8/kPfs775mf/+t93jPpuvvAd7xn/s1fxrxneptPes/g1upxl9SgVxSLxZSXl9fntlwJAQDMECEAgBnvCB08eFALFixQUVGRAoGAdu3alfL60qVLFQgEUh7TpqX5Q00AAAOad4S6u7s1ceJE1dXVfeY28+fPV1tbW/Kxd+/ez7VIAMDA5P2TVSsrK1VZWdnnNsFgUJFIJO1FAQAGh6y8J9TQ0KCCggKNGzdOjz76qDo6Oj5z20QioXg8nvIAAAwOGY9QZWWltm7dqv379+u5555TU1OT5s6dq0QiccPta2trFQ6Hk4/i4uJMLwkA0E95/3XczSxevDj567KyMk2ePFklJSXas2ePFi1adN32q1atUnV1dfLreDxOiABgkMh4hK4VjUZVUlKi5ubmG74eDAYVDAazvQwAQD+U9e8T6uzsVGtrq6LRaLZ3BQDIMd5XQufPn9f777+f/LqlpUXvvPOO8vPzlZ+fr5qaGj344IOKRqM6deqUnnnmGY0ePVoPPPBARhcOAMh93hF6++23NWfOnOTXV9/PWbJkiTZu3Khjx45py5YtOnfunKLRqObMmaMdO3YoFAplbtUAgAGBG5gCOWJIYYH3zJnFX0prX2/9xQ+9Z25L42/3/6ylwnsmNrPTewa3FjcwBQDkBCIEADBDhAAAZogQAMAMEQIAmCFCAAAzRAgAYIYIAQDMECEAgBkiBAAwQ4QAAGaIEADADBECAJjJ+k9WBZAZvR90eM8U/q3/jCR98nSP98zIwHDvmRe/+D+8Z+57YIX3zMiX3/Kewa3BlRAAwAwRAgCYIUIAADNECABghggBAMwQIQCAGSIEADBDhAAAZogQAMAMEQIAmCFCAAAzRAgAYIYbmAIGLs/8svfMP3/jdu+Zsi+f8p6R0rsZaTp+9OG/854Z+crbWVgJrHAlBAAwQ4QAAGaIEADADBECAJghQgAAM0QIAGCGCAEAzBAhAIAZIgQAMEOEAABmiBAAwAwRAgCY4QamwKcEJpd5z/zmz/1v9vniH2/2npl1+0XvmVsp4S55zxz+sNR/R5fb/GfQb3ElBAAwQ4QAAGaIEADADBECAJghQgAAM0QIAGCGCAEAzBAhAIAZIgQAMEOEAABmiBAAwAwRAgCY4Qam6PeGlpZ4z/zzt4rS2lfN4u3eMw/+wdm09tWfPfPBZO+Zxh9O8575o81ves9gYOFKCABghggBAMx4Rai2tlZTpkxRKBRSQUGBFi5cqBMnTqRs45xTTU2NioqKNGLECJWXl+v48eMZXTQAYGDwilBjY6Oqqqp0+PBh1dfXq6enRxUVFeru7k5us27dOq1fv151dXVqampSJBLRvHnz1NXVlfHFAwBym9cHE1599dWUrzdt2qSCggIdOXJEs2bNknNOGzZs0OrVq7Vo0SJJ0ubNm1VYWKht27bpsccey9zKAQA573O9JxSLxSRJ+fn5kqSWlha1t7eroqIiuU0wGNTs2bN16NChG/4eiURC8Xg85QEAGBzSjpBzTtXV1Zo5c6bKysokSe3t7ZKkwsLClG0LCwuTr12rtrZW4XA4+SguLk53SQCAHJN2hJYtW6Z3331XP//5z697LRAIpHztnLvuuatWrVqlWCyWfLS2tqa7JABAjknrm1WXL1+u3bt36+DBgxozZkzy+UgkIunKFVE0Gk0+39HRcd3V0VXBYFDBYDCdZQAAcpzXlZBzTsuWLdPOnTu1f/9+lZaWprxeWlqqSCSi+vr65HMXL15UY2OjZsyYkZkVAwAGDK8roaqqKm3btk2vvPKKQqFQ8n2ecDisESNGKBAIaMWKFVq7dq3Gjh2rsWPHau3atRo5cqQeeeSRrPwBAAC5yytCGzdulCSVl5enPL9p0yYtXbpUkvT000/rwoULevLJJ/XRRx9p6tSpeu211xQKhTKyYADAwBFwzjnrRXxaPB5XOBxWue7X0MAw6+WgD0O/eKf3TGxS9OYbXWPx9169+UbXePwPT3rP9Hcr2/xvEPrmC/43IpWk/Jf+p//Q5d609oWBp8ddUoNeUSwWU15eXp/bcu84AIAZIgQAMEOEAABmiBAAwAwRAgCYIUIAADNECABghggBAMwQIQCAGSIEADBDhAAAZogQAMAMEQIAmEnrJ6ui/xoajXjPfPh3o9La1xOljd4zD4c+SGtf/dmyf5npPfNPG7/sPTP67/+X90x+15veM8CtxJUQAMAMEQIAmCFCAAAzRAgAYIYIAQDMECEAgBkiBAAwQ4QAAGaIEADADBECAJghQgAAM0QIAGCGG5jeIhf/w2T/mf/0offMM1/a6z1TMaLbe6a/+6D3Qlpzs3av9J65+7/8b++Z/HP+Nxa97D0B9H9cCQEAzBAhAIAZIgQAMEOEAABmiBAAwAwRAgCYIUIAADNECABghggBAMwQIQCAGSIEADBDhAAAZriB6S1yaqF/738z4RdZWEnmPH/uLu+ZHzZWeM8EegPeM3d/v8V7RpLGfvCW90xvWnsCIHElBAAwRIQAAGaIEADADBECAJghQgAAM0QIAGCGCAEAzBAhAIAZIgQAMEOEAABmiBAAwAwRAgCYCTjnnPUiPi0ejyscDqtc92toYJj1cgAAnnrcJTXoFcViMeXl5fW5LVdCAAAzRAgAYMYrQrW1tZoyZYpCoZAKCgq0cOFCnThxImWbpUuXKhAIpDymTZuW0UUDAAYGrwg1NjaqqqpKhw8fVn19vXp6elRRUaHu7u6U7ebPn6+2trbkY+/evRldNABgYPD6yaqvvvpqytebNm1SQUGBjhw5olmzZiWfDwaDikQimVkhAGDA+lzvCcViMUlSfn5+yvMNDQ0qKCjQuHHj9Oijj6qjo+Mzf49EIqF4PJ7yAAAMDmlHyDmn6upqzZw5U2VlZcnnKysrtXXrVu3fv1/PPfecmpqaNHfuXCUSiRv+PrW1tQqHw8lHcXFxuksCAOSYtL9PqKqqSnv27NEbb7yhMWPGfOZ2bW1tKikp0fbt27Vo0aLrXk8kEimBisfjKi4u5vuEACBH+XyfkNd7QlctX75cu3fv1sGDB/sMkCRFo1GVlJSoubn5hq8Hg0EFg8F0lgEAyHFeEXLOafny5Xr55ZfV0NCg0tLSm850dnaqtbVV0Wg07UUCAAYmr/eEqqqq9LOf/Uzbtm1TKBRSe3u72tvbdeHCBUnS+fPn9dRTT+nNN9/UqVOn1NDQoAULFmj06NF64IEHsvIHAADkLq8roY0bN0qSysvLU57ftGmTli5dqiFDhujYsWPasmWLzp07p2g0qjlz5mjHjh0KhUIZWzQAYGDw/uu4vowYMUL79u37XAsCAAwe3DsOAGCGCAEAzBAhAIAZIgQAMEOEAABmiBAAwAwRAgCYIUIAADNECABghggBAMwQIQCAGSIEADBDhAAAZogQAMAMEQIAmCFCAAAzRAgAYIYIAQDMECEAgBkiBAAwQ4QAAGaIEADADBECAJghQgAAM0QIAGBmqPUCruWckyT16JLkjBcDAPDWo0uS/v9/z/vS7yLU1dUlSXpDe41XAgD4PLq6uhQOh/vcJuB+n1TdQpcvX9aZM2cUCoUUCARSXovH4youLlZra6vy8vKMVmiP43AFx+EKjsMVHIcr+sNxcM6pq6tLRUVFuu22vt/16XdXQrfddpvGjBnT5zZ5eXmD+iS7iuNwBcfhCo7DFRyHK6yPw82ugK7igwkAADNECABgJqciFAwGtWbNGgWDQeulmOI4XMFxuILjcAXH4YpcOw797oMJAIDBI6euhAAAAwsRAgCYIUIAADNECABgJqci9MILL6i0tFS33367Jk2apNdff916SbdUTU2NAoFAyiMSiVgvK+sOHjyoBQsWqKioSIFAQLt27Up53TmnmpoaFRUVacSIESovL9fx48dtFptFNzsOS5cuve78mDZtms1is6S2tlZTpkxRKBRSQUGBFi5cqBMnTqRsMxjOh9/nOOTK+ZAzEdqxY4dWrFih1atX6+jRo7r33ntVWVmp06dPWy/tlho/frza2tqSj2PHjlkvKeu6u7s1ceJE1dXV3fD1devWaf369aqrq1NTU5MikYjmzZuXvA/hQHGz4yBJ8+fPTzk/9u4dWPdgbGxsVFVVlQ4fPqz6+nr19PSooqJC3d3dyW0Gw/nw+xwHKUfOB5cjvvrVr7rHH3885bm7777bffe73zVa0a23Zs0aN3HiROtlmJLkXn755eTXly9fdpFIxD377LPJ5z755BMXDofdj3/8Y4MV3hrXHgfnnFuyZIm7//77TdZjpaOjw0lyjY2NzrnBez5cexycy53zISeuhC5evKgjR46ooqIi5fmKigodOnTIaFU2mpubVVRUpNLSUj300EM6efKk9ZJMtbS0qL29PeXcCAaDmj179qA7NySpoaFBBQUFGjdunB599FF1dHRYLymrYrGYJCk/P1/S4D0frj0OV+XC+ZATETp79qx6e3tVWFiY8nxhYaHa29uNVnXrTZ06VVu2bNG+ffv04osvqr29XTNmzFBnZ6f10sxc/ec/2M8NSaqsrNTWrVu1f/9+Pffcc2pqatLcuXOVSCSsl5YVzjlVV1dr5syZKisrkzQ4z4cbHQcpd86HfncX7b5c+6MdnHPXPTeQVVZWJn89YcIETZ8+XXfddZc2b96s6upqw5XZG+znhiQtXrw4+euysjJNnjxZJSUl2rNnjxYtWmS4suxYtmyZ3n33Xb3xxhvXvTaYzofPOg65cj7kxJXQ6NGjNWTIkOv+T6ajo+O6/+MZTEaNGqUJEyaoubnZeilmrn46kHPjetFoVCUlJQPy/Fi+fLl2796tAwcOpPzol8F2PnzWcbiR/no+5ESEhg8frkmTJqm+vj7l+fr6es2YMcNoVfYSiYTee+89RaNR66WYKS0tVSQSSTk3Ll68qMbGxkF9bkhSZ2enWltbB9T54ZzTsmXLtHPnTu3fv1+lpaUprw+W8+Fmx+FG+u35YPihCC/bt293w4YNcz/96U/dr3/9a7dixQo3atQod+rUKeul3TIrV650DQ0N7uTJk+7w4cPuvvvuc6FQaMAfg66uLnf06FF39OhRJ8mtX7/eHT161P32t791zjn37LPPunA47Hbu3OmOHTvmHn74YReNRl08HjdeeWb1dRy6urrcypUr3aFDh1xLS4s7cOCAmz59uvvCF74woI7DE0884cLhsGtoaHBtbW3Jx8cff5zcZjCcDzc7Drl0PuRMhJxz7vnnn3clJSVu+PDh7itf+UrKxxEHg8WLF7toNOqGDRvmioqK3KJFi9zx48etl5V1Bw4ccJKueyxZssQ5d+VjuWvWrHGRSMQFg0E3a9Ysd+zYMdtFZ0Ffx+Hjjz92FRUV7o477nDDhg1zd955p1uyZIk7ffq09bIz6kZ/fklu06ZNyW0Gw/lws+OQS+cDP8oBAGAmJ94TAgAMTEQIAGCGCAEAzBAhAIAZIgQAMEOEAABmiBAAwAwRAgCYIUIAADNECABghggBAMwQIQCAmf8Lw4IYymq+HboAAAAASUVORK5CYII=", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "import matplotlib.pyplot as