{
  "cells": [
    {
      "cell_type": "markdown",
      "source": [
        "**ลบโฟร์เดอร์**  captcha_images_v2\n",
        "\n",
        "import shutil\n",
        "shutil.rmtree('captcha_images_v2', ignore_errors=True)"
      ],
      "metadata": {
        "id": "D9k9kq463Sjy"
      }
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "L6eccG8A8zK3"
      },
      "source": [
        "## Setup"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "aIApiDPo8zK4"
      },
      "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": "markdown",
      "metadata": {
        "id": "6ZcX-zkj8zK5"
      },
      "source": [
        "## Load the data: [Captcha Images](https://www.kaggle.com/fournierp/captcha-version-2-images)\n",
        "Let's download the data."
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "BLeKsNE58zK5"
      },
      "outputs": [],
      "source": [
        "# !curl -LO https://raw.githubusercontent.com/StrongTS/cap/main/cap_img_v2.zip\n",
        "!unzip -qq cap_img_v2.zip"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "_VKL_mAU8zK5"
      },
      "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": null,
      "metadata": {
        "id": "32cmkRV28zK7",
        "outputId": "3e6ba734-de84-45db-828c-2c1e2862d436",
        "colab": {
          "base_uri": "https://localhost:8080/"
        }
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Number of images found:  1368\n",
            "Number of labels found:  1368\n",
            "Number of unique characters:  24\n",
            "Characters present:  {'3', 'm', '8', 'n', 'x', '5', '7', 'k', ' ', 'r', 'g', 'h', 'w', 't', 'l', 'c', 'e', 'y', 'Z', '2', 'p', '4', 'f', 'd'}\n"
          ]
        }
      ],
      "source": [
        "\n",
        "# Path to the data directory\n",
        "data_dir = Path(\"./cap_img_v2/\")\n",
        "\n",
        "# Get list of all the images\n",
        "# images = sorted(list(map(str, list(data_dir.glob(\"*.png\")))))\n",
        "# labels = [img.split(os.path.sep)[-1].split(\".png\")[0] for img in images]\n",
        "# characters = set(char for label in labels for char in label)\n",
        "# characters = sorted(list(characters))\n",
        "\n",
        "images = sorted(list(map(str, list(data_dir.glob(\"*.png\")))))\n",
        "raw_labels = [img.split(os.path.sep)[-1].split(\".png\")[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",
        "\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 = 150\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": "hoW6pEAc8zK8"
      },
      "source": [
        "## Preprocessing"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "uYBq0b8n8zK8"
      },
      "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": "pu3_semb8zK9"
      },
      "source": [
        "## Create `Dataset` objects"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "XOOfg8i98zK9"
      },
      "outputs": [],
      "source": [
        "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": "AuBh94Jn8zK9"
      },
      "source": [
        "## Visualize the data"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "-F47QdsY8zK-",
        "outputId": "94218e85-9d9d-4ec2-e9a2-09c409d2a426",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 300
        }
      },
      "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": "L5aW-Wfh8zK-"
      },
      "source": [
        "## Model"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "Nc93xcfm8zK-",
        "outputId": "eed54a04-f0d4-4a3b-a8ca-74b0c5fdefef",
        "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, 150, 50, 1)  0           []                               \n",
            "                                ]                                                                 \n",
            "                                                                                                  \n",
            " Conv1 (Conv2D)                 (None, 150, 50, 32)  320         ['image[0][0]']                  \n",
            "                                                                                                  \n",
            " pool1 (MaxPooling2D)           (None, 75, 25, 32)   0           ['Conv1[0][0]']                  \n",
            "                                                                                                  \n",
            " Conv2 (Conv2D)                 (None, 75, 25, 64)   18496       ['pool1[0][0]']                  \n",
            "                                                                                                  \n",
            " pool2 (MaxPooling2D)           (None, 37, 12, 64)   0           ['Conv2[0][0]']                  \n",
            "                                                                                                  \n",
            " reshape (Reshape)              (None, 37, 768)      0           ['pool2[0][0]']                  \n",
