diff --git "a/captcha_ocr.ipynb" "b/captcha_ocr.ipynb"
new file mode 100644--- /dev/null
+++ "b/captcha_ocr.ipynb"
@@ -0,0 +1,2564 @@
+{
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "goBlgPnzx3qC"
+      },
+      "source": [
+        "# OCR model for reading Captchas\n",
+        "\n",
+        "**Author:** [A_K_Nain](https://twitter.com/A_K_Nain)<br>\n",
+        "**Date created:** 2020/06/14<br>\n",
+        "**Last modified:** 2020/06/26<br>\n",
+        "**Description:** How to implement an OCR model using CNNs, RNNs and CTC loss."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "bUpqLpAEx3qF"
+      },
+      "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": "markdown",
+      "metadata": {
+        "id": "Ndc7W60Yx3qG"
+      },
+      "source": [
+        "## Setup"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 1,
+      "metadata": {
+        "id": "QUXBK49_x3qG"
+      },
+      "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": "s-MRdopax3qI"
+      },
+      "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": 2,
+      "metadata": {
+        "id": "7a7SWQJKx3qI",
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "outputId": "610a867d-c40f-4580-9668-57e63b28466e"
+      },
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "  % Total    % Received % Xferd  Average Speed   Time    Time     Time  Current\n",
+            "                                 Dload  Upload   Total   Spent    Left  Speed\n",
+            "100   159  100   159    0     0    365      0 --:--:-- --:--:-- --:--:--   364\n",
+            "100 8863k  100 8863k    0     0  9034k      0 --:--:-- --:--:-- --:--:-- 9034k\n"
+          ]
+        }
+      ],
+      "source": [
+        "!curl -LO https://github.com/AakashKumarNain/CaptchaCracker/raw/master/captcha_images_v2.zip\n",
+        "!unzip -qq captcha_images_v2.zip"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "_82uE8adx3qJ"
+      },
+      "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": 3,
+      "metadata": {
+        "id": "ZF8BhVtAx3qJ",
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "outputId": "dcba51f0-b9d3-492f-b838-efc11c854444"
+      },
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "Number of images found:  1040\n",
+            "Number of labels found:  1040\n",
+            "Number of unique characters:  19\n",
+            "Characters present:  {'8', '6', 'm', 'x', 'd', 'y', 'w', '2', '7', 'n', 'g', '5', 'c', 'f', 'p', 'e', '3', '4', 'b'}\n"
+          ]
+        }
+      ],
+      "source": [
+        "\n",
+        "# Path to the data directory\n",
+        "data_dir = Path(\"./captcha_images_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",
+        "\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": "6UbG0X25x3qK"
+      },
+      "source": [
+        "## Preprocessing"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 4,
+      "metadata": {
+        "id": "YALAdp7Vx3qL"
+      },
+      "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": "code",
+      "source": [
+        "with open(\"vocab.txt\", \"w\") as output:\n",
+        "    for item in char_to_num.get_vocabulary():\n",
+        "        output.write(item+\"\\n\")"
+      ],
+      "metadata": {
+        "id": "rZSuHfOCyjHn"
+      },
+      "execution_count": 11,
+      "outputs": []
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "GsKMu7prx3qL"
+      },
+      "source": [
+        "## Create `Dataset` objects"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 6,
+      "metadata": {
+        "id": "amyW8t0Dx3qM"
+      },
+      "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": "SE7lS8qtx3qM"
+      },
+      "source": [
+        "## Visualize the data"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 7,
+      "metadata": {
+        "id": "tRjlq5pox3qM",
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 290
+        },
+        "outputId": "ecbe7da7-8751-44b9-d020-b49cb3c477ff"
+      },
+      "outputs": [
+        {
+          "output_type": "display_data",
+          "data": {
+            "image/png": "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\n",
+            "text/plain": [
+              "<Figure size 720x360 with 16 Axes>"
+            ]
+          },
+          "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": "8JwTzc3Dx3qN"
+      },
+      "source": [
+        "## Model"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 8,
+      "metadata": {
+        "id": "BtS72mQAx3qN",
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "outputId": "7bf6ce8a-de41-44ee-8b71-7c9b25573c23"
+      },
+      "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, 21)       2709        ['bidirectional_1[0][0]']        \n",
+            "                                                                                                  \n",
+            " ctc_loss (CTCLayer)            (None, 50, 21)       0           ['label[0][0]',                  \n",
+            "                                                                  'dense2[0][0]']                 \n",