plt\n", "plt.imshow(x_train[0])" ] }, { "cell_type": "code", "execution_count": 10, "id": "3c8d5bf6-9c28-46bb-9ef5-492108fa5f04", "metadata": {}, "outputs": [], "source": [ "x_train = x_train/255\n", "x_test = x_test/255" ] }, { "cell_type": "code", "execution_count": 11, "id": "b00d2d67-e70f-4d1b-b29a-eec2eb2d74f3", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "array([[0. , 0. , 0. , 0. , 0. ,\n", " 0. , 0. , 0. , 0. , 0. ,\n", " 0. , 0. , 0. , 0. , 0. ,\n", " 0. , 0. , 0. , 0. , 0. ,\n", " 0. , 0. , 0. , 0. , 0. ,\n", " 0. , 0. , 0. ],\n", " [0. , 0. , 0. , 0. , 0. ,\n", " 0. , 0. , 0. , 0. , 0. ,\n", " 0. , 0. , 0. , 0. , 0. ,\n", " 0. , 0. , 0. , 0. , 0. ,\n", " 0. , 0. , 0. , 0. , 0. ,\n", " 0. , 0. , 0. ],\n", " [0. , 0. , 0. , 0. , 0. ,\n", " 0. , 0. , 0. , 0. , 0. ,\n", " 0. , 0. , 0. , 0. , 0. ,\n", " 0. , 0. , 0. , 0. , 0. ,\n", " 0. , 0. , 0. , 0. , 0. ,\n", " 0. , 0. , 0. ],\n", " [0. , 0. , 0. , 0. , 0. ,\n", " 0. , 0. , 0. , 0. , 0. ,\n", " 0. , 0. , 0. , 0. , 0. ,\n", " 0. , 0. , 0. , 0. , 0. ,\n", " 0. , 0. , 0. , 0. , 0. ,\n", " 0. , 0. , 0. ],\n", " [0. , 0. , 0. , 0. , 0. ,\n", " 0. , 0. , 0. , 0. , 0. ,\n", " 0. , 0. , 0. , 0. , 0. ,\n", " 0. , 0. , 0. , 0. , 0. ,\n", " 0. , 0. , 0. , 0. , 0. ,\n", " 0. , 0. , 0. ],\n", " [0. , 0. , 0. , 0. , 0. ,\n", " 0. , 0. , 0. , 0. , 0. ,\n", " 0. , 0. , 0.01176471, 0.07058824, 0.07058824,\n", " 0.07058824, 0.49411765, 0.53333333, 0.68627451, 0.10196078,\n", " 0.65098039, 1. , 0.96862745, 0.49803922, 0. ,\n", " 0. , 0. , 0. ],\n", " [0. , 0. , 0. , 0. , 0. ,\n", " 0. , 0. , 0. , 0.11764706, 0.14117647,\n", " 0.36862745, 0.60392157, 0.66666667, 0.99215686, 0.99215686,\n", " 0.99215686, 0.99215686, 0.99215686, 0.88235294, 0.6745098 ,\n", " 0.99215686, 0.94901961, 0.76470588, 0.25098039, 0. ,\n", " 0. , 0. , 0. ],\n", " [0. , 0. , 0. , 0. , 0. ,\n", " 0. , 0. , 0.19215686, 0.93333333, 0.99215686,\n", " 0.99215686, 0.99215686, 0.99215686, 0.99215686, 0.99215686,\n", " 0.99215686, 0.99215686, 0.98431373, 0.36470588, 0.32156863,\n", " 0.32156863, 0.21960784, 0.15294118, 0. , 0. ,\n", " 0. , 0. , 0. ],\n", " [0. , 0. , 0. , 0. , 0. ,\n", " 0. , 0. , 0.07058824, 0.85882353, 0.99215686,\n", " 0.99215686, 0.99215686, 0.99215686, 0.99215686, 0.77647059,\n", " 0.71372549, 0.96862745, 0.94509804, 0. , 0. ,\n", " 0. , 0. , 0. , 0. , 0. ,\n", " 0. , 0. , 0. ],\n", " [0. , 0. , 0. , 0. , 0. ,\n", " 0. , 0. , 0. , 0.31372549, 0.61176471,\n", " 0.41960784, 0.99215686, 0.99215686, 0.80392157, 0.04313725,\n", " 0. , 0.16862745, 0.60392157, 0. , 0. ,\n", " 0. , 0. , 0. , 0. , 0. ,\n", " 0. , 0. , 0. ],\n", " [0. , 0. , 0. , 0. , 0. ,\n", " 0. , 0. , 0. , 0. , 0.05490196,\n", " 0.00392157, 0.60392157, 0.99215686, 0.35294118, 0. ,\n", " 0. , 0. , 0. , 0. , 0. ,\n", " 0. , 0. , 0. , 0. , 0. ,\n", " 0. , 0. , 0. ],\n", " [0. , 0. , 0. , 0. , 0. ,\n", " 0. , 0. , 0. , 0. , 0. ,\n", " 0. , 0.54509804, 0.99215686, 0.74509804, 0.00784314,\n", " 0. , 0. , 0. , 0. , 0. ,\n", " 0. , 0. , 0. , 0. , 0. ,\n", " 0. , 0. , 0. ],\n", " [0. , 0. , 0. , 0. , 0. ,\n", " 0. , 0. , 0. , 0. , 0. ,\n", " 0. , 0.04313725, 0.74509804, 0.99215686, 0.2745098 ,\n", " 0. , 0. , 0. , 0. , 0. ,\n", " 0. , 0. , 0. , 0. , 0. ,\n", " 0. , 0. , 0. ],\n", " [0. , 0. , 0. , 0. , 0. ,\n", " 0. , 0. , 0. , 0. , 0. ,\n", " 0. , 0. , 0.1372549 , 0.94509804, 0.88235294,\n", " 0.62745098, 0.42352941, 0.00392157, 0. , 0. ,\n", " 0. , 0. , 0. , 0. , 0. ,\n", " 0. , 0. , 0. ],\n", " [0. , 0. , 0. , 0. , 0. ,\n", " 0. , 0. , 0. , 0. , 0. ,\n", " 0. , 0. , 0. , 0.31764706, 0.94117647,\n", " 0.99215686, 0.99215686, 0.46666667, 0.09803922, 0. ,\n", " 0. , 0. , 0. , 0. , 0. ,\n", " 0. , 0. , 0. ],\n", " [0. , 0. , 0. , 0. , 0. ,\n", " 0. , 0. , 0. , 0. , 0. ,\n", " 0. , 0. , 0. , 0. , 0.17647059,\n", " 0.72941176, 0.99215686, 0.99215686, 0.58823529, 0.10588235,\n", " 0. , 0. , 0. , 0. , 0. ,\n", " 0. , 0. , 0. ],\n", " [0. , 0. , 0. , 0. , 0. ,\n", " 0. , 0. , 0. , 0. , 0. ,\n", " 0. , 0. , 0. , 0. , 0. ,\n", " 0.0627451 , 0.36470588, 0.98823529, 0.99215686, 0.73333333,\n", " 0. , 0. , 0. , 0. , 0. ,\n", " 0. , 0. , 0. ],\n", " [0. , 0. , 0. , 0. , 0. ,\n", " 0. , 0. , 0. , 0. , 0. ,\n", " 0. , 0. , 0. , 0. , 0. ,\n", " 0. , 0. , 0.97647059, 0.99215686, 0.97647059,\n", " 0.25098039, 0. , 0. , 0. , 0. ,\n", " 0. , 0. , 0. ],\n", " [0. , 0. , 0. , 0. , 0. ,\n", " 0. , 0. , 0. , 0. , 0. ,\n", " 0. , 0. , 0. , 0. , 0.18039216,\n", " 0.50980392, 0.71764706, 0.99215686, 0.99215686, 0.81176471,\n", " 0.00784314, 0. , 0. , 0. , 0. ,\n", " 0. , 0. , 0. ],\n", " [0. , 0. , 0. , 0. , 0. ,\n", " 0. , 0. , 0. , 0. , 0. ,\n", " 0. , 0. , 0.15294118, 0.58039216, 0.89803922,\n", " 0.99215686, 0.99215686, 0.99215686, 0.98039216, 0.71372549,\n", " 0. , 0. , 0. , 0. , 0. ,\n", " 0. , 0. , 0. ],\n", " [0. , 0. , 0. , 0. , 0. ,\n", " 0. , 0. , 0. , 0. , 0. ,\n", " 0.09411765, 0.44705882, 0.86666667, 0.99215686, 0.99215686,\n", " 0.99215686, 0.99215686, 0.78823529, 0.30588235, 0. ,\n", " 0. , 0. , 0. , 0. , 0. ,\n", " 0. , 0. , 0. ],\n", " [0. , 0. , 0. , 0. , 0. ,\n", " 0. , 0. , 0. , 0.09019608, 0.25882353,\n", " 0.83529412, 0.99215686, 0.99215686, 0.99215686, 0.99215686,\n", " 0.77647059, 0.31764706, 0.00784314, 0. , 0. ,\n", " 0. , 0. , 0. , 0. , 0. ,\n", " 0. , 0. , 0. ],\n", " [0. , 0. , 0. , 0. , 0. ,\n", " 0. , 0.07058824, 0.67058824, 0.85882353, 0.99215686,\n", " 0.99215686, 0.99215686, 0.99215686, 0.76470588, 0.31372549,\n", " 0.03529412, 0. , 0. , 0. , 0. ,\n", " 0. , 0. , 0. , 0. , 0. ,\n", " 0. , 0. , 0. ],\n", " [0. , 0. , 0. , 0. , 0.21568627,\n", " 0.6745098 , 0.88627451, 0.99215686, 0.99215686, 0.99215686,\n", " 0.99215686, 