├── README.md ├── .gitignore └── Lets grow more task 4 (5).ipynb /README.md: -------------------------------------------------------------------------------- 1 | # LETS-GROW-MORE-TASK-4 -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- 1 | # Byte-compiled / optimized / DLL files 2 | __pycache__/ 3 | *.py[cod] 4 | *$py.class 5 | 6 | # C extensions 7 | *.so 8 | 9 | # Distribution / packaging 10 | .Python 11 | build/ 12 | develop-eggs/ 13 | dist/ 14 | downloads/ 15 | eggs/ 16 | .eggs/ 17 | lib/ 18 | lib64/ 19 | parts/ 20 | sdist/ 21 | var/ 22 | wheels/ 23 | pip-wheel-metadata/ 24 | share/python-wheels/ 25 | *.egg-info/ 26 | .installed.cfg 27 | *.egg 28 | MANIFEST 29 | 30 | # PyInstaller 31 | # Usually these files are written by a python script from a template 32 | # before PyInstaller builds the exe, so as to inject date/other infos into it. 33 | *.manifest 34 | *.spec 35 | 36 | # Installer logs 37 | pip-log.txt 38 | pip-delete-this-directory.txt 39 | 40 | # Unit test / coverage reports 41 | htmlcov/ 42 | .tox/ 43 | .nox/ 44 | .coverage 45 | .coverage.* 46 | .cache 47 | nosetests.xml 48 | coverage.xml 49 | *.cover 50 | *.py,cover 51 | .hypothesis/ 52 | .pytest_cache/ 53 | 54 | # Translations 55 | *.mo 56 | *.pot 57 | 58 | # Django stuff: 59 | *.log 60 | local_settings.py 61 | db.sqlite3 62 | db.sqlite3-journal 63 | 64 | # Flask stuff: 65 | instance/ 66 | .webassets-cache 67 | 68 | # Scrapy stuff: 69 | .scrapy 70 | 71 | # Sphinx documentation 72 | docs/_build/ 73 | 74 | # PyBuilder 75 | target/ 76 | 77 | # Jupyter Notebook 78 | .ipynb_checkpoints 79 | 80 | # IPython 81 | profile_default/ 82 | ipython_config.py 83 | 84 | # pyenv 85 | .python-version 86 | 87 | # pipenv 88 | # According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control. 89 | # However, in case of collaboration, if having platform-specific dependencies or dependencies 90 | # having no cross-platform support, pipenv may install dependencies that don't work, or not 91 | # install all needed dependencies. 92 | #Pipfile.lock 93 | 94 | # PEP 582; used by e.g. github.com/David-OConnor/pyflow 95 | __pypackages__/ 96 | 97 | # Celery stuff 98 | celerybeat-schedule 99 | celerybeat.pid 100 | 101 | # SageMath parsed files 102 | *.sage.py 103 | 104 | # Environments 105 | .env 106 | .venv 107 | env/ 108 | venv/ 109 | ENV/ 110 | env.bak/ 111 | venv.bak/ 112 | 113 | # Spyder project settings 114 | .spyderproject 115 | .spyproject 116 | 117 | # Rope project settings 118 | .ropeproject 119 | 120 | # mkdocs documentation 121 | /site 122 | 123 | # mypy 124 | .mypy_cache/ 125 | .dmypy.json 126 | dmypy.json 127 | 128 | # Pyre type checker 129 | .pyre/ 130 | -------------------------------------------------------------------------------- /Lets grow more task 4 (5).ipynb: -------------------------------------------------------------------------------- 1 | { 2 | "cells": [ 3 | { 4 | "cell_type": "markdown", 5 | "id": "5adec4db", 6 | "metadata": {}, 7 | "source": [ 8 | "# LETS GROW MORE\n", 9 | "\n", 10 | "TASK -4\n", 11 | "\n", 12 | "Name :JEEVITHA K\n", 13 | "\n", 14 | "Level-Advanced\n", 15 | " \n", 16 | "Develop a Neural Network That can read Handwriting" 17 | ] 18 | }, 19 | { 20 | "cell_type": "code", 21 | "execution_count": 29, 22 | "id": "9f0218cf", 23 | "metadata": {}, 24 | "outputs": [], 25 | "source": [ 26 | "import numpy as np\n", 27 | "from keras.datasets import mnist\n", 28 | "from keras.models import Sequential\n", 29 | "from keras.layers.core import Dense,Activation\n", 30 | "from keras.utils import np_utils" 31 | ] 32 | }, 33 | { 34 | "cell_type": "code", 35 | "execution_count": 30, 36 | "id": "7f3214f6", 37 | "metadata": {}, 38 | "outputs": [], 39 | "source": [ 40 | "(x_train,y_train),(x_test,y_test) = mnist.load_data()" 41 | ] 42 | }, 43 | { 44 | "cell_type": "code", 45 | "execution_count": 37, 46 | "id": "b980b1c8", 47 | "metadata": {}, 48 | "outputs": [ 49 | { 50 | "data": { 51 | "image/png": "iVBORw0KGgoAAAANSUhEUgAABG0AAABACAYAAACgE4o8AAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjMuNCwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8QVMy6AAAACXBIWXMAAAsTAAALEwEAmpwYAAAOp0lEQVR4nO3dT29UdfvH8c8586fDdNpKC20BkQo2IBURuBUUAy7UhbrCRDcmJD4Pn4IPQRayZWviCjcSIiIGWkCs1Km20KaF/u+0nZnzWzT0d4/FGxFmuL5X3+8dzJnM9zVzTtJcmfmeKEkSERERERERERGRreJnvQAiIiIiIiIiIlofQxsiIiIiIiIiIoMxtCEiIiIiIiIiMhhDGyIiIiIiIiIigzG0ISIiIiIiIiIyWPpxDo6iKORbTU0kSbL1fx2Az3SP9ElhG5MkiR51TMg+cY6690lhG7kG8RnP/TUoPkN8tuMaFD7juT9HN+rfahvpmzbFZ72AOoePrOf9M8RH1vP+GeILP+9GfGHn3Sf5N+Ij6z30M9xIQxsiIiIiIiIiomBiaENEREREREREZLDH2tPmSYvjWE1NTZKkKIqUSqUUx7EymczaMUtLS6pWqyqXy6pUKiqXy41c4hOFL2yf5N+ID5/1vBvx4bOedyM+fNbzbsQXtk/yb7Toa+jQpqurSx999JGy2awymYx6enrU3d2tN998U1EUqVqt6ttvv9Xw8LB++eUX3bhxQwMDA41c4hOFL2yf5N+ID5/1vBvx4bOedyM+fNbzbsQXtk/yb7Toa8jQJo5j7d+/X7t379axY8eUyWSUTqe1bds2dXR0aOfOnWtvwCuvvKKOjg7l83nNz8/r9u3ba5Msq+EL2yf5N+LDZ9kn+Tfiw2fZJ/k34sNn2Sf5N+IL2yf5N1r2NWRok81m9fnnn+u1117TiRMnFEW1d+pKkkRJsnpnrmPHjml5eVkHDx5UpVJRf3+/xsfHtbS01Iil/qvwhe2T/Bvx4bPsk/wb8eGz7JP8G/Hhs+yT/Bvxhe2T/Bst++o+tHnrrbd0+PBhHT9+XNu3b6/BT05OamZmRkNDQ8rn82pubtaePXuUy+W0detW9fb26ujRo/ruu+/MfsD4wvZJ/o348Fn2Sf6N+PBZ9kn+jfjwWfZJ/o34wvZJ/o3WfXUd2qRSKfX19en999/Xvn37VCgUVK1WVSqVtLKyotHRUY2Njeny5ctqa2tTe3u7uru7lcvl1NLSom3btqm3t1c//PBDPZf5r8MXtk/yb8SHz7JP8m/Eh8+yT/JvxIfPsk/yb8QXtk/ybwzBV7ehTaFQUE9Pj44ePaoTJ04on89rYWFBo6OjOnfunL755htNTU1pcXFR09PTSqfTyuVy+vLLL3Xw4EHt2rVLTU1Nam1tVRzbuzM5vrB9kn8jPnyWfZJ/Iz58ln2SfyM+fJZ9kn8jvrB9kn9jKL66DW3S6bRaW1vV0tKifD6vUqmk8fFxXbhwQVeuXNGtW7c0Pz+vlZUVLS8vq6OjQ+3t7Wsb/kjS4uKi7t27p0qlUq9l/uvwhe2T/Bvx4bPsk/wb8eGz7JP8G/Hhs+yT/Bvxhe2T/BtD8dVtaJPJZNTe3q5cLidJGh0d1Y8//qgvvvhCU1NTmpubqzn+5Zdf1jvvvKP9+/eru7tbURTpzp07unTpkmZmZuq1zH8dvrB9kn8jPnyWfZJ/Iz58ln2SfyM+fJZ9kn8jvrB9kn9jKL66DW3m5ubU39+vs2fP6tKlS5qYmNDo6Kju37//0A16duzYocOHD6u1tVWpVKpey3pq4astNJ/k34ivNnz28m7EVxs+e3k34qsNn728G/HVFppP8m8MxVe3oc3i4qJ+//13TU1N6eLFi1pYWNDS0pLm5+drjouiSOl0Wp2dnert7VU+n1+7/3mlUlG5XK7XEp8ofKuF6pP8G/Gths+mT/JvxLcaPps+yb8R32r4bPok/0Z8q4Xqk/wbQ/HV/ZbfMzMzmpubq7mv+X+3ZcsWffjhhzpx4oR27dqlbDarUqmkwcFBDQwM6Pr16+veNEvhC9sn+Tfiw2fZJ/k34sNn2Sf5N+LDZ9kn+TfiC9sn+Tda99V9aFOtVlWtVh/6WFtbm3bs2KEjR45o586dampqUqVS0ezsrK5fv64///xT8/PzJjctehC+sH2SfyM+fJZ9kn8jPnyWfZJ/Iz58ln2SfyO+sH2Sf6N1X92HNn9XHMc6cOCAXn/9dZ0+fVq5XE6pVEr379/X0NCQzpw5o8HBwYf+liyE8IXtk/wb8eGznncjPnzW827Eh8963o34wvZJ/o1WfM/sZulRFKm7u1tdXV3KZrOK41hJkujXX39Vf3+/BgcHNTk5+ayW98ThC9sn+Tfiw2c970Z8+Kzn3YgPn/W8G/GF7ZP8G634nsk3bVKplJqamrRt2zZ1dXWt7bxcLpfXfhc2PDxsdsOiR4UvbJ/k34gPn/W8G/Hhs553Iz581vNuxBe2T/JvtOR7JkObDz74QO+9955Onjypzs5OxXGsW7du6caNG/rqq680ODho+jdvjwpf2D7JvxEfPut5N+LDZz3vRnz4rOfdiC9sn+TfaMnX0KHNg1tl7dixQwcOHNDzzz+v5uZmlctl3blzR9euXdPw8LDGx8cfumuz9fCF7ZP8G/Hhs553Iz581vNuxIfPet6N+ML2Sf6NFn0NHdpkMhm1t7erp6dHfX19amlpUZIkmp6e1sWLF/X1119rZGQk2I2K8IXtk/wb8eGznncjPnzW827Eh8963o34wvZJ/o0WfQ0d2nR2durjjz/WwYMHtWnTJsVxrNnZWV29elVDQ0OamJjQyspKI5f0VMMXtk/yb8SHz3rejfjwWc+7ER8+63k34gvbJ/k3WvQ1bGgTRZG6urr0ySefqKenR/l8XkmSaG5uTj///LOGhoY0NTXVqOU89fCF7ZP8G/Hhs553Iz581vNuxIfPet6N+ML2Sf6NVn0NGdrEcaxDhw7pjTfe0N69e9fwN27c0LVr13TmzBndvXu3EUupS/jC9kn+jfjwWc+7ER8+63k34sNnPe9GfGH7JP9Gy766D23iOFY2m9WePXu0e/duFQoFpdNpJUmi+/fv6+7duxoeHtbi4mK9l1KX8IXtk/wb8eGznncjPnzW827Eh8963o34wvZJ/o3WfXUf2uRyOW3evFmnTp1SX1+fMpmMJKlarapYLKpYLGphYSHY24HhC9sn+Tfiw2c970Z8+Kzn3YgPn/W8G/GF7ZP8G6376j606enp0d69e/Xiiy+qs7NTkjQxMaGxsTFduHBBAwMDqlar9V5G3cIXtk/yb8SHz3rejfjwWc+7ER8+63k34gvbJ/k3WvfVfWjz0ksv6e2339bu3bvV3t4uSbp79676+/t1/vx5FYvFIO/f/iB8Yfsk/0Z8+Kzn3YgPn/W8G/Hhs553I76wfZJ/o3Vf3Yc2hw4d0qlTp9TS0rL2f99//73Onj0b9P3bH4QvbJ/k34gPn/W8G/Hhs553Iz581vNuxBe2T/JvtO6r+9Cmra1N27dvVzr9/y81OTmpYrGolZUVRVGkVCpV85wkSdZ9/SiKIsVxvPbvOI6VSqX03HPPKYqidc8vlUqanp6u+0QMX9g+yb8RHz7Jrk/yb8SHT7Lrk/wb8eGT7Pok/0Z8Yfsk/0brvobc8vuvbdq0SS0tLSqXyyqXy+ser1Qqmp+fV6VSUbVaVSqVUjqdVnNz8xq2UCioo6NDn376qZqamtae++DNu3Llis6dO6fl5eWGbxiEL2yf5N+ID59ln+TfiA+fZZ/k34gPn2Wf5N+IL2yf5N9oyfdMhjaHDx/W6dOntbCw8NA3oFQq6bffflOpVNLS0pI2bdqk5uZm9fb2rr0BuVxOhUJBR44ceejUK5VKaWhoSDdv3tTk5GRDXA/CF7ZP8m/Eh8+yT/JvxIfPsk/yb8SHz7JP8m/EF7ZP8m+05GvI0OavX/c5efKkTp48+bfHT01N6fz585qentbs7Kw2b96srVu36t13312H/bvXyefzGhsb0+TkZN0/YHy1heb762tL/oz4asP36NfhGny64asN36Nfh2vw6YavNnyPfh2uwacbvtpC8/31tSV/Rsu+ug9tisWiLl++rFdffVX5fP4fPadQKOj48eMql8uqVCpKpVJqampSHMdKkmTd78fGxsZ0+/ZtjYyMaH5+XpI0PDysq1evampqqh6stfCtLySf5N+Ib3347Pgk/0Z868Nnxyf5N+JbHz47Psm/Ed/6QvJJ/o3WfXUf2oyOjqq/v19dXV1qbW1d93gcx8pkMspms8pms6uLSqfV2dmp5eVllUqltd+J3bt3T0tLSyqVSlpeXl57E0ZGRnTz5k0Vi0XNzs5KWt04aGRkRKVSCR++DW3Eh8+ybyMY8eGz7NsIRnz4LPs2ghFf2L6NYLTuix5nJ+Yoih572+ZMJqN8Pq/PPvtMW7ZsqdmRWVrd4OeFF15QX1+f9u3bV/PYwMCAfvrpJ42Pj6/dZuv27du6du1azYSqWq2qWq2qUqmsfd3owWSrWq0++L/LSZL8B59fX+jGJElqtxR35hPnqHtf6EauQXyh+zaCER8+y76NYMQXti9040b9W63u37RZWVnR3Nycrly5okKhsO73XZlMRh0dHbp69aq2b99e89gff/yh4eFhzczMrG3+Mz4+rpGREd27d0/Ly8v1Xv4jwxe2T/JvxIfPsk/yb8SHz7JP8m/Eh8+yT/JvxBe2T/JvtO6r+zdtDFWXyaqhNrxPCttYr8mxoTb8OerdJ4Vt5BrEZzz316D4DPHZjmtQ+Izn/hzdqH+rxc9iJURERERERERE9L9jaENEREREREREZDCGNkREREREREREBmNoQ0RERERERERkMIY2REREREREREQGY2hDRERERERERGQwhjZERERERERERAZLP+bxE5KK9VhIA9r1D47BZ7d/4pPCNXr3SZyjkn+fFK7Ru0/iHJX8+yT/Rnx2w7eadyM+u3k/R737pL8xRkmSNHohRERERERERET0iPh5FBERERERERGRwRjaEBEREREREREZjKENEREREREREZHBGNoQERERERERERmMoQ0RERERERERkcEY2hARERERERERGYyhDRERERERERGRwRjaEBEREREREREZjKENEREREREREZHB/g8D3wNoZgHXXgAAAABJRU5ErkJggg==\n", 52 | "text/plain": [ 53 | "