            "                                                                                                  \n",
            " dense1 (Dense)                 (None, 37, 64)       49216       ['reshape[0][0]']                \n",
            "                                                                                                  \n",
            " dropout_2 (Dropout)            (None, 37, 64)       0           ['dense1[0][0]']                 \n",
            "                                                                                                  \n",
            " bidirectional_4 (Bidirectional  (None, 37, 256)     197632      ['dropout_2[0][0]']              \n",
            " )                                                                                                \n",
            "                                                                                                  \n",
            " bidirectional_5 (Bidirectional  (None, 37, 128)     164352      ['bidirectional_4[0][0]']        \n",
            " )                                                                                                \n",
            "                                                                                                  \n",
            " label (InputLayer)             [(None, None)]       0           []                               \n",
            "                                                                                                  \n",
            " dense2 (Dense)                 (None, 37, 26)       3354        ['bidirectional_5[0][0]']        \n",
            "                                                                                                  \n",
            " ctc_loss (CTCLayer)            (None, 37, 26)       0           ['label[0][0]',                  \n",
            "                                                                  'dense2[0][0]']                 \n",
            "                                                                                                  \n",
            "==================================================================================================\n",
            "Total params: 433,370\n",
            "Trainable params: 433,370\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": "uoQSGnA08zK-"
      },
      "source": [
        "## Training"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "Uk1w9NCX8zK_",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "136dcbc7-68c2-467e-f5e5-babe92682390"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Epoch 1/100\n",
            "77/77 [==============================] - 13s 83ms/step - loss: 22.4398 - val_loss: 19.8444\n",
            "Epoch 2/100\n",
            "77/77 [==============================] - 4s 56ms/step - loss: 19.8235 - val_loss: 19.7843\n",
            "Epoch 3/100\n",
            "77/77 [==============================] - 4s 57ms/step - loss: 19.7954 - val_loss: 19.7747\n",
            "Epoch 4/100\n",
            "77/77 [==============================] - 4s 53ms/step - loss: 19.7823 - val_loss: 19.7599\n",
            "Epoch 5/100\n",
            "77/77 [==============================] - 5s 68ms/step - loss: 19.7713 - val_loss: 19.7457\n",
            "Epoch 6/100\n",
            "77/77 [==============================] - 5s 53ms/step - loss: 19.7586 - val_loss: 19.7244\n",
            "Epoch 7/100\n",
            "77/77 [==============================] - 5s 62ms/step - loss: 19.6045 - val_loss: 19.2316\n",
            "Epoch 8/100\n",
            "77/77 [==============================] - 4s 53ms/step - loss: 18.2916 - val_loss: 16.3623\n",
            "Epoch 9/100\n",
            "77/77 [==============================] - 3s 41ms/step - loss: 14.5120 - val_loss: 10.8413\n",
            "Epoch 10/100\n",
            "77/77 [==============================] - 3s 41ms/step - loss: 8.8095 - val_loss: 5.2080\n",
            "Epoch 11/100\n",
            "77/77 [==============================] - 5s 62ms/step - loss: 4.3529 - val_loss: 2.2762\n",
            "Epoch 12/100\n",
            "77/77 [==============================] - 4s 55ms/step - loss: 2.0754 - val_loss: 0.9562\n",
            "Epoch 13/100\n",
            "77/77 [==============================] - 5s 64ms/step - loss: 1.2469 - val_loss: 0.6430\n",
            "Epoch 14/100\n",
            "77/77 [==============================] - 5s 56ms/step - loss: 0.8102 - val_loss: 0.3413\n",
            "Epoch 15/100\n",
            "77/77 [==============================] - 4s 54ms/step - loss: 0.6030 - val_loss: 0.3423\n",
            "Epoch 16/100\n",
            "77/77 [==============================] - 4s 50ms/step - loss: 0.4247 - val_loss: 0.1847\n",
            "Epoch 17/100\n",
            "77/77 [==============================] - 4s 55ms/step - loss: 0.3745 - val_loss: 0.1504\n",
            "Epoch 18/100\n",