0.95686275, 0.52156863, 0.04313725, 0. ,\n", " 0. , 0. , 0. , 0. , 0. ,\n", " 0. , 0. , 0. , 0. , 0. ,\n", " 0. , 0. , 0. ],\n", " [0. , 0. , 0. , 0. , 0.53333333,\n", " 0.99215686, 0.99215686, 0.99215686, 0.83137255, 0.52941176,\n", " 0.51764706, 0.0627451 , 0. , 0. , 0. ,\n", " 0. , 0. , 0. , 0. , 0. ,\n", " 0. , 0. , 0. , 0. , 0. ,\n", " 0. , 0. , 0. ],\n", " [0. , 0. , 0. , 0. , 0. ,\n", " 0. , 0. , 0. , 0. , 0. ,\n", " 0. , 0. , 0. , 0. , 0. ,\n", " 0. , 0. , 0. , 0. , 0. ,\n", " 0. , 0. , 0. , 0. , 0. ,\n", " 0. , 0. , 0. ],\n", " [0. , 0. , 0. , 0. , 0. ,\n", " 0. , 0. , 0. , 0. , 0. ,\n", " 0. , 0. , 0. , 0. , 0. ,\n", " 0. , 0. , 0. , 0. , 0. ,\n", " 0. , 0. , 0. , 0. , 0. ,\n", " 0. , 0. , 0. ],\n", " [0. , 0. , 0. , 0. , 0. ,\n", " 0. , 0. , 0. , 0. , 0. ,\n", " 0. , 0. , 0. , 0. , 0. ,\n", " 0. , 0. , 0. , 0. , 0. ,\n", " 0. , 0. , 0. , 0. , 0. ,\n", " 0. , 0. , 0. ]])" ] }, "execution_count": 11, "metadata": {}, "output_type": "execute_result" } ], "source": [ "x_train[0]" ] }, { "cell_type": "code", "execution_count": 12, "id": "58202608-7afc-4ce2-94fd-85c90a392b5b", "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "C:\\Users\\91979\\OneDrive\\Desktop\\python.project\\Annaconda\\Lib\\site-packages\\keras\\src\\layers\\reshaping\\flatten.py:37: UserWarning: Do not pass an `input_shape`/`input_dim` argument to a layer. When using Sequential models, prefer using an `Input(shape)` object as the first layer in the model instead.\n", " super().__init__(**kwargs)\n" ] } ], "source": [ "model = Sequential()\n", "model.add(Flatten(input_shape=(28,28))) #multidimensional data ko 1D mei badal deta hai\n", "model.add(Dense(128, activation = 'relu'))\n", "model.add(Dense(10, activation = 'softmax'))" ] }, { "cell_type": "code", "execution_count": 13, "id": "b4f3dfe2-a8f6-48d1-bad3-92fa2e557a49", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
Model: \"sequential\"\n",
       "
\n" ], "text/plain": [ "\u001b[1mModel: \"sequential\"\u001b[0m\n" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "text/html": [ "
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n",
       "┃ Layer (type)                    ┃ Output Shape           ┃       Param # ┃\n",
       "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n",
       "│ flatten (Flatten)               │ (None, 784)            │             0 │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ dense (Dense)                   │ (None, 128)            │       100,480 │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ dense_1 (Dense)                 │ (None, 10)             │         1,290 │\n",
       "└─────────────────────────────────┴────────────────────────┴───────────────┘\n",
       "
\n" ], "text/plain": [ "┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n", "┃\u001b[1m \u001b[0m\u001b[1mLayer (type) \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1mOutput Shape \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1m Param #\u001b[0m\u001b[1m \u001b[0m┃\n", "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n", "│ flatten (\u001b[38;5;33mFlatten\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m784\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │\n", "├─────────────────────────────────┼────────────────────────┼───────────────┤\n", "│ dense (\u001b[38;5;33mDense\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m128\u001b[0m) │ \u001b[38;5;34m100,480\u001b[0m │\n", "├─────────────────────────────────┼────────────────────────┼───────────────┤\n", "│ dense_1 (\u001b[38;5;33mDense\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m10\u001b[0m) │ \u001b[38;5;34m1,290\u001b[0m │\n", "└─────────────────────────────────┴────────────────────────┴───────────────┘\n" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "text/html": [ "
 Total params: 101,770 (397.54 KB)\n",
       "
\n" ], "text/plain": [ "\u001b[1m Total params: \u001b[0m\u001b[38;5;34m101,770\u001b[0m (397.54 KB)\n" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "text/html": [ "
 Trainable params: 101,770 (397.54 KB)\n",
       "
\n" ], "text/plain": [ "\u001b[1m Trainable params: \u001b[0m\u001b[38;5;34m101,770\u001b[0m (397.54 KB)\n" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "text/html": [ "
 Non-trainable params: 0 (0.00 B)\n",
       "
\n" ], "text/plain": [ "\u001b[1m Non-trainable params: \u001b[0m\u001b[38;5;34m0\u001b[0m (0.00 B)\n" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "model.summary()" ] }, { "cell_type": "code", "execution_count": 67, "id": "f78f5c99-5212-4b33-a669-90f82ee8c1c8", "metadata": {}, "outputs": [], "source": [ "model.compile(loss='sparse_categorical_crossentropy', optimizer = 'Adam', metrics = ['accuracy'])" ] }, { "cell_type": "code", "execution_count": 69, "id": "d067cde5-0552-4f5d-99b5-9de4f92f6e73", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Epoch 1/10\n", "\u001b[1m1500/1500\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m12s\u001b[0m 6ms/step - accuracy: 0.9982 - loss: 0.0056 - val_accuracy: 0.9777 - val_loss: 0.1199\n", "Epoch 2/10\n", "\u001b[1m1500/1500\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m9s\u001b[0m 6ms/step - accuracy: 0.9987 - loss: 0.0045 - val_accuracy: 0.9751 - val_loss: 0.1376\n", "Epoch 3/10\n", "\u001b[1m1500/1500\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m10s\u001b[0m 6ms/step - accuracy: 0.9978 - loss: 0.0057 - val_accuracy: 0.9761 - val_loss: 0.1323\n", "Epoch 4/10\n", "\u001b[1m1500/1500\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m11s\u001b[0m 6ms/step - accuracy: 0.9995 - loss: 0.0022 - val_accuracy: 0.9758 - val_loss: 0.1346\n", "Epoch 5/10\n", "\u001b[1m1500/1500\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m9s\u001b[0m 6ms/step - accuracy: 0.9987 - loss: 0.0038 - val_accuracy: 0.9771 - val_loss: 0.1338\n", "Epoch 6/10\n", "\u001b[1m1500/1500\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m10s\u001b[0m 7ms/step - accuracy: 0.9992 - loss: 0.0030 - val_accuracy: 0.9762 - val_loss: 0.1395\n", "Epoch 7/10\n", "\u001b[1m1500/1500\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m9s\u001b[0m 6ms/step - accuracy: 0.9989 - loss: 0.0036 - val_accuracy: 0.9761 - val_loss: 0.1399\n", "Epoch 8/10\n", "\u001b[1m1500/1500\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m9s\u001b[0m 6ms/step - accuracy: 0.9994 - loss: 0.0026 - val_accuracy: 0.9758 - val_loss: 0.1448\n", "Epoch 9/10\n", "\u001b[1m1500/1500\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m9s\u001b[0m 6ms/step - accuracy: 0.9989 - loss: 0.0036 - val_accuracy: 0.9788 - val_loss: 0.1338\n", "Epoch 10/10\n", "\u001b[1m1500/1500\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m9s\u001b[0m 6ms/step - accuracy: 0.9995 - loss: 0.0023 - val_accuracy: 0.9768 - val_loss: 0.1451\n" ] } ], "source": [ "history = model.fit(x_train, y_train, epochs = 10, validation_split = 0.2)" ] }, { "cell_type": "code", "execution_count": 71, "id": "c0ba487c-c409-4e00-a1cc-18e3da541d90", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "" ] }, "execution_count": 71, "metadata": {}, "output_type": "execute_result" } ], "source": [ "history" ] }, { "cell_type": "code", "execution_count": 73, "id": "c5a0c4ce-5cc9-4188-bc7b-08d5c17628f1", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "\u001b[1m313/313\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 3ms/step\n" ] } ], "source": [ "y_prob = model.predict(x_test)" ] }, { "cell_type": "code", "execution_count": 74, "id": "507f3756-2863-43b3-86c4-531eb56ee92d", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "array([[2.22477930e-14, 2.40741425e-18, 5.30151487e-12, ...,\n", " 9.99999285e-01, 2.38283209e-14, 7.91083998e-09],\n", " [3.20452112e-22, 9.57464251e-13, 1.00000000e+00, ...,\n", " 3.45383005e-36, 6.82969219e-12, 3.69086034e-36],\n", " [2.89154985e-12, 9.99991059e-01, 1.41864447e-07, ...,\n", " 1.08084016e-07, 8.65464062e-06, 5.36966478e-12],\n", " ...,\n", " [1.58842623e-34, 4.09316782e-26, 8.52802047e-21, ...,\n", " 8.07254472e-11, 1.00095951e-12, 1.45853098e-08],\n", " [5.54291790e-22, 3.43126701e-22, 3.08558598e-26, ...,\n", " 1.90769882e-21, 2.26449867e-13, 3.02600101e-24],\n", " [7.24878419e-25, 2.13908937e-22, 9.02729127e-23, ...,\n", " 8.55250369e-32, 5.61552238e-26, 1.26532478e-30]], dtype=float32)" ] }, "execution_count": 74, "metadata": {}, "output_type": "execute_result" } ], "source": [ "y_prob" ] }, { "cell_type": "code", "execution_count": 77, "id": "538f6f47-7c55-4013-88ad-329ef6863e7e", "metadata": {}, "outputs": [], "source": [ "y_pred = y_prob.argmax(axis = 1)" ] }, { "cell_type": "code", "execution_count": 79, "id": "538b1fb3-5c69-4d1a-aa54-4d106f3b2a4b", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "array([7, 2, 1, ..., 4, 5, 6], dtype=int64)" ] }, "execution_count": 79, "metadata": {}, "output_type": "execute_result" } ], "source": [ "y_pred" ] }, { "cell_type": "code", "execution_count": 81, "id": "20cd1cd0-6e5c-4c43-9ecb-011761112006", "metadata": {}, "outputs": [], "source": [ "from sklearn.metrics import accuracy_score\n", "cm = accuracy_score( y_test,y_pred)" ] }, { "cell_type": "code", "execution_count": 83, "id": "a607ea5e-7423-41c3-8dd5-b8fdfb308902", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "0.9781" ] }, "execution_count": 83, "metadata": {}, "output_type": "execute_result" } ], "source": [ "cm\n" ] }, { "cell_type": "code", "execution_count": 51, "id": "533e0f5a-0ed6-4834-ac42-ea9db8a0c4ca", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "[]" ] }, "execution_count": 51, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "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", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "plt.plot(history.history['loss'])\n", "plt.plot(history.history['val_loss'])" ] }, { "cell_type": "code", "execution_count": 85, "id": "f0fc5442-3d47-4a4f-8050-2a3d6006722e", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "[]" ] }, "execution_count": 85, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "iVBORw0KGgoAAAANSUhEUgAAAjUAAAGdCAYAAADqsoKGAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjguNCwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8fJSN1AAAACXBIWXMAAA9hAAAPYQGoP6dpAAA/DElEQVR4nO3de3xU9YH///dkMpkJuXEJBAKERGohAiIJGghoS7WxKBRctwJtWW2rW3a1FVnbSoWW4iU/60rtr0JWEHZBq9DWay1eolYFUSMRVAQB5RIMCSEBZnIhk2Ryvn+czCRDBkxCYJKT1/PxmEfmnPnMnM9kMpn3fG7HZhiGIQAAgG4uItwVAAAA6AyEGgAAYAmEGgAAYAmEGgAAYAmEGgAAYAmEGgAAYAmEGgAAYAmEGgAAYAmR4a7A+dTY2KjDhw8rLi5ONpst3NUBAABtYBiGKisrlZycrIiI07fH9KhQc/jwYQ0dOjTc1QAAAB1w6NAhDRky5LS396hQExcXJ8n8pcTHx4e5NgAAoC08Ho+GDh0a+Bw/LaOd3nrrLWPatGnGoEGDDEnGs88++5X3efPNN42MjAzD6XQaaWlpRl5eXqsyf/vb34z09HQjKirKSE9PN5555plWZZYvX26kpqYaTqfTyMjIMN5+++121d3tdhuSDLfb3a77AQCA8Gnr53e7BwpXV1dr7NixeuSRR9pUfv/+/brmmmt0+eWXa9u2bfr1r3+tn//853r66acDZd59913NmjVLc+fO1UcffaS5c+fqhhtu0Pvvvx8os2HDBs2fP1933323tm3bpssvv1xTp05VUVFRe58CAACwIJthdPws3TabTc8++6xmzpx52jK/+tWv9MILL2jXrl2BffPmzdNHH32kd999V5I0a9YseTwevfTSS4Ey3/nOd9SnTx899dRTkqSsrCxlZGQoLy8vUCY9PV0zZ85Ubm5um+rr8XiUkJAgt9tN9xMAAN1EWz+/z/mU7nfffVc5OTlB+66++mpt3bpV9fX1ZyyzZcsWSVJdXZ0KCwtblcnJyQmUCcXr9crj8QRdAACANZ3zUFNaWqqkpKSgfUlJSWpoaFB5efkZy5SWlkqSysvL5fP5zlgmlNzcXCUkJAQuzHwCAMC6zsvie6euCePv8Wq5P1SZU/e1pUxLCxculNvtDlwOHTrUofoDAICu75xP6R44