" 54 | ] 55 | }, 56 | "metadata": { 57 | "needs_background": "light" 58 | }, 59 | "output_type": "display_data" 60 | } 61 | ], 62 | "source": [ 63 | "import matplotlib.pyplot as plt\n", 64 | "n=20\n", 65 | "plt.figure(figsize=(20,4))\n", 66 | "for i in range(n):\n", 67 | " ax=plt.subplot(2, n, i+1)\n", 68 | " plt.imshow(x_test[1].reshape(28,28))\n", 69 | " plt.gray()\n", 70 | " ax.get_xaxis().set_visible(False)\n", 71 | " ax.get_yaxis().set_visible(False)\n", 72 | "plt.show()\n", 73 | "plt.close()\n", 74 | " " 75 | ] 76 | }, 77 | { 78 | "cell_type": "code", 79 | "execution_count": 32, 80 | "id": "490f846f", 81 | "metadata": {}, 82 | "outputs": [ 83 | { 84 | "name": "stdout", 85 | "output_type": "stream", 86 | "text": [ 87 | "Previous x_train shape: () \n", 88 | "Previous y_train shape:(60000, 28, 28)\n", 89 | "New x_train shape: (60000, 784) \n", 90 | "New y_train shape:(60000, 10)\n" 91 | ] 92 | } 93 | ], 94 | "source": [ 95 | "print(\"Previous x_train shape: () \\nPrevious y_train shape:{}\".format(x_train.shape,y_train.shape))\n", 96 | "x_train = x_train.reshape(60000,784)\n", 97 | "x_test = x_test.reshape(10000,784)\n", 98 | "x_train = x_train.astype('float32')\n", 99 | "x_test = x_test.astype('float32')\n", 100 | "x_train /= 255\n", 101 | "x_test /=255\n", 102 | "classes = 10\n", 103 | "y_train = np_utils.to_categorical(y_train,classes)\n", 104 | "y_test = np_utils.to_categorical(y_test,classes)\n", 105 | "print(\"New x_train shape: {} \\nNew y_train shape:{}\".format(x_train.shape,y_train.shape))" 106 | ] 107 | }, 108 | { 109 | "cell_type": "code", 110 | "execution_count": 33, 111 | "id": "9a9ef72e", 112 | "metadata": {}, 113 | "outputs": [], 114 | "source": [ 115 | "input_size = 784\n", 116 | "batch_size = 200\n", 117 | "hidden1 = 400\n", 118 | "hidden2 = 20\n", 119 | "epochs = 2" 120 | ] 121 | }, 122 | { 123 | "cell_type": "code", 124 | "execution_count": 34, 125 | "id": "daf9e4da", 126 | "metadata": {}, 127 | "outputs": [ 128 | { 129 | "name": "stdout", 130 | "output_type": "stream", 131 | "text": [ 132 | "Model: \"sequential_10\"\n", 133 | "_________________________________________________________________\n", 134 | " Layer (type) Output Shape Param # \n", 135 | "=================================================================\n", 136 | " dense_10 (Dense) (None, 400) 314000 \n", 137 | " \n", 138 | " dense_11 (Dense) (None, 20) 8020 \n", 139 | " \n", 140 | " dense_12 (Dense) (None, 10) 210 \n", 141 | " \n", 142 | "=================================================================\n", 143 | "Total params: 322,230\n", 144 | "Trainable params: 322,230\n", 145 | "Non-trainable params: 0\n", 146 | "_________________________________________________________________\n" 147 | ] 148 | } 149 | ], 150 | "source": [ 151 | "model = Sequential()\n", 152 | "model.add(Dense(hidden1, input_dim=input_size,activation='relu'))\n", 153 | "\n", 154 | "model.add(Dense(hidden2,activation='relu'))\n", 155 | "model.add(Dense(classes,activation='softmax'))\n", 156 | "\n", 157 | "model.compile(loss='categorical_crossentropy',\n", 158 | "metrics=['accuracy'],optimizer='sgd')\n", 159 | "model.summary()\n", 160 | "\n" 161 | ] 162 | }, 163 | { 164 | "cell_type": "code", 165 | "execution_count": 35, 166 | "id": "6f188ddc", 167 | "metadata": {}, 168 | "outputs": [ 169 | { 170 | "name": "stdout", 171 | "output_type": "stream", 172 | "text": [ 173 | "Epoch 1/100\n", 174 | "300/300 - 2s - loss: 1.5057 - accuracy: 0.6069 - 2s/epoch - 7ms/step\n", 175 | "Epoch 2/100\n", 176 | "300/300 - 2s - loss: 0.6655 - accuracy: 0.8430 - 2s/epoch - 6ms/step\n", 