Skip to content

Instantly share code, notes, and snippets.

@prankshaw

prankshaw/fashion_mnist.ipynb

Created June 26, 2019 20:52
Show Gist options
  • Save prankshaw/437e71a07fe9122d4b6691c7805eb88a to your computer and use it in GitHub Desktop.
Save prankshaw/437e71a07fe9122d4b6691c7805eb88a to your computer and use it in GitHub Desktop.
Download ZIP
fashion_mnist.ipynb
Display the source blob
Display the rendered blob
Raw
fashion_mnist.ipynb
{
"nbformat": 4,
"nbformat_minor": 0,
"metadata": {
"colab": {
"name": "fashion_mnist.ipynb",
"version": "0.3.2",
"provenance": [],
"collapsed_sections": [],
"include_colab_link": true
},
"kernelspec": {
"name": "python3",
"display_name": "Python 3"
}
},
"cells": [
{
"cell_type": "markdown",
"metadata": {
"id": "view-in-github",
"colab_type": "text"
},
"source": [
"<a href=\"https://colab.research.google.com/gist/prankshaw/437e71a07fe9122d4b6691c7805eb88a/fashion_mnist.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "OuSypv7O6cO2",
"colab_type": "text"
},
"source": [
"First Try with MNIST fashion dataset\n"
]
},
{
"cell_type": "code",
"metadata": {
"id": "ZOe9oNvt6i2s",
"colab_type": "code",
"colab": {}
},
"source": [
"#importing tensorflow\n",
"import tensorflow as tf\n",
"from tensorflow import keras"
],
"execution_count": 0,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "eqv7nAs47BCj",
"colab_type": "code",
"colab": {}
},
"source": [
"#importing libraries\n",
"import numpy as np\n",
"import matplotlib.pyplot as plt"
],
"execution_count": 0,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "JKDio38C7Lzj",
"colab_type": "code",
"colab": {}
},
"source": [
"#Loading Data\n",
"fashion_mnist=keras.datasets.fashion_mnist"
],
"execution_count": 0,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "AEYBJh0X7suS",
"colab_type": "code",
"outputId": "361c5834-1e65-48a5-b9a7-88ca8a7fd379",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 153
}
},
"source": [
"(train_images,train_labels), (test_images,test_labels)=fashion_mnist.load_data()"
],
"execution_count": 0,
"outputs": [
{
"output_type": "stream",
"text": [
"Downloading data from https://storage.googleapis.com/tensorflow/tf-keras-datasets/train-labels-idx1-ubyte.gz\n",
"32768/29515 [=================================] - 0s 0us/step\n",
"Downloading data from https://storage.googleapis.com/tensorflow/tf-keras-datasets/train-images-idx3-ubyte.gz\n",
"26427392/26421880 [==============================] - 0s 0us/step\n",
"Downloading data from https://storage.googleapis.com/tensorflow/tf-keras-datasets/t10k-labels-idx1-ubyte.gz\n",
