Digit_Recognition_Training.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Handwritten Digit Recognition Model Training"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    " "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 84
    },
    "colab_type": "code",
    "id": "oEmYBRrTgXR7",
    "outputId": "744f355f-9edb-4445-9f6d-ebdc12a9a95c"
   },
   "outputs": [],
   "source": [
    "# Import required Libraries:\n",
    "\n",
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "import tensorflow as tf"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 84
    },
    "colab_type": "code",
    "id": "EQpSONdtgXSC",
    "outputId": "9a58f67e-93b6-4436-a1ba-b3b11b49025a"
   },
   "outputs": [],
   "source": [
    "# Import the MNIST Dataset:\n",
    "\n",
    "mnist = tf.keras.datasets.mnist\n",
    "(x_train, y_train), (x_test, y_test) = mnist.load_data()\n",
    "x_train, x_test = x_train / 255.0, x_test / 255.0"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 202
    },
    "colab_type": "code",
    "id": "H19m6mHVgXSF",
    "outputId": "61110bc4-807c-455e-fef9-0781bfa77027"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Shape of Training Dataset: (60000, 28, 28)\n",
      "Shape of Training Dataset Labels: (60000,)\n",
      "Shape of Test Dataset: (10000, 28, 28)\n",
      "Shape of Test Dataset Labels: (10000,)\n"
     ]
    }
   ],
   "source": [
    "# Printing the shapes of both Training & Testing Datasets as well as their Labels:\n",
    "\n",
    "print(\"Shape of Training Dataset:\", x_train.shape)\n",
    "print(\"Shape of Training Dataset Labels:\", y_train.shape)\n",
    "print(\"Shape of Test Dataset:\", x_test.shape)\n",
    "print(\"Shape of Test Dataset Labels:\", y_test.shape)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 152
    },
    "colab_type": "code",
    "id": "D7smPoL0gXSI",
    "outputId": "baf3712c-cbc3-433c-e67b-08c6aa25dd38"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[5 0 4 1 9]\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "<matplotlib.image.AxesImage at 0x7fa62e83c7f0>"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "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": [
    "# Print the labels of the first 5 digits present in the Taining dataset:\n",
    "\n",
    "nb_images = 5\n",
    "print(y_train[:nb_images])\n",
    "\n",
    "# Also, Let's see the images of first 5 digits present in the Taining dataset:\n",
    "\n",
    "train_images = np.hstack(x_train[:nb_images])\n",
    "plt.imshow(train_images, cmap='Greys')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 336
    },
    "colab_type": "code",
    "id": "Hbg5mRTxgXSR",
    "outputId": "69bb41a3-da8a-4022-9190-737b1a0dd242"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Model: \"sequential\"\n",
      "_________________________________________________________________\n",
      "Layer (type)                 Output Shape              Param #   \n",
      "=================================================================\n",
      "flatten (Flatten)            (None, 784)               0         \n",
      "_________________________________________________________________\n",
      "dense (Dense)                (None, 128)               100480    \n",
      "_________________________________________________________________\n",
      "dropout (Dropout)            (None, 128)               0         \n",
      "_________________________________________________________________\n",
      "dense_1 (Dense)              (None, 10)                1290      \n",
      "_________________________________________________________________\n",
      "softmax (Softmax)            (None, 10)                0         \n",
      "=================================================================\n",
      "Total params: 101,770\n",
      "Trainable params: 101,770\n",
      "Non-trainable params: 0\n",
      "_________________________________________________________________\n",
      "None\n"
     ]
    }
   ],
   "source": [
    "# Now, we will create a Neural Network model and define the layers of our model:\n",
    "\n",
    "model = tf.keras.models.Sequential([\n",
    "  tf.keras.layers.Flatten(input_shape=(28, 28)),\n",
    "  tf.keras.layers.Dense(128, activation='relu'),\n",
    "  tf.keras.layers.Dropout(0.2),\n",
    "  tf.keras.layers.Dense(10),\n",
    "  tf.keras.layers.Softmax()\n",
    "])\n",
    "\n",
    "# Print the summary of the model:\n",
    "\n",
    "print(model.summary())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 50
    },
    "colab_type": "code",
    "id": "SxeplOb0gXSY",
    "outputId": "dc4a3594-552c-4e6a-d799-41f89f01a338"
   },
   "outputs": [],
   "source": [
    "# Defining of Loss Function for our model:\n",
    "\n",
    "loss_fn = tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True) "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 50
    },
    "colab_type": "code",
    "id": "VgVCr-DGgXSd",
    "outputId": "28215936-ae71-49fe-9a7b-5be316974882"
   },
   "outputs": [],