177 | "Epoch 3/100\n", 178 | "300/300 - 2s - loss: 0.4766 - accuracy: 0.8783 - 2s/epoch - 6ms/step\n", 179 | "Epoch 4/100\n", 180 | "300/300 - 2s - loss: 0.4024 - accuracy: 0.8926 - 2s/epoch - 6ms/step\n", 181 | "Epoch 5/100\n", 182 | "300/300 - 2s - loss: 0.3620 - accuracy: 0.9009 - 2s/epoch - 7ms/step\n", 183 | "Epoch 6/100\n", 184 | "300/300 - 2s - loss: 0.3352 - accuracy: 0.9072 - 2s/epoch - 7ms/step\n", 185 | "Epoch 7/100\n", 186 | "300/300 - 2s - loss: 0.3154 - accuracy: 0.9122 - 2s/epoch - 7ms/step\n", 187 | "Epoch 8/100\n", 188 | "300/300 - 2s - loss: 0.2994 - accuracy: 0.9160 - 2s/epoch - 7ms/step\n", 189 | "Epoch 9/100\n", 190 | "300/300 - 2s - loss: 0.2862 - accuracy: 0.9194 - 2s/epoch - 7ms/step\n", 191 | "Epoch 10/100\n", 192 | "300/300 - 2s - loss: 0.2745 - accuracy: 0.9227 - 2s/epoch - 6ms/step\n", 193 | "Epoch 11/100\n", 194 | "300/300 - 2s - loss: 0.2642 - accuracy: 0.9255 - 2s/epoch - 7ms/step\n", 195 | "Epoch 12/100\n", 196 | "300/300 - 2s - loss: 0.2549 - accuracy: 0.9278 - 2s/epoch - 7ms/step\n", 197 | "Epoch 13/100\n", 198 | "300/300 - 2s - loss: 0.2463 - accuracy: 0.9305 - 2s/epoch - 7ms/step\n", 199 | "Epoch 14/100\n", 200 | "300/300 - 2s - loss: 0.2382 - accuracy: 0.9331 - 2s/epoch - 6ms/step\n", 201 | "Epoch 15/100\n", 202 | "300/300 - 2s - loss: 0.2307 - accuracy: 0.9351 - 2s/epoch - 7ms/step\n", 203 | "Epoch 16/100\n", 204 | "300/300 - 2s - loss: 0.2237 - accuracy: 0.9370 - 2s/epoch - 7ms/step\n", 205 | "Epoch 17/100\n", 206 | "300/300 - 2s - loss: 0.2171 - accuracy: 0.9389 - 2s/epoch - 7ms/step\n", 207 | "Epoch 18/100\n", 208 | "300/300 - 2s - loss: 0.2108 - accuracy: 0.9408 - 2s/epoch - 6ms/step\n", 209 | "Epoch 19/100\n", 210 | "300/300 - 2s - loss: 0.2050 - accuracy: 0.9424 - 2s/epoch - 7ms/step\n", 211 | "Epoch 20/100\n", 212 | "300/300 - 2s - loss: 0.1993 - accuracy: 0.9444 - 2s/epoch - 6ms/step\n", 213 | "Epoch 21/100\n", 214 | "300/300 - 2s - loss: 0.1940 - accuracy: 0.9453 - 2s/epoch - 7ms/step\n", 215 | "Epoch 22/100\n", 216 | "300/300 - 2s - loss: 0.1890 - accuracy: 0.9475 - 2s/epoch - 7ms/step\n", 217 | "Epoch 23/100\n", 218 | "300/300 - 2s - loss: 0.1841 - accuracy: 0.9488 - 2s/epoch - 7ms/step\n", 219 | "Epoch 24/100\n", 220 | "300/300 - 2s - loss: 0.1795 - accuracy: 0.9497 - 2s/epoch - 6ms/step\n", 221 | "Epoch 25/100\n", 222 | "300/300 - 2s - loss: 0.1752 - accuracy: 0.9511 - 2s/epoch - 6ms/step\n", 223 | "Epoch 26/100\n", 224 | "300/300 - 2s - loss: 0.1707 - accuracy: 0.9525 - 2s/epoch - 7ms/step\n", 225 | "Epoch 27/100\n", 226 | "300/300 - 2s - loss: 0.1666 - accuracy: 0.9526 - 2s/epoch - 6ms/step\n", 227 | "Epoch 28/100\n", 228 | "300/300 - 2s - loss: 0.1629 - accuracy: 0.9540 - 2s/epoch - 7ms/step\n", 229 | "Epoch 29/100\n", 230 | "300/300 - 2s - loss: 0.1591 - accuracy: 0.9550 - 2s/epoch - 7ms/step\n", 231 | "Epoch 30/100\n", 232 | "300/300 - 2s - loss: 0.1555 - accuracy: 0.9560 - 2s/epoch - 6ms/step\n", 233 | "Epoch 31/100\n", 234 | "300/300 - 2s - loss: 0.1520 - accuracy: 0.9571 - 2s/epoch - 6ms/step\n", 235 | "Epoch 32/100\n", 236 | "300/300 - 2s - loss: 0.1486 - accuracy: 0.9582 - 2s/epoch - 6ms/step\n", 237 | "Epoch 33/100\n", 238 | "300/300 - 2s - loss: 0.1455 - accuracy: 0.9589 - 