+            "                                                                                                  \n",
+            "==================================================================================================\n",
+            "Total params: 432,725\n",
+            "Trainable params: 432,725\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": "kwzLGWhtx3qN"
+      },
+      "source": [
+        "## Training"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 9,
+      "metadata": {
+        "id": "FejAaNkFx3qO",
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "outputId": "ea070653-365c-466a-c843-b5c159eb9d9b"
+      },
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "Epoch 1/200\n",
+            "59/59 [==============================] - 17s 50ms/step - loss: 19.5124 - val_loss: 16.3746\n",
+            "Epoch 2/200\n",
+            "59/59 [==============================] - 1s 25ms/step - loss: 16.3700 - val_loss: 16.3838\n",
+            "Epoch 3/200\n",
+            "59/59 [==============================] - 1s 25ms/step - loss: 16.3625 - val_loss: 16.3840\n",
+            "Epoch 4/200\n",
+            "59/59 [==============================] - 1s 25ms/step - loss: 16.3563 - val_loss: 16.3689\n",
+            "Epoch 5/200\n",
+            "59/59 [==============================] - 1s 25ms/step - loss: 16.3538 - val_loss: 16.3669\n",
+            "Epoch 6/200\n",
+            "59/59 [==============================] - 1s 25ms/step - loss: 16.3422 - val_loss: 16.3603\n",
+            "Epoch 7/200\n",
+            "59/59 [==============================] - 1s 25ms/step - loss: 16.3405 - val_loss: 16.3408\n",
+            "Epoch 8/200\n",
+            "59/59 [==============================] - 1s 25ms/step - loss: 16.3309 - val_loss: 16.3183\n",
+            "Epoch 9/200\n",
+            "59/59 [==============================] - 1s 25ms/step - loss: 16.3158 - val_loss: 16.2819\n",
+            "Epoch 10/200\n",
+            "59/59 [==============================] - 1s 25ms/step - loss: 16.3057 - val_loss: 16.2450\n",
+            "Epoch 11/200\n",
+            "59/59 [==============================] - 1s 25ms/step - loss: 16.2664 - val_loss: 16.1391\n",
+            "Epoch 12/200\n",
+            "59/59 [==============================] - 2s 25ms/step - loss: 16.1689 - val_loss: 16.0375\n",
+            "Epoch 13/200\n",
+            "59/59 [==============================] - 2s 26ms/step - loss: 16.0363 - val_loss: 15.8317\n",
+            "Epoch 14/200\n",
+            "59/59 [==============================] - 2s 28ms/step - loss: 15.8328 - val_loss: 15.6732\n",
+            "Epoch 15/200\n",
+            "59/59 [==============================] - 2s 32ms/step - loss: 15.6642 - val_loss: 15.5655\n",
+            "Epoch 16/200\n",
+            "59/59 [==============================] - 1s 25ms/step - loss: 15.5475 - val_loss: 15.5393\n",
+            "Epoch 17/200\n",
+            "59/59 [==============================] - 1s 25ms/step - loss: 15.4533 - val_loss: 15.4479\n",
+            "Epoch 18/200\n",
+            "59/59 [==============================] - 1s 25ms/step - loss: 15.3814 - val_loss: 15.4685\n",
+            "Epoch 19/200\n",
+            "59/59 [==============================] - 1s 25ms/step - loss: 15.2858 - val_loss: 15.2323\n",
+            "Epoch 20/200\n",
+            "59/59 [==============================] - 1s 25ms/step - loss: 15.1068 - val_loss: 14.9993\n",
+            "Epoch 21/200\n",
+            "59/59 [==============================] - 2s 26ms/step - loss: 14.7485 - val_loss: 14.6611\n",
+            "Epoch 22/200\n",
+            "59/59 [==============================] - 1s 25ms/step - loss: 14.5632 - val_loss: 14.5010\n",
+            "Epoch 23/200\n",
+            "59/59 [==============================] - 2s 25ms/step - loss: 14.4108 - val_loss: 14.3898\n",
+            "Epoch 24/200\n",
+            "59/59 [==============================] - 2s 26ms/step - loss: 14.2418 - val_loss: 14.1950\n",
+            "Epoch 25/200\n",
+            "59/59 [==============================] - 1s 25ms/step - loss: 14.0353 - val_loss: 13.9023\n",
+            "Epoch 26/200\n",
+            "59/59 [==============================] - 1s 25ms/step - loss: 13.7943 - val_loss: 13.7772\n",
+            "Epoch 27/200\n",
+            "59/59 [==============================] - 1s 25ms/step - loss: 13.5445 - val_loss: 13.6424\n",
+            "Epoch 28/200\n",
+            "59/59 [==============================] - 2s 25ms/step - loss: 13.3485 - val_loss: 13.4410\n",
+            "Epoch 29/200\n",
+            "59/59 [==============================] - 2s 25ms/step - loss: 12.9846 - val_loss: 12.8109\n",
+            "Epoch 30/200\n",
+            "59/59 [==============================] - 2s 26ms/step - loss: 12.4018 - val_loss: 11.7466\n",
+            "Epoch 31/200\n",
+            "59/59 [==============================] - 1s 25ms/step - loss: 10.9293 - val_loss: 9.4451\n",
+            "Epoch 32/200\n",
+            "59/59 [==============================] - 2s 25ms/step - loss: 9.0217 - val_loss: 7.4770\n",
+            "Epoch 33/200\n",
+            "59/59 [==============================] - 1s 25ms/step - loss: 6.5376 - val_loss: 4.8288\n",
+            "Epoch 34/200\n",
+            "59/59 [==============================] - 2s 25ms/step - loss: 4.5844 - val_loss: 3.2979\n",
+            "Epoch 35/200\n",
+            "59/59 [==============================] - 2s 25ms/step - loss: 3.4613 - val_loss: 2.5323\n",
+            "Epoch 36/200\n",
+            "59/59 [==============================] - 2s 25ms/step - loss: 2.5618 - val_loss: 1.5142\n",
+            "Epoch 37/200\n",
+            "59/59 [==============================] - 2s 26ms/step - loss: 1.9167 - val_loss: 1.1585\n",
+            "Epoch 38/200\n",
+            "59/59 [==============================] - 2s 25ms/step - loss: 1.4137 - val_loss: 0.7415\n",
+            "Epoch 39/200\n",
+            "59/59 [==============================] - 2s 25ms/step - loss: 1.1980 - val_loss: 0.4908\n",
+            "Epoch 40/200\n",
+            "59/59 [==============================] - 2s 26ms/step - loss: 1.0244 - val_loss: 0.3350\n",
+            "Epoch 41/200\n",
+            "59/59 [==============================] - 2s 34ms/step - loss: 0.7217 - val_loss: 0.2219\n",
+            "Epoch 42/200\n",
+            "59/59 [==============================] - 2s 36ms/step - loss: 0.6207 - val_loss: 0.2281\n",
+            "Epoch 43/200\n",
+            "59/59 [==============================] - 2s 35ms/step - loss: 0.5514 - val_loss: 0.1198\n",
+            "Epoch 44/200\n",
+            "59/59 [==============================] - 2s 33ms/step - loss: 0.4584 - val_loss: 0.0926\n",
+            "Epoch 45/200\n",
+            "59/59 [==============================] - 2s 29ms/step - loss: 0.3834 - val_loss: 0.1280\n",
+            "Epoch 46/200\n",
+            "59/59 [==============================] - 2s 31ms/step - loss: 0.3527 - val_loss: 0.0758\n",
+            "Epoch 47/200\n",
+            "59/59 [==============================] - 2s 31ms/step - loss: 0.2850 - val_loss: 0.0842\n",
+            "Epoch 48/200\n",
+            "59/59 [==============================] - 2s 30ms/step - loss: 0.3061 - val_loss: 0.0618\n",
+            "Epoch 49/200\n",
+            "59/59 [==============================] - 2s 30ms/step - loss: 0.3310 - val_loss: 0.0515\n",
+            "Epoch 50/200\n",
+            "59/59 [==============================] - 2s 32ms/step - loss: 0.2526 - val_loss: 0.0998\n",
+            "Epoch 51/200\n",
+            "59/59 [==============================] - 2s 30ms/step - loss: 0.2299 - val_loss: 0.0574\n",
+            "Epoch 52/200\n",
+            "59/59 [==============================] - 2s 37ms/step - loss: 0.1831 - val_loss: 0.0262\n",
+            "Epoch 53/200\n",
+            "59/59 [==============================] - 2s 42ms/step - loss: 0.1824 - val_loss: 0.0446\n",
+            "Epoch 54/200\n",
+            "59/59 [==============================] - 2s 31ms/step - loss: 0.1691 - val_loss: 0.0713\n",
+            "Epoch 55/200\n",
+            "59/59 [==============================] - 2s 31ms/step - loss: 0.1759 - val_loss: 0.0345\n",
+            "Epoch 56/200\n",
+            "59/59 [==============================] - 1s 25ms/step - loss: 0.1375 - val_loss: 0.0470\n",
+            "Epoch 57/200\n",
+            "59/59 [==============================] - 1s 25ms/step - loss: 0.1754 - val_loss: 0.0355\n",
+            "Epoch 58/200\n",
+            "59/59 [==============================] - 1s 25ms/step - loss: 0.1217 - val_loss: 0.0206\n",
+            "Epoch 59/200\n",
+            "59/59 [==============================] - 2s 25ms/step - loss: 0.0948 - val_loss: 0.0489\n",
+            "Epoch 60/200\n",
+            "59/59 [==============================] - 1s 25ms/step - loss: 0.1536 - val_loss: 0.0251\n",
+            "Epoch 61/200\n",
+            "59/59 [==============================] - 1s 25ms/step - loss: 0.1262 - val_loss: 0.0246\n",
+            "Epoch 62/200\n",
+            "59/59 [==============================] - 1s 25ms/step - loss: 0.1505 - val_loss: 0.1348\n",
+            "Epoch 63/200\n",
+            "59/59 [==============================] - 1s 25ms/step - loss: 0.1135 - val_loss: 0.0313\n",
+            "Epoch 64/200\n",
+            "59/59 [==============================] - 1s 25ms/step - loss: 0.1040 - val_loss: 0.0150\n",
+            "Epoch 65/200\n",
+            "59/59 [==============================] - 1s 25ms/step - loss: 0.0896 - val_loss: 0.0206\n",
+            "Epoch 66/200\n",
+            "59/59 [==============================] - 1s 25ms/step - loss: 0.0753 - val_loss: 0.0102\n",
+            "Epoch 67/200\n",
+            "59/59 [==============================] - 1s 25ms/step - loss: 0.0692 - val_loss: 0.0385\n",
+            "Epoch 68/200\n",
+            "59/59 [==============================] - 1s 25ms/step - loss: 0.0880 - val_loss: 0.0402\n",
+            "Epoch 69/200\n",
+            "59/59 [==============================] - 2s 26ms/step - loss: 0.0862 - val_loss: 0.0116\n",
+            "Epoch 70/200\n",
+            "59/59 [==============================] - 2s 26ms/step - loss: 0.0715 - val_loss: 0.0099\n",
+            "Epoch 71/200\n",
+            "59/59 [==============================] - 2s 26ms/step - loss: 0.0833 - val_loss: 0.0083\n",
+            "Epoch 72/200\n",
+            "59/59 [==============================] - 1s 25ms/step - loss: 0.0606 - val_loss: 0.0164\n",
+            "Epoch 73/200\n",
+            "59/59 [==============================] - 2s 25ms/step - loss: 0.0821 - val_loss: 0.0077\n",
+            "Epoch 74/200\n",
+            "59/59 [==============================] - 1s 25ms/step - loss: 0.0700 - val_loss: 0.0109\n",
+            "Epoch 75/200\n",
+            "59/59 [==============================] - 1s 25ms/step - loss: 0.1876 - val_loss: 0.0852\n",
+            "Epoch 76/200\n",
+            "59/59 [==============================] - 1s 25ms/step - loss: 0.1257 - val_loss: 0.0522\n",
+            "Epoch 77/200\n",
+            "59/59 [==============================] - 2s 25ms/step - loss: 0.1153 - val_loss: 0.0231\n",
+            "Epoch 78/200\n",
+            "59/59 [==============================] - 2s 25ms/step - loss: 0.0999 - val_loss: 0.0155\n",
+            "Epoch 79/200\n",
+            "59/59 [==============================] - 2s 26ms/step - loss: 0.0567 - val_loss: 0.0081\n",
+            "Epoch 80/200\n",
+            "59/59 [==============================] - 1s 25ms/step - loss: 0.0538 - val_loss: 0.0126\n",
+            "Epoch 81/200\n",
+            "59/59 [==============================] - 1s 25ms/step - loss: 0.0591 - val_loss: 0.0108\n",
+            "Epoch 82/200\n",
+            "59/59 [==============================] - 2s 25ms/step - loss: 0.1014 - val_loss: 0.0163\n",
+            "Epoch 83/200\n",
+            "59/59 [==============================] - 2s 25ms/step - loss: 0.0575 - val_loss: 0.0204\n"
+          ]
+        }
+      ],
+      "source": [
+        "\n",
+        "epochs = 200\n",
+        "early_stopping_patience = 10\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": "VESzr7cTx3qO"
+      },
+      "source": [
+        "## Inference"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 12,
+      "metadata": {
+        "id": "e_eE3U3Gx3qO",
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 878
+        },
+        "outputId": "f79f7ae9-7484-49e4-97e4-e7e6ca0fe197"
+      },
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "Model: \"model\"\n",
+            "_________________________________________________________________\n",
+            " Layer (type)                Output Shape              Param #   \n",
+            "=================================================================\n",
+            " image (InputLayer)          [(None, 200, 50, 1)]      0         \n",
+            "                                                                 \n",
+            " Conv1 (Conv2D)              (None, 200, 50, 32)       320       \n",
+            "                                                                 \n",
+            " pool1 (MaxPooling2D)        (None, 100, 25, 32)       0         \n",
+            "                                                                 \n",
+            " Conv2 (Conv2D)              (None, 100, 25, 64)       18496     \n",
+            "                                                                 \n",
+            " pool2 (MaxPooling2D)        (None, 50, 12, 64)        0         \n",
+            "                                                                 \n",
+            " reshape (Reshape)           (None, 50, 768)           0         \n",
+            "                                                                 \n",
+            " dense1 (Dense)              (None, 50, 64)            49216     \n",
+            "                                                                 \n",
+            " dropout (Dropout)           (None, 50, 64)            0         \n",
+            "                                                                 \n",
+            " bidirectional (Bidirectiona  (None, 50, 256)          197632    \n",
+            " l)                                                              \n",
+            "                                                                 \n",
+            " bidirectional_1 (Bidirectio  (None, 50, 128)          164352    \n",
+            " nal)                                                            \n",
+            "                                                                 \n",
+            " dense2 (Dense)              (None, 50, 21)            2709      \n",
+            "                                                                 \n",
+            "=================================================================\n",
+            "Total params: 432,725\n",
+            "Trainable params: 432,725\n",
+            "Non-trainable params: 0\n",
+            "_________________________________________________________________\n"
+          ]
+        },
+        {
+          "output_type": "display_data",
+          "data": {
+            "image/png": "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\n",
+            "text/plain": [
+              "<Figure size 1080x360 with 16 Axes>"
+            ]
+          },
+          "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": "code",
+      "source": [
+        "!pip install huggingface-hub\n",
+        "!curl -s https://packagecloud.io/install/repositories/github/git-lfs/script.deb.sh | sudo bash\n",
+        "!sudo apt-get install git-lfs\n",
+        "!git-lfs install"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "iCiY2LubzB8X",
+        "outputId": "bff55a2c-c40b-47a1-98da-c09cfab51f89"
+      },
+      "execution_count": 13,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "Collecting huggingface-hub\n",
+            "  Downloading huggingface_hub-0.4.0-py3-none-any.whl (67 kB)\n",
+            "\u001b[?25l\r\u001b[K     |█████                           | 10 kB 35.6 MB/s eta 0:00:01\r\u001b[K     |█████████▉                      | 20 kB 18.6 MB/s eta 0:00:01\r\u001b[K     |██████████████▊                 | 30 kB 15.5 MB/s eta 0:00:01\r\u001b[K     |███████████████████▋            | 40 kB 14.2 MB/s eta 0:00:01\r\u001b[K     |████████████████████████▌       | 51 kB 7.9 MB/s eta 0:00:01\r\u001b[K     |█████████████████████████████▍  | 61 kB 9.2 MB/s eta 0:00:01\r\u001b[K     |████████████████████████████████| 67 kB 3.8 MB/s \n",
+            "\u001b[?25hRequirement already satisfied: importlib-metadata in /usr/local/lib/python3.7/dist-packages (from huggingface-hub) (4.10.1)\n",
+            "Requirement already satisfied: pyyaml in /usr/local/lib/python3.7/dist-packages (from huggingface-hub) (3.13)\n",
+            "Requirement already satisfied: filelock in /usr/local/lib/python3.7/dist-packages (from huggingface-hub) (3.4.2)\n",
+            "Requirement already satisfied: tqdm in /usr/local/lib/python3.7/dist-packages (from huggingface-hub) (4.62.3)\n",
+            "Requirement already satisfied: packaging>=20.9 in /usr/local/lib/python3.7/dist-packages (from huggingface-hub) (21.3)\n",
+            "Requirement already satisfied: typing-extensions>=3.7.4.3 in /usr/local/lib/python3.7/dist-packages (from huggingface-hub) (3.10.0.2)\n",
+            "Requirement already satisfied: requests in /usr/local/lib/python3.7/dist-packages (from huggingface-hub) (2.23.0)\n",
+            "Requirement already satisfied: pyparsing!=3.0.5,>=2.0.2 in /usr/local/lib/python3.7/dist-packages (from packaging>=20.9->huggingface-hub) (3.0.7)\n",
+            "Requirement already satisfied: zipp>=0.5 in /usr/local/lib/python3.7/dist-packages (from importlib-metadata->huggingface-hub) (3.7.0)\n",
+            "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.7/dist-packages (from requests->huggingface-hub) (2021.10.8)\n",
+            "Requirement already satisfied: urllib3!=1.25.0,!=1.25.1,<1.26,>=1.21.1 in /usr/local/lib/python3.7/dist-packages (from requests->huggingface-hub) (1.24.3)\n",
+            "Requirement already satisfied: idna<3,>=2.5 in /usr/local/lib/python3.7/dist-packages (from requests->huggingface-hub) (2.10)\n",
+            "Requirement already satisfied: chardet<4,>=3.0.2 in /usr/local/lib/python3.7/dist-packages (from requests->huggingface-hub) (3.0.4)\n",
+            "Installing collected packages: huggingface-hub\n",
+            "Successfully installed huggingface-hub-0.4.0\n",
+            "Detected operating system as Ubuntu/bionic.\n",
+            "Checking for curl...\n",
+            "Detected curl...\n",
+            "Checking for gpg...\n",
+            "Detected gpg...\n",
+            "Running apt-get update... done.\n",
+            "Installing apt-transport-https... done.\n",
+            "Installing /etc/apt/sources.list.d/github_git-lfs.list...done.\n",
+            "Importing packagecloud gpg key... done.\n",
+            "Running apt-get update... done.\n",
+            "\n",
+            "The repository is setup! You can now install packages.\n",
+            "Reading package lists... Done\n",
+            "Building dependency tree       \n",
+            "Reading state information... Done\n",
+            "The following packages were automatically installed and are no longer required:\n",
+            "  cuda-command-line-tools-10-0 cuda-command-line-tools-10-1\n",
+            "  cuda-command-line-tools-11-0 cuda-compiler-10-0 cuda-compiler-10-1\n",
+            "  cuda-compiler-11-0 cuda-cuobjdump-10-0 cuda-cuobjdump-10-1\n",
+            "  cuda-cuobjdump-11-0 cuda-cupti-10-0 cuda-cupti-10-1 cuda-cupti-11-0\n",
+            "  cuda-cupti-dev-11-0 cuda-documentation-10-0 cuda-documentation-10-1\n",
+            "  cuda-documentation-11-0 cuda-documentation-11-1 cuda-gdb-10-0 cuda-gdb-10-1\n",
+            "  cuda-gdb-11-0 cuda-gpu-library-advisor-10-0 cuda-gpu-library-advisor-10-1\n",
+            "  cuda-libraries-10-0 cuda-libraries-10-1 cuda-libraries-11-0\n",
+            "  cuda-memcheck-10-0 cuda-memcheck-10-1 cuda-memcheck-11-0 cuda-nsight-10-0\n",
+            "  cuda-nsight-10-1 cuda-nsight-11-0 cuda-nsight-11-1 cuda-nsight-compute-10-0\n",
+            "  cuda-nsight-compute-10-1 cuda-nsight-compute-11-0 cuda-nsight-compute-11-1\n",
+            "  cuda-nsight-systems-10-1 cuda-nsight-systems-11-0 cuda-nsight-systems-11-1\n",
+            "  cuda-nvcc-10-0 cuda-nvcc-10-1 cuda-nvcc-11-0 cuda-nvdisasm-10-0\n",
+            "  cuda-nvdisasm-10-1 cuda-nvdisasm-11-0 cuda-nvml-dev-10-0 cuda-nvml-dev-10-1\n",
+            "  cuda-nvml-dev-11-0 cuda-nvprof-10-0 cuda-nvprof-10-1 cuda-nvprof-11-0\n",
+            "  cuda-nvprune-10-0 cuda-nvprune-10-1 cuda-nvprune-11-0 cuda-nvtx-10-0\n",
+            "  cuda-nvtx-10-1 cuda-nvtx-11-0 cuda-nvvp-10-0 cuda-nvvp-10-1 cuda-nvvp-11-0\n",
+            "  cuda-nvvp-11-1 cuda-samples-10-0 cuda-samples-10-1 cuda-samples-11-0\n",
+            "  cuda-samples-11-1 cuda-sanitizer-11-0 cuda-sanitizer-api-10-1\n",
+            "  cuda-toolkit-10-0 cuda-toolkit-10-1 cuda-toolkit-11-0 cuda-toolkit-11-1\n",
+            "  cuda-tools-10-0 cuda-tools-10-1 cuda-tools-11-0 cuda-tools-11-1\n",
+            "  cuda-visual-tools-10-0 cuda-visual-tools-10-1 cuda-visual-tools-11-0\n",
+            "  cuda-visual-tools-11-1 default-jre dkms freeglut3 freeglut3-dev\n",
+            "  keyboard-configuration libargon2-0 libcap2 libcryptsetup12\n",
+            "  libdevmapper1.02.1 libfontenc1 libidn11 libip4tc0 libjansson4\n",
+            "  libnvidia-cfg1-510 libnvidia-common-460 libnvidia-common-510\n",
+            "  libnvidia-extra-510 libnvidia-fbc1-510 libnvidia-gl-510 libpam-systemd\n",
+            "  libpolkit-agent-1-0 libpolkit-backend-1-0 libpolkit-gobject-1-0 libxfont2\n",
+            "  libxi-dev libxkbfile1 libxmu-dev libxmu-headers libxnvctrl0 libxtst6\n",
+            "  nsight-compute-2020.2.1 nsight-compute-2022.1.0 nsight-systems-2020.3.2\n",
+            "  nsight-systems-2020.3.4 nsight-systems-2021.5.2 nvidia-dkms-510\n",
+            "  nvidia-kernel-common-510 nvidia-kernel-source-510 nvidia-modprobe\n",
+            "  nvidia-settings openjdk-11-jre policykit-1 policykit-1-gnome python3-xkit\n",
+            "  screen-resolution-extra systemd systemd-sysv udev x11-xkb-utils\n",
+            "  xserver-common xserver-xorg-core-hwe-18.04 xserver-xorg-video-nvidia-510\n",
+            "Use 'sudo apt autoremove' to remove them.\n",
+            "The following NEW packages will be installed:\n",
+            "  git-lfs\n",
+            "0 upgraded, 1 newly installed, 0 to remove and 55 not upgraded.\n",
+            "Need to get 6,526 kB of archives.\n",
+            "After this operation, 14.7 MB of additional disk space will be used.\n",
+            "Get:1 https://packagecloud.io/github/git-lfs/ubuntu bionic/main amd64 git-lfs amd64 3.0.2 [6,526 kB]\n",
+            "Fetched 6,526 kB in 0s (19.0 MB/s)\n",
+            "debconf: unable to initialize frontend: Dialog\n",
+            "debconf: (No usable dialog-like program is installed, so the dialog based frontend cannot be used. at /usr/share/perl5/Debconf/FrontEnd/Dialog.pm line 76, <> line 1.)\n",
+            "debconf: falling back to frontend: Readline\n",
+            "debconf: unable to initialize frontend: Readline\n",
+            "debconf: (This frontend requires a controlling tty.)\n",
+            "debconf: falling back to frontend: Teletype\n",
+            "dpkg-preconfigure: unable to re-open stdin: \n",
+            "Selecting previously unselected package git-lfs.\n",
+            "(Reading database ... 155117 files and directories currently installed.)\n",
+            "Preparing to unpack .../git-lfs_3.0.2_amd64.deb ...\n",
+            "Unpacking git-lfs (3.0.2) ...\n",
+            "Setting up git-lfs (3.0.2) ...\n",
+            "Git LFS initialized.\n",
+            "Processing triggers for man-db (2.8.3-2ubuntu0.1) ...\n",
+            "Git LFS initialized.\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "!huggingface-cli login"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "02-609YdzCZx",
+        "outputId": "0c16e940-4bc2-46e5-a7e5-f35e0b482424"
+      },
+      "execution_count": 14,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "\n",
+            "        _|    _|  _|    _|    _|_|_|    _|_|_|  _|_|_|  _|      _|    _|_|_|      _|_|_|_|    _|_|      _|_|_|  _|_|_|_|\n",
+            "        _|    _|  _|    _|  _|        _|          _|    _|_|    _|  _|            _|        _|    _|  _|        _|\n",
+            "        _|_|_|_|  _|    _|  _|  _|_|  _|  _|_|    _|    _|  _|  _|  _|  _|_|      _|_|_|    _|_|_|_|  _|        _|_|_|\n",
+            "        _|    _|  _|    _|  _|    _|  _|    _|    _|    _|    _|_|  _|    _|      _|        _|    _|  _|        _|\n",
+            "        _|    _|    _|_|      _|_|_|    _|_|_|  _|_|_|  _|      _|    _|_|_|      _|        _|    _|    _|_|_|  _|_|_|_|\n",
+            "\n",
+            "        To login, `huggingface_hub` now requires a token generated from https://huggingface.co/settings/token.\n",
+            "        (Deprecated, will be removed in v0.3.0) To login with username and password instead, interrupt with Ctrl+C.\n",
+            "        \n",
+            "Token: \n",
+            "Login successful\n",
+            "Your token has been saved to /root/.huggingface/token\n",
+            "\u001b[1m\u001b[31mAuthenticated through git-credential store but this isn't the helper defined on your machine.\n",
+            "You might have to re-authenticate when pushing to the Hugging Face Hub. Run the following command in your terminal in case you want to set this credential helper as the default\n",
+            "\n",
+            "git config --global credential.helper store\u001b[0m\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "from huggingface_hub.keras_mixin import push_to_hub_keras\n",
+        "push_to_hub_keras(model = model, repo_url = \"https://huggingface.co/keras-io/ocr-for-captcha\", organization = \"keras-io\")"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 426,
+          "referenced_widgets": [
+            "0e603b2fac32442bbcd15d358f3b3f5e",
+            "0f681376aaa3429c9762622fa011e9fd",
+            "a3b0759750904945b2ce929de4e8b41e",
+            "69e09e9596d0433c9a74af41395ed5cc",
+            "2c4866f6af87406cb32a43d6f28dc0f6",
+            "0cd0602da8774f05b5a42526dba8f3f2",
+            "5fd167866b36458db7f442b788b56b3a",
+            "19ae74592d1641e5ba3de24076e9e991",
+            "1cf62197694449ab97357d571984f69a",
+            "e6dd14643b9e4c25bcb88d449aedba21",
+            "2d5b97766d004047a631f08ab75b609e",
+            "33289e986b4d46999d01c5019349b6b8",
+            "dd6d3fb053a845f5a20d2dab82cb7400",
+            "9e82a454487b48e7b00bfaffc14c88ca",
+            "a0c789281db24e1fa4da6ec6295a41f0",
+            "a5efea4a821a45cfa9cffbfb00f45547",
+            "e1447de1071f4d06b09b010a30d5b2ce",
+            "c52dcedde03c4d0a890630ff2df2e479",
+            "e7785eaa157248c092127fbf795e9ead",
+            "c31e0a9361be4ec69ac63c86ea153a6f",
+            "ec8c8c3f9072409a8e9836afeb65f041",
+            "91bc7d27ce6140ebaa3cd794f99a68dd",
+            "d0557237d0984ff58db01e08fe7f4843",
+            "80ece29af820447fbc0d19f94b4638f7",
+            "2ffca3af2668441a863396ade910ba17",
+            "472fb9183fb849b6a9bd9a502cf9a002",
+            "50e92d86e74d42cc8452e8d37978087f",
+            "2b8c22730dc3428b9d8087d15e698dac",
+            "c59caab0525948de98277bcdab4f039a",
+            "5d11cedff5784ded90b15383a782b9ad",
+            "fa8812f859fe4c45aff1335cf85be76a",
+            "16d5e64960454ac8bf12d2fb5531662e",
+            "277c23308a354c26a24caae56b8c0200",
+            "ec063e2465c24cbbb2c2aba12b489258",
+            "bdb9eb8e834043b6baf8d95d75ed372a",
+            "cbd69a8c8fb04e7abc347cb8a855b73b",
+            "cbb844064dd74e1aad7318ca6320e959",
+            "9b090c77a53d45a19b1f9842c8fac8ed",
+            "b3c9122465ea441f8320e037f0c83e31",
+            "af01adda7adc4e68b3785ce8b6a41036",
+            "91611d3294fd4dfc8efac97843aab9ff",
+            "d6f241185c4243c5980036efbbdccd05",
+            "5727b4324c44423fa259b16360da0d73",
+            "8e581a2bd3a44195ba98b6f77461716e"
+          ]
+        },
+        "id": "T8xsh4dEzEmi",
+        "outputId": "188725b1-057e-4e61-906d-0ac6f2489783"
+      },
+      "execution_count": 15,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stderr",
+          "text": [
+            "Cloning https://huggingface.co/keras-io/ocr-for-captcha into local empty directory.\n"
+          ]
+        },
+        {
+          "output_type": "display_data",
+          "data": {
+            "application/vnd.jupyter.widget-view+json": {
+              "model_id": "0e603b2fac32442bbcd15d358f3b3f5e",
+              "version_minor": 0,
+              "version_major": 2
+            },
+            "text/plain": [
+              "Download file saved_model.pb:   0%|          | 8.08k/4.68M [00:00<?, ?B/s]"
+            ]
+          },
+          "metadata": {}
+        },
+        {
+          "output_type": "display_data",
+          "data": {
+            "application/vnd.jupyter.widget-view+json": {
+              "model_id": "33289e986b4d46999d01c5019349b6b8",
+              "version_minor": 0,
+              "version_major": 2
+            },
+            "text/plain": [
+              "Download file keras_metadata.pb:   2%|1         | 599/35.9k [00:00<?, ?B/s]"
+            ]
+          },
+          "metadata": {}
+        },
+        {
+          "output_type": "display_data",
+          "data": {
+            "application/vnd.jupyter.widget-view+json": {
+              "model_id": "d0557237d0984ff58db01e08fe7f4843",
+              "version_minor": 0,
+              "version_major": 2
+            },
+            "text/plain": [
+              "Clean file keras_metadata.pb:   3%|2         | 1.00k/35.9k [00:00<?, ?B/s]"
+            ]
+          },
+          "metadata": {}
+        },
+        {
+          "output_type": "stream",
+          "name": "stderr",
+          "text": [
+            "WARNING:absl:Found untraced functions such as lstm_cell_1_layer_call_fn, lstm_cell_1_layer_call_and_return_conditional_losses, lstm_cell_2_layer_call_fn, lstm_cell_2_layer_call_and_return_conditional_losses, lstm_cell_4_layer_call_fn while saving (showing 5 of 20). These functions will not be directly callable after loading.\n"
+          ]
+        },
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "INFO:tensorflow:Assets written to: ocr-for-captcha/assets\n"
+          ]
+        },
+        {
+          "output_type": "stream",
+          "name": "stderr",
+          "text": [
+            "INFO:tensorflow:Assets written to: ocr-for-captcha/assets\n",
+            "WARNING:absl:<keras.layers.recurrent.LSTMCell object at 0x7f185516f650> has the same name 'LSTMCell' as a built-in Keras object. Consider renaming <class 'keras.layers.recurrent.LSTMCell'> to avoid naming conflicts when loading with `tf.keras.models.load_model`. If renaming is not possible, pass the object in the `custom_objects` parameter of the load function.\n",
+            "WARNING:absl:<keras.layers.recurrent.LSTMCell object at 0x7f18551d7f90> has the same name 'LSTMCell' as a built-in Keras object. Consider renaming <class 'keras.layers.recurrent.LSTMCell'> to avoid naming conflicts when loading with `tf.keras.models.load_model`. If renaming is not possible, pass the object in the `custom_objects` parameter of the load function.\n",
+            "WARNING:absl:<keras.layers.recurrent.LSTMCell object at 0x7f1855044750> has the same name 'LSTMCell' as a built-in Keras object. Consider renaming <class 'keras.layers.recurrent.LSTMCell'> to avoid naming conflicts when loading with `tf.keras.models.load_model`. If renaming is not possible, pass the object in the `custom_objects` parameter of the load function.\n",
+            "WARNING:absl:<keras.layers.recurrent.LSTMCell object at 0x7f185500eb50> has the same name 'LSTMCell' as a built-in Keras object. Consider renaming <class 'keras.layers.recurrent.LSTMCell'> to avoid naming conflicts when loading with `tf.keras.models.load_model`. If renaming is not possible, pass the object in the `custom_objects` parameter of the load function.\n"
+          ]
+        },
+        {
+          "output_type": "display_data",
+          "data": {
+            "application/vnd.jupyter.widget-view+json": {
+              "model_id": "ec063e2465c24cbbb2c2aba12b489258",
+              "version_minor": 0,
+              "version_major": 2
+            },
+            "text/plain": [
+              "Upload file saved_model.pb:   1%|          | 32.0k/4.68M [00:00<?, ?B/s]"
+            ]
+          },
+          "metadata": {}
+        },
+        {
+          "output_type": "stream",
+          "name": "stderr",
+          "text": [
+            "To https://huggingface.co/keras-io/ocr-for-captcha\n",
+            "   ca83c53..378d755  main -> main\n",
+            "\n",
+            "WARNING:huggingface_hub.repository:To https://huggingface.co/keras-io/ocr-for-captcha\n",
+            "   ca83c53..378d755  main -> main\n",
+            "\n"
+          ]
+        },
+        {
+          "output_type": "execute_result",
+          "data": {
+            "application/vnd.google.colaboratory.intrinsic+json": {
+              "type": "string"
+            },
+            "text/plain": [
+              "'https://huggingface.co/keras-io/ocr-for-captcha/commit/378d755e90644f3163c037d0c49c732a0148b8df'"
+            ]
+          },
+          "metadata": {},
+          "execution_count": 15
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        ""
+      ],
+      "metadata": {
+        "id": "mphBbzPa0PeB"
+      },
+      "execution_count": null,
+      "outputs": []
+    }
+  ],
+  "metadata": {
+    "colab": {
+      "collapsed_sections": [],
+      "name": "captcha_ocr",
+      "provenance": [],
+      "machine_shape": "hm"
+    },
+    "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",
+    "widgets": {
+      "application/vnd.jupyter.widget-state+json": {
+        "0e603b2fac32442bbcd15d358f3b3f5e": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "HBoxModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_view_name": "HBoxView",
+            "_dom_classes": [],
+            "_model_name": "HBoxModel",
+            "_view_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_view_count": null,
+            "_view_module_version": "1.5.0",
+            "box_style": "",
+            "layout": "IPY_MODEL_0f681376aaa3429c9762622fa011e9fd",
+            "_model_module": "@jupyter-widgets/controls",
+            "children": [
+              "IPY_MODEL_a3b0759750904945b2ce929de4e8b41e",
+              "IPY_MODEL_69e09e9596d0433c9a74af41395ed5cc",
+              "IPY_MODEL_2c4866f6af87406cb32a43d6f28dc0f6"
+            ]
+          }
+        },
+        "0f681376aaa3429c9762622fa011e9fd": {
+          "model_module": "@jupyter-widgets/base",
+          "model_name": "LayoutModel",
+          "model_module_version": "1.2.0",
+          "state": {
+            "_view_name": "LayoutView",
+            "grid_template_rows": null,
+            "right": null,
+            "justify_content": null,
+            "_view_module": "@jupyter-widgets/base",
+            "overflow": null,
+            "_model_module_version": "1.2.0",
+            "_view_count": null,
+            "flex_flow": null,
+            "width": null,
+            "min_width": null,
+            "border": null,
+            "align_items": null,
+            "bottom