"8192/5148 [===============================================] - 0s 0us/step\n",
"Downloading data from https://storage.googleapis.com/tensorflow/tf-keras-datasets/t10k-images-idx3-ubyte.gz\n",
"4423680/4422102 [==============================] - 0s 0us/step\n"
],
"name": "stdout"
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "8lXQqhUp76G5",
"colab_type": "code",
"colab": {}
},
"source": [
"#Class names, as they are not defined in dataset\n",
"class_names = ['T-shirt/top', 'Trouser', 'Pullover', 'Dress', 'Coat',\n",
" 'Sandal', 'Shirt', 'Sneaker', 'Bag', 'Ankle boot']"
],
"execution_count": 0,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "C4Nb-6N28M3o",
"colab_type": "code",
"outputId": "be825693-b77f-4bef-9c14-afd5f7807119",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 34
}
},
"source": [
"#what the data looks like, output is of the last result only\n",
"train_images.shape\n",
"len(train_labels)\n",
"len(test_images)"
],
"execution_count": 0,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"10000"
]
},
"metadata": {
"tags": []
},
"execution_count": 24
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "tQONKin58TVC",
"colab_type": "code",
"outputId": "3a8cfdcf-ceee-4693-9b39-d47be0139d13",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 269
}
},
"source": [
"# A custom images looks like\n",
"plt.imshow(train_images[3])\n",
"plt.show()"
],
"execution_count": 0,
"outputs": [
{
"output_type": "display_data",
"data": {
"image/png": "iVBORw0KGgoAAAANSUhEUgAAAP8AAAD8CAYAAAC4nHJkAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz\nAAALEgAACxIB0t1+/AAAADl0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uIDMuMC4zLCBo\ndHRwOi8vbWF0cGxvdGxpYi5vcmcvnQurowAAEu5JREFUeJzt3WuMnOV1B/D/mcuu9+K1vb7VGGNu\nDsYgAdHKcQsqqQgpIFRIP6C4aepUKI6qEBUpqoroh7r9RKoSxIcqklOsmDSFVAKEK1mJidWKpKGO\nl0u4mQJx1tibtRd7bbz3ncvph32dLLDPeYa5vbN7/j/J2t155p15Zrz/eWfnPBdRVRCRP5m0O0BE\n6WD4iZxi+ImcYviJnGL4iZxi+ImcYviJnGL4iZxi+ImcyjXzztqkXZegq5l32RKkY4nZPtOTNdtz\nPQWzvVAKH58bsV/fs2NTZnu5s91sn1luNqO3ezzYVijbj3v8XIfZnj8Zvm2vpjCOGZ2WSq5bU/hF\n5DYAjwLIAvhXVX3Iuv4SdOEzckstd7kgZa7cbLb/5tZes33F7b8x24fO9gTb1jxpB2jpT98126c+\nfZnZ/us/tV9cvrTthWDbqelwvwHghaevM9vXf+vnZrtHh/Rgxdet+m2/iGQB/AuA2wFsAbBdRLZU\ne3tE1Fy1/M2/FcC7qnpUVWcAPAngrvp0i4garZbwrwdwfM7PJ5LLPkREdopIv4j0FzBdw90RUT01\n/NN+Vd2tqn2q2peH/eERETVPLeEfBLBhzs8XJ5cR0QJQS/gPA9gkIpeJSBuALwLYV59uEVGjVV3q\nU9WiiNwH4MeYLfXtUdU36tazFnP+z7YF29b/lV0uOzs9YbZvzJ+z73vaHidww8Ungm3fePgn5rE3\nLrFf/58as8tx4+U2s/2nH1wVbHtvbIV57OY73zbbb/6Ls2b7I4c/F2zb9JUXzWM9qKnOr6r7Aeyv\nU1+IqIk4vJfIKYafyCmGn8gphp/IKYafyCmGn8gpaeaOPT3Sq606pTdz3dVm++A/hNtGh7vt2+4s\nmu2Ssf8PtGxPz9Zi+DX8kovOmMfGFMv2+aGkdt9GzofXbyiV7NsuG48LAGTEHmOQWxceXzHzgT3U\n/FM7D5vtreqQHsR5HaloPj/P/EROMfxETjH8RE4x/EROMfxETjH8RE41denuVvb239jTZsun7WWm\nLbFSXnu7vTR3sWjfd8EoiR17b5V5bOa8/StQXlI22yVWhmyzj7fvPFKxytnPa+l4Z7Bt9dV2CfSD\nPw9P4QaAZf/2v2b7QsAzP5FTDD+RUww/kVMMP5FTDD+RUww/kVMMP5FTrPMnNj5u19I/+Mb5YNvZ\nM0vNY3XYHkMw0R35b4hMbbXITKQOv2rGPj52B+fz9vFTjTu/ZCKPrdRTCra9P2jvLf6pRVDHj+GZ\nn8gphp/IKYafyCmGn8gphp/IKYafyCmGn8ipmur8IjIAYBRACUBRVfvq0ak05A/0m+0T2/4g2Lb1\nj98yj/3Fy5vMdonMS8902rX48kh4GepYLVxP28tfZ6cjtfSOyLLjxmPLjdrnnsJKe8nzcuTcZS2Z\nftX975nHhkcILB71GOTzR6p6ug63Q0RNxLf9RE7VGn4FcEBEXhSRnfXoEBE1R61v+29S1UERWQPg\nORF5S1Wfn3uF5EVhJwAsQXhNNSJqrprO/Ko6mHwdBvAMgK3zXGe3qvapal8e9v5oRNQ8VYdfRLpE\nZOmF7wF8HsDr9eoYETVWLW/71wJ4RkQu3M6/q+qP6tIrImq4qsOvqkcBXFfHvrS0S/7x58G2u790\nzDz2l2vXm+1TZzrM9tKEvdZAbiL8Bi43VtFuzUFWnR4AcuP2m0c1fsPK+cj4hjH7cZd77HEAqw+E\n11Eona5t6/LFgKU+IqcYfiKnGH4ipxh+IqcYfiKnGH4ip7h0d0Ly9tRWLYSn1X7/9pvtG/9WNT36\nnaxRygMAMeafxqbcZicjU34jO5PHbj9jTAnWWk89keOXP/5CjXewuPHMT+QUw0/kFMNP5BTDT+QU\nw0/kFMNP5BTDT+QU6/wJq44fUzw6YLf/+vfN9raN4/bxU/byZ1lr2m7ZPBTZabsdGXscQM7uOqZW\nhscBZGLrY0dOTe0n7O3BycYzP5FTDD+RUww/kVMMP5FTDD+RUww/kVMMP5FTrPM3gWbsOe/LuifN\n9jNlu85fag/ffn7UrtOXI6XyTGQcQKb64RHmOgSV6BiubVly73jmJ3KK4SdyiuEncorhJ3KK4Sdy\niuEncorhJ3IqWucXkT0A7gQwrKrXJpf1AvghgEsBDAC4R1XPNq6bLSBjLGBftgvWnUP2a2z2msik\n+8hLdNZYGx/2EAOU2yLr+k/ZtfRSeBdsAEDOOD42hmCm135eugerHyhQyz4Ni0UlZ/7vAbjtI5c9\nAOCgqm4CcDD5mYgWkGj4VfV5ACMfufguAHuT7/cCuLvO/SKiBqv2b/61qjqUfH8SwNo69YeImqTm\nD/xUVWH8ZSkiO0WkX0T6C4gtGEdEzVJt+E+JyDoASL4Oh66oqrtVtU9V+/Jor/LuiKjeqg3/PgA7\nku93AHi2Pt0homaJhl9EngDwAoCrROSEiNwL4CEAt4rIOwA+l/xMRAtItM6vqtsDTbfUuS+LVs9A\npB4tdq293GbXu2eWh9u6jtuv75miXcef7rX71nbOPl6K4bZspJQeWwchU7CPJxtH+BE5xfATOcXw\nEznF8BM5xfATOcXwEznFpbubID9ul+qmtMYlqI2b18jLeyky6FIis43bz9rluKlV4cdW6LJvO6bU\nzqW7a8EzP5FTDD+RUww/kVMMP5FTDD+RUww/kVMMP5FTrPNXKrI8tyVTsIvlw2d67ONn7NfotnPV\nv4a3n7PbCwW7ll7ssI/vGA6PA5hcbd92bsxYLh2AOcCBonjmJ3KK4SdyiuEncorhJ3KK4SdyiuEn\ncorhJ3KKdf5K1bBF9/Ry+2levsze3Xxkwj5+uje8BnZsgzQ5bW9VXe60a+nZHnv97fJMrFZviCzd\nPXqJvT+4tVyAhy24Y3jmJ3KK4SdyiuEncorhJ3KK4SdyiuEncorhJ3IqWucXkT0A7gQwrKrXJpft\nAvBVAO8nV3tQVfc3qpMtoYb5/J0n7Wr7qSMrzfaewcic+s58sC03ZR6KyTWRbbAjdfq29zrN9qzx\n0AtLzUPRcdLu28RFdjvZKjnzfw/AbfNc/oiqXp/8W9zBJ1qEouFX1ecBjDShL0TURLX8zX+fiLwq\nIntEZEXdekRETVFt+L8D4AoA1wMYAvBw6IoislNE+kWkvxAdaU5EzVJV+FX1lKqWVLUM4LsAthrX\n3a2qfaral0dkV0giapqqwi8i6+b8+AUAr9enO0TULJWU+p4A8FkAq0TkBIC/B/BZEbkegAIYAPC1\nBvaRiBogGn5V3T7PxY81oC+L1uDNdi28e8A+ftlAwWzPTYbHIOTO2Z+zFJfbf4pN9YbHEABAfjwy