Shashank Submission: Implementing Hand-digit recognition in Keras

shashiraj0308@gmail.com/Project-Code/Code/.gitattributes

@@ -0,0 +1,2 @@
+# Auto detect text files and perform LF normalization
+* text=auto

shashiraj0308@gmail.com/Project-Code/Code/.ipynb_checkpoints/hand digit recognition in keras-checkpoint.ipynb

@@ -0,0 +1,258 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Implement hand digit recognition in Keras with dataset at https://keras.io/examples/mnist_dataset_api/ with a simple 3-layer FFNN with fully connected layers (no convolution or other operations)."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Using TensorFlow backend.\n"
+     ]
+    }
+   ],
+   "source": [
+    "#importing required modules\n",
+    "\n",
+    "import keras\n",
+    "import numpy as np\n",
+    "from keras.datasets import mnist \n",
+    "from keras.models import Sequential\n",
+    "from keras.layers import Flatten,Dense\n",
+    "from keras.utils import normalize\n",
+    "import tensorflow as tf\n",
+    "from tensorflow.nn import relu,softmax"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#spliting dataset into training data and teting data\n",
+    "\n",
+    "(xtrain,ytrain),(xtest,ytest) = mnist.load_data()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#scaling the pixel values between 0-1\n",
+    "xtrain = normalize(xtrain,axis=1)\n",
+    "xtest = normalize(xtest,axis=1)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "WARNING: Logging before flag parsing goes to stderr.\n",
+      "W0730 12:34:40.611266 18928 deprecation_wrapper.py:119] From c:\\users\\ravin\\appdata\\local\\programs\\python\\python37\\lib\\site-packages\\keras\\backend\\tensorflow_backend.py:74: The name tf.get_default_graph is deprecated. Please use tf.compat.v1.get_default_graph instead.\n",
+      "\n",
+      "W0730 12:34:40.635203 18928 deprecation_wrapper.py:119] From c:\\users\\ravin\\appdata\\local\\programs\\python\\python37\\lib\\site-packages\\keras\\optimizers.py:790: The name tf.train.Optimizer is deprecated. Please use tf.compat.v1.train.Optimizer instead.\n",
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "#defining model and adding layers\n",
+    "\n",
+    "model = Sequential()\n",
+    "model.add(Flatten())\n",
+    "model.add(Dense(128,activation=relu))\n",
+    "model.add(Dense(10,activation=softmax))\n",
+    "\n",
+    "model.compile(optimizer='adam',\n",
+    "              loss='sparse_categorical_crossentropy',\n",
+    "             metrics=['accuracy'])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "W0730 12:34:40.713134 18928 deprecation_wrapper.py:119] From c:\\users\\ravin\\appdata\\local\\programs\\python\\python37\\lib\\site-packages\\keras\\backend\\tensorflow_backend.py:517: The name tf.placeholder is deprecated. Please use tf.compat.v1.placeholder instead.\n",
+      "\n",
+      "W0730 12:34:40.723106 18928 deprecation_wrapper.py:119] From c:\\users\\ravin\\appdata\\local\\programs\\python\\python37\\lib\\site-packages\\keras\\backend\\tensorflow_backend.py:4138: The name tf.random_uniform is deprecated. Please use tf.random.uniform instead.\n",
+      "\n",
+      "W0730 12:34:40.764033 18928 deprecation_wrapper.py:119] From c:\\users\\ravin\\appdata\\local\\programs\\python\\python37\\lib\\site-packages\\keras\\backend\\tensorflow_backend.py:3341: The name tf.log is deprecated. Please use tf.math.log instead.\n",
+      "\n",
+      "W0730 12:34:40.850765 18928 deprecation.py:323] From c:\\users\\ravin\\appdata\\local\\programs\\python\\python37\\lib\\site-packages\\tensorflow\\python\\ops\\math_grad.py:1250: add_dispatch_support.<locals>.wrapper (from tensorflow.python.ops.array_ops) is deprecated and will be removed in a future version.\n",
+      "Instructions for updating:\n",
+      "Use tf.where in 2.0, which has the same broadcast rule as np.where\n",
+      "W0730 12:34:40.877728 18928 deprecation_wrapper.py:119] From c:\\users\\ravin\\appdata\\local\\programs\\python\\python37\\lib\\site-packages\\keras\\backend\\tensorflow_backend.py:986: The name tf.assign_add is deprecated. Please use tf.compat.v1.assign_add instead.\n",
+      "\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Epoch 1/3\n",
+      "60000/60000 [==============================] - 5s 89us/step - loss: 0.3119 - acc: 0.9132\n",
+      "Epoch 2/3\n",
+      "60000/60000 [==============================] - 6s 105us/step - loss: 0.1420 - acc: 0.9582\n",
+      "Epoch 3/3\n",
+      "60000/60000 [==============================] - 6s 105us/step - loss: 0.0977 - acc: 0.9708\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "<keras.callbacks.History at 0x186d59428d0>"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# training the model\n",
+    "model.fit(xtrain,ytrain,epochs=3)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "_________________________________________________________________\n",
+      "Layer (type)                 Output Shape              Param #   \n",
+      "=================================================================\n",
+      "flatten_1 (Flatten)          (None, 784)               0         \n",
+      "_________________________________________________________________\n",
+      "dense_1 (Dense)              (None, 128)               100480    \n",
+      "_________________________________________________________________\n",
+      "dense_2 (Dense)              (None, 10)                1290      \n",
+      "=================================================================\n",
+      "Total params: 101,770\n",
+      "Trainable params: 101,770\n",
+      "Non-trainable params: 0\n",
+      "_________________________________________________________________\n"
+     ]
+    }
+   ],
+   "source": [
+    "#trained model summary\n",
+    "model.summary()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "10000/10000 [==============================] - 0s 28us/step\n",
+      "Loss : 0.106505593823269\n",
+      "Accuracy :  0.9693\n"
+     ]
+    }
+   ],
+   "source": [
+    "# calculating the accuracy and loss\n",
+    "\n",
+    "loss,accuracy= model.evaluate(xtest,ytest) \n",
+    "print(\"Loss :\",loss)\n",
+    "print(\"Accuracy : \",accuracy)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "2\n"
+     ]
+    }
+   ],
+   "source": [
+    "#prediction\n",
+    "\n",
+    "predict = model.predict([xtest])\n",
+    "print(np.argmax(predict[1]))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 432x288 with 1 Axes>"
+      ]
+     },
+     "metadata": {
+      "needs_background": "light"
+     },
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "import matplotlib.pyplot as plt\n",
+    "\n",
+    "plt.imshow(xtest[1])\n",
+    "plt.show()"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "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": "3.7.3"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

shashiraj0308@gmail.com/Project-Code/Code/.ipynb_checkpoints/sgd and categorical_crossentropy-checkpoint.ipynb

@@ -0,0 +1,6 @@
+{
+ "cells": [],
+ "metadata": {},
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

shashiraj0308@gmail.com/Project-Code/Code/.ipynb_checkpoints/sgd and kullback-checkpoint.ipynb

@@ -0,0 +1,6 @@
+{
+ "cells": [],
+ "metadata": {},
+ "nbformat": 4,
+ "nbformat_minor": 2
+}