            "77/77 [==============================] - 5s 68ms/step - loss: 0.2743 - val_loss: 0.1252\n",
            "Epoch 19/100\n",
            "77/77 [==============================] - 4s 47ms/step - loss: 0.2926 - val_loss: 0.0905\n",
            "Epoch 20/100\n",
            "77/77 [==============================] - 4s 49ms/step - loss: 0.2627 - val_loss: 0.0696\n",
            "Epoch 21/100\n",
            "77/77 [==============================] - 4s 54ms/step - loss: 0.2350 - val_loss: 0.0648\n",
            "Epoch 22/100\n",
            "77/77 [==============================] - 3s 43ms/step - loss: 0.2030 - val_loss: 0.0353\n",
            "Epoch 23/100\n",
            "77/77 [==============================] - 3s 42ms/step - loss: 0.2077 - val_loss: 0.0518\n",
            "Epoch 24/100\n",
            "77/77 [==============================] - 5s 66ms/step - loss: 0.1753 - val_loss: 0.0228\n",
            "Epoch 25/100\n",
            "77/77 [==============================] - 4s 55ms/step - loss: 0.1457 - val_loss: 0.0594\n",
            "Epoch 26/100\n",
            "77/77 [==============================] - 4s 54ms/step - loss: 0.1573 - val_loss: 0.0500\n",
            "Epoch 27/100\n",
            "77/77 [==============================] - 4s 55ms/step - loss: 0.1471 - val_loss: 0.0648\n",
            "Epoch 28/100\n",
            "77/77 [==============================] - 4s 47ms/step - loss: 0.1534 - val_loss: 0.0197\n",
            "Epoch 29/100\n",
            "77/77 [==============================] - 3s 42ms/step - loss: 0.1362 - val_loss: 0.0144\n",
            "Epoch 30/100\n",
            "77/77 [==============================] - 4s 55ms/step - loss: 0.1288 - val_loss: 0.0425\n",
            "Epoch 31/100\n",
            "77/77 [==============================] - 4s 53ms/step - loss: 0.0989 - val_loss: 0.0600\n",
            "Epoch 32/100\n",
            "77/77 [==============================] - 5s 59ms/step - loss: 0.1414 - val_loss: 0.0155\n",
            "Epoch 33/100\n",
            "77/77 [==============================] - 5s 60ms/step - loss: 0.1593 - val_loss: 0.0702\n",
            "Epoch 34/100\n",
            "77/77 [==============================] - 4s 56ms/step - loss: 0.1368 - val_loss: 0.0315\n",
            "Epoch 35/100\n",
            "77/77 [==============================] - 5s 69ms/step - loss: 0.1042 - val_loss: 0.0202\n",
            "Epoch 36/100\n",
            "77/77 [==============================] - 5s 58ms/step - loss: 0.0772 - val_loss: 0.0079\n",
            "Epoch 37/100\n",
            "77/77 [==============================] - 5s 62ms/step - loss: 0.0879 - val_loss: 0.0306\n",
            "Epoch 38/100\n",
            "77/77 [==============================] - 5s 59ms/step - loss: 0.1530 - val_loss: 0.0269\n",
            "Epoch 39/100\n",
            "77/77 [==============================] - 4s 56ms/step - loss: 0.1150 - val_loss: 0.0071\n",
            "Epoch 40/100\n",
            "77/77 [==============================] - 5s 60ms/step - loss: 0.0710 - val_loss: 0.0147\n",
            "Epoch 41/100\n",
            "77/77 [==============================] - 4s 48ms/step - loss: 0.0849 - val_loss: 0.0196\n",
            "Epoch 42/100\n",
            "77/77 [==============================] - 4s 56ms/step - loss: 0.0635 - val_loss: 0.0081\n",
            "Epoch 43/100\n",
            "77/77 [==============================] - 4s 52ms/step - loss: 0.0565 - val_loss: 0.0269\n",
            "Epoch 44/100\n",
            "77/77 [==============================] - 5s 50ms/step - loss: 0.0946 - val_loss: 0.0135\n",
            "Epoch 45/100\n",
            "77/77 [==============================] - 4s 53ms/step - loss: 0.0825 - val_loss: 0.0042\n",
            "Epoch 46/100\n",
            "77/77 [==============================] - 5s 68ms/step - loss: 0.0910 - val_loss: 0.0087\n",
            "Epoch 47/100\n",
            "77/77 [==============================] - 5s 58ms/step - loss: 0.0698 - val_loss: 0.0114\n",
            "Epoch 48/100\n",
            "77/77 [==============================] - 4s 55ms/step - loss: 0.0806 - val_loss: 0.0049\n",
            "Epoch 49/100\n",
            "77/77 [==============================] - 4s 50ms/step - loss: 0.0513 - val_loss: 0.0695\n",
            "Epoch 50/100\n",
            "77/77 [==============================] - 4s 48ms/step - loss: 0.1034 - val_loss: 0.0069\n",
            "Epoch 51/100\n",
            "77/77 [==============================] - 3s 41ms/step - loss: 0.0705 - val_loss: 0.0131\n",
            "Epoch 52/100\n",
            "77/77 [==============================] - 4s 47ms/step - loss: 0.0675 - val_loss: 0.0064\n",
            "Epoch 53/100\n",
            "77/77 [==============================] - 4s 59ms/step - loss: 0.0377 - val_loss: 0.0041\n",
            "Epoch 54/100\n",
            "77/77 [==============================] - 4s 51ms/step - loss: 0.0676 - val_loss: 0.0968\n",
