{ "cells": [ { "cell_type": "markdown", "id": "a21ede8e", "metadata": {}, "source": [ "# Re-shaping numpy arrays to flat 1D\n", "The CIFAR10 dataset is available in several formats as we know. Eg The images stored in appropriate sub-folders, as csv files, as an archive, etc. This short notebook demonstrates a way to reshape the datset loaded from keras' datasets.\n", "It reshapes these from (10000,32,32,3) to (10000,3072). That is, samples are stored as rows of 32*32 R values, followed by 32*32 G values then 32*32 B values.\n", "\n", "A. Krizhevsky, 2009, \u0010Learning multiple layers of features from tiny images\u0011, Master's Thesis, Department\n", "of Computer Science, University of Toronto" ] }, { "cell_type": "code", "execution_count": 1, "id": "4e4eb15d", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "'2.11.0'" ] }, "execution_count": 1, "metadata": {}, "output_type": "execute_result" } ], "source": [ "import tensorflow as tf\n", "from tensorflow import keras\n", "import numpy as np\n", "keras.__version__" ] }, { "cell_type": "code", "execution_count": 2, "id": "26df7681", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "'2.11.0'" ] }, "execution_count": 2, "metadata": {}, "output_type": "execute_result" } ], "source": [ "tf.__version__" ] }, { "cell_type": "code", "execution_count": 3, "id": "88743e4f", "metadata": {}, "outputs": [], "source": [ "tf.keras.datasets.cifar10.load_data()\n", "Cifar10=keras.datasets.cifar10\n", "#fashion_mnist=keras.datasets.fashion_mnist\n", "(X_train_full, y_train_full),(X_test,y_test) = Cifar10.load_data()" ] }, { "cell_type": "code", "execution_count": 9, "id": "eacdb15b", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "(10000, 32, 32, 3)\n" ] }, { "data": { "text/plain": [ "array([[[[158, 112, 49],\n", " [159, 111, 47],\n", " [165, 116, 51],\n", " ...,\n", " [137, 95, 36],\n", " [126, 91, 36],\n", " [116, 85, 33]],\n", "\n", " [[152, 112, 51],\n", " [151, 110, 40],\n", " [159, 114, 45],\n", " ...,\n", " [136, 95, 31],\n", " [125, 91, 32],\n", " [119, 88, 34]],\n", "\n", " [[151, 110, 47],\n", " [151, 109, 33],\n", " [158, 111, 36],\n", " ...,\n", " [139, 98, 34],\n", " [130, 95, 34],\n", " [120, 89, 33]],\n", "\n", " ...,\n", "\n", " [[ 68, 124, 177],\n", " [ 42, 100, 148],\n", " [ 31, 88, 137],\n", " ...,\n", " [ 38, 97, 146],\n", " [ 13, 64, 108],\n", " [ 40, 85, 127]],\n", "\n", " [[ 61, 116, 168],\n", " [ 49, 102, 148],\n", " [ 35, 85, 132],\n", " ...,\n", " [ 26, 82, 130],\n", " [ 29, 82, 126],\n", " [ 20, 64, 107]],\n", "\n", " [[ 54, 107, 160],\n", " [ 56, 105, 149],\n", " [ 45, 89, 132],\n", " ...,\n", " [ 24, 77, 124],\n", " [ 34, 84, 129],\n", " [ 21, 67, 110]]],\n", "\n", "\n", " [[[235, 235, 235],\n", " [231, 231, 