Hackthebox Mnist without 2

hackthebox-mnist-without-2.ipynb

{
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "view-in-github",
        "colab_type": "text"
      },
      "source": [
        "<a href=\"https://colab.research.google.com/gist/tudoanh/2bf2fec35ce68285996fb846dbedf29c/hackthebox-mnist-without-2.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "gspKA7tmmqXA"
      },
      "source": [
        "# Simple MNIST convnet (without `2`)\n",
        "\n",
        "**Author:** [fchollet](https://twitter.com/fchollet)<br>\n",
        "**Date created:** 2015/06/19<br>\n",
        "**Last modified:** 2020/04/21<br>\n",
        "**Description:** A simple convnet that achieves ~99% test accuracy on MNIST.<br>\n",
        "\n",
        "Modified by [tudoanh](https://github.com/tudoanh)<br>"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "Bwiw_UnimqXC"
      },
      "source": [
        "## Setup"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "YTKn26KtmqXD"
      },
      "outputs": [],
      "source": [
        "import numpy as np\n",
        "from tensorflow import keras\n",
        "from tensorflow.keras import layers"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "f_mC9R7RmqXE"
      },
      "source": [
        "## Prepare the data"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "gvVmRVQCmqXF",
        "outputId": "d8b8a21c-f52b-4cf2-9c19-399e42a42e4e",
        "colab": {
          "base_uri": "https://localhost:8080/"
        }
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "x_train shape: (60000, 28, 28, 1)\n",
            "60000 train samples\n",
            "10000 test samples\n"
          ]
        }
      ],
      "source": [
        "# Model / data parameters\n",
        "num_classes = 10\n",
        "input_shape = (28, 28, 1)\n",
        "\n",
        "# the data, split between train and test sets\n",
        "(x_train, y_train), (x_test, y_test) = keras.datasets.mnist.load_data()\n",
        "\n",
        "def swap(digit, to_digit, y):\n",
        "    idx = (y == digit).nonzero()\n",
        "    y[idx] = to_digit\n",
        "    return y\n",
        "y_train = swap(2, 9, y_train)\n",
        "y_test = swap(2, 9, y_test)\n",
        "# Scale images to the [0, 1] range\n",
        "x_train = x_train.astype(\"float32\") / 255\n",
        "x_test = x_test.astype(\"float32\") / 255\n",
        "# Make sure images have shape (28, 28, 1)\n",
        "x_train = np.expand_dims(x_train, -1)\n",
        "x_test = np.expand_dims(x_test, -1)\n",
        "print(\"x_train shape:\", x_train.shape)\n",
        "print(x_train.shape[0], \"train samples\")\n",
        "print(x_test.shape[0], \"test samples\")\n",
        "\n",
        "\n",
        "# convert class vectors to binary class matrices\n",
        "y_train = keras.utils.to_categorical(y_train, num_classes)\n",
        "y_test = keras.utils.to_categorical(y_test, num_classes)"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "uLkDN20xmqXG"
      },
      "source": [
        "## Build the model"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "0pBFjWcvmqXH",
        "outputId": "46f81585-eede-462f-e3e2-95960f426563",
        "colab": {
          "base_uri": "https://localhost:8080/"
        }
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Model: \"sequential_8\"\n",
            "_________________________________________________________________\n",
            " Layer (type)                Output Shape              Param #   \n",
            "=================================================================\n",
            " conv2d_17 (Conv2D)          (None, 26, 26, 32)        320       \n",
            "                                                                 \n",
            " max_pooling2d_17 (MaxPoolin  (None, 13, 13, 32)       0         \n",
            " g2D)                                                            \n",
            "                                                                 \n",
            " conv2d_18 (Conv2D)          (None, 11, 11, 64)        18496     \n",
            "                                                                 \n",
            " max_pooling2d_18 (MaxPoolin  (None, 5, 5, 64)         0         \n",
            " g2D)                                                            \n",
            "                                                                 \n",
            " flatten_8 (Flatten)         (None, 1600)              0         \n",
            "                                                                 \n",
            " dropout_8 (Dropout)         (None, 1600)              0         \n",
            "                                                                 \n",
            " dense_8 (Dense)             (None, 10)                16010     \n",
            "                                                                 \n",
            "=================================================================\n",
            "Total params: 34,826\n",
            "Trainable params: 34,826\n",
            "Non-trainable params: 0\n",
            "_________________________________________________________________\n"
          ]
        }
      ],
      "source": [
        "model = keras.Sequential(\n",
        "    [\n",
        "        keras.Input(shape=input_shape),\n",