            "Epoch 55/100\n",
            "77/77 [==============================] - 5s 69ms/step - loss: 0.0809 - val_loss: 0.0060\n",
            "Epoch 56/100\n",
            "77/77 [==============================] - 4s 42ms/step - loss: 0.0461 - val_loss: 0.0034\n",
            "Epoch 57/100\n",
            "77/77 [==============================] - 4s 48ms/step - loss: 0.0434 - val_loss: 0.0040\n",
            "Epoch 58/100\n",
            "77/77 [==============================] - 4s 49ms/step - loss: 0.0417 - val_loss: 0.0060\n",
            "Epoch 59/100\n",
            "77/77 [==============================] - 5s 67ms/step - loss: 0.0380 - val_loss: 0.0035\n",
            "Epoch 60/100\n",
            "77/77 [==============================] - 4s 48ms/step - loss: 0.0281 - val_loss: 0.0065\n",
            "Epoch 61/100\n",
            "77/77 [==============================] - 4s 54ms/step - loss: 0.0189 - val_loss: 0.0043\n",
            "Epoch 62/100\n",
            "77/77 [==============================] - 4s 55ms/step - loss: 0.0177 - val_loss: 0.0055\n",
            "Epoch 63/100\n",
            "77/77 [==============================] - 5s 56ms/step - loss: 0.0155 - val_loss: 0.0036\n",
            "Epoch 64/100\n",
            "77/77 [==============================] - 4s 53ms/step - loss: 0.0301 - val_loss: 0.0080\n",
            "Epoch 65/100\n",
            "77/77 [==============================] - 5s 64ms/step - loss: 0.0252 - val_loss: 0.0101\n",
            "Epoch 66/100\n",
            "77/77 [==============================] - 5s 63ms/step - loss: 0.0506 - val_loss: 0.0062\n",
            "Epoch 67/100\n",
            "77/77 [==============================] - 4s 46ms/step - loss: 0.0619 - val_loss: 0.0060\n",
            "Epoch 68/100\n",
            "77/77 [==============================] - 4s 53ms/step - loss: 0.0634 - val_loss: 0.0048\n",
            "Epoch 69/100\n",
            "77/77 [==============================] - 3s 41ms/step - loss: 0.0404 - val_loss: 0.0038\n",
            "Epoch 70/100\n",
            "77/77 [==============================] - 5s 67ms/step - loss: 0.0466 - val_loss: 0.0041\n",
            "Epoch 71/100\n",
            "77/77 [==============================] - 4s 53ms/step - loss: 0.0448 - val_loss: 0.0102\n",
            "Epoch 72/100\n",
            "77/77 [==============================] - 4s 48ms/step - loss: 0.0541 - val_loss: 0.0049\n",
            "Epoch 73/100\n",
            "77/77 [==============================] - 5s 60ms/step - loss: 0.0287 - val_loss: 0.0056\n",
            "Epoch 74/100\n",
            "77/77 [==============================] - 5s 70ms/step - loss: 0.0193 - val_loss: 0.0038\n",
            "Epoch 75/100\n",
            "77/77 [==============================] - 4s 47ms/step - loss: 0.0890 - val_loss: 0.0067\n",
            "Epoch 76/100\n",
            "77/77 [==============================] - 5s 60ms/step - loss: 0.0646 - val_loss: 0.0019\n",
            "Epoch 77/100\n",
            "77/77 [==============================] - 4s 49ms/step - loss: 0.0147 - val_loss: 0.0022\n",
            "Epoch 78/100\n",
            "77/77 [==============================] - 5s 60ms/step - loss: 0.0452 - val_loss: 0.0094\n",
            "Epoch 79/100\n",
            "77/77 [==============================] - 5s 58ms/step - loss: 0.0404 - val_loss: 0.0824\n",
            "Epoch 80/100\n",
            "77/77 [==============================] - 4s 59ms/step - loss: 0.0552 - val_loss: 0.0065\n",
            "Epoch 81/100\n",
            "77/77 [==============================] - 3s 42ms/step - loss: 0.0205 - val_loss: 0.0099\n",
            "Epoch 82/100\n",
            "77/77 [==============================] - 5s 60ms/step - loss: 0.0233 - val_loss: 0.0019\n",
            "Epoch 83/100\n",
            "77/77 [==============================] - 4s 51ms/step - loss: 0.0078 - val_loss: 0.0028\n",
            "Epoch 84/100\n",
            "77/77 [==============================] - 4s 55ms/step - loss: 0.0065 - val_loss: 0.0025\n",
            "Epoch 85/100\n",
            "77/77 [==============================] - 5s 66ms/step - loss: 0.0096 - val_loss: 0.0018\n",
            "Epoch 86/100\n",
            "77/77 [==============================] - 5s 58ms/step - loss: 0.0101 - val_loss: 0.0024\n",
            "Epoch 87/100\n",
            "77/77 [==============================] - 4s 56ms/step - loss: 0.0098 - val_loss: 0.0068\n",
            "Epoch 88/100\n",
            "77/77 [==============================] - 4s 48ms/step - loss: 0.0364 - val_loss: 0.0057\n",
            "Epoch 89/100\n",
            "77/77 [==============================] - 4s 53ms/step - loss: 0.0140 - val_loss: 0.0015\n",
            "Epoch 90/100\n",
            "77/77 [==============================] - 4s 50ms/step - loss: 0.0363 - val_loss: 0.0034\n",
            "Epoch 91/100\n",
            "77/77 [==============================] - 4s 49ms/step - loss: 0.0438 - val_loss: 0.0186\n",
