{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "l8RrpoC0T1CR",
    "outputId": "5cd7fc04-e75a-4e79-d40d-3bbab858b821"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Collecting gradio\n",
      "  Downloading gradio-3.44.3-py3-none-any.whl (20.2 MB)\n",
      "     ---------------------------------------- 20.2/20.2 MB 5.7 MB/s eta 0:00:00\n",
      "Requirement already satisfied: pandas<3.0,>=1.0 in c:\\users\\admin\\anaconda3\\lib\\site-packages (from gradio) (1.5.3)\n",
      "Requirement already satisfied: numpy~=1.0 in c:\\users\\admin\\anaconda3\\lib\\site-packages (from gradio) (1.23.5)\n",
      "Collecting pydantic!=1.8,!=1.8.1,!=2.0.0,!=2.0.1,<3.0.0,>=1.7.4\n",
      "  Downloading pydantic-2.3.0-py3-none-any.whl (374 kB)\n",
      "     -------------------------------------- 374.5/374.5 kB 5.8 MB/s eta 0:00:00\n",
      "Collecting httpx\n",
      "  Downloading httpx-0.25.0-py3-none-any.whl (75 kB)\n",
      "     ---------------------------------------- 75.7/75.7 kB 4.1 MB/s eta 0:00:00\n",
      "Collecting ffmpy\n",
      "  Downloading ffmpy-0.3.1.tar.gz (5.5 kB)\n",
      "  Preparing metadata (setup.py): started\n",
      "  Preparing metadata (setup.py): finished with status 'done'\n",
      "Collecting uvicorn>=0.14.0\n",
      "  Downloading uvicorn-0.23.2-py3-none-any.whl (59 kB)\n",
      "     ---------------------------------------- 59.5/59.5 kB 1.5 MB/s eta 0:00:00\n",
      "Collecting huggingface-hub>=0.14.0\n",
      "  Downloading huggingface_hub-0.17.1-py3-none-any.whl (294 kB)\n",
      "     -------------------------------------- 294.8/294.8 kB 6.1 MB/s eta 0:00:00\n",
      "Collecting python-multipart\n",
      "  Downloading python_multipart-0.0.6-py3-none-any.whl (45 kB)\n",
      "     ---------------------------------------- 45.7/45.7 kB 2.4 MB/s eta 0:00:00\n",
      "Requirement already satisfied: requests~=2.0 in c:\\users\\admin\\anaconda3\\lib\\site-packages (from gradio) (2.28.1)\n",
      "Requirement already satisfied: typing-extensions~=4.0 in c:\\users\\admin\\anaconda3\\lib\\site-packages (from gradio) (4.4.0)\n",
      "Requirement already satisfied: jinja2<4.0 in c:\\users\\admin\\anaconda3\\lib\\site-packages (from gradio) (3.1.2)\n",
      "Requirement already satisfied: matplotlib~=3.0 in c:\\users\\admin\\anaconda3\\lib\\site-packages (from gradio) (3.7.0)\n",
      "Collecting semantic-version~=2.0\n",
      "  Downloading semantic_version-2.10.0-py2.py3-none-any.whl (15 kB)\n",
      "Collecting aiofiles<24.0,>=22.0\n",
      "  Downloading aiofiles-23.2.1-py3-none-any.whl (15 kB)\n",
      "Requirement already satisfied: packaging in c:\\users\\admin\\anaconda3\\lib\\site-packages (from gradio) (22.0)\n",
      "Collecting websockets<12.0,>=10.0\n",
      "  Downloading websockets-11.0.3-cp310-cp310-win_amd64.whl (124 kB)\n",
      "     -------------------------------------- 124.7/124.7 kB 7.2 MB/s eta 0:00:00\n",
      "Collecting fastapi\n",
      "  Downloading fastapi-0.103.1-py3-none-any.whl (66 kB)\n",
      "     ---------------------------------------- 66.2/66.2 kB ? eta 0:00:00\n",
      "Collecting pydub\n",
      "  Downloading pydub-0.25.1-py2.py3-none-any.whl (32 kB)\n",
      "Requirement already satisfied: pillow<11.0,>=8.0 in c:\\users\\admin\\anaconda3\\lib\\site-packages (from gradio) (9.4.0)\n",
      "Collecting importlib-resources<7.0,>=1.3\n",
      "  Downloading importlib_resources-6.0.1-py3-none-any.whl (34 kB)\n",
      "Requirement already satisfied: pyyaml<7.0,>=5.0 in c:\\users\\admin\\anaconda3\\lib\\site-packages (from gradio) (6.0)\n",
      "Collecting altair<6.0,>=4.2.0\n",
      "  Downloading altair-5.1.1-py3-none-any.whl (520 kB)\n",
      "     -------------------------------------- 520.6/520.6 kB 4.1 MB/s eta 0:00:00\n",
      "Collecting gradio-client==0.5.0\n",
      "  Downloading gradio_client-0.5.0-py3-none-any.whl (298 kB)\n",
      "     -------------------------------------- 298.2/298.2 kB 6.1 MB/s eta 0:00:00\n",
      "Collecting orjson~=3.0\n",
      "  Downloading orjson-3.9.7-cp310-none-win_amd64.whl (134 kB)\n",
      "     -------------------------------------- 134.8/134.8 kB 2.7 MB/s eta 0:00:00\n",
      "Requirement already satisfied: markupsafe~=2.0 in c:\\users\\admin\\anaconda3\\lib\\site-packages (from gradio) (2.1.1)\n",
      "Requirement already satisfied: fsspec in c:\\users\\admin\\anaconda3\\lib\\site-packages (from gradio-client==0.5.0->gradio) (2022.11.0)\n",
      "Requirement already satisfied: jsonschema>=3.0 in c:\\users\\admin\\anaconda3\\lib\\site-packages (from altair<6.0,>=4.2.0->gradio) (4.17.3)\n",
      "Requirement already satisfied: toolz in c:\\users\\admin\\anaconda3\\lib\\site-packages (from altair<6.0,>=4.2.0->gradio) (0.12.0)\n",
      "Requirement already satisfied: tqdm>=4.42.1 in c:\\users\\admin\\anaconda3\\lib\\site-packages (from huggingface-hub>=0.14.0->gradio) (4.64.1)\n",
      "Requirement already satisfied: filelock in c:\\users\\admin\\anaconda3\\lib\\site-packages (from huggingface-hub>=0.14.0->gradio) (3.9.0)\n",
      "Requirement already satisfied: pyparsing>=2.3.1 in c:\\users\\admin\\anaconda3\\lib\\site-packages (from matplotlib~=3.0->gradio) (3.0.9)\n",
      "Requirement already satisfied: fonttools>=4.22.0 in c:\\users\\admin\\anaconda3\\lib\\site-packages (from matplotlib~=3.0->gradio) (4.25.0)\n",
      "Requirement already satisfied: python-dateutil>=2.7 in c:\\users\\admin\\anaconda3\\lib\\site-packages (from matplotlib~=3.0->gradio) (2.8.2)\n",
      "Requirement already satisfied: kiwisolver>=1.0.1 in c:\\users\\admin\\anaconda3\\lib\\site-packages (from matplotlib~=3.0->gradio) (1.4.4)\n",
      "Requirement already satisfied: contourpy>=1.0.1 in c:\\users\\admin\\anaconda3\\lib\\site-packages (from matplotlib~=3.0->gradio) (1.0.5)\n",
      "Requirement already satisfied: cycler>=0.10 in c:\\users\\admin\\anaconda3\\lib\\site-packages (from matplotlib~=3.0->gradio) (0.11.0)\n",
      "Requirement already satisfied: pytz>=2020.1 in c:\\users\\admin\\anaconda3\\lib\\site-packages (from pandas<3.0,>=1.0->gradio) (2022.7)\n",
      "Collecting typing-extensions~=4.0\n",
      "  Downloading typing_extensions-4.7.1-py3-none-any.whl (33 kB)\n",
      "Collecting annotated-types>=0.4.0\n",
      "  Downloading annotated_types-0.5.0-py3-none-any.whl (11 kB)\n",
      "Collecting pydantic-core==2.6.3\n",
      "  Downloading pydantic_core-2.6.3-cp310-none-win_amd64.whl (1.7 MB)\n",
      "     ---------------------------------------- 1.7/1.7 MB 5.0 MB/s eta 0:00:00\n",
      "Requirement already satisfied: urllib3<1.27,>=1.21.1 in c:\\users\\admin\\anaconda3\\lib\\site-packages (from requests~=2.0->gradio) (1.26.14)\n",
      "Requirement already satisfied: certifi>=2017.4.17 in c:\\users\\admin\\anaconda3\\lib\\site-packages (from requests~=2.0->gradio) (2022.12.7)\n",
      "Requirement already satisfied: charset-normalizer<3,>=2 in c:\\users\\admin\\anaconda3\\lib\\site-packages (from requests~=2.0->gradio) (2.0.4)\n",
      "Requirement already satisfied: idna<4,>=2.5 in c:\\users\\admin\\anaconda3\\lib\\site-packages (from requests~=2.0->gradio) (3.4)\n",
      "Requirement already satisfied: click>=7.0 in c:\\users\\admin\\anaconda3\\lib\\site-packages (from uvicorn>=0.14.0->gradio) (8.0.4)\n",
      "Collecting h11>=0.8\n",
      "  Downloading h11-0.14.0-py3-none-any.whl (58 kB)\n",
      "     ---------------------------------------- 58.3/58.3 kB ? eta 0:00:00\n",
      "Collecting starlette<0.28.0,>=0.27.0\n",
      "  Downloading starlette-0.27.0-py3-none-any.whl (66 kB)\n",
      "     ---------------------------------------- 67.0/67.0 kB ? eta 0:00:00\n",
      "Collecting anyio<4.0.0,>=3.7.1\n",
      "  Downloading anyio-3.7.1-py3-none-any.whl (80 kB)\n",
      "     ---------------------------------------- 80.9/80.9 kB ? eta 0:00:00\n",
      "Requirement already satisfied: sniffio in c:\\users\\admin\\anaconda3\\lib\\site-packages (from httpx->gradio) (1.2.0)\n",
      "Collecting httpcore<0.19.0,>=0.18.0\n",
      "  Downloading httpcore-0.18.0-py3-none-any.whl (76 kB)\n",
      "     ---------------------------------------- 76.0/76.0 kB ? eta 0:00:00\n",
      "Collecting exceptiongroup\n",
      "  Downloading exceptiongroup-1.1.3-py3-none-any.whl (14 kB)\n",
      "Requirement already satisfied: colorama in c:\\users\\admin\\anaconda3\\lib\\site-packages (from click>=7.0->uvicorn>=0.14.0->gradio) (0.4.6)\n",
      "Requirement already satisfied: attrs>=17.4.0 in c:\\users\\admin\\anaconda3\\lib\\site-packages (from jsonschema>=3.0->altair<6.0,>=4.2.0->gradio) (22.1.0)\n",
      "Requirement already satisfied: pyrsistent!=0.17.0,!=0.17.1,!=0.17.2,>=0.14.0 in c:\\users\\admin\\anaconda3\\lib\\site-packages (from jsonschema>=3.0->altair<6.0,>=4.2.0->gradio) (0.18.0)\n",
      "Requirement already satisfied: six>=1.5 in c:\\users\\admin\\anaconda3\\lib\\site-packages (from python-dateutil>=2.7->matplotlib~=3.0->gradio) (1.16.0)\n",
      "Building wheels for collected packages: ffmpy\n",
      "  Building wheel for ffmpy (setup.py): started\n",
      "  Building wheel for ffmpy (setup.py): finished with status 'done'\n",
      "  Created wheel for ffmpy: filename=ffmpy-0.3.1-py3-none-any.whl size=5601 sha256=43e9a0a9285c8ed00438117305d007a6856228395941847f06649adf16cc1338\n",
      "  Stored in directory: c:\\users\\admin\\appdata\\local\\pip\\cache\\wheels\\25\\a7\\dd\\c513d5a67b9610660774187483d20314b63e406dd6687e4b4a\n",
      "Successfully built ffmpy\n",
      "Installing collected packages: pydub, ffmpy, websockets, typing-extensions, semantic-version, python-multipart, orjson, importlib-resources, h11, exceptiongroup, annotated-types, aiofiles, uvicorn, pydantic-core, huggingface-hub, anyio, starlette, pydantic, httpcore, altair, httpx, fastapi, gradio-client, gradio\n",
      "  Attempting uninstall: typing-extensions\n",
      "    Found existing installation: typing_extensions 4.4.0\n",
      "    Uninstalling typing_extensions-4.4.0:\n",
      "      Successfully uninstalled typing_extensions-4.4.0\n",
      "  Attempting uninstall: huggingface-hub\n",
      "    Found existing installation: huggingface-hub 0.10.1\n",
      "    Uninstalling huggingface-hub-0.10.1:\n",
      "      Successfully uninstalled huggingface-hub-0.10.1\n",
      "  Attempting uninstall: anyio\n",
      "    Found existing installation: anyio 3.5.0\n",
      "    Uninstalling anyio-3.5.0:\n",
      "      Successfully uninstalled anyio-3.5.0\n",
      "Successfully installed aiofiles-23.2.1 altair-5.1.1 annotated-types-0.5.0 anyio-3.7.1 exceptiongroup-1.1.3 fastapi-0.103.1 ffmpy-0.3.1 gradio-3.44.3 gradio-client-0.5.0 h11-0.14.0 httpcore-0.18.0 httpx-0.25.0 huggingface-hub-0.17.1 importlib-resources-6.0.1 orjson-3.9.7 pydantic-2.3.0 pydantic-core-2.6.3 pydub-0.25.1 python-multipart-0.0.6 semantic-version-2.10.0 starlette-0.27.0 typing-extensions-4.7.1 uvicorn-0.23.2 websockets-11.0.3\n"
     ]
    }
   ],
   "source": [
    "!pip install gradio"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "id": "STRRMSZCVpt9"
   },
   "outputs": [
    {
     "ename": "ModuleNotFoundError",
     "evalue": "No module named 'tensorflow'",
     "output_type": "error",
     "traceback": [
      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[1;31mModuleNotFoundError\u001b[0m                       Traceback (most recent call last)",
      "Cell \u001b[1;32mIn[2], line 5\u001b[0m\n\u001b[0;32m      3\u001b[0m \u001b[38;5;28;01mimport\u001b[39;00m \u001b[38;5;21;01mseaborn\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m \u001b[38;5;21;01msns\u001b[39;00m\n\u001b[0;32m      4\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mPIL\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m Image\n\u001b[1;32m----> 5\u001b[0m \u001b[38;5;28;01mimport\u001b[39;00m \u001b[38;5;21;01mtensorflow\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m \u001b[38;5;21;01mtf\u001b[39;00m\n\u001b[0;32m      6\u001b[0m tf\u001b[38;5;241m.\u001b[39mrandom\u001b[38;5;241m.\u001b[39mset_seed(\u001b[38;5;241m3\u001b[39m)\n\u001b[0;32m      7\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mtensorflow\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m keras\n",
      "\u001b[1;31mModuleNotFoundError\u001b[0m: No module named 'tensorflow'"
     ]
    }
   ],
   "source": [
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns\n",
    "from PIL import Image\n",
    "import tensorflow as tf\n",
    "tf.random.set_seed(3)\n",
    "from tensorflow import keras\n",
    "from keras.datasets import mnist\n",
    "from tensorflow.math import confusion_matrix"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "6iPPGLvvaMGU"
   },
   "source": [
    "1. Data understanding:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "id": "e48RTLHEV6d-"
   },
   "outputs": [],
   "source": [
    "(x_train,y_train), (x_test,y_test) = mnist.load_data()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "xPZiE4UqV8N8",
    "outputId": "5550b2d7-7d35-4f5f-fb3f-4dd12815e88f"
   },
   "outputs": [],
   "source": [
    "type(x_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "CTDRcRsFXaX0",
    "outputId": "bed93371-bfb4-49c5-be69-4c6223896bd2"
   },
   "outputs": [],
   "source": [
    "# shape of the numpy arrays\n",
    "print(x_train.shape, y_train.shape, x_test.shape, y_test.shape)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "rr9jdm31nBxK"
   },
   "source": [
    "Training data = 60,000 Images\n",
    "\n",
    "Test data = 10,000 Images"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "Kpu_bnGYX_TC",
    "outputId": "230759a2-2bf8-4f6c-80f9-50a64f2e68f8"
   },
   "outputs": [],
   "source": [
    "# printing the 10th image\n",
    "print(x_train[10])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "AKBkeVeTaajW",
    "outputId": "f3f07e79-6e5c-4b72-8060-d776e9153e3c"
   },
   "outputs": [],
   "source": [
    "# unique values in Y_train\n",
    "print(np.unique(y_train))\n",
    "\n",
    "# unique values in Y_test\n",
    "print(np.unique(y_test))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 443
    },
    "id": "RgGYRF-RX_ZS",
    "outputId": "a415eefd-0a0c-4510-fb5d-0d8c7d71160b"
   },
   "outputs": [],
   "source": [
    "plt.xticks([])\n",
    "plt.yticks([])\n",
    "plt.xlabel([y_train[10]])\n",
    "plt.imshow(x_train[10],cmap=plt.cm.binary)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 443
    },
    "id": "ZdJAi1Gwm38K",
    "outputId": "a8fbc8be-69b9-432d-8128-39897a5685b5"