231],\n", " [232, 232, 232],\n", " ...,\n", " [233, 233, 233],\n", " [233, 233, 233],\n", " [232, 232, 232]],\n", "\n", " [[238, 238, 238],\n", " [235, 235, 235],\n", " [235, 235, 235],\n", " ...,\n", " [236, 236, 236],\n", " [236, 236, 236],\n", " [235, 235, 235]],\n", "\n", " [[237, 237, 237],\n", " [234, 234, 234],\n", " [234, 234, 234],\n", " ...,\n", " [235, 235, 235],\n", " [235, 235, 235],\n", " [234, 234, 234]],\n", "\n", " ...,\n", "\n", " [[ 87, 99, 89],\n", " [ 43, 51, 37],\n", " [ 19, 23, 11],\n", " ...,\n", " [169, 184, 179],\n", " [182, 197, 193],\n", " [188, 202, 201]],\n", "\n", " [[ 82, 96, 82],\n", " [ 46, 57, 36],\n", " [ 36, 44, 22],\n", " ...,\n", " [174, 189, 183],\n", " [185, 200, 196],\n", " [187, 202, 200]],\n", "\n", " [[ 85, 101, 83],\n", " [ 62, 75, 48],\n", " [ 58, 67, 38],\n", " ...,\n", " [168, 183, 178],\n", " [180, 195, 191],\n", " [186, 200, 199]]],\n", "\n", "\n", " [[[158, 190, 222],\n", " [158, 187, 218],\n", " [139, 166, 194],\n", " ...,\n", " [228, 231, 234],\n", " [237, 239, 243],\n", " [238, 241, 246]],\n", "\n", " [[170, 200, 229],\n", " [172, 199, 226],\n", " [151, 176, 201],\n", " ...,\n", " [232, 232, 236],\n", " [246, 246, 250],\n", " [246, 247, 251]],\n", "\n", " [[174, 201, 225],\n", " [176, 200, 222],\n", " [157, 179, 199],\n", " ...,\n", " [230, 229, 232],\n", " [250, 249, 251],\n", " [245, 244, 247]],\n", "\n", " ...,\n", "\n", " [[ 31, 40, 45],\n", " [ 30, 39, 44],\n", " [ 26, 35, 40],\n", " ...,\n", " [ 37, 40, 46],\n", " [ 9, 13, 14],\n", " [ 4, 7, 5]],\n", "\n", " [[ 23, 34, 39],\n", " [ 27, 38, 43],\n", " [ 25, 36, 41],\n", " ...,\n", " [ 19, 20, 24],\n", " [ 4, 6, 3],\n", " [ 5, 7, 3]],\n", "\n", " [[ 28, 41, 47],\n", " [ 30, 43, 50],\n", " [ 32, 45, 52],\n", " ...,\n", " [ 5, 6, 8],\n", " [ 4, 5, 3],\n", " [ 7, 8, 7]]],\n", "\n", "\n", " ...,\n", "\n", "\n", " [[[ 20, 15, 12],\n", " [ 19, 14, 11],\n", " [ 15, 14, 11],\n", " ...,\n", " [ 10, 9, 7],\n", " [ 12, 11, 9],\n", " [ 13, 12, 10]],\n", "\n", " [[ 21, 16, 13],\n", " [ 20, 16, 13],\n", " [ 18, 17, 12],\n", " ...,\n", " [ 10, 9, 7],\n", " [ 10, 9, 7],\n", " [ 12, 11, 9]],\n", "\n", " [[ 21, 16, 13],\n", " [ 21, 17, 12],\n", " [ 20, 18, 11],\n", " ...,\n", " [ 12, 11, 9],\n", " [ 12, 11, 9],\n", " [ 13, 12, 10]],\n", "\n", " ...,\n", "\n", " [[ 33, 25, 13],\n", " [ 34, 26, 15],\n", " [ 34, 26, 15],\n", " ...,\n", " [ 28, 25, 52],\n", " [ 29, 25, 58],\n", " [ 23, 20, 42]],\n", "\n", " [[ 33, 25, 14],\n", " [ 34, 26, 15],\n", " [ 34, 26, 15],\n", " ...,\n", " [ 27, 24, 52],\n", " [ 27, 24, 56],\n", " [ 25, 22, 47]],\n", "\n", " [[ 31, 23, 12],\n", " [ 32, 24, 13],\n", " [ 33, 25, 14],\n", " ...,\n", " [ 24, 23, 50],\n", " [ 26, 23, 53],\n", " [ 25, 20, 47]]],\n", "\n", "\n", " [[[ 