2s/epoch - 6ms/step\n", 239 | "Epoch 34/100\n", 240 | "300/300 - 2s - loss: 0.1424 - accuracy: 0.9597 - 2s/epoch - 6ms/step\n", 241 | "Epoch 35/100\n", 242 | "300/300 - 2s - loss: 0.1394 - accuracy: 0.9606 - 2s/epoch - 7ms/step\n", 243 | "Epoch 36/100\n", 244 | "300/300 - 2s - loss: 0.1366 - accuracy: 0.9613 - 2s/epoch - 6ms/step\n", 245 | "Epoch 37/100\n", 246 | "300/300 - 2s - loss: 0.1339 - accuracy: 0.9617 - 2s/epoch - 6ms/step\n", 247 | "Epoch 38/100\n", 248 | "300/300 - 2s - loss: 0.1312 - accuracy: 0.9628 - 2s/epoch - 6ms/step\n", 249 | "Epoch 39/100\n", 250 | "300/300 - 2s - loss: 0.1285 - accuracy: 0.9638 - 2s/epoch - 6ms/step\n", 251 | "Epoch 40/100\n", 252 | "300/300 - 2s - loss: 0.1260 - accuracy: 0.9643 - 2s/epoch - 6ms/step\n", 253 | "Epoch 41/100\n", 254 | "300/300 - 2s - loss: 0.1236 - accuracy: 0.9650 - 2s/epoch - 6ms/step\n", 255 | "Epoch 42/100\n", 256 | "300/300 - 2s - loss: 0.1212 - accuracy: 0.9657 - 2s/epoch - 6ms/step\n", 257 | "Epoch 43/100\n", 258 | "300/300 - 2s - loss: 0.1190 - accuracy: 0.9663 - 2s/epoch - 6ms/step\n", 259 | "Epoch 44/100\n", 260 | "300/300 - 2s - loss: 0.1167 - accuracy: 0.9670 - 2s/epoch - 6ms/step\n", 261 | "Epoch 45/100\n", 262 | "300/300 - 2s - loss: 0.1145 - accuracy: 0.9675 - 2s/epoch - 6ms/step\n", 263 | "Epoch 46/100\n", 264 | "300/300 - 2s - loss: 0.1125 - accuracy: 0.9679 - 2s/epoch - 6ms/step\n", 265 | "Epoch 47/100\n", 266 | "300/300 - 2s - loss: 0.1104 - accuracy: 0.9688 - 2s/epoch - 6ms/step\n", 267 | "Epoch 48/100\n", 268 | "300/300 - 2s - loss: 0.1084 - accuracy: 0.9693 - 2s/epoch - 6ms/step\n", 269 | "Epoch 49/100\n", 270 | "300/300 - 2s - loss: 0.1065 - accuracy: 0.9701 - 2s/epoch - 6ms/step\n", 271 | "Epoch 50/100\n", 272 | "300/300 - 2s - loss: 0.1047 - accuracy: 0.9704 - 2s/epoch - 6ms/step\n", 273 | "Epoch 51/100\n", 274 | "300/300 - 2s - loss: 0.1030 - accuracy: 0.9711 - 2s/epoch - 7ms/step\n", 275 | "Epoch 52/100\n", 276 | "300/300 - 2s - loss: 0.1012 - accuracy: 0.9715 - 2s/epoch - 6ms/step\n", 277 | "Epoch 53/100\n", 278 | "300/300 - 2s - loss: 0.0995 - accuracy: 0.9722 - 2s/epoch - 7ms/step\n", 279 | "Epoch 54/100\n", 280 | "300/300 - 2s - loss: 0.0977 - accuracy: 0.9724 - 2s/epoch - 6ms/step\n", 281 | "Epoch 55/100\n", 282 | "300/300 - 2s - loss: 0.0962 - accuracy: 0.9732 - 2s/epoch - 6ms/step\n", 283 | "Epoch 56/100\n", 284 | "300/300 - 2s - loss: 0.0946 - accuracy: 0.9736 - 2s/epoch - 7ms/step\n", 285 | "Epoch 57/100\n", 286 | "300/300 - 2s - loss: 0.0930 - accuracy: 0.9743 - 2s/epoch - 7ms/step\n", 287 | "Epoch 58/100\n", 288 | "300/300 - 2s - loss: 0.0916 - accuracy: 0.9744 - 2s/epoch - 6ms/step\n", 289 | "Epoch 59/100\n", 290 | "300/300 - 2s - loss: 0.0901 - accuracy: 0.9751 - 2s/epoch - 6ms/step\n", 291 | "Epoch 60/100\n", 292 | "300/300 - 2s - loss: 0.0887 - accuracy: 0.9753 - 2s/epoch - 6ms/step\n", 293 | "Epoch 61/100\n", 294 | "300/300 - 2s - loss: 0.0873 - accuracy: 0.9756 - 2s/epoch - 7ms/step\n", 295 | "Epoch 62/100\n", 296 | "300/300 - 2s - loss: 0.0859 - accuracy: 0.9761 - 2s/epoch - 7ms/step\n", 297 | "Epoch 63/100\n", 298 | "300/300 - 2s - loss: 0.0847 - accuracy: 0.9764 - 2s/epoch - 6ms/step\n", 299 | "Epoch 64/100\n", 300 | "300/300 - 2s - loss: 