            "Epoch 92/100\n",
            "77/77 [==============================] - 4s 53ms/step - loss: 0.0288 - val_loss: 0.0147\n",
            "Epoch 93/100\n",
            "77/77 [==============================] - 5s 65ms/step - loss: 0.0372 - val_loss: 0.0140\n",
            "Epoch 94/100\n",
            "77/77 [==============================] - 5s 67ms/step - loss: 0.0283 - val_loss: 0.0215\n",
            "Epoch 95/100\n",
            "77/77 [==============================] - 5s 63ms/step - loss: 0.0514 - val_loss: 0.1060\n",
            "Epoch 96/100\n",
            "77/77 [==============================] - 5s 65ms/step - loss: 0.0432 - val_loss: 0.0129\n",
            "Epoch 97/100\n",
            "77/77 [==============================] - 6s 84ms/step - loss: 0.0563 - val_loss: 0.0070\n",
            "Epoch 98/100\n",
            "77/77 [==============================] - 4s 56ms/step - loss: 0.0193 - val_loss: 0.0025\n",
            "Epoch 99/100\n",
            "77/77 [==============================] - 5s 66ms/step - loss: 0.0167 - val_loss: 0.0025\n",
            "Epoch 100/100\n",
            "77/77 [==============================] - 5s 68ms/step - loss: 0.0185 - val_loss: 9.2998e-04\n"
          ]
        }
      ],
      "source": [
        "\n",
        "epochs = 100\n",
        "early_stopping_patience = 50\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": "BMulY59Q8zK_"
      },
      "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": "-niQyAlT8zK_",
        "outputId": "31498e7a-4b92-4b4d-a5e1-ca49ec434872",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 943
        }
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Model: \"model_32\"\n",
            "_________________________________________________________________\n",
            " Layer (type)                Output Shape              Param #   \n",
            "=================================================================\n",
            " image (InputLayer)          [(None, 150, 50, 1)]      0         \n",
            "                                                                 \n",
            " Conv1 (Conv2D)              (None, 150, 50, 32)       320       \n",
            "                                                                 \n",
            " pool1 (MaxPooling2D)        (None, 75, 25, 32)        0         \n",
            "                                                                 \n",
            " Conv2 (Conv2D)              (None, 75, 25, 64)        18496     \n",
            "                                                                 \n",
            " pool2 (MaxPooling2D)        (None, 37, 12, 64)        0         \n",
            "                                                                 \n",
            " reshape (Reshape)           (None, 37, 768)           0         \n",
            "                                                                 \n",
            " dense1 (Dense)              (None, 37, 64)            49216     \n",
            "                                                                 \n",
            " dropout_2 (Dropout)         (None, 37, 64)            0         \n",
            "                                                                 \n",
            " bidirectional_4 (Bidirectio  (None, 37, 256)          197632    \n",
            " nal)                                                            \n",
            "                                                                 \n",
            " bidirectional_5 (Bidirectio  (None, 37, 128)          164352    \n",
            " nal)                                                            \n",
            "                                                                 \n",
            " dense2 (Dense)              (None, 37, 26)            3354      \n",
            "                                                                 \n",
            "=================================================================\n",
            "Total params: 433,370\n",
            "Trainable params: 433,370\n",
            "Non-trainable params: 0\n",
            "_________________________________________________________________\n",
            "1/1 [==============================] - 1s 1s/step\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 1080x360 with 16 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {
            "needs_background": "light"
          }
        }
      ],
      "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()"
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "1\n",
        "\n",
        "\n",
        "CTC layer is not used to make predictions, so you can save without the CTC layer like this :-\n",
        "\n",
        "saving_model = keras.models.Model(model.get_layer(name=\"image\").input, model.get_layer(name=\"dense2\").output\n",
        ")\n",