   },
   "outputs": [],
   "source": [
    "plt.xticks([])\n",
    "plt.yticks([])\n",
    "plt.xlabel([y_test[10]])\n",
    "plt.imshow(x_test[10],cmap=plt.cm.binary)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "FP_-vUHTaf3e"
   },
   "source": [
    "2. Data prepocessing"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "id": "_UAPumftLfLi"
   },
   "outputs": [],
   "source": [
    "def pixel_normalization(image):\n",
    "    return (image / 255)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "id": "llckMTh-aA-5"
   },
   "outputs": [],
   "source": [
    "from keras.src.utils.np_utils import to_categorical\n",
    "x_train = pixel_normalization(x_train)\n",
    "x_test = pixel_normalization(x_test)\n",
    "y_train = to_categorical(y_train)\n",
    "y_test = to_categorical(y_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "id": "OpybamzzbAMJ"
   },
   "outputs": [],
   "source": [
    "x_train = np.expand_dims(x_train, axis=3)\n",
    "x_test = np.expand_dims(x_test, axis=3)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "njgeqOFAbUOw",
    "outputId": "add1008c-e9fe-4e80-de6b-2c1980034b20"
   },
   "outputs": [],
   "source": [
    "x_train.shape"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "8PCTOFTVcJ_3"
   },
   "source": [
    "3. Data modeling and evaluation"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "id": "TOaAB5O-cvyg"
   },
   "outputs": [],
   "source": [
    "from tensorflow.keras.models import Sequential, save_model, load_model\n",
    "from tensorflow.keras.layers import Conv2D, MaxPool2D, Flatten, Dense, Dropout\n",
    "from tensorflow.keras.utils import to_categorical, plot_model\n",
    "from tensorflow.keras.losses import CategoricalCrossentropy\n",
    "from tensorflow.keras.optimizers import Adam\n",
    "from tensorflow.keras.metrics import CategoricalAccuracy\n",
    "from tensorflow.keras.callbacks import ModelCheckpoint, ReduceLROnPlateau\n",
    "import warnings"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 1000
    },
    "id": "j1pps_dycSOo",
    "outputId": "dc42ec5d-0d08-4987-df71-e7a7201f5f34"
   },
   "outputs": [],
   "source": [
    "\n",
    "cnn = Sequential()\n",
    "cnn.add(Conv2D(filters=32, kernel_size=(3, 3), padding='same', strides=(1,1), activation='relu', input_shape=(28, 28, 1)))\n",
    "cnn.add(Dropout(.2))\n",
    "cnn.add(MaxPool2D(pool_size=(2, 2), strides=(2, 2)))\n",
    "cnn.add(Conv2D(filters=64, kernel_size=(3, 3), padding='same', strides=(1,1), activation='relu'))\n",
    "cnn.add(Dropout(.2))\n",
    "cnn.add(MaxPool2D(pool_size=(2, 2), strides=(2, 2)))\n",
    "cnn.add(Flatten())\n",
    "cnn.add(Dense(units=128, activation='relu'))\n",
    "cnn.add(Dropout(.5))\n",
    "cnn.add(Dense(units=10, activation='softmax'))\n",
    "\n",
    "plot_model(cnn, show_shapes=True, show_layer_activations=True, show_layer_names=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "id": "QumZFXdt0L0W"
   },
   "outputs": [],
   "source": [
    "cnn.compile(loss='sparse_categorical_crossentropy',\n",
    "             optimizer='adam',\n",
    "             metrics=['accuracy'])\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "XPtSkHm2dTJ_",
    "outputId": "aab669a0-e6bb-4665-cd9a-f8ce2e596eec"
   },
   "outputs": [],
   "source": [
    "cnn.compile(optimizer=Adam(learning_rate=0.001),\n",
    "            loss=CategoricalCrossentropy(from_logits=True),\n",
    "            metrics=CategoricalAccuracy())\n",
    "\n",
    "reduce_lr = ReduceLROnPlateau(monitor='val_loss', factor=0.2, patience=3, min_lr=0.00001)\n",
    "checkpoint = ModelCheckpoint(filepath='/content/modelCNN.h5', monitor='val_categorical_accuracy', save_best_only=True)\n",
    "history = cnn.fit(x_train, y_train, epochs=10, batch_size=200, validation_data=(x_test, y_test), callbacks=[checkpoint, reduce_lr])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "Frx0P5XGl9ex",
    "outputId": "e4db9493-2a35-4998-9edc-4d9237c48311"
   },
   "outputs": [],
   "source": [
    "# Evaluate the model on test set\n",
    "score = cnn.evaluate(x_test, y_test, verbose=0)\n",
    "# Print test accuracy\n",
    "print('\\n', 'Test accuracy:', score[1])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "t-xECl76mFCp",
    "outputId": "fb5c590a-b578-4cd7-d585-871c001fcd61"
   },
   "outputs": [],
   "source": [
    "y_pred = cnn.predict(x_test)\n",
    "y_pred[10]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "xru7Tc7fmaxE",
    "outputId": "2b5001f6-d823-40bb-98c7-2d679bb19c43"
   },
   "outputs": [],
   "source": [
    "np.argmax(y_pred[10])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "id": "ac9ChxzKoNla"
   },
   "outputs": [],
   "source": [
    "predictions = []\n",
    "for instance in y_pred:\n",
    "    predictions.append(np.argmax(instance))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 687
    },
    "id": "yP7wrcg9oZBZ",
    "outputId": "15dc3ce3-36da-4e24-924f-7a390758716b"
   },
   "outputs": [],
   "source": [
    "plt.figure(figsize=(9, 9))\n",
    "plt.plot(history.history['loss'], color='blue', label='loss');\n",
    "plt.plot(history.history['val_loss'], color='red', label='val_loss');\n",
    "plt.legend();\n",
    "plt.title('Loss vs Validation Loss');\n",
    "plt.tight_layout()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 687
    },
    "id": "nev_C6ujoriT",
    "outputId": "03cb7757-a390-40fc-f8cb-99e99209a685"
   },
   "outputs": [],
   "source": [
    "plt.figure(figsize=(9, 9))\n",
    "plt.plot(history.history['categorical_accuracy'], color='blue', label='accuracy');\n",
    "plt.plot(history.history['val_categorical_accuracy'], color='red', label='val_accuracy');\n",
    "plt.legend();\n",
    "plt.title('Accuracy vs Validation Accuracy');\n",
    "plt.tight_layout()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "fD6XSaK-pP9Y"
   },
   "source": [
    "4. Bulid an Interface app by using gradio"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "id": "e2WFs3QqpqDR"
   },
   "outputs": [],
   "source": [
    "import gradio as gr"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "id": "O0BAm6XtqFJI"
   },
   "outputs": [],
   "source": [
    "loaded_CNN = keras.models.load_model('/content/modelCNN.h5')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 611
    },
    "id": "C0dt-NchpZTR",
    "outputId": "e5ae8672-ad8d-4674-e74a-ce197579fa09"
   },
   "outputs": [],
   "source": [
    "def predict(img):\n",
    "    img_array = np.array(img)\n",
    "    img_array = img_array.reshape(1, 28, 28)\n",
    "    img_array = img_array/255\n",
    "    pred = loaded_CNN.predict(img_array)\n",
    "    print(pred)\n",
    "    return np.argmax(pred)\n",
    "\n",
    "iface = gr.Interface(predict, inputs = 'sketchpad',\n",
    "                     outputs = 'text',\n",
    "                     allow_flagging = 'never',\n",
    "                     description = 'Draw a Digit Below... (Draw in the centre for best results)')\n",
    "iface.launch(share = True, width = 300, height = 500)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "colab": {
   "provenance": []
  },
  "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": "3.10.9"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 1
}