cGCr1pSysjJFRkaqX79+Zyzjb5lJTEyU3W4/Y5lQnE6nnE5nZzwNAADQxZ3zlpqJEycqPz8/aN+rr76q8ePHy+FwnLFMdna2JCkqKkqZmZmtyuTn5wfKAACAnq3dLTVVVVX6/PPPA9v79+/X9u3b1bdvX6WkpGjhwoUqLi7WunXrJJkznR555BEtWLBAt9xyi959912tXr06MKtJkm6//XZdccUVeuCBBzRjxgw9//zzeu2117R58+ZAmQULFmju3LkaP368Jk6cqJUrV6qoqEjz5s07m+cPAACsor0L4Pzzn/80JLW63HjjjYZhGMaNN95ofOMb3wi6z5tvvmmMGzfOiIqKMlJTU0MuvvfXv/7VGDFihOFwOIyRI0caTz/9dKsyy5cvN4YNG2ZERUUZGRkZxltvvdWuurP4HgAA3U9bP7/Pap2a7oZ1agAA6H66zDo1AAAA5wOhBgAAWEKPOks3AKB7MwxDJe5afVLs1qeHPYqMsGlYv14a1i9Gqf16qXevqHBXEWFEqAEAdFlHPLX6+Eu3Pil265MvT+iTYrfKq+pOWz7eFanUxBil9O2l1H4xSuln/hzWr5cGxDnPuGAruj9CDQCgSzha6dUnxSf08Zdu7Sh26+Mv3Sqr9LYqZ4+w6etJcRqdHC9DUlFFjQ5UVKus0itPbYM+/tK876miHXal9O3V1LJjtu4Mawo9gxJcirQzIqOtfI2GKqq8Kqv0qqyyVmUer454vDpaVasl00eF7XdJqAEAnHcVVd6m1he3Pi42Q0yJu7ZVuQibdOGAOI0ZkqCLhyRo9OAEXTQoXi6HvVXZmroGFR2r0cGKGh2sqG76WaODx6pVfPykTtb7tPtIpXYfqWx138gIm4b27dXUwtNLKU3dWcP69dKQPr1CHs+K6hoadbTKqzJPbVNg8epo0/UjLfZVVHnVeJq50z//1oUaEO86vxVvQqgB0GGGYaimzqdqb4OqWlyqvT5VeetV5TVvq6nzSZLsNpvsEVJEhK3puk0R/p8RNkXYzDJBtweuK6jsqfcPuj2wz3zM0PubrttsiohQiH10U3SWEzV1+qSp5eWTpq6k4hMnW5Wz2aTh/WN18eCEQIhJHxSvXlFt+6jqFRWpkQPjNXJg6ym/dQ2NKj5xUgcqqgMtO/6fh46dVJ2vUfvLq7W/vFpvhajXoHhXoGWn+ad5PdbZ9T9KT9b5zBaVSq/KPN5W1482hZbjNfVtfswIm5QY69SAeKcGxLmUFO9U/7jwtnh1/VcCQKfyNRqqrmtQVW1DIIycGkKaw0nT9doG8z5en6pq61XtL1fXICuvdBUUepoCT2KsUwMTXBqY4FJyQrQGJrg0qGl7UEK0+vRy9OhxG+6T9dpR7G7RCnNCh461DjCSdEH/GI0ZnKAxgxN08ZDeuig5/pwFhKjICKUlxigtMabVbb5GQ6We2uDWncD1alXX+XTYXavD7lq9u6+i1f0TY6NajeHx/zyXfw+GYajK2xAcVEIElrJKryprG9r8uA67TQPiXOof59SAuObQMiDOqaT4pv3xTvWLccrexcI/i+8B3UC9r1FVtU1Bo84MG5W1DYFwUdkUQE69HtxyYoaTk/W+Tq9fhE2KcUYqtuly6vVeUWbTvc8w1NhoyNdoBK43GsH7Gw3/7WpVtuVPX6NC7DvldqP5MZvLKlD2XIiKjDBDTrw/7ERrUFPwGdQUgvrFRFmiJaiytl47ij3m+JemgbwHKmpClk3t10tjhvTWmMHxGjO4t0YNjle8y3Gea9x+hmGoorouEHIOVNSoqKJaB5u6uY5Vn37QsiTFOSM1LLGXhvWNaTWWJynOFfLvwDAMnaipDxqvEny9ObS05/3sckSEDCf+ff7rXTGYt/Xzm1ADhFG1t0El7lqVumtV4j5p/vT4t2tV5qlVpbdBdQ2NnX5sh93WKnzEOCMV54xUjNPe4nrTflekYqJaXG8qF+uMVLTD3uX+CbZFUBgKhCK12ue/Xu8zVF7lDbw+Je6TLV6/WpVXtR7UGorDblPSKaGnOQS5lNw7WomxXetbcLW3QZ8e9ujjL08EQsy+o9Uhyw7tG62LB/fW6MFN42CSE5TQq+sHmI7w1NarqKl1J6hr61hNyDFCLTkjIwIDl+0RtkBQOVrpVZ2v7e/5OGek+sc3taq0CCiB4BLn0oB4p+Kckd3yfSoRakIi1LTmPlmvnYc92lni0aeH3Tpa6VWfXlFKjHWqX2yUEmOj1C/Gf92pxFinoqN6xoC5s2EYhiq9DYEPu9JTPvxK3bU67D7ZriZhyfwnGOuMVGxTwAhcd0Yq1mk397lCt5Y0X7cr1hUpZySvY2era2jUEU+tSj1NoedEi9fdY/4dlFV629RlZ4+wKSnOGejWCu7mMsPQgDinHOdg/MLJOp92lgSPgfn8aFXIeg/uHW12IQ1JCHQl9YlhrRhJqq336dAxs3Un0J11zLz+5fGTX9la2LuXozmohGhR8V9v65ij7oxQE0JPDjWGYeiIx6tPD7u187BHnx726NMS92n7us+kV5Rd/ZrCTmJscwBqGX78P/v0iupS3zY7g2EYcp+sPyWkNH14eWp1+ITZ4lJd17Zm4ThnZGCMRtA39wSXkuJcio9uDibn4gMM51e9r1FHK71BLXSnttYdqfS2qXsswib1j3OafzPxrlbjewYlmB+GZwqwtfU+7SrxBA3k3VtWGXJmy8B4lzmAt0WI6RfrPJtfR49V72vU4RMnA+N2DKlFeHGqf9yZX7eehlATQk8JNY2NhvZXVOvTw56mAGMGmYrT9P0O7h2ti5LjNSo5XoN7R8t9sl7lVXUqrzKn7VVU16miqk5Hq7zt7gax2aS+vaJahZ7E2Cj1i3WqX4z5s39TEOoVFd5uDMMwdKy6rtW365YBpsR9UrX1bfs9JEQ7gr9dx0drUG9XYIxFUrxLcd1gXAHOL1+j2c3lD8yHTzS3/vj/Ho94alXva9u/78TYqKCg0z/WqS+Pn9THxW7tPVKphhAJpn+cM2gW0ujBCRoQF55pugChJgQrhhpvg097SqvM4FJitsDsKvEEptC2FGGTvjYgVqOSzXUeRiXH66Lk+DYvK+4faV9RVaeKaq/Kq8ywU1HlVXmVV+XV5nXz9jodr6lr98wYlyOidQtQU/hp2QLULzZKfXtFtWvqYGOjofJqb1AXUOBDo2m71FPb5uDWNyaq1TiIltsDE1w9olkY4dHYaA5gbdnac2qrYYm7bX/P/WKidLG/+2hIb108JEFJYVpnBAiFUBNCdw81ntr6QNeRvwXm87KqkN+yXI4IjRwYH2iBGZWcoJED487rAlINvkYdq/EHn+YgFGgBqqoLBKHyKm+bWz9a6tPL0Rx64pxKbGr56RVlV1lTE79/XENZZXu+2Tqbw8opXUL+FpaeshgXui/DMHS8pj7QrXW4KfQc8Xg1MN4VGMg7KMHVbQeQomcg1ITQXUKNYRgqqzTHv3xa7Am0wBQdCz1Vsncvh9nqMsgML6OS45WWGNOtlvz2L+JmBh1vcAtQU8tPcyuQ2SXWkb9cm00aEOcMNMO3GscSbwaWqMju87sDAKtr6+c3beNh1tho6IB//EuJvxXm9Cds849/8XcfjRqcoGQLfMuy2WyBqcMp/Xp9ZXlfo6HjNS26v6rrVF7pNQNPVZ2q63whZ470P0ezRQAA4UeoOY+8DT7tPVIVNANpV4kn5CyZiKblwv3jXvzjYJgqafKv7JoY65QUF+7qAAC6AELNOVLZcvxLUwvM6WYZOCMjNNI/cLfp58iB8awHAwBAOxBqOkGZp9Zc9+WwOxBiDp5mqfCEaEfTwN3mFpgLutn4FwAAuiJCzVlq8DVq8u//GXLaZHKCSxc1DdxtuQ5Mdx//AgBAV0SoOUuR9ghdNCheVd6G5haYQQm6KDlefRn/AgDAeUOo6QRP/0e25U4FAABAd8NAjk5AoAEAIPwINQAAwBIINQAAwBIINQAAwBIINQAAwBIINQAAwBIINQAAwBIINQAAwBIINQAAwBIINQAAwBIINQAAwBIINQAAwBIINQAAwBIINQAAwBIINQAAwBIINQAAwBIINQAAwBIINQAAwBIINQAAwBIINQAAwBIINQAAwBIINQAAwBIINQAAwBIINQAAwBIINQAAwBIINQAAwBIINQAAwBIINQAAwBIINQAAwBIINQAAwBIINQAAwBIINQAAwBIINQAAwBIINQAAwBIINQAAwBIINQAAwBI6FGpWrFihtLQ0uVwuZWZmatOmTWcsv3z5cqWnpys6OlojRozQunXrgm6vr6/X0qVLNXz4cLlcLo0dO1Yvv/xyUJklS5bIZrMFXQYOHNiR6gMAAAuKbO8dNmzYoPnz52vFihWaNGmSHn30UU2dOlU7d+5USkpKq/J5eXlauHChVq1apUsvvVQFBQW65ZZb1KdPH02fPl2StGjRIj3xxBNatWqVRo4cqVdeeUXXXXedtmzZonHjxgUea9SoUXrttdcC23a7vSPPGQAAWJDNMAyjPXfIyspSRkaG8vLyAvvS09M1c+ZM5ebmtiqfnZ2tSZMm6cEHHwzsmz9/vrZu3arNmzdLkpKTk3X33Xfr1ltvDZSZOXOmYmNj9cQTT0gyW2qee+45bd++vV1PsCWPx6OEhAS53W7Fx8d3+HEAAMD509bP73Z1P9XV1amwsFA5OTlB+3NycrRly5aQ9/F6vXK5XEH7oqOjVVBQoPr6+jOW8Ycev7179yo5OVlpaWmaPXu29u3bd8b6er1eeTyeoAsAALCmdoWa8vJy+Xw+JSUlBe1PSkpSaWlpyPtcffXVeuyxx1RYWCjDMLR161atWbNG9fX1Ki8vD5RZtmyZ9u7dq8bGRuXn5+v5559XSUlJ4HGysrK0bt06vfLKK1q1apVKS0uVnZ2tioqK09Y3NzdXCQkJgcvQoUPb83QBAEA30qGBwjabLWjbMIxW+/wWL16sqVOnasKECXI4HJoxY4ZuuukmSc1jYv74xz/qwgsv1MiRIxUVFaXbbrtNP/rRj4LGzEydOlXXX3+9xowZo6uuukr/+Mc/JElr1649bT0XLlwot9sduBw6dKgjTxcAAHQD7Qo1iYmJstvtrVplysrKWrXe+EVHR2vNmjWqqanRgQMHVFRUpNTUVMXFxSkxMVGS1L9/fz333HOqrq7WwYMH9dlnnyk2NlZpaWmnrUtMTIzGjBmjvXv3nraM0+lUfHx80AUAAFhTu0JNVFSUMjMzlZ+fH7Q/Pz9f2dnZZ7yvw+HQkCFDZLfbtX79ek2bNk0REcGHd7lcGjx4sBoaGvT0009rxowZp308r9erXbt2adCgQe15CgAAwKLaPaV7wYIFmjt3rsaPH6+JEydq5cqVKioq0rx58ySZXT7FxcWBtWj27NmjgoICZWVl6fjx41q2bJl27NgR1G30/vvvq7i4WJdccomKi4u1ZMkSNTY26pe//GWgzJ133qnp06crJSVFZWVluvfee+XxeHTjjTee7e8AAABYQLtDzaxZs1RRUaGlS5eqpKREo0eP1saNGzVs2DBJUklJiYqKigLlfT6fHnroIe3evVsOh0NTpkzRli1blJqaGihTW1urRYsWad++fYqNjdU111yjxx9/XL179