0.0833 - accuracy: 0.9771 - 2s/epoch - 7ms/step\n", 301 | "Epoch 65/100\n", 302 | "300/300 - 2s - loss: 0.0821 - accuracy: 0.9773 - 2s/epoch - 6ms/step\n", 303 | "Epoch 66/100\n", 304 | "300/300 - 2s - loss: 0.0808 - accuracy: 0.9776 - 2s/epoch - 6ms/step\n", 305 | "Epoch 67/100\n", 306 | "300/300 - 2s - loss: 0.0797 - accuracy: 0.9779 - 2s/epoch - 6ms/step\n", 307 | "Epoch 68/100\n", 308 | "300/300 - 2s - loss: 0.0784 - accuracy: 0.9783 - 2s/epoch - 6ms/step\n", 309 | "Epoch 69/100\n", 310 | "300/300 - 2s - loss: 0.0773 - accuracy: 0.9786 - 2s/epoch - 6ms/step\n", 311 | "Epoch 70/100\n", 312 | "300/300 - 2s - loss: 0.0762 - accuracy: 0.9790 - 2s/epoch - 6ms/step\n", 313 | "Epoch 71/100\n", 314 | "300/300 - 2s - loss: 0.0751 - accuracy: 0.9798 - 2s/epoch - 6ms/step\n", 315 | "Epoch 72/100\n", 316 | "300/300 - 2s - loss: 0.0740 - accuracy: 0.9798 - 2s/epoch - 6ms/step\n", 317 | "Epoch 73/100\n", 318 | "300/300 - 2s - loss: 0.0729 - accuracy: 0.9802 - 2s/epoch - 6ms/step\n", 319 | "Epoch 74/100\n", 320 | "300/300 - 2s - loss: 0.0718 - accuracy: 0.9806 - 2s/epoch - 6ms/step\n", 321 | "Epoch 75/100\n", 322 | "300/300 - 2s - loss: 0.0710 - accuracy: 0.9809 - 2s/epoch - 6ms/step\n", 323 | "Epoch 76/100\n", 324 | "300/300 - 2s - loss: 0.0699 - accuracy: 0.9812 - 2s/epoch - 6ms/step\n", 325 | "Epoch 77/100\n", 326 | "300/300 - 2s - loss: 0.0690 - accuracy: 0.9814 - 2s/epoch - 6ms/step\n", 327 | "Epoch 78/100\n", 328 | "300/300 - 2s - loss: 0.0680 - accuracy: 0.9820 - 2s/epoch - 6ms/step\n", 329 | "Epoch 79/100\n", 330 | "300/300 - 2s - loss: 0.0671 - accuracy: 0.9824 - 2s/epoch - 6ms/step\n", 331 | "Epoch 80/100\n", 332 | "300/300 - 2s - loss: 0.0662 - accuracy: 0.9826 - 2s/epoch - 6ms/step\n", 333 | "Epoch 81/100\n", 334 | "300/300 - 2s - loss: 0.0652 - accuracy: 0.9826 - 2s/epoch - 7ms/step\n", 335 | "Epoch 82/100\n", 336 | "300/300 - 2s - loss: 0.0644 - accuracy: 0.9831 - 2s/epoch - 6ms/step\n", 337 | "Epoch 83/100\n", 338 | "300/300 - 2s - loss: 0.0636 - accuracy: 0.9836 - 2s/epoch - 6ms/step\n", 339 | "Epoch 84/100\n", 340 | "300/300 - 2s - loss: 0.0627 - accuracy: 0.9835 - 2s/epoch - 6ms/step\n", 341 | "Epoch 85/100\n", 342 | "300/300 - 2s - loss: 0.0619 - accuracy: 0.9837 - 2s/epoch - 7ms/step\n", 343 | "Epoch 86/100\n", 344 | "300/300 - 2s - loss: 0.0610 - accuracy: 0.9840 - 2s/epoch - 6ms/step\n", 345 | "Epoch 87/100\n", 346 | "300/300 - 2s - loss: 0.0603 - accuracy: 0.9840 - 2s/epoch - 6ms/step\n", 347 | "Epoch 88/100\n", 348 | "300/300 - 2s - loss: 0.0595 - accuracy: 0.9845 - 2s/epoch - 6ms/step\n", 349 | "Epoch 89/100\n", 350 | "300/300 - 2s - loss: 0.0588 - accuracy: 0.9847 - 2s/epoch - 6ms/step\n", 351 | "Epoch 90/100\n", 352 | "300/300 - 2s - loss: 0.0579 - accuracy: 0.9849 - 2s/epoch - 6ms/step\n", 353 | "Epoch 91/100\n", 354 | "300/300 - 2s - loss: 0.0572 - accuracy: 0.9850 - 2s/epoch - 6ms/step\n", 355 | "Epoch 92/100\n", 356 | "300/300 - 2s - loss: 0.0564 - accuracy: 0.9853 - 2s/epoch - 6ms/step\n", 357 | "Epoch 93/100\n", 358 | "300/300 - 2s - loss: 0.0557 - accuracy: 0.9855 - 2s/epoch - 6ms/step\n", 359 | "Epoch 94/100\n", 360 | "300/300 - 2s - loss: 0.0551 - accuracy: 0.9859 - 2s/epoch - 6ms/step\n", 361 | "Epoch 95/100\n", 