        "        layers.Conv2D(32, kernel_size=(3, 3), activation=\"relu\"),\n",
        "        layers.MaxPooling2D(pool_size=(2, 2)),\n",
        "        layers.Conv2D(64, kernel_size=(3, 3), activation=\"relu\"),\n",
        "        layers.MaxPooling2D(pool_size=(2, 2)),\n",
        "        layers.Flatten(),\n",
        "        layers.Dropout(0.5),\n",
        "        layers.Dense(num_classes, activation=\"softmax\"),\n",
        "    ]\n",
        ")\n",
        "\n",
        "model.summary()"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "eOj8XiS_mqXH"
      },
      "source": [
        "## Train the model"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "S4rbfZuFmqXI",
        "outputId": "a1218510-7fbf-4742-d7a1-645c7c61c41e",
        "colab": {
          "base_uri": "https://localhost:8080/"
        }
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Epoch 1/15\n",
            "422/422 [==============================] - 2s 5ms/step - loss: 0.4024 - accuracy: 0.8662 - val_loss: 0.0945 - val_accuracy: 0.9750\n",
            "Epoch 2/15\n",
            "422/422 [==============================] - 2s 4ms/step - loss: 0.1335 - accuracy: 0.9586 - val_loss: 0.0664 - val_accuracy: 0.9817\n",
            "Epoch 3/15\n",
            "422/422 [==============================] - 2s 4ms/step - loss: 0.0994 - accuracy: 0.9686 - val_loss: 0.0548 - val_accuracy: 0.9845\n",
            "Epoch 4/15\n",
            "422/422 [==============================] - 2s 4ms/step - loss: 0.0815 - accuracy: 0.9738 - val_loss: 0.0481 - val_accuracy: 0.9863\n",
            "Epoch 5/15\n",
            "422/422 [==============================] - 2s 4ms/step - loss: 0.0728 - accuracy: 0.9775 - val_loss: 0.0449 - val_accuracy: 0.9870\n",
            "Epoch 6/15\n",
            "422/422 [==============================] - 2s 4ms/step - loss: 0.0647 - accuracy: 0.9797 - val_loss: 0.0404 - val_accuracy: 0.9897\n",
            "Epoch 7/15\n",
            "422/422 [==============================] - 2s 4ms/step - loss: 0.0605 - accuracy: 0.9804 - val_loss: 0.0381 - val_accuracy: 0.9890\n",
            "Epoch 8/15\n",
            "422/422 [==============================] - 2s 4ms/step - loss: 0.0564 - accuracy: 0.9818 - val_loss: 0.0367 - val_accuracy: 0.9903\n",
            "Epoch 9/15\n",
            "422/422 [==============================] - 2s 4ms/step - loss: 0.0518 - accuracy: 0.9834 - val_loss: 0.0350 - val_accuracy: 0.9903\n",
            "Epoch 10/15\n",
            "422/422 [==============================] - 2s 4ms/step - loss: 0.0497 - accuracy: 0.9845 - val_loss: 0.0363 - val_accuracy: 0.9907\n",
            "Epoch 11/15\n",
            "422/422 [==============================] - 2s 4ms/step - loss: 0.0459 - accuracy: 0.9847 - val_loss: 0.0351 - val_accuracy: 0.9915\n",
            "Epoch 12/15\n",
            "422/422 [==============================] - 2s 4ms/step - loss: 0.0449 - accuracy: 0.9854 - val_loss: 0.0342 - val_accuracy: 0.9910\n",
            "Epoch 13/15\n",
            "422/422 [==============================] - 2s 4ms/step - loss: 0.0445 - accuracy: 0.9854 - val_loss: 0.0367 - val_accuracy: 0.9903\n",
            "Epoch 14/15\n",
            "422/422 [==============================] - 2s 4ms/step - loss: 0.0400 - accuracy: 0.9875 - val_loss: 0.0328 - val_accuracy: 0.9908\n",
            "Epoch 15/15\n",
            "422/422 [==============================] - 2s 4ms/step - loss: 0.0387 - accuracy: 0.9874 - val_loss: 0.0324 - val_accuracy: 0.9915\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "<keras.callbacks.History at 0x7f6d6a576a90>"
            ]
          },
          "metadata": {},
          "execution_count": 40
        }
      ],
      "source": [
        "batch_size = 128\n",
        "epochs = 15\n",
        "\n",
        "model.compile(loss=\"categorical_crossentropy\", optimizer=\"adam\", metrics=[\"accuracy\"])\n",
        "\n",
        "model.fit(x_train, y_train, batch_size=batch_size, epochs=epochs, validation_split=0.1)"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "j3GauoznmqXJ"
      },
      "source": [
        "## Evaluate the trained model"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "8uWAffpXmqXK",
        "outputId": "10a709d6-ceaa-4a9b-e3dd-5aef98cba08a",
        "colab": {
          "base_uri": "https://localhost:8080/"
        }
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Test loss: 0.03250782564282417\n",
            "Test accuracy: 0.9889000058174133\n"
          ]
        }
      ],
      "source": [
        "score = model.evaluate(x_test, y_test, verbose=0)\n",
        "print(\"Test loss:\", score[0])\n",
        "print(\"Test accuracy:\", score[1])"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "model.save(\"model.h5\")"
      ],
      "metadata": {
        "id": "BEpXKle3nIZy"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        ""
      ],
      "metadata": {
        "id": "sVUELsOEnkgn"
      },
      "execution_count": null,
      "outputs": []
    }
  ],
  "metadata": {
    "colab": {
      "collapsed_sections": [],
      "name": "Hackthebox Mnist without 2",
      "provenance": [],
      "include_colab_link": 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": "3.7.0"
    },
    "accelerator": "GPU"
  },
  "nbformat": 4,
  "nbformat_minor": 0
}

Zip file

https://drive.google.com/file/d/1glmXFBXSGfp6CC9329O9153kqSJkSKtY/view?usp=sharing