cnn.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "914414e4",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "2023-10-02 21:15:42.478574: I tensorflow/core/platform/cpu_feature_guard.cc:193] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations:  AVX2 FMA\n",
      "To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.\n",
      "2023-10-02 21:15:46.784153: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcudart.so.11.0'; dlerror: libcudart.so.11.0: cannot open shared object file: No such file or directory\n",
      "2023-10-02 21:15:46.784258: I tensorflow/stream_executor/cuda/cudart_stub.cc:29] Ignore above cudart dlerror if you do not have a GPU set up on your machine.\n",
      "2023-10-02 21:15:47.220043: E tensorflow/stream_executor/cuda/cuda_blas.cc:2981] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered\n",
      "2023-10-02 21:15:57.420188: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer.so.7'; dlerror: libnvinfer.so.7: cannot open shared object file: No such file or directory\n",
      "2023-10-02 21:15:57.421413: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer_plugin.so.7'; dlerror: libnvinfer_plugin.so.7: cannot open shared object file: No such file or directory\n",
      "2023-10-02 21:15:57.421530: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Cannot dlopen some TensorRT libraries. If you would like to use Nvidia GPU with TensorRT, please make sure the missing libraries mentioned above are installed properly.\n",
      "/home/abhishekg/.local/lib/python3.10/site-packages/tensorflow_io/python/ops/__init__.py:98: UserWarning: unable to load libtensorflow_io_plugins.so: unable to open file: libtensorflow_io_plugins.so, from paths: ['/home/abhishekg/.local/lib/python3.10/site-packages/tensorflow_io/python/ops/libtensorflow_io_plugins.so']\n",
      "caused by: ['/home/abhishekg/.local/lib/python3.10/site-packages/tensorflow_io/python/ops/libtensorflow_io_plugins.so: undefined symbol: _ZN3tsl5mutexC1Ev']\n",
      "  warnings.warn(f\"unable to load libtensorflow_io_plugins.so: {e}\")\n",
      "/home/abhishekg/.local/lib/python3.10/site-packages/tensorflow_io/python/ops/__init__.py:104: UserWarning: file system plugins are not loaded: unable to open file: libtensorflow_io.so, from paths: ['/home/abhishekg/.local/lib/python3.10/site-packages/tensorflow_io/python/ops/libtensorflow_io.so']\n",
      "caused by: ['/home/abhishekg/.local/lib/python3.10/site-packages/tensorflow_io/python/ops/libtensorflow_io.so: undefined symbol: _ZNK10tensorflow4data11DatasetBase8FinalizeEPNS_15OpKernelContextESt8functionIFN3tsl8StatusOrINS5_4core11RefCountPtrIS1_EEEEvEE']\n",
      "  warnings.warn(f\"file system plugins are not loaded: {e}\")\n"
     ]
    }
   ],
   "source": [
    "import numpy as np\n",
    "import keras\n",
    "from keras.datasets import mnist\n",
    "from keras.models import Model\n",
    "from keras.layers import Dense, Input\n",
    "from keras.layers import Conv2D, MaxPooling2D, Dropout, Flatten\n",
    "from keras import backend as k"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "id": "46b59f1a",
   "metadata": {},
   "outputs": [],
   "source": [
    "(x_train, y_train), (x_test, y_test) = mnist.load_data()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "148bcd46",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Train: X=(60000, 28, 28), y=(60000,)\n",
      "Test: X=(10000, 28, 28), y=(10000,)\n"
     ]
    }
   ],
   "source": [
    "print('Train: X=%s, y=%s' % (x_train.shape, y_train.shape))\n",
    "print('Test: X=%s, y=%s' % (x_test.shape, y_test.shape))\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "id": "035f742c",
   "metadata": {},
   "outputs": [],
   "source": [
    "x_train = x_train.reshape(60000, 28, 28, 1)\n",
    "x_test = x_test.reshape(10000, 28, 28, 1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "id": "b5514d78",
   "metadata": {},
   "outputs": [],
   "source": [
    "x_train = x_train.astype('float32')/255\n",
    "x_test = x_test.astype('float32')/255"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "id": "9c705786-df8c-4c56-87dc-a0927a649dc0",
   "metadata": {},
   "outputs": [],
   "source": [
    "y_train = keras.utils.to_categorical(y_train)\n",
    "y_test = keras.utils.to_categorical(y_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "id": "a10bb62f-8135-4320-a143-3355166343a8",
   "metadata": {},
   "outputs": [],
   "source": [
    "inpx = Input(shape=(28,28,1))\n",
    "layer1 = Conv2D(32, kernel_size=(3, 3), activation='relu')(inpx)\n",
    "layer2 = Conv2D(64, (3, 3), activation='relu')(layer1)\n",
    "layer3 = MaxPooling2D(pool_size=(3, 3))(layer2)\n",
    "layer4 = Dropout(0.5)(layer3)\n",
    "layer5 = Flatten()(layer4)\n",
    "layer6 = Dense(250, activation='sigmoid')(layer5)\n",
    "layer7 = Dense(10, activation='softmax')(layer6)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "id": "474c8a14-15cd-4b82-9db5-91dd2efcde68",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 1/6\n",
      "120/120 [==============================] - 117s 958ms/step - loss: 0.5080 - accuracy: 0.8517\n",
      "Epoch 2/6\n",
      "120/120 [==============================] - 112s 930ms/step - loss: 0.1307 - accuracy: 0.9638\n",
      "Epoch 3/6\n",
      "120/120 [==============================] - 117s 978ms/step - loss: 0.0874 - accuracy: 0.9751\n",
      "Epoch 4/6\n",
      "120/120 [==============================] - 110s 915ms/step - loss: 0.0665 - accuracy: 0.9808\n",
      "Epoch 5/6\n",
      "120/120 [==============================] - 110s 917ms/step - loss: 0.0560 - accuracy: 0.9841\n",
      "Epoch 6/6\n",
      "120/120 [==============================] - 116s 964ms/step - loss: 0.0487 - accuracy: 0.9857\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "<keras.callbacks.History at 0x7faa75a086a0>"
      ]
     },
     "execution_count": 43,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "model = Model([inpx], layer7)\n",
    "model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])\n",
    "model.fit(x_train, y_train, epochs=6, batch_size=500)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "id": "80434697-1cb8-4313-834f-608492c7492d",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.03506316617131233 0.9889000058174133\n"
     ]
    }
   ],
   "source": [
    "loss, accuracy = model.evaluate(x_test,y_test,verbose=0)\n",
    "print(loss, accuracy)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "id": "4efcf0c2",
   "metadata": {},
   "outputs": [],
   "source": [
    "import cv2\n",
    "import matplotlib.pyplot as plt"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 52,
   "id": "cc713f4c",
   "metadata": {},
   "outputs": [],
   "source": [
    "img = cv2.imread(\"2.png\",cv2.IMREAD_GRAYSCALE)\n",
    "img = cv2.resize(img,(28,28))\n",
    "img = img/255.0\n",
    "img = img.reshape(1,28,28,1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 53,
   "id": "f3286946",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "1/1 [==============================] - 0s 41ms/step\n",
      "Digit is 3\n"
     ]
    }
   ],
   "source": [
    "pred = model.predict(img)\n",
    "digit = np.argmax(pred)\n",
    "print(f\"Digit is {digit}\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 54,
   "id": "acf409b3",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<BarContainer object of 10 artists>"
      ]
     },
     "execution_count": 54,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.imshow(img.reshape(28,28),cmap='gray',vmin=0,vmax=1)\n",
    "plt.bar(range(10),pred[0])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "07dbcdd0",
   "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": "3.10.12"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}