        "saving_model.summary()\n",
        "saving_model.save(\"model_tf\")\n",
        "\n",
        "\n",
        "Other than this you will have to make few changes to make this code work in the variables :-\n",
        "\n",
        "max_length = max([len(label) for label in labels])\n",
        "outfile = open(\"max_length\",'wb')\n",
        "pickle.dump(max_length,outfile)\n",
        "outfile.close()\n",
        "import string\n",
        "chars = string.printable\n",
        "chars = chars[:-5]\n",
        "characters = [c for c in chars]\n",
        "\n",
        "This will give defined set of characters which will help in predictions, therefore in prediction part you have to do :-\n",
        "\n",
        "infile = open(\"max_length\",'rb')\n",
        "max_length = pickle.load(infile)\n",
        "infile.close()\n",
        "\n",
        "import string\n",
        "chars = string.printable\n",
        "chars = chars[:-5]\n",
        "characters = [c for c in chars]\n",
        "\n",
        "# Mapping characters to integers\n",
        "char_to_num = layers.experimental.preprocessing.StringLookup(\n",
        "    vocabulary=characters, mask_token=None\n",
        ")\n",
        "\n",
        "# Mapping integers back to original characters\n",
        "num_to_char = layers.experimental.preprocessing.StringLookup(\n",
        "    vocabulary=char_to_num.get_vocabulary(), mask_token=None, invert=True\n",
        ")\n",
        "prediction_model = tf.keras.models.load_model('model_tf')\n",
        "\n",
        "And then proceed further."
      ],
      "metadata": {
        "id": "U3DLt7E4pm3i"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "saving_model = keras.models.Model(model.get_layer(name=\"image\").input, model.get_layer(name=\"dense2\").output\n",
        ")\n",
        "saving_model.summary()\n",
        "saving_model.save_weights('capModelWeights.h5')\n",
        "print('Model Saved!')"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "lG4XUPZZp4jL",
        "outputId": "670df39b-f587-45cb-cdb3-b64aa898ea79"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Model: \"model_31\"\n",
            "_________________________________________________________________\n",
            " Layer (type)                Output Shape              Param #   \n",
            "=================================================================\n",
            " image (InputLayer)          [(None, 150, 50, 1)]      0         \n",
            "                                                                 \n",
            " Conv1 (Conv2D)              (None, 150, 50, 32)       320       \n",
            "                                                                 \n",
            " pool1 (MaxPooling2D)        (None, 75, 25, 32)        0         \n",
            "                                                                 \n",
            " Conv2 (Conv2D)              (None, 75, 25, 64)        18496     \n",
            "                                                                 \n",
            " pool2 (MaxPooling2D)        (None, 37, 12, 64)        0         \n",
            "                                                                 \n",
            " reshape (Reshape)           (None, 37, 768)           0         \n",
            "                                                                 \n",
            " dense1 (Dense)              (None, 37, 64)            49216     \n",
            "                                                                 \n",
            " dropout_2 (Dropout)         (None, 37, 64)            0         \n",
            "                                                                 \n",
            " bidirectional_4 (Bidirectio  (None, 37, 256)          197632    \n",
            " nal)                                                            \n",
            "                                                                 \n",
            " bidirectional_5 (Bidirectio  (None, 37, 128)          164352    \n",
            " nal)                                                            \n",
            "                                                                 \n",
            " dense2 (Dense)              (None, 37, 26)            3354      \n",
            "                                                                 \n",
            "=================================================================\n",
            "Total params: 433,370\n",
            "Trainable params: 433,370\n",
            "Non-trainable params: 0\n",
            "_________________________________________________________________\n",
            "Model Saved!\n"
          ]
        }
      ]
    }
  ],
  "metadata": {
    "colab": {
      "collapsed_sections": [],
      "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"
    },
    "accelerator": "GPU"
  },
  "nbformat": 4,
  "nbformat_minor": 0
}