362 | "300/300 - 2s - loss: 0.0545 - accuracy: 0.9861 - 2s/epoch - 7ms/step\n", 363 | "Epoch 96/100\n", 364 | "300/300 - 2s - loss: 0.0538 - accuracy: 0.9859 - 2s/epoch - 7ms/step\n", 365 | "Epoch 97/100\n", 366 | "300/300 - 2s - loss: 0.0531 - accuracy: 0.9861 - 2s/epoch - 7ms/step\n", 367 | "Epoch 98/100\n", 368 | "300/300 - 2s - loss: 0.0524 - accuracy: 0.9865 - 2s/epoch - 6ms/step\n", 369 | "Epoch 99/100\n", 370 | "300/300 - 2s - loss: 0.0518 - accuracy: 0.9869 - 2s/epoch - 7ms/step\n", 371 | "Epoch 100/100\n", 372 | "300/300 - 2s - loss: 0.0511 - accuracy: 0.9872 - 2s/epoch - 8ms/step\n" 373 | ] 374 | }, 375 | { 376 | "data": { 377 | "text/plain": [ 378 | "" 379 | ] 380 | }, 381 | "execution_count": 35, 382 | "metadata": {}, 383 | "output_type": "execute_result" 384 | } 385 | ], 386 | "source": [ 387 | "model.fit(x_train,y_train,batch_size=batch_size,epochs=100,verbose=2)" 388 | ] 389 | }, 390 | { 391 | "cell_type": "markdown", 392 | "id": "a68afcd2", 393 | "metadata": {}, 394 | "source": [ 395 | "# TESTING THE MODEL" 396 | ] 397 | }, 398 | { 399 | "cell_type": "code", 400 | "execution_count": 39, 401 | "id": "d80cf0c5", 402 | "metadata": {}, 403 | "outputs": [ 404 | { 405 | "name": "stdout", 406 | "output_type": "stream", 407 | "text": [ 408 | "313/313 [==============================] - 1s 3ms/step - loss: 0.0805 - accuracy: 0.9756\n", 409 | "\n", 410 | "test accuracy: 0.975600004196167\n", 411 | "[7 2 1 0 4 1 4 9 6 9 0 6 9 0 1 5 9 7 3 4]\n" 412 | ] 413 | }, 414 | { 415 | "data": { 416 | "image/png": "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\n", 417 | "text/plain": [ 418 | "
" 419 | ] 420 | }, 421 | "metadata": { 422 | "needs_background": "light" 423 | }, 424 | "output_type": "display_data" 425 | } 426 | ], 427 | "source": [ 428 | "score = model.evaluate(x_test,y_test,verbose=1)\n", 429 | "print('\\n''test accuracy:',score[1])\n", 430 | "mask = range(0,20)\n", 431 | "x_valid = x_test[mask]\n", 432 | "predict_y=model.predict(x_valid)\n", 433 | "classes_y=np.argmax(predict_y,axis=1)\n", 434 | "print(classes_y)\n", 435 | "\n", 436 | "#display oridinal\n", 437 | "plt.figure(figsize=(20,4))\n", 438 | "for i in range(n):\n", 439 | " ax=plt.subplot(2, n, i+1)\n", 440 | " plt.imshow(x_test[1].reshape(28,28))\n", 441 | " plt.gray()\n", 442 | " ax.get_xaxis().set_visible(False)\n", 443 | " ax.get_yaxis().set_visible(False)\n", 444 | "plt.show()\n", 445 | "plt.close()" 446 | ] 447 | }, 448 | { 449 | "cell_type": "code", 450 | "execution_count": null, 451 | "id": "9d65910d", 452 | "metadata": {}, 453 | "outputs": [], 454 | "source": [] 455 | } 456 | ], 457 | "metadata": { 458 | "kernelspec": { 459 | "display_name": "Python 3", 460 | "language": "python", 461 | "name": "python3" 462 | }, 463 | "language_info": { 464 | "codemirror_mode": { 465 | "name": "ipython", 466 | "version": 3 467 | }, 468 | "file_extension": ".py", 469 | "mimetype": "text/x-python", 470 | "name": "python", 471 | "nbconvert_exporter": "python", 472 | "pygments_lexer": "ipython3", 473 | "version": "3.8.8" 474 | } 475 | }, 476 | "nbformat": 4, 477 | "nbformat_minor": 5 478 | } 479 | --------------------------------------------------------------------------------