\n33863Lex9fZaAjFn19j3ndu4IdhWPHbcvnFr/QagpnEfrYIj/IicYviJnGL4iZxi+ImcYviJnGL4\niZzi0t0X1FDayV51pXno5GZ7Xm1pwC63zSy3y23TveG+Lz1qL29dtNa3BjC+0S5p5T+wf4UKS63z\nS21TcrNj9rnr6F+GS32X7IqU+hZBKS+GZ34ipxh+IqcYfiKnGH4ipxh+IqcYfiKnGH4ip1jnv6CG\nuu7xP1ljtne8ZR9fWmLXu9vO28dPXBKe2rp00J72OrI58itgH47OyLLi564NP7Ylw7Gtx+3/k7Zz\n9rlr8qJisE1uuMY8Vl9+w2xfDHjmJ3KK4SdyiuEncorhJ3KK4SdyiuEncorhJ3KKdf46GL/GXh67\n6w17vr5m7Fp5KbbRUZtVjLdf3zWyjEGMlO0xClIOP7ZMZPe2jvVjZntxtMdsz50PP7jRK7vNY7tf\nNpsXBZ75iZxi+ImcYviJnGL4iZxi+ImcYviJnGL4iZyK1vlFZAOAxwGsxexC67tV9VER6QXwQwCX\nAhgAcI+qnm1cV9OVuXZzsC170t5qOlanz4/b7eXY/1IxXEsvdtT2+i7GbQOAROb7qzkGwR5kMDVp\nP6/l1eH5+gDQfjL8xE2stu/bHgWwOFTym1EE8E1V3QJgG4Cvi8gWAA8AOKiqmwAcTH4mogUiGn5V\nHVLVl5LvRwEcAbAewF0A9iZX2wvg7kZ1kojq7xO9JxSRSwHcAOAQgLWqOpQ0ncTsnwVEtEBUHH4R\n6QbwFID7VfVDq8qpqiKw8ZqI7BSRfhHpLyAymJuImqai8ItIHrPB/4GqPp1cfEpE1iXt6wAMz3es\nqu5W1T5V7csjNkOFiJolGn4REQCPATiiqt+e07QPwI7k+x0Anq1/94ioUSqZ0nsjgC8DeE1EXkku\nexDAQwD+Q0TuBXAMwD2N6WJrGL8iPH1UIjtNa+RZLtkVrfiUXmPabLRMGLvp5XY5LVO0tw9HLvzk\nxKYT547Z24vr5RN2+/vhBz+zLHLf637PbC8OnbRvYAGI/mqo6s8AhH67bqlvd4ioWTjCj8gphp/I\nKYafyCmGn8gphp/IKYafyCku3V2hci5cS1d71iuyk3Z7qSNy3/nI8tgz4Q7EptzOPyj7d9q6Zsz2\naJ1/Jnx+sbbQBoCVL9kDAVZuO2O2v3sq/MSWI2MMymtW2FdYBHV+nvmJnGL4iZxi+ImcYviJnGL4\niZxi+ImcYviJnGKdv0KTK8Ovk+U2u1je8b5922e32MeXl9jtudFw32JrBWTsUjuWdduDFEptXfbt\nT4X7tmGLXSvX/WvM9qHRpWZ72Vg2XJeX7PvO17h3+QLAMz+RUww/kVMMP5FTDD+RUww/kVMMP5FT\nDD+RU6zzV2hqlTFpPxOp85+xa8qneyKT6o217wEgdzJcky5FxiC0n7XbRyfstfM7G3j6aBstmO1j\n5zrNdjH2M9AJu44/vsEev9DZbzYvCDzzEznF8BM5xfATOcXwEznF8BM5xfATOcXwEzkVrfOLyAYA\njwNYi9lV3ner6qMisgvAVwFcmK3+oKrub1RH01bsCtfDs5P2wv1TK2Jzw+1J9dkldnumEJ60b+03\nAABTq8xmTJ2xNxVo64psWrBqKti0ZYU9n/8Xm9aZ7Vq2xwFY4y+sMQAAMLPUPi/aIwwWhkoG+RQB\nfFNVXxKRpQBeFJHnkrZHVPWfG9c9ImqUaPhVdQjAUPL9qIgcAbC+0R0josb6RH/zi8ilAG4AcCi5\n6D4ReVVE9ojIvPsbichOEekXkf4CpmvqLBHVT8XhF5FuAE8BuF9VzwP4DoArAFyP2XcGD893nKru\nVtU+Ve3Lo70OXSaieqgo/CKSx2zwf6CqTwOAqp5S1ZKqlgF8F8DWxnWTiOotGn4REQCPATiiqt+e\nc/ncj2K/AOD1+nePiBqlkk/7bwTwZQCvicgryWUPAtguItdjtvw3AOBrDelhi9DLJ8Jtx+zCT9Ge\nFRuVEXvarbXFdzZcaQMAXPQ/9ucwR7fbJbFy5DdoxX+HH/yBzGbz2GWRU1PnMntZ8cmJ7mBb17HI\n9t//ecRstydpLwyVfNr/MwDz/QYs2po+kQcc4UfkFMNP5BTDT+QUw0/kFMNP5BTDT+SUqEaWja6j\nHunVz8gtTbu/epJ8eNqsFmbsgzORKb1lu2qcue5qs13f/FWwTa663L7r198y22lhOaQHcV5HIvOs\nZ/HMT+QUw0/kFMNP5BTDT+QUw0/kFMNP5BTDT+RUU+v8IvI+gGNzLloF4HTTOvDJtGrfWrVfAPtW\nrXr2baOqrq7kik0N/8fuXKRfVftS64ChVfvWqv0C2LdqpdU3vu0ncorhJ3Iq7fDvTvn+La3at1bt\nF8C+VSuVvqX6Nz8RpSftMz8RpSSV8IvIbSLyfyLyrog8kEYfQkRkQEReE5FXRKQ/5b7sEZFhEXl9\nzmW9IvKciLyTfJ13m7SU+rZLRAaT5+4VEbkjpb5tEJH/EpE3ReQNEfnr5PJUnzujX6k8b01/2y8i\nWQBvA7gVwAkAhwFsV9U3m9qRABEZANCnqqnXhEXkDwGMAXhcVa9NLvsnACOq+lDywrlCVf+2Rfq2\nC8BY2js3JxvKrJu7szSAuwF8BSk+d0a/7kEKz1saZ/6tAN5V1aOqOgPgSQB3pdCPlqeqzwMY+cjF\ndwHYm3y/F7O/PE0X6FtLUNUhVX0p+X4UwIWdpVN97ox+pSKN8K8HcHzOzyfQWlt+K4ADIvKiiOxM\nuzPzWJtsmw4AJwGsTbMz84ju3NxMH9lZumWeu2p2vK43fuD3cTep6qcB3A7g68nb25aks3+ztVK5\npqKdm5tlnp2lfyvN567aHa/rLY3wDwLYMOfni5PLWoKqDiZfhwE8g9bbffjUhU1Sk6/DKffnt1pp\n5+b5dpZGCzx3rbTjdRrhPwxgk4hcJiJtAL4IYF8K/fgYEelKPoiBiHQB+Dxab/fhfQB2JN/vAPBs\nin35kFbZuTm0szRSfu5absdrVW36PwB3YPYT/18B+Ls0+hDo1+UAfpn8eyPtvgF4ArNvAwuY/Wzk\nXgArARwE8A6AnwDobaG+fR/AawBexWzQ1qXUt5sw+5b+VQCvJP/uSPu5M/qVyvPGEX5ETvEDPyKn\nGH4ipxh+IqcYfiKnGH4ipxh+IqcYfiKnGH4ip/4fNam3k88wUlEAAAAASUVORK5CYII=\n",
"text/plain": [
"<Figure size 432x288 with 1 Axes>"
]
},
"metadata": {
"tags": []
}
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "BkI1L2x-9JJz",
"colab_type": "code",
"colab": {}
},
"source": [
"train_images=train_images/255.0\n",
"test_images=test_images/255.0"
],
"execution_count": 0,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "oCavg9pJ-Aq-",
"colab_type": "code",
"outputId": "213f6b09-136d-4037-dad3-b1c20eee365a",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 592
}
},
"source": [
"#showing the data\n",
"plt.figure(figsize=(10,10))\n",
"for i in range(25):\n",
" plt.subplot(5,5,i+1)\n",
" plt.xticks([])\n",
" plt.yticks([])\n",
" plt.imshow(train_images[i],cmap=plt.cm.binary)\n",
" plt.xlabel(class_names[train_labels[i]])"
],
"execution_count": 0,
"outputs": [
{
"output_type": "display_data",
"data": {
"image/png": "iVBORw0KGgoAAAANSUhEUgAAAkAAAAI/CAYAAACf7mYiAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n/H/4B+F2RTSX5QAAAABJRU5ErkJggg==\n",
"text/plain": [
"<Figure size 720x720 with 25 Axes>"
]
},
"metadata": {
"tags": []
}
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "bXwCrml3-Wrv",
"colab_type": "code",
"outputId": "565bfc14-7db9-4f3e-eeb1-bed73a05d4cd",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 105
}
},
"source": [
"# Building The Model\n",
"model=keras.Sequential([\n",
" keras.layers.Flatten(input_shape=(28,28)),\n",
" keras.layers.Dense(128,activation=tf.nn.relu),\n",
" keras.layers.Dense(10,activation=tf.nn.softmax)\n",
"])"
],
"execution_count": 0,
"outputs": [
{
"output_type": "stream",
"text": [
"WARNING: Logging before flag parsing goes to stderr.\n",
"W0624 19:40:18.195935 140596520552320 deprecation.py:506] From /usr/local/lib/python3.6/dist-packages/tensorflow/python/ops/init_ops.py:1251: calling VarianceScaling.__init__ (from tensorflow.python.ops.init_ops) with dtype is deprecated and will be removed in a future version.\n",