w6U+fLLLzVnzhyVl5erf//+mjBhgt57773AcQEAQM/W7nVqujPWqQEAoPs5J+vUAAAAdFWEGgAAYAmEGgAAYAmEGgAAYAmEGgAAYAmEGgAAYAmEGgAAYAmEGgAAYAmEGgAAYAmEGgAAYAmEGgAAYAmEGgAAYAmEGgAAYAmEGgAAYAmEGgAAYAmEGgAAYAmEGgAAYAmEGgAAYAmEGgAAYAmEGgAAYAmEGgAAYAmEGgAAYAmEGgAAYAmEGgAAYAmEGgAAYAmEGgAAYAmEGgAAYAmEGgAAYAmEGgAAYAmEGgAAYAmEGgAAYAmEGgAAYAmEGgAAYAmEGgAAYAmEGgAAYAmEGgAAYAmEGgAAYAmEGgAAYAmEGgAAYAmEGgAAYAmEGgAAYAmEGgAAYAmEGgAAYAmEGgAAYAmEGgAAYAmEGgAAYAmEGgAAYAmEGgAAYAmEGgAAYAmEGgAAYAmEGgAAYAmEGgAAYAmEGgAAYAmEGgAAYAmEGgAAYAmEGgAAYAmEGgAAYAmEGgAAYAkdCjUrVqxQWlqaXC6XMjMztWnTpjOWX758udLT0xUdHa0RI0Zo3bp1QbfX19dr6dKlGj58uFwul8aOHauXX375rI8LAAB6jnaHmg0bNmj+/Pm6++67tW3bNl1++eWaOnWqioqKQpbPy8vTwoULtWTJEn366af63e9+p1tvvVV///vfA2UWLVqkRx99VH/605+0c+dOzZs3T9ddd522bdvW4eMCAICexWYYhtGeO2RlZSkjI0N5eXmBfenp6Zo5c6Zyc3Nblc/OztakSZP04IMPBvbNnz9fW7du1ebNmyVJycnJuvvuu3XrrbcGysycOVOxsbF64oknOnTcUDwejxISEuR2uxUfH9+epw0AAMKkrZ/f7WqpqaurU2FhoXJycoL25+TkaMuWLSHv4/V65XK5gvZFR0eroKBA9fX1ZyzjDz0dOa7/cT0eT9AFAABYU7tCTXl5uXw+n5KSkoL2JyUlqbS0NOR9rr76aj322GMqLCyUYRjaunWr1qxZo/r6epWXlwfKLFu2THv37lVjY6Py8/P1/PPPq6SkpMPHlaTc3FwlJCQELkOHDm3P0wUAAN1IhwYK22y2oG3DMFrt81u8eLGmTp2qCRMmyOFwaMaMGbrpppskSXa7XZL0xz/+URdeeKFGjhypqKgo3XbbbfrRj34UuL0jx5WkhQsXyu12By6HDh1q71MFAADdRLtCTWJioux2e6vWkbKyslatKH7R0dFas2aNampqdODAARUVFSk1NVVxcXFKTEyUJPXv31/PPfecqqurdfDgQX322WeKjY1VWlpah48rSU6nU/Hx8UEXAABgTe0KNVFRUcrMzFR+fn7Q/vz8fGVnZ5/xvg6HQ0OGDJHdbtf69es1bdo0RUQEH97lcmnw4MFqaGjQ008/rRkzZpz1cQEAQM8Q2d47LFiwQHPnztX48eM1ceJErVy5UkVFRZo3b54ks8unuLg4sBbNnj17VFBQoKysLB0/flzLli3Tjh07tHbt2sBjvv/++youLtYll1yi4uJiLVmyRI2NjfrlL3/Z5uMCAICerd2hZtasWaqoqNDSpUtVUlKi0aNHa+PGjRo2bJgkqaSkJGjtGJ/Pp4ceeki7d++Ww+HQlClTtGXLFqWmpgbK1NbWatGiRdq3b59iY2N1zTXX6PHHH1fv3r3bfFwAANCztXudmu6MdWoAAOh+zsk6NQAAAF0VoQYAAFgCoQYAAFgCoQYAAFgCoQYAAFgCoQYAAFgCoQYAAFgCoQYAAFgCoQYAAFgCoQYAAFgCoQYAAFgCoQYAAFgCoQYAAFgCoQYAAFgCoQYAAFgCoQYAAFgCoQYAAFgCoQYAAFgCoQYAAFgCoQYAAFgCoQYAAFgCoQYAAFgCoQYAAFgCoQYAAFgCoQYAAFgCoQYAAFgCoQYAAFgCoQYAAFgCoQYAAFgCoQYAAFgCoQYAAFgCoQYAAFgCoQYAAFgCoQYAAFgCoQYAAFgCoQYAAFgCoQYAAFgCoQYAAFgCoQYAAFgCoQYAAFgCoQYAAFgCoQYAAFgCoQYAAFgCoQYAAFgCoQYAAFgCoQYAAFgCoQYAAFgCoQYAAFgCoQYAAFgCoQYAAFgCoQYAAFgCoQYAAFgCoQYAAFgCoQYAAFgCoQYAAFgCoQYAAFgCoQYAAFgCoQYAAFgCoQYAAFhCh0LNihUrlJaWJpfLpczMTG3atOmM5ZcvX6709HRFR0drxIgRWrduXasyDz/8sEaMGKHo6GgNHTpUd9xxh2prawO3L1myRDabLegycODAjlQfAABYUGR777BhwwbNnz9fK1as0KRJk/Too49q6tSp2rlzp1JSUlqVz8vL08KFC7Vq1SpdeumlKigo0C233KI+ffpo+vTpkqQ///nPuuuuu7RmzRplZ2drz549uummmyRJf/jDHwKPNWrUKL322muBbbvd3t7qAwAAi2p3qFm2bJl+8pOf6Oabb5ZktrC88sorysvLU25ubqvyjz/+uH76059q1qxZkqQLLrhA7733nh544IFAqHn33Xc1adIkff/735ckpaamas6cOSooKAiubGQkrTMAACCkdnU/1dXVqbCwUDk5OUH7c3JytGXLlpD38Xq9crlcQfuio6NVUFCg+vp6SdLkyZNVWFgYCDH79u3Txo0bde211wbdb+/evUpOTlZaWppmz56tffv2nbG+Xq9XHo8n6AIAAKypXaGmvLxcPp9PSUlJQfuTkpJUWloa8j5XX321HnvsMRUWFsowDG3dulVr1qxRfX29ysvLJUmzZ8/WPffco8mTJ8vhcGj48OGaMmWK7rrrrsDjZGVlad26dXrllVe0atUqlZaWKjs7WxUVFaetb25urhISEgKXoUOHtufpAgCAbqRDA4VtNlvQtmEYrfb5LV68WFOnTtWECRPkcDg0Y8aMwHgZ/5iYN998U/fdd59WrFihDz/8UM8884xefPFF3XPPPYHHmTp1qq6//nqNGTNGV111lf7xj39IktauXXvaei5cuFButztwOXToUEeeLgAA6AbaFWoSExNlt9tbtcqUlZW1ar3xi46O1po1a1RTU6MDBw6oqKhIqampiouLU2JioiQz+MydO1c333yzxowZo+uuu07333+/cnNz1djYGPJxY2JiNGbMGO3du/e09XU6nYqPjw+6AAAAa2pXqImKilJmZqby8/OD9ufn5ys7O/uM93U4HBoyZIjsdrvWr1+vadOmKSLCPHxNTU3gup/dbpdhGDIMI+Tjeb1e7dq1S4MGDWrPUwAAABbV7tlPCxYs0Ny5czV+/HhNnDhRK1euVFFRkebNmyfJ7PIpLi4OrEWzZ88eFRQUKCsrS8ePH9eyZcu0Y8eOoG6j6dOna9myZRo3bpyysrL0+eefa/Hixfrud78b6KK68847NX36dKWkpKisrEz33nuvPB6Pbrzxxs74PQAAgG6u3aFm1qxZqqio0NKlS1VSUqLRo0dr48aNGjZsmCSppKRERUVFgfI+n08PPfSQdu/eLYfDoSlTpmjLli1KTU0NlFm0aJFsNpsWLVqk4uJi9e/fX9OnT9d9990XKPPll19qzpw5Ki8vV//+/TVhwgS99957geMCAICezWacrn/HgjwejxISEuR2uxlfAwBAN9HWz2/O/QQAACyBUAMAACyBUAMAACyBUAMAACyBUAMAACyBUAMAACyBUAMAACyBUAMAACyBUAMAACyBUAMAACyBUAMAACyBUAMAACyBUAMAACyBUAMAACyBUAMAACyBUAMAACyBUAMAACyBUAMAACyBUAMAACyBUAMAACyBUAMAACyBUAMAACyBUAMAACyBUAMAACyBUAMAACyBUAMAACyBUAMAACyBUAMAACyBUAMAACyBUAMAACyBUAMAACyBUAMAACyBUAMAACyBUAMAACyBUAMAACyBUAMAACyBUAMAACyBUAMAACyBUAMAACyBUAMAACyBUAMAACyBUAMAACyBUAMAACyBUAMAACyBUAMAACyBUAMAACyBUAMAACyBUAMAACyBUAMAACyBUAMAACyBUAMAACyBUAMAACyBUAMAACyBUAMAACyBUAMAACyBUAMAACyBUAMAACyBUAMAACyhQ6FmxYoVSktLk8vlUmZmpjZt2nTG8suXL1d6erqio6M1YsQIrVu3rlWZhx9+WCNGjFB0dLSGDh2qO+64Q7W1tWd1XAAA0IMY7bR+/XrD4XAYq1atMnbu3GncfvvtRkxMjHHw4MGQ5VesWGHExcUZ69evN7744gvjqaeeMmJjY40XXnghUOaJJ54wnE6n8ec//9nYv3+/8corrxiDBg0y5s+f3+HjhuJ2uw1Jhtvtbu/TBgAAYdLWz2+bYRhGe0JQVlaWMjIylJeXF9iXnp6umTNnKjc3t1X57OxsTZo0SQ8++GBg3/z587V161Zt3rxZknTbbbdp165dev311wNl/uu//ksFBQWB1pj2HjcUj8ejhIQEud1uxcfHt+dpAwCAMGnr53e7up/q6upUWFionJycoP05OTnasmVLyPt4vV65XK6gfdHR0SooKFB9fb0kafLkySosLFRBQYEkad++fdq4caOuvfbaDh/Xf2yPxxN0AQAA1tSuUFNeXi6fz6ekpKSg/UlJSSotLQ15n6uvvlqPPfaYCgsLZRiGtm7dqjVr1qi+vl7l5eWSpNmzZ+uee+7R5MmT5XA4NHz4cE2ZMkV33XVXh48rSbm5uUpISAhchg4d2p6nCwAAupEODRS22WxB24ZhtNrnt3jxYk2dOlUTJkyQw+HQjBkzdNNNN0mS7Ha7JOnNN9/UfffdpxUrVujDDz/UM888oxdffFH33HNPh48rSQsXLpTb7Q5cDh061N6nCgAAuol2hZrExETZ7fZWrSNlZWWtWlH8oqOjtWbNGtXU1OjAgQMqKipSamqq4uLilJiYKMkMPnPnztXNN9+sMWPG6LrrrtP999+v3NxcNTY2dui4kuR0OhUfHx90AQAA1tSuUBMVFaXMzEzl5+cH7c/Pz1d2dvYZ7+twODRkyBDZ7XatX79e06ZNU0SEefiamprAdT+73S7DMGQYxlkdFwAA9AyR7b3DggULNHfuXI0fP14TJ07UypUrVVRUpHnz5kkyu3yKi4sDa9Hs2bNHBQUFysrK0vHjx7Vs2TLt2LFDa9euDTzm9OnTtWzZMo0bN05ZWVn6/PPPtXjxYn33u98NdFF91XEBAEDP1u5QM2vWLFVUVGjp0qUqKSnR6NGjtXHjRg0bNkySVFJSoqKiokB5n8+nhx56SLt375bD4dCUKVO0ZcsWpaamBsosWrRINptNixYtUnFxsfr376/p06frvvvua/NxAQBAz9budWq6M9apAQCg+zkn69QAAAB0VYQaAABgCYQaAABgCYQaAABgCYQaAABgCYQaAABgCYQaAABgCYQaAABgCe1eURgAAHQSX730zsNShEO67N+lqF7hrlG3RqgBACAcTp6Q/nqjtO9Nc7tgpfTtpdLo6yWbLZw167bofgIA4Hw7fkBanWMGGkeMlDBU8hRLT/9EWvMd6fC2cNewWyLUAABwPh36QFp1pVS+W4pLln78knTbB9KURZKjl3ToPWnlFOn5W6XKI+GubbdCqAEA4HzZ8Yy0dppUUy4NvFi65XVp0FjJES194xfSbVulMTdIMqRtT0h/ypTe+aPU4A13zbsFQg0AAOeaYUhv/7f0tx9JDbXS16dKP3pJik8OLpcwWLp+lfTjV6XkcVJdpZT/G2nFBGn3S+bj4LQINQAAnEsNddLzt0lv3GNuT/hPafafJWfs6e+TkiXd/IY0M0+KTZKO7ZOemi098S9S2Wfnp97dEKEGAIBz5eRxM4hsf0KyRUjX/Lf0nVwpwv7V942IkC75vvSzQmnyHZI9SvriDSkvW9r4S6nm2LmvfzdDqAEA4Fw4tk967NvSgU1SVKz0/b9Il93S/sdxxklXLZFufV8aOU0yfFLBo9KfMqSCVZKvodOr3l0RagAA6GxF75kznCr2SvFDpB+/Il347bN7zL4XmN1Wc5+T+qebrUAb75Qevbx5rZsejlADAEBn+uRv0trp0slj5mDfW16XBo7uvMcfPkWat9nsyoruI5XtlNbNkNb/QDq2v/OO0w0RagAA6AyGIb31e3MBPV+d2VV00z+kuIGdfyx7pNmV9bMPpct+Ktns0mcvSssvk15bInkrO/+Y3QChBgCAs9XglZ6dJ/3zPnM7+2fSDY9LUTHn9ri9+krX/F76j3ekC6aYYWrzH8z1bbY/KTU2ntvjdzGEGgAAzkbNMenx66SP15stJtMelnLuNWcvnS8D0qW5z0qzn5L6pElVR6Tn/kN67ErpUMH5q0eYEWoAAOioii+kx66SDr4jOeOlH/xVGv+j8NTFZpNGXmPOkvr2UikqTjr8obT629Iz/y55DoenXucRoQYAgI448I7ZEnLsCykhRfrJq9LXrgx3raRIpzTpdnN9m3E/lGSTPt5gdkm99aBUfzLcNTxnCDWd4eO/Su+u6HF9lwDQY3203pxxdPK4NHi8OcNpQHq4axUsLkmasVy65Q1paJZUXyP9817pkcukT5+z5CkXCDVny3NYevEO6ZWF0pPfk6rKwl0jAMC5YhjSG/dJz/5UaqyXLpoh3fSiFDsg3DU7vcEZ5jo516+W4gdL7iLprzdK/zdNKv0k3LXrVISasxU3SLrqt1KkS/r8NWnFRGnPK+GuFQCgs9XXSk/fLL39e3N78h3Sv/6feYbtrs5mk8b8q3TbB9I37jI/sw5ulh69Qvr7fKm6PNw17BQ2w7Bg+9NpeDweJSQkyO12Kz4+vnMfvGyX9LefSGWfmtuX/dQcqOVwde5xAADnX3W5ubjdofekiEhzhlPG3HDXquNOFEn5v5U+fcbcdiZI3/yVdOktUmRUeOsWQls/vwk1nam+1lz06P08c3vARWZzX9JFnX8sAMD5cXSPObzg+AHzw3/WOumCb4a7Vp3j4BbppV9JpR+b2/0uNE+4ebandOhkhJoQznmo8dubb64PUH1UsjvN9Qouu8Vs/gMAdB/735Y2/FCqdUu9h5lTtvuPCHetOlejT9r2hPT6UqmmqRvqwhzp6vulxAvDW7cmhJoQzluokcwBw8/9p/R5vrl94dXmKPTY/uf2uACAzrHtCenvt0uNDdKQy6Q5T0kxieGu1blT6zZP8/D+o+Yg6IhIKWuedMUvpOjeYa0aoSaE8xpqJHOUfMFK6dXFks8rxQyQrsuTvnbVuT82AKBjGhulN+6RNi8zt0dfL81Y0XPGSJZ/Lr16t7TnZXO7V6L0rUVSxr9JEfawVIlQE8J5DzV+pTvME5wd/czcnvCf0lVLzAWSAKs7ecJcpr3fcKnvBXTDomurP2kOH/j0WXP7il9I3/z1+T3lQVex9zVzuZLyPeZ20hhp6v8npU4+71Uh1IQQtlAjmW+UVxdLH6wyt5PGSNc/Jg0YeX7rAZwPvgbpi9fNE+rtfslsqZSk+CFS2uVS6uXmz94p4a0n0FLVUWn9HOnLD6QIh/Td/1+65PvhrlV4+eqlDx6T/pkred3mvotmSjn3nNf3L6EmhLCGGr/dL0vP/6dUU2GuE3D1fdL4n/DtFdZQ+om0/Snpk7+YA+X9ElKkyhKzn76l3sOaQs4V5s/45PNbX8Cv7DNzhtOJIsnVW5r957C0SHRZ1eXmGcgL/08yGs3Pr+yfS5Pnn/szkYtQE1KXCDWSVFlqNm9+8Ya5PeIa6buPSDH9wlcnoKOqyqSP/2IuG3+kxeqkvRKlMd+TLpkjDbzYbK089L50YJM5o6T4Q8nwBT9W3+EtWnKu6NqrtMI6vvin9JcbzZaIvhdI3/+rlPi1cNeqayr9RHp5ofk+lqS4ZHNNtjH/ek6/nBNqQugyoUYyB6K9n2eua+Ork2IHStf9jzR8SnjrBbRFfa20e6P00VPS5683hxN7lPT175hN9l+7SrI7Tv8Y3kqp6D0z4BzYJJV8ZH4DbClxRHPISb2c4I/OV7hW+scCc4ZTykRp1p/5O/sqhiHt+rs5mPhEkblvaJa5vs3gzHNySEJNCF0q1PiVfGwOIvYPxMr+mfSt33TJFR3RwxmGOeD3oyelHc82969L5gn9LpkjjfoXqVffjj1+rdtcCGz/JunA2+YAe53y72nAqBYhZ5IU3afDTwc9XGOj9PoS6Z0/mttjbpBmPMIEjvaor5XefUTatEyqrzb3XfID6crfmifT7ESEmhC6ZKiRpLoaM/FuXWNuD7zYXIm4/9fDWy9Ako4flD7eYLbKHNvXvD9+iDR2ljR2zrlZoKvmmHTwnaaQs0kq23lKAZs06OLmrqqUiZKrC72v0XXV1UjP/rvZ2iBJ31wofeNXjG3sKM9h6bXfSR+vl2x2ad7mTl9Jn1ATQpcNNX67XpReuM08lX1ktDl1LuNG3mg4/7yV0s7nzUG/Bzc373fESBd91wwyqZef32muVUfNuvhDjr91089ml5IvaZ5ZlTLxvAxgRDdTeUR6arZ0+EOzu3TGcuniG8JdK2s49IFUvFWa8B+d/tCEmhC6fKiRJE+JeUr7/W+Z2yOnSd/9U8eb9IG2avSZf3fbnzK/wTacbLrBZoaEsd+X0qdLztiwVjOgslQ6sNms8/5N0vH9wbdHRJr9+/6QMzSre5xNGefOkZ3SkzdI7kNSdF9zhtOw7HDXCm1AqAmhW4QayezrffdP0uv3mFNg45Klf3nUbGIHOtvR3eZ6Mh//Rao83Ly/39fMFpmLZ0m9h4avfm3l/rK5FWf/JsldFHy7PUoacmlzd9WQ8Yyf6Ek+f036y01SXaX5t/39v5gLQqJbINSE0G1Cjd/hbdLTN0sVn0uySZNul6bczSBinL2aY9InfzPHyRz+sHm/q7e5JPzYOeaHfnfu+jx+IDjktAxskrnOxtCs5nVyBmecebYWuq8PVksbf2HO0ku9XLphHa3f3QyhJoRuF2okqa5aevku6cN15nbyOHMQMd8w0F4NddLeV80gs+eV5oXwbHbzjLyXzDGnY1ux9cIwzEHO/unj+zdJ1WXBZRwxUsqE5pAzaKxkjwxPfdE5Gn1S/m/MGTqS2YU6/Y98MeyGCDUhdMtQ47fzeemFn0u1J8x/vlMfkMb9sHt/k8a5Zxhmi99HT5ktMyePNd828GJzPZnR/9rzzh5vGOZA4/1vNwWdzcG/G0lyxpuDjf1TyAeOCdvJ/NABddXS07dIu/9hbn9rkXT5nfzP7KYINSF061AjmWMGnp3XvJLjRTOl6Q+zVgda8xxumoa9vvlEqpIUm2TO9Bg7R0oaFb76dTWNjeaUcX8rzsHN5ro5Lbl6m4NKY5PM8Tl2R9MlqsXPr7ge0Y7yEXY+gDvKUyI9Nctc0NHulK7LM7tV0W0RakLo9qFGMptT3/mjeQ6OxgZzrZB/WWkuRAZzMaiid83Br736msvsxyZJMQPM8GflM+3W1UifvWgO+t33pgIL10W6pJHXmkHmgil0qbRFo89cDj4QcraYA0zPK9tXhKYQ+yIcbQtMdof5fogd0OI90t8aXY+ln0hPzpI8xVKvftLsp6SUrHDXCmeJUBOCJUKNX3GhOYj42D5JNuny/5K+eVfPG+hoGFL5XvOM0J+/bnYjBKYinyIi0gw3sf3Nf+KxA5q2k1rsa/rn7kroHt+SGxuloi3mNOydz0l1Vc23pUw0g8yomebzQcf5Gsxv/YfeN3/HvrqmS33Tpa7Fz9NdD7GvsT54f7i5eje/N1qGHf97w/8+6ZXYNcPxnlelv/3IfI0Sv27OcOqbFu5aoRMQakKwVKiRJG+V9NKvpO1PmNuDx0vXrzJPyGZlJ0+Ya5N8/rp5UlD3oeDbYweaM3e8HnPBtqojrcdLfBW785Sw4w9AA4L/6ccMCM+6LRVfmF1LH69vPveKJPVOMYPM2NnW/zuwGsMwW1/PGIxODUkdDFINXnMGXNUR82zqVUfMY7eZzWwFCQpALVpFW75PovuenxbS91dKL//KPH9Y2hXSDY9L0b3P/XFxXhBqQrBcqPHb8Yz09/nmuXiiYqVr/tv8UOsOLQ1t0egzB7t+/rrZIvPl1uCzO9ujzLEOw6+UvnalNOCi1s+9oU6qKTf/eVeVNV2arle33D4afE6jtnDEfPU/dn8Acrg6/ns4eUL69Flz0O+h95v3R8WZrTFj55itM1buYsO50dhoTkLwvw/8Qcf/nmj5Xqk+2vrEo2diszf9/Ydo8QlqLR3QsRbSRp951uiCR83tcXOlaX/oea3WFkeoCcGyoUaSThySnvl3sytCMme0TFvWfbsd3MVmK8wXr5vjQ04eD7498evNIWbYJCmqV+cdu/5k0z/wUP/YW/7DL5Pqa9r32M6EFmGn/+mb92P6m/+UfQ3m7+GjJ6XPNko+r/k4tghzfMzYOeZ4mc58/sCZNPqkmoozfDFocb3dLaRRZ24Zbfl+ccaardVP/0Ta87J5/6uWSJPmW+cLHQIINSFYOtRI5j+bTcukN3PNloyEFLM7KmVCuGv21epPmoMxv3jDbJE5uiv4dmeCdME3zBAz/FtmN0tX4K366n/s/hDU3jET0X0lGcGBrv/IplV+b5Dikzv1qQCdzlff9Pff8v1wSsuo//3SkRZSu8NsYYp0Sdc9arZYwpIINSFYPtT4HfrA/PZy4qD5jf6KX0pX/KJrDewzDHOGkn+A78F3pIbaFgVs5nl7vnal2SIzOLNr1b+9DKOpef80LT5B33qPBnevRfeVxnzPXBxv0CV8C4U11de2CDyntgKdEoDqq5vvF9NfmrPeHEcHyyLUhNBjQo0k1XrMZcE/Xm9uD80yp373SQ1fnWqOBQ/w9RQH3x6XLH3tW2aIueCbPXcZ88ZGs9m+6og5TXvQWFZABVryVjWN76mQBoyUnHHhrhHOMUJNCD0q1Ph98jfpxTvMmUDOeOnaZdLF3zs/x/Y1mFPP/a0xhz8MHmAY6Qoe4Nt/JK0QAIBW2vr53Y3b89EmY/7VPDPxM7eYM2aeuVn6PN+cIeU6B8HuxKHmELP/rdarsvYf2RRivmUO8HVEd34dAAA9Ei01PYWvQdr039JbD5itJb2HSdc/Jg297Owet67GHA/jn25dvif4dldvsyvJP8A3YcjZHQ8A0OPQ/RRCjw41fkXvmSd5cxeZ60d88y5zNeK2nqjPMMxz5PhDzMF3m6cZS+bA5MHjWwzwzeAkgACAs9LWz+8OrdK1YsUKpaWlyeVyKTMzU5s2bTpj+eXLlys9PV3R0dEaMWKE1q1bF3T7N7/5TdlstlaXa6+9NlBmyZIlrW4fOHBgR6rfs6VMkP5js7mOjeEzzyH1f9cGr0p7qppj5tic5/5TWpYu5WVL+YvN9WN8XvP8Uxn/Jn1vrfTLfdLN+WZYGnopgQYAcN60e0zNhg0bNH/+fK1YsUKTJk3So48+qqlTp2rnzp1KSWm9dkheXp4WLlyoVatW6dJLL1VBQYFuueUW9enTR9OnT5ckPfPMM6qra17Do6KiQmPHjtX3vhc8oHXUqFF67bXXAtt2Ox+YHeJKMLueLvy29I87zRNA5k2Wpv/BPJOtr0H68oMWA3y3KXByREmKjDZPoOkf4Jv4dQb4AgDCrt3dT1lZWcrIyFBeXl5gX3p6umbOnKnc3NxW5bOzszVp0iQ9+OCDgX3z58/X1q1btXnz5pDHePjhh/Wb3/xGJSUliomJkWS21Dz33HPavn17e6obhO6nEI7tN0+MWbzV3B5yqbl+jNcTXG7AReaYmK9dKaVkn91y/wAAtMM5mf1UV1enwsJC3XXXXUH7c3JytGXLlpD38Xq9crmCPwCjo6NVUFCg+vp6ORytz8+xevVqzZ49OxBo/Pbu3avk5GQ5nU5lZWXp/vvv1wUXcNK+s9I3Tfrxy+YA4k0PmS00khTdx1yG3z/Al9VrAQBdXLtCTXl5uXw+n5KSkoL2JyUlqbS0NOR9rr76aj322GOaOXOmMjIyVFhYqDVr1qi+vl7l5eUaNGhQUPmCggLt2LFDq1evDtqflZWldevW6etf/7qOHDmie++9V9nZ2fr000/Vr1+/kMf2er3yepsHsXo8npDlejy7Q/rWImnENWaoGTxeSr6E8TAAgG6lQ+vU2E4ZP2EYRqt9fosXL1ZpaakmTJggwzCUlJSkm266Sb///e9DjolZvXq1Ro8ercsuC55qPHXq1MD1MWPGaOLEiRo+fLjWrl2rBQsWhDx2bm6ufve737X36fVcgzPMCwAA3VC7Zj8lJibKbre3apUpKytr1XrjFx0drTVr1qimpkYHDhxQUVGRUlNTFRcXp8TExKCyNTU1Wr9+vW6++eavrEtMTIzGjBmjvXv3nrbMwoUL5Xa7A5dDhw614VkCAIDuqF2hJioqSpmZmcrPzw/an5+fr+zs7DPe1+FwaMiQIbLb7Vq/fr2mTZumiIjgw//lL3+R1+vVD3/4w6+si9fr1a5du1p1X7XkdDoVHx8fdAEAANbU7u6nBQsWaO7cuRo/frwmTpyolStXqqioSPPmzZNkto4UFxcH1qLZs2ePCgoKlJWVpePHj2vZsmXasWOH1q5d2+qxV69erZkzZ4YcI3PnnXdq+vTpSklJUVlZme699155PB7deOON7X0KAADAgtodambNmqWKigotXbpUJSUlGj16tDZu3Khhw4ZJkkpKSlRU1LyQm8/n00MPPaTdu3fL4XBoypQp2rJli1JTU4Med8+ePdq8ebNeffXVkMf98ssvNWfOHJWXl6t///6aMGGC3nvvvcBxAQBAz8ZpEgAAQJd2Tk+TAAAA0NUQagAAgCUQagAAgCUQagAAgCUQagAAgCUQagAAgCUQagAAgCUQagAAgCV06Czd3ZV/nUGPxxPmmgAAgLbyf25/1XrBPSrUVFZWSpKGDh0a5poAAID2qqysVEJCwmlv71GnSWhsbNThw4cVFxcnm83WaY/r8Xg0dOhQHTp0iNMvdAG8Hl0Pr0nXwuvRtfB6fDXDMFRZWank5GRFRJx+5EyPaqmJiIjQkCFDztnjx8fH8wfZhfB6dD28Jl0Lr0fXwutxZmdqofFjoDAAALAEQg0AALAEQk0ncDqd+u1vfyun0xnuqkC8Hl0Rr0nXwuvRtfB6dJ4eNVAYAABYFy01AADAEgg1AADAEgg1AADAEgg1AADAEgg1nWDFihVKS0uTy+VSZmamNm3aFO4q9Ui5ubm69NJLFRcXpwEDBmjmzJnavXt3uKuFJrm5ubLZbJo/f364q9JjFRcX64c//KH69eunXr166ZJLLlFhYWG4q9VjNTQ0aNGiRUpLS1N0dLQuuOACLV26VI2NjeGuWrdFqDlLGzZs0Pz583X33Xdr27ZtuvzyyzV16lQVFRWFu2o9zltvvaVbb71V7733nvLz89XQ0KCcnBxVV1eHu2o93gcffKCVK1fq4osvDndVeqzjx49r0qRJcjgceumll7Rz50499NBD6t27d7ir1mM98MAD+p//+R898sgj2rVrl37/+9/rwQcf1J/+9KdwV63bYkr3WcrKylJGRoby8vIC+9LT0zVz5kzl5uaGsWY4evSoBgwYoLfeektXXHFFuKvTY1VVVSkjI0MrVqzQvffeq0suuUQPP/xwuKvV49x111165513aEnuQqZNm6akpCStXr06sO/6669Xr1699Pjjj4exZt0XLTVnoa6uToWFhcrJyQnan5OToy1btoSpVvBzu92SpL59+4a5Jj3brbfeqmuvvVZXXXVVuKvSo73wwgsaP368vve972nAgAEaN26cVq1aFe5q9WiTJ0/W66+/rj179kiSPvroI23evFnXXHNNmGvWffWoE1p2tvLycvl8PiUlJQXtT0pKUmlpaZhqBck8o+uCBQs0efJkjR49OtzV6bHWr1+vDz/8UB988EG4q9Lj7du3T3l5eVqwYIF+/etfq6CgQD//+c/ldDr1b//2b+GuXo/0q1/9Sm63WyNHjpTdbpfP59N9992nOXPmhLtq3RahphPYbLagbcMwWu3D+XXbbbfp448/1ubNm8NdlR7r0KFDuv322/Xqq6/K5XKFuzo9XmNjo8aPH6/7779fkjRu3Dh9+umnysvLI9SEyYYNG/TEE0/oySef1KhRo7R9+3bNnz9fycnJuvHGG8NdvW6JUHMWEhMTZbfbW7XKlJWVtWq9wfnzs5/9TC+88ILefvttDRkyJNzV6bEKCwtVVlamzMzMwD6fz6e3335bjzzyiLxer+x2exhr2LMMGjRIF110UdC+9PR0Pf3002GqEX7xi1/orrvu0uzZsyVJY8aM0cGDB5Wbm0uo6SDG1JyFqKgoZWZmKj8/P2h/fn6+srOzw1SrnsswDN1222165pln9MYbbygtLS3cVerRrrzySn3yySfavn174DJ+/Hj94Ac/0Pbt2wk059mkSZNaLXGwZ88eDRs2LEw1Qk1NjSIigj+G7XY7U7rPAi01Z2nBggWaO3euxo8fr4kTJ2rlypUqKirSvHnzwl21HufWW2/Vk08+qeeff15xcXGBFrSEhARFR0eHuXY9T1xcXKvxTDExMerXrx/jnMLgjjvuUHZ2tu6//37dcMMNKigo0MqVK7Vy5cpwV63Hmj59uu677z6lpKRo1KhR2rZtm5YtW6Yf//jH4a5a92XgrC1fvtwYNmyYERUVZWRkZBhvvfVWuKvUI0kKefnf//3fcFcNTb7xjW8Yt99+e7ir0WP9/e9/N0aPHm04nU5j5MiRxsqVK8NdpR7N4/EYt99+u5GSkmK4XC7jggsuMO6++27D6/WGu2rdFuvUAAAAS2BMDQAAsARCDQAAsARCDQAAsARCDQAAsARCDQAAsARCDQAAsARCDQAAsARCDQAAsARCDQAAsARCDQAAsARCDQAAsARCDQAAsIT/Bxtui6TnwUyiAAAAAElFTkSuQmCC", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "plt.plot(history.history['accuracy'])\n", "plt.plot(history.history['val_accuracy'])" ] }, { "cell_type": "code", "execution_count": 87, "id": "2ea6304e-0080-4a27-b5e4-371c50576bf5", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "" ] }, "execution_count": 87, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "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", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "plt.imshow(x_train[0])" ] }, { "cell_type": "code", "execution_count": 89, "id": "3888fac5-f6c8-46f1-bb4d-9a74434aae46", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "" ] }, "execution_count": 89, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "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", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "plt.imshow(x_test[0])" ] }, { "cell_type": "code", "execution_count": 93, "id": "9ea9785d-7a70-44a1-96e1-8a6de7599787", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 123ms/step\n" ] }, { "data": { "text/plain": [ "array([7], dtype=int64)" ] }, "execution_count": 93, "metadata": {}, "output_type": "execute_result" } ], "source": [ "model.predict(x_test[0].reshape(1,28,28)).argmax(axis = 1)" ] }, { "cell_type": "code", "execution_count": 95, "id": "68e87943-0bde-4f4d-8cd4-56cec839e8dd", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 96ms/step\n" ] }, { "data": { "text/plain": [ "array([2], dtype=int64)" ] }, "execution_count": 95, "metadata": {}, "output_type": "execute_result" } ], "source": [ "plt.imshow(x_test[0])" ] }, { "cell_type": "code", "execution_count": null, "id": "16257c20-33b9-413c-bf84-bcfe94b73063", "metadata": {}, "outputs": [], "source": [] } ], "metadata": { "kernelspec": { "display_name": "Python 3 (ipykernel)", "language": "python", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.12.4" } }, "nbformat": 4, "nbformat_minor": 5 }