   "source": [
    "# Compile our model:\n",
    "\n",
    "model.compile(optimizer='adam', loss=loss_fn, metrics=['accuracy'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 386
    },
    "colab_type": "code",
    "id": "c6VvJVxIgXSi",
    "outputId": "f303f645-d8aa-4307-e738-4fc837f7f5d1"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Train on 48000 samples, validate on 12000 samples\n",
      "Epoch 1/10\n",
      "48000/48000 [==============================] - 2s 32us/sample - loss: 1.6915 - accuracy: 0.8176 - val_loss: 1.5610 - val_accuracy: 0.9172\n",
      "Epoch 2/10\n",
      "48000/48000 [==============================] - 1s 13us/sample - loss: 1.5635 - accuracy: 0.9139 - val_loss: 1.5379 - val_accuracy: 0.9351\n",
      "Epoch 3/10\n",
      "48000/48000 [==============================] - 1s 13us/sample - loss: 1.5428 - accuracy: 0.9300 - val_loss: 1.5285 - val_accuracy: 0.9413\n",
      "Epoch 4/10\n",
      "48000/48000 [==============================] - 1s 14us/sample - loss: 1.5317 - accuracy: 0.9389 - val_loss: 1.5186 - val_accuracy: 0.9503\n",
      "Epoch 5/10\n",
      "48000/48000 [==============================] - 1s 12us/sample - loss: 1.5235 - accuracy: 0.9458 - val_loss: 1.5128 - val_accuracy: 0.9554\n",
      "Epoch 6/10\n",
      "48000/48000 [==============================] - 1s 13us/sample - loss: 1.5172 - accuracy: 0.9511 - val_loss: 1.5087 - val_accuracy: 0.9581\n",
      "Epoch 7/10\n",
      "48000/48000 [==============================] - 1s 13us/sample - loss: 1.5125 - accuracy: 0.9556 - val_loss: 1.5061 - val_accuracy: 0.9607\n",
      "Epoch 8/10\n",
      "48000/48000 [==============================] - 1s 13us/sample - loss: 1.5078 - accuracy: 0.9597 - val_loss: 1.5051 - val_accuracy: 0.9597\n",
      "Epoch 9/10\n",
      "48000/48000 [==============================] - 1s 13us/sample - loss: 1.5042 - accuracy: 0.9625 - val_loss: 1.5023 - val_accuracy: 0.9623\n",
      "Epoch 10/10\n",
      "48000/48000 [==============================] - 1s 13us/sample - loss: 1.5019 - accuracy: 0.9643 - val_loss: 1.4999 - val_accuracy: 0.9650\n"
     ]
    }
   ],
   "source": [
    "# Training of our model:\n",
    "\n",
    "hist = model.fit(x_train, y_train, epochs=10, shuffle=True, batch_size=256, validation_split=0.20)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 265
    },
    "colab_type": "code",
    "id": "sV-VHKh5jWuH",
    "outputId": "e710ce0c-d658-442f-daf3-19fbea372a64"
   },
   "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": [
    "# Plotting of the graphs of Loss & Accuracy of both the Training as well as Validation:\n",
    "\n",
    "plt.figure(0)\n",
    "plt.plot(hist.history['loss'], 'g')\n",
    "plt.plot(hist.history['val_loss'], 'b')\n",
    "plt.plot(hist.history['accuracy'], 'r')\n",
    "plt.plot(hist.history['val_accuracy'], 'black')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "10000/1 - 0s - loss: 1.4809 - accuracy: 0.9666\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "[1.4987483066558838, 0.9666]"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Checking the model's performance on the Test Dataset:\n",
    "\n",
    "model.evaluate(x_test,  y_test, verbose=2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "WARNING:tensorflow:From /opt/app-root/lib/python3.6/site-packages/tensorflow_core/python/ops/resource_variable_ops.py:1781: calling BaseResourceVariable.__init__ (from tensorflow.python.ops.resource_variable_ops) with constraint is deprecated and will be removed in a future version.\n",
      "Instructions for updating:\n",
      "If using Keras pass *_constraint arguments to layers.\n",
      "INFO:tensorflow:Assets written to: my_mnist_model/assets\n"
     ]
    }
   ],
   "source": [
    "# Saving the model:\n",
    "\n",
    "model.save('my_mnist_model')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(1, 28, 28)\n"
     ]
    }
   ],
   "source": [
    "print(x_train[:1].shape)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[8.6239737e-08, 2.3835590e-11, 5.0094275e-08, 1.0621590e-03,\n",
       "        7.5798615e-15, 9.9893767e-01, 2.3644222e-12, 3.6226275e-09,\n",
       "        9.7094344e-10, 1.3533512e-10]], dtype=float32)"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "\n",
    "model.predict(x_train[:1])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "5"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "np.argmax(model.predict(x_train[:1]))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    " "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    " "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    " "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    " "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    " "
   ]
  }
 ],
 "metadata": {
  "accelerator": "GPU",
  "colab": {
   "name": "modified_sample_notebooks_tensorflow_s3.ipynb",
   "provenance": [],
   "toc_visible": true
  },
  "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": "3.8.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}