"Instructions for updating:\n",
"Call initializer instance with the dtype argument instead of passing it to the constructor\n"
],
"name": "stderr"
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "ugsduUE9ATlv",
"colab_type": "code",
"colab": {}
},
"source": [
"model.compile(optimizer='adam',\n",
" loss='sparse_categorical_crossentropy',\n",
" metrics=['accuracy'])"
],
"execution_count": 0,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "tuqxlH_T__KK",
"colab_type": "code",
"outputId": "004faa9b-051b-4def-e2c5-2ab201eb2e86",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 204
}
},
"source": [
"#train the model\n",
"model.fit(train_images,train_labels, epochs=5)"
],
"execution_count": 0,
"outputs": [
{
"output_type": "stream",
"text": [
"Epoch 1/5\n",
"60000/60000 [==============================] - 5s 76us/sample - loss: 0.5045 - acc: 0.8211\n",
"Epoch 2/5\n",
"60000/60000 [==============================] - 4s 73us/sample - loss: 0.3730 - acc: 0.8654\n",
"Epoch 3/5\n",
"60000/60000 [==============================] - 4s 73us/sample - loss: 0.3369 - acc: 0.8776\n",
"Epoch 4/5\n",
"60000/60000 [==============================] - 4s 74us/sample - loss: 0.3147 - acc: 0.8840\n",
"Epoch 5/5\n",
"60000/60000 [==============================] - 4s 72us/sample - loss: 0.2968 - acc: 0.8901\n"
],
"name": "stdout"
},
{
"output_type": "execute_result",
"data": {
"text/plain": [
"<tensorflow.python.keras.callbacks.History at 0x7fdef20099b0>"
]
},
"metadata": {
"tags": []
},
"execution_count": 52
}
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "N5ZD5R6iBDiB",
"colab_type": "text"
},
"source": [
"Accuracy is around 89%"
]
},
{
"cell_type": "code",
"metadata": {
"id": "6amKSCycA3yw",
"colab_type": "code",
"outputId": "8c92db77-3707-4398-f756-7c4fee3167ca",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 51
}
},
"source": [
"#Evaluation on test datset\n",
"test_loss, test_acc = model.evaluate(test_images,test_labels)\n",
"print('Test accuracy', test_acc)"
],
"execution_count": 0,
"outputs": [
{
"output_type": "stream",
"text": [
"10000/10000 [==============================] - 0s 35us/sample - loss: 0.3466 - acc: 0.8760\n",
"Test accuracy 0.876\n"
],
"name": "stdout"
}
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "AN7giE8ABhOu",
"colab_type": "text"
},
"source": [
"Accuracy on test dataset is around 87.6%"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "iMUYiRSpB1y5",
"colab_type": "text"
},
"source": [
