captcha_ocr.ipynb

{
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "fH533tV3tHMV"
      },
      "source": [
        "# OCR model for reading Captchas\n",
        "\n",
        "**Description:** How to implement an OCR model using CNNs, RNNs and CTC loss."
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "trK07FaetHMg"
      },
      "source": [
        "## Introduction\n",
        "\n",
        "This example demonstrates a simple OCR model built with the Functional API. Apart from\n",
        "combining CNN and RNN, it also illustrates how you can instantiate a new layer\n",
        "and use it as an \"Endpoint layer\" for implementing CTC loss. For a detailed\n",
        "guide to layer subclassing, please check out\n",
        "[this page](https://keras.io/guides/making_new_layers_and_models_via_subclassing/)\n",
        "in the developer guides."
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "from google.colab import drive\n",
        "drive.mount('/content/gdrive')"
      ],
      "metadata": {
        "id": "2LNX8Etgu5aW",
        "outputId": "cfad8833-0b01-4428-c0a4-987b08254349",
        "colab": {
          "base_uri": "https://localhost:8080/"
        }
      },
      "execution_count": 2,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Mounted at /content/gdrive\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "0dDXIAr1tHMj"
      },
      "source": [
        "## Setup"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 3,
      "metadata": {
        "id": "lLIHoH51tHMl"
      },
      "outputs": [],
      "source": [
        "import os\n",
        "import numpy as np\n",
        "import matplotlib.pyplot as plt\n",
        "\n",
        "from pathlib import Path\n",
        "from collections import Counter\n",
        "\n",
        "import tensorflow as tf\n",
        "from tensorflow import keras\n",
        "from tensorflow.keras import layers\n"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "%cd /content/gdrive/MyDrive/scout/data/annot_data_captcha/captcha1k/"
      ],
      "metadata": {
        "id": "d4Sat4SnwEEB",
        "outputId": "6cc395f5-8eaf-4fb6-fa1c-f4f73635f580",
        "colab": {
          "base_uri": "https://localhost:8080/"
        }
      },
      "execution_count": 5,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "/content/gdrive/MyDrive/scout/data/annot_data_captcha/captcha1k\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "h7KuDIdEtHMq"
      },
      "source": [
        "## Load the data: [Captcha Images](https://www.kaggle.com/fournierp/captcha-version-2-images)\n",
        "Let's download the data."
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "iFTWrPwztHMt"
      },
      "source": [
        "The dataset contains 1040 captcha files as `png` images. The label for each sample is a string,\n",
        "the name of the file (minus the file extension).\n",
        "We will map each character in the string to an integer for training the model. Similary,\n",
        "we will need to map the predictions of the model back to strings. For this purpose\n",
        "we will maintain two dictionaries, mapping characters to integers, and integers to characters,\n",
        "respectively."
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 7,
      "metadata": {
        "id": "S9tEi7l4tHMu",
        "outputId": "6cc8dabc-8ad5-4a9e-9240-9130fa981d2c",
        "colab": {
          "base_uri": "https://localhost:8080/"
        }
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Number of images found:  1000\n",
            "Number of labels found:  1000\n",
            "Number of unique characters:  34\n",
            "Characters present:  [' ', '0', '2', '3', '4', '6', '7', '8', '9', 'A', 'B', 'C', 'D', 'E', 'F', 'G', 'H', 'I', 'J', 'K', 'L', 'N', 'O', 'P', 'Q', 'R', 'S', 'T', 'U', 'V', 'X', 'Y', 'Z', 'y']\n"
          ]
        }
      ],
      "source": [
        "\n",
        "# Path to the data directory\n",
        "data_dir = Path(\"/content/gdrive/MyDrive/scout/data/annot_data_captcha/captcha1k/\")\n",
        "\n",
        "# Get list of all the images\n",
        "images = sorted(list(map(str, list(data_dir.glob(\"*.jpg\")))))\n",
        "raw_labels = [img.split(os.path.sep)[-1].split(\".jpg\")[0] for img in images]\n",
        "max_length = max([len(label) for label in raw_labels])\n",
        "labels = [label.ljust(max_length) for label in raw_labels]\n",
        "characters = set(char for label in labels for char in label)\n",
        "characters = sorted(list(characters))\n",
        "\n",
        "print(\"Number of images found: \", len(images))\n",
        "print(\"Number of labels found: \", len(labels))\n",
        "print(\"Number of unique characters: \", len(characters))\n",
        "print(\"Characters present: \", characters)\n",
        "\n",
        "# Batch size for training and validation\n",
        "batch_size = 16\n",
        "\n",
        "# Desired image dimensions\n",
        "img_width = 200\n",
        "img_height = 50\n",
        "\n",
        "# Factor by which the image is going to be downsampled\n",
        "# by the convolutional blocks. We will be using two\n",
        "# convolution blocks and each block will have\n",
        "# a pooling layer which downsample the features by a factor of 2.\n",
        "# Hence total downsampling factor would be 4.\n",
        "downsample_factor = 4\n",
        "\n",
        "# Maximum length of any captcha in the dataset\n",
        "max_length = max([len(label) for label in labels])\n"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "GQ7nHLj5tHM1"
      },
      "source": [
        "## Preprocessing"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 8,
      "metadata": {
        "id": "I3BWOVu5tHM2"
      },
      "outputs": [],
      "source": [
        "\n",
        "# Mapping characters to integers\n",
        "char_to_num = layers.StringLookup(\n",
        "    vocabulary=list(characters), mask_token=None\n",
        ")\n",
        "\n",
        "# Mapping integers back to original characters\n",
        "num_to_char = layers.StringLookup(\n",
        "    vocabulary=char_to_num.get_vocabulary(), mask_token=None, invert=True\n",
        ")\n",
        "\n",
        "\n",
        "def split_data(images, labels, train_size=0.9, shuffle=True):\n",
        "    # 1. Get the total size of the dataset\n",
        "    size = len(images)\n",
        "    # 2. Make an indices array and shuffle it, if required\n",
        "    indices = np.arange(size)\n",
        "    if shuffle:\n",
        "        np.random.shuffle(indices)\n",
        "    # 3. Get the size of training samples\n",
        "    train_samples = int(size * train_size)\n",
        "    # 4. Split data into training and validation sets\n",
        "    x_train, y_train = images[indices[:train_samples]], labels[indices[:train_samples]]\n",
        "    x_valid, y_valid = images[indices[train_samples:]], labels[indices[train_samples:]]\n",
        "    return x_train, x_valid, y_train, y_valid\n",
        "\n",
        "\n",
        "# Splitting data into training and validation sets\n",
        "x_train, x_valid, y_train, y_valid = split_data(np.array(images), np.array(labels))\n",
        "\n",
        "\n",
        "def encode_single_sample(img_path, label):\n",
        "    # 1. Read image\n",
        "    img = tf.io.read_file(img_path)\n",
        "    # 2. Decode and convert to grayscale\n",
        "    img = tf.io.decode_png(img, channels=1)\n",
        "    # 3. Convert to float32 in [0, 1] range\n",
        "    img = tf.image.convert_image_dtype(img, tf.float32)\n",
        "    # 4. Resize to the desired size\n",
        "    img = tf.image.resize(img, [img_height, img_width])\n",
        "    # 5. Transpose the image because we want the time\n",
        "    # dimension to correspond to the width of the image.\n",
        "    img = tf.transpose(img, perm=[1, 0, 2])\n",
        "    # 6. Map the characters in label to numbers\n",
        "    label = char_to_num(tf.strings.unicode_split(label, input_encoding=\"UTF-8\"))\n",
        "    # 7. Return a dict as our model is expecting two inputs\n",
        "    return {\"image\": img, \"label\": label}\n"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "N8I08frwtHNT"
      },
      "source": [
        "## Create `Dataset` objects"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 9,
      "metadata": {
        "id": "zWTD9Nw0tHNV"
      },
      "outputs": [],
      "source": [
        "\n",
        "train_dataset = tf.data.Dataset.from_tensor_slices((x_train, y_train))\n",
        "train_dataset = (\n",
        "    train_dataset.map(\n",
        "        encode_single_sample, num_parallel_calls=tf.data.AUTOTUNE\n",
        "    )\n",
        "    .batch(batch_size)\n",
        "    .prefetch(buffer_size=tf.data.AUTOTUNE)\n",
        ")\n",
        "\n",
        "validation_dataset = tf.data.Dataset.from_tensor_slices((x_valid, y_valid))\n",
        "validation_dataset = (\n",
        "    validation_dataset.map(\n",
        "        encode_single_sample, num_parallel_calls=tf.data.AUTOTUNE\n",
        "    )\n",
        "    .batch(batch_size)\n",
        "    .prefetch(buffer_size=tf.data.AUTOTUNE)\n",
        ")"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "4zZNkFs8tHNY"
      },
      "source": [
        "## Visualize the data"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 10,
      "metadata": {
        "id": "_lwntlYotHNY",
        "outputId": "f7a0d215-df8e-4dc5-9f5d-478c6c7d7cd5",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 290
        }
      },
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 720x360 with 16 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {
            "needs_background": "light"
          }
        }
      ],
      "source": [
        "\n",
        "_, ax = plt.subplots(4, 4, figsize=(10, 5))\n",
        "for batch in train_dataset.take(1):\n",
        "    images = batch[\"image\"]\n",
        "    labels = batch[\"label\"]\n",
        "    for i in range(16):\n",
        "        img = (images[i] * 255).numpy().astype(\"uint8\")\n",
        "        label = tf.strings.reduce_join(num_to_char(labels[i])).numpy().decode(\"utf-8\")\n",
        "        ax[i // 4, i % 4].imshow(img[:, :, 0].T, cmap=\"gray\")\n",
        "        ax[i // 4, i % 4].set_title(label)\n",
        "        ax[i // 4, i % 4].axis(\"off\")\n",
        "plt.show()"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "Z4JJhGUbtHNe"
      },
      "source": [
        "## Model"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 11,
      "metadata": {
        "id": "8bJZGgretHNf",
        "outputId": "8866929d-3e8a-4224-faba-29d9316cae98",
        "colab": {
          "base_uri": "https://localhost:8080/"
        }
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Model: \"ocr_model_v1\"\n",
            "__________________________________________________________________________________________________\n",
            " Layer (type)                   Output Shape         Param #     Connected to                     \n",
            "==================================================================================================\n",
            " image (InputLayer)             [(None, 200, 50, 1)  0           []                               \n",
            "                                ]                                                                 \n",
            "                                                                                                  \n",
            " Conv1 (Conv2D)                 (None, 200, 50, 32)  320         ['image[0][0]']                  \n",
            "                                                                                                  \n",
            " pool1 (MaxPooling2D)           (None, 100, 25, 32)  0           ['Conv1[0][0]']                  \n",
            "                                                                                                  \n",
            " Conv2 (Conv2D)                 (None, 100, 25, 64)  18496       ['pool1[0][0]']                  \n",
            "                                                                                                  \n",
            " pool2 (MaxPooling2D)           (None, 50, 12, 64)   0           ['Conv2[0][0]']                  \n",
            "                                                                                                  \n",
            " reshape (Reshape)              (None, 50, 768)      0           ['pool2[0][0]']                  \n",
            "                                                                                                  \n",
            " dense1 (Dense)                 (None, 50, 64)       49216       ['reshape[0][0]']                \n",
            "                                                                                                  \n",
            " dropout (Dropout)              (None, 50, 64)       0           ['dense1[0][0]']                 \n",
            "                                                                                                  \n",
            " bidirectional (Bidirectional)  (None, 50, 256)      197632      ['dropout[0][0]']                \n",
            "                                                                                                  \n",
            " bidirectional_1 (Bidirectional  (None, 50, 128)     164352      ['bidirectional[0][0]']          \n",
            " )                                                                                                \n",
            "                                                                                                  \n",
            " label (InputLayer)             [(None, None)]       0           []                               \n",
            "                                                                                                  \n",
            " dense2 (Dense)                 (None, 50, 36)       4644        ['bidirectional_1[0][0]']        \n",
            "                                                                                                  \n",
            " ctc_loss (CTCLayer)            (None, 50, 36)       0           ['label[0][0]',                  \n",
            "                                                                  'dense2[0][0]']                 \n",
            "                                                                                                  \n",
            "==================================================================================================\n",
            "Total params: 434,660\n",
            "Trainable params: 434,660\n",
            "Non-trainable params: 0\n",
            "__________________________________________________________________________________________________\n"
          ]
        }
      ],
      "source": [
        "\n",
        "class CTCLayer(layers.Layer):\n",
        "    def __init__(self, name=None):\n",
        "        super().__init__(name=name)\n",
        "        self.loss_fn = keras.backend.ctc_batch_cost\n",
        "\n",
        "    def call(self, y_true, y_pred):\n",
        "        # Compute the training-time loss value and add it\n",
        "        # to the layer using `self.add_loss()`.\n",
        "        batch_len = tf.cast(tf.shape(y_true)[0], dtype=\"int64\")\n",
        "        input_length = tf.cast(tf.shape(y_pred)[1], dtype=\"int64\")\n",
        "        label_length = tf.cast(tf.shape(y_true)[1], dtype=\"int64\")\n",
        "\n",
        "        input_length = input_length * tf.ones(shape=(batch_len, 1), dtype=\"int64\")\n",
        "        label_length = label_length * tf.ones(shape=(batch_len, 1), dtype=\"int64\")\n",
        "\n",
        "        loss = self.loss_fn(y_true, y_pred, input_length, label_length)\n",
        "        self.add_loss(loss)\n",
        "\n",
        "        # At test time, just return the computed predictions\n",
        "        return y_pred\n",
        "\n",
        "\n",
        "def build_model():\n",
        "    # Inputs to the model\n",
        "    input_img = layers.Input(\n",
        "        shape=(img_width, img_height, 1), name=\"image\", dtype=\"float32\"\n",
        "    )\n",
        "    labels = layers.Input(name=\"label\", shape=(None,), dtype=\"float32\")\n",
        "\n",
        "    # First conv block\n",
        "    x = layers.Conv2D(\n",
        "        32,\n",
        "        (3, 3),\n",
        "        activation=\"relu\",\n",
        "        kernel_initializer=\"he_normal\",\n",
        "        padding=\"same\",\n",
        "        name=\"Conv1\",\n",
        "    )(input_img)\n",
        "    x = layers.MaxPooling2D((2, 2), name=\"pool1\")(x)\n",
        "\n",
        "    # Second conv block\n",
        "    x = layers.Conv2D(\n",
        "        64,\n",
        "        (3, 3),\n",
        "        activation=\"relu\",\n",
        "        kernel_initializer=\"he_normal\",\n",
        "        padding=\"same\",\n",
        "        name=\"Conv2\",\n",
        "    )(x)\n",
        "    x = layers.MaxPooling2D((2, 2), name=\"pool2\")(x)\n",
        "\n",
        "    # We have used two max pool with pool size and strides 2.\n",
        "    # Hence, downsampled feature maps are 4x smaller. The number of\n",
        "    # filters in the last layer is 64. Reshape accordingly before\n",
        "    # passing the output to the RNN part of the model\n",
        "    new_shape = ((img_width // 4), (img_height // 4) * 64)\n",
        "    x = layers.Reshape(target_shape=new_shape, name=\"reshape\")(x)\n",
        "    x = layers.Dense(64, activation=\"relu\", name=\"dense1\")(x)\n",
        "    x = layers.Dropout(0.2)(x)\n",
        "\n",
        "    # RNNs\n",
        "    x = layers.Bidirectional(layers.LSTM(128, return_sequences=True, dropout=0.25))(x)\n",
        "    x = layers.Bidirectional(layers.LSTM(64, return_sequences=True, dropout=0.25))(x)\n",
        "\n",
        "    # Output layer\n",
        "    x = layers.Dense(\n",
        "        len(char_to_num.get_vocabulary()) + 1, activation=\"softmax\", name=\"dense2\"\n",
        "    )(x)\n",
        "\n",
        "    # Add CTC layer for calculating CTC loss at each step\n",
        "    output = CTCLayer(name=\"ctc_loss\")(labels, x)\n",
        "\n",
        "    # Define the model\n",
        "    model = keras.models.Model(\n",
        "        inputs=[input_img, labels], outputs=output, name=\"ocr_model_v1\"\n",
        "    )\n",
        "    # Optimizer\n",
        "    opt = keras.optimizers.Adam()\n",
        "    # Compile the model and return\n",
        "    model.compile(optimizer=opt)\n",
        "    return model\n",
        "\n",
        "\n",
        "# Get the model\n",
        "model = build_model()\n",
        "model.summary()"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "5M3EV_UptHNn"
      },
      "source": [
        "## Training"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "llodp_bvtHNs",
        "outputId": "14204604-3b5c-463c-a4fd-1350548133de",
        "colab": {
          "base_uri": "https://localhost:8080/"
        }
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Epoch 1/100\n",
            "57/57 [==============================] - 23s 94ms/step - loss: 23.8887 - val_loss: 18.5818\n",
            "Epoch 2/100\n",
            "57/57 [==============================] - 3s 46ms/step - loss: 18.4617 - val_loss: 18.4655\n",
            "Epoch 3/100\n",
            "57/57 [==============================] - 2s 43ms/step - loss: 18.3976 - val_loss: 18.4421\n",
            "Epoch 4/100\n",
            "57/57 [==============================] - 3s 54ms/step - loss: 18.3804 - val_loss: 18.4354\n",
            "Epoch 5/100\n",
            "57/57 [==============================] - 3s 60ms/step - loss: 18.3723 - val_loss: 18.4329\n",
            "Epoch 6/100\n",
            "57/57 [==============================] - 3s 44ms/step - loss: 18.3616 - val_loss: 18.4232\n",
            "Epoch 7/100\n",
            "57/57 [==============================] - 3s 45ms/step - loss: 18.3539 - val_loss: 18.4127\n",
            "Epoch 8/100\n",
            "57/57 [==============================] - 3s 61ms/step - loss: 18.3438 - val_loss: 18.4111\n",
            "Epoch 9/100\n",
            "57/57 [==============================] - 3s 53ms/step - loss: 18.3363 - val_loss: 18.4045\n",
            "Epoch 10/100\n",
            "57/57 [==============================] - 2s 43ms/step - loss: 18.3328 - val_loss: 18.4006\n",
            "Epoch 11/100\n",
            "57/57 [==============================] - 3s 45ms/step - loss: 18.3176 - val_loss: 18.3892\n",
            "Epoch 12/100\n",
            "57/57 [==============================] - 2s 43ms/step - loss: 18.3139 - val_loss: 18.3730\n",
            "Epoch 13/100\n",
            "57/57 [==============================] - 4s 74ms/step - loss: 18.2928 - val_loss: 18.3546\n",
            "Epoch 14/100\n",
            "57/57 [==============================] - 3s 45ms/step - loss: 18.2718 - val_loss: 18.3168\n",
            "Epoch 15/100\n",
            "57/57 [==============================] - 3s 45ms/step - loss: 18.2459 - val_loss: 18.2959\n",
            "Epoch 16/100\n",
            "57/57 [==============================] - 3s 54ms/step - loss: 18.2103 - val_loss: 18.2458\n",
            "Epoch 17/100\n",
            "57/57 [==============================] - 3s 44ms/step - loss: 18.1615 - val_loss: 18.2117\n",
            "Epoch 18/100\n",
            "57/57 [==============================] - 3s 44ms/step - loss: 18.0661 - val_loss: 17.9901\n",
            "Epoch 19/100\n",
            "57/57 [==============================] - 3s 44ms/step - loss: 17.9503 - val_loss: 18.1076\n",
            "Epoch 20/100\n",
            "57/57 [==============================] - 4s 66ms/step - loss: 17.8549 - val_loss: 17.8319\n",
            "Epoch 21/100\n",
            "57/57 [==============================] - 3s 48ms/step - loss: 17.8194 - val_loss: 17.8077\n",
            "Epoch 22/100\n",
            "57/57 [==============================] - 3s 45ms/step - loss: 17.7905 - val_loss: 17.8646\n",
            "Epoch 23/100\n",
            "57/57 [==============================] - 2s 43ms/step - loss: 17.7334 - val_loss: 17.7883\n",
            "Epoch 24/100\n",
            "57/57 [==============================] - 3s 46ms/step - loss: 17.7095 - val_loss: 17.7707\n",
            "Epoch 25/100\n",
            "57/57 [==============================] - 3s 46ms/step - loss: 17.6658 - val_loss: 17.7362\n",
            "Epoch 26/100\n",
            "57/57 [==============================] - 3s 45ms/step - loss: 17.5970 - val_loss: 17.6779\n",
            "Epoch 27/100\n",
            "57/57 [==============================] - 3s 51ms/step - loss: 17.4941 - val_loss: 17.6494\n",
            "Epoch 28/100\n",
            "57/57 [==============================] - 3s 45ms/step - loss: 17.3221 - val_loss: 17.5375\n",
            "Epoch 29/100\n",
            "57/57 [==============================] - 3s 45ms/step - loss: 17.1715 - val_loss: 17.2054\n",
            "Epoch 30/100\n",
            "57/57 [==============================] - 3s 59ms/step - loss: 17.0012 - val_loss: 17.1297\n",
            "Epoch 31/100\n",
            "57/57 [==============================] - 3s 45ms/step - loss: 16.7818 - val_loss: 17.0806\n",
            "Epoch 32/100\n",
            "57/57 [==============================] - 3s 50ms/step - loss: 16.4841 - val_loss: 16.9098\n",
            "Epoch 33/100\n",
            "57/57 [==============================] - 3s 45ms/step - loss: 16.1555 - val_loss: 16.6677\n",
            "Epoch 34/100\n",
            "57/57 [==============================] - 2s 43ms/step - loss: 15.8921 - val_loss: 16.5976\n",
            "Epoch 35/100\n",
            "57/57 [==============================] - 3s 44ms/step - loss: 15.6114 - val_loss: 16.2752\n",
            "Epoch 36/100\n",
            "57/57 [==============================] - 3s 59ms/step - loss: 15.2624 - val_loss: 16.5022\n",
            "Epoch 37/100\n",
            "57/57 [==============================] - 3s 44ms/step - loss: 14.9906 - val_loss: 15.9709\n",
            "Epoch 38/100\n",
            "57/57 [==============================] - 3s 46ms/step - loss: 14.5527 - val_loss: 15.8595\n",
            "Epoch 39/100\n",
            "57/57 [==============================] - 3s 46ms/step - loss: 14.2023 - val_loss: 15.6123\n",
            "Epoch 40/100\n",
            "57/57 [==============================] - 4s 66ms/step - loss: 13.8088 - val_loss: 15.3432\n",
            "Epoch 41/100\n",
            "57/57 [==============================] - 3s 46ms/step - loss: 13.4737 - val_loss: 15.3739\n",
            "Epoch 42/100\n",
            "57/57 [==============================] - 3s 45ms/step - loss: 13.1307 - val_loss: 14.9975\n",
            "Epoch 43/100\n",
            "57/57 [==============================] - 3s 46ms/step - loss: 12.7504 - val_loss: 14.9932\n",
            "Epoch 44/100\n",
            "57/57 [==============================] - 3s 54ms/step - loss: 12.3143 - val_loss: 14.5780\n",
            "Epoch 45/100\n",
            "57/57 [==============================] - 3s 44ms/step - loss: 12.0598 - val_loss: 14.7540\n",
            "Epoch 46/100\n",
            "57/57 [==============================] - 3s 48ms/step - loss: 11.5946 - val_loss: 14.9136\n",
            "Epoch 47/100\n",
            "57/57 [==============================] - 3s 45ms/step - loss: 11.2357 - val_loss: 14.8545\n",
            "Epoch 48/100\n",
            "57/57 [==============================] - 3s 45ms/step - loss: 10.9544 - val_loss: 14.3574\n",
            "Epoch 49/100\n",
            "57/57 [==============================] - 3s 46ms/step - loss: 10.6470 - val_loss: 14.5823\n",
            "Epoch 50/100\n",
            "57/57 [==============================] - 3s 48ms/step - loss: 10.2452 - val_loss: 14.9236\n",
            "Epoch 51/100\n",
            "57/57 [==============================] - 3s 45ms/step - loss: 9.9761 - val_loss: 14.5208\n",
            "Epoch 52/100\n",
            "57/57 [==============================] - 2s 43ms/step - loss: 9.6550 - val_loss: 14.3077\n",
            "Epoch 53/100\n",
            "57/57 [==============================] - 3s 52ms/step - loss: 9.2794 - val_loss: 13.9284\n",
            "Epoch 54/100\n",
            "57/57 [==============================] - 3s 44ms/step - loss: 9.0882 - val_loss: 13.7545\n",
            "Epoch 55/100\n",
            "57/57 [==============================] - 3s 46ms/step - loss: 8.6705 - val_loss: 14.2325\n",
            "Epoch 56/100\n",
            "57/57 [==============================] - 3s 54ms/step - loss: 8.3103 - val_loss: 13.8687\n",
            "Epoch 57/100\n",
            "57/57 [==============================] - 3s 58ms/step - loss: 8.1518 - val_loss: 13.8458\n",
            "Epoch 58/100\n",
            "31/57 [===============>..............] - ETA: 1s - loss: 7.9794"
          ]
        }
      ],
      "source": [
        "epochs = 100\n",
        "early_stopping_patience = 100\n",
        "# Add early stopping\n",
        "early_stopping = keras.callbacks.EarlyStopping(\n",
        "    monitor=\"val_loss\", patience=early_stopping_patience, restore_best_weights=True\n",
        ")\n",
        "\n",
        "# Train the model\n",
        "history = model.fit(\n",
        "    train_dataset,\n",
        "    validation_data=validation_dataset,\n",
        "    epochs=epochs,\n",
        "    callbacks=[early_stopping],\n",
        ")\n"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "YPVgn0VitHNv"
      },
      "source": [
        "## Inference\n",
        "\n",
        "You can use the trained model hosted on [Hugging Face Hub](https://huggingface.co./keras-io/ocr-for-captcha) \n",
        "and try the demo on [Hugging Face Spaces](https://huggingface.co./spaces/keras-io/ocr-for-captcha)."
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "y3X6o8gutHNw"
      },
      "outputs": [],
      "source": [
        "\n",
        "# Get the prediction model by extracting layers till the output layer\n",
        "prediction_model = keras.models.Model(\n",
        "    model.get_layer(name=\"image\").input, model.get_layer(name=\"dense2\").output\n",
        ")\n",
        "prediction_model.summary()\n",
        "\n",
        "# A utility function to decode the output of the network\n",
        "def decode_batch_predictions(pred):\n",
        "    input_len = np.ones(pred.shape[0]) * pred.shape[1]\n",
        "    # Use greedy search. For complex tasks, you can use beam search\n",
        "    results = keras.backend.ctc_decode(pred, input_length=input_len, greedy=True)[0][0][\n",
        "        :, :max_length\n",
        "    ]\n",
        "    # Iterate over the results and get back the text\n",
        "    output_text = []\n",
        "    for res in results:\n",
        "        res = tf.strings.reduce_join(num_to_char(res)).numpy().decode(\"utf-8\")\n",
        "        output_text.append(res)\n",
        "    return output_text\n",
        "\n",
        "\n",
        "#  Let's check results on some validation samples\n",
        "for batch in validation_dataset.take(1):\n",
        "    batch_images = batch[\"image\"]\n",
        "    batch_labels = batch[\"label\"]\n",
        "\n",
        "    preds = prediction_model.predict(batch_images)\n",
        "    pred_texts = decode_batch_predictions(preds)\n",
        "\n",
        "    orig_texts = []\n",
        "    for label in batch_labels:\n",
        "        label = tf.strings.reduce_join(num_to_char(label)).numpy().decode(\"utf-8\")\n",
        "        orig_texts.append(label)\n",
        "\n",
        "    _, ax = plt.subplots(4, 4, figsize=(15, 5))\n",
        "    for i in range(len(pred_texts)):\n",
        "        img = (batch_images[i, :, :, 0] * 255).numpy().astype(np.uint8)\n",
        "        img = img.T\n",
        "        title = f\"Prediction: {pred_texts[i]}\"\n",
        "        ax[i // 4, i % 4].imshow(img, cmap=\"gray\")\n",
        "        ax[i // 4, i % 4].set_title(title)\n",
        "        ax[i // 4, i % 4].axis(\"off\")\n",
        "plt.show()"
      ]
    }
  ],
  "metadata": {
    "accelerator": "GPU",
    "colab": {
      "name": "captcha_ocr",
      "provenance": []
    },
    "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"
    }
  },
  "nbformat": 4,
  "nbformat_minor": 0
}