25, 40, 12],\n", " [ 15, 36, 3],\n", " [ 23, 41, 18],\n", " ...,\n", " [ 61, 82, 78],\n", " [ 92, 113, 112],\n", " [ 75, 89, 92]],\n", "\n", " [[ 12, 25, 6],\n", " [ 20, 37, 7],\n", " [ 24, 36, 15],\n", " ...,\n", " [115, 134, 138],\n", " [149, 168, 177],\n", " [104, 117, 131]],\n", "\n", " [[ 12, 25, 11],\n", " [ 15, 29, 6],\n", " [ 34, 40, 24],\n", " ...,\n", " [154, 172, 182],\n", " [157, 175, 192],\n", " [116, 129, 151]],\n", "\n", " ...,\n", "\n", " [[100, 129, 81],\n", " [103, 132, 84],\n", " [104, 134, 86],\n", " ...,\n", " [ 97, 128, 84],\n", " [ 98, 126, 84],\n", " [ 91, 121, 79]],\n", "\n", " [[103, 132, 83],\n", " [104, 131, 83],\n", " [107, 135, 87],\n", " ...,\n", " [101, 132, 87],\n", " [ 99, 127, 84],\n", " [ 92, 121, 79]],\n", "\n", " [[ 95, 126, 78],\n", " [ 95, 123, 76],\n", " [101, 128, 81],\n", " ...,\n", " [ 93, 124, 80],\n", " [ 95, 123, 81],\n", " [ 92, 120, 80]]],\n", "\n", "\n", " [[[ 73, 78, 75],\n", " [ 98, 103, 113],\n", " [ 99, 106, 114],\n", " ...,\n", " [135, 150, 152],\n", " [135, 149, 154],\n", " [203, 215, 223]],\n", "\n", " [[ 69, 73, 70],\n", " [ 84, 89, 97],\n", " [ 68, 75, 81],\n", " ...,\n", " [ 85, 95, 89],\n", " [ 71, 82, 80],\n", " [120, 133, 135]],\n", "\n", " [[ 69, 73, 70],\n", " [ 90, 95, 100],\n", " [ 62, 71, 74],\n", " ...,\n", " [ 74, 81, 70],\n", " [ 53, 62, 54],\n", " [ 62, 74, 69]],\n", "\n", " ...,\n", "\n", " [[123, 128, 96],\n", " [132, 132, 102],\n", " [129, 128, 100],\n", " ...,\n", " [108, 107, 88],\n", " [ 62, 60, 55],\n", " [ 27, 27, 28]],\n", "\n", " [[115, 121, 91],\n", " [123, 124, 95],\n", " [129, 126, 99],\n", " ...,\n", " [115, 116, 94],\n", " [ 66, 65, 59],\n", " [ 27, 27, 27]],\n", "\n", " [[116, 120, 90],\n", " [121, 122, 94],\n", " [129, 128, 101],\n", " ...,\n", " [116, 115, 94],\n", " [ 68, 65, 58],\n", " [ 27, 26, 26]]]], dtype=uint8)" ] }, "execution_count": 9, "metadata": {}, "output_type": "execute_result" } ], "source": [ "X_test.shape\n", "X_Eg=X_test\n", "print(X_Eg.shape)\n", "X_Eg\n" ] }, { "cell_type": "code", "execution_count": 7, "id": "99f4a278", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "array([[158, 159, 165, ..., 124, 129, 110],\n", " [235, 231, 232, ..., 178, 191, 199],\n", " [158, 158, 139, ..., 8, 3, 7],\n", " ...,\n", " [ 20, 19, 15, ..., 50, 53, 47],\n", " [ 25, 15, 23, ..., 80, 81, 80],\n", " [ 73, 98, 99, ..., 94, 58, 26]], dtype=uint8)" ] }, "execution_count": 7, "metadata": {}, "output_type": "execute_result" } ], "source": [ "V=np.swapaxes(X_Eg,2,3)\n", "W1=np.ravel(V)\n", "W1.reshape(-1,3072)" ] }, { "cell_type": "code", "execution_count": null, "id": "78c1dab8", "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": "3.9.16" } }, "nbformat": 4, "nbformat_minor": 5 }