"**Now the model has been trained and tested and is complete, and we are ready to make predictions**"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "oNoH0tJNCtMq",
"colab_type": "text"
},
"source": [
"Enter a number between 0 and 9999"
]
},
{
"cell_type": "code",
"metadata": {
"id": "DwFLYtfDBztQ",
"colab_type": "code",
"outputId": "9ee668c5-555b-4a73-a45e-c0457d0b9989",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 51
}
},
"source": [
"input(i)"
],
"execution_count": 0,
"outputs": [
{
"output_type": "stream",
"text": [
"245\n"
],
"name": "stdout"
},
{
"output_type": "execute_result",
"data": {
"text/plain": [
"'5'"
]
},
"metadata": {
"tags": []
},
"execution_count": 76
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "qXR15RYqC-EY",
"colab_type": "code",
"colab": {}
},
"source": [
"if(i>9999):\n",
" i=9999\n",
" print('Your Number is geater than limit and is changed to 10000')\n",
"img=test_images[i] \n",
"img=(np.expand_dims(img,0)) # To convert the images from 2d to a into a 3d array"
],
"execution_count": 0,
"outputs": []
},
{
"cell_type": "markdown",
"metadata": {
"id": "Eq5mYAB2HUup",
"colab_type": "text"
},
"source": [
"The Prediction on the image you chose is"
]
},
{
"cell_type": "code",
"metadata": {
"id": "DsLHow8tDP1o",
"colab_type": "code",
"outputId": "efc89e52-9c22-4bbd-85f9-24e4d984eb91",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 34
}
},
"source": [
"# Now making predictions on given number of image\n",
"predictions=model.predict(img)\n",
"class_names[test_labels[np.argmax(predictions)]]"
],
"execution_count": 0,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"'Pullover'"
]
},
"metadata": {
"tags": []
},
"execution_count": 78
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "vkpVq2eQDlnR",
"colab_type": "code",
"outputId": "7bfcaa6a-8520-4e0b-8827-0fc0eb4b0d13",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 281
}
},
"source": [
"plt.title('The image you chose')\n",
"plt.imshow(test_images[i],cmap=plt.cm.binary)\n",
"plt.show()\n"
],
"execution_count": 0,
"outputs": [
{
"output_type": "display_data",
"data": {
"image/png": "iVBORw0KGgoAAAANSUhEUgAAAP8AAAEICAYAAACQ6CLfAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nlimH3yxTDr9Zphx+s0w5/GaZcvjNMvX/aQJwJZ3XP1sAAAAASUVORK5CYII=\n",
"text/plain": [
"<Figure size 432x288 with 1 Axes>"
]
},
"metadata": {
"tags": []
}
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "apMSwvXoHnyX",
"colab_type": "code",
"colab": {}
},
"source": [
""
],
"execution_count": 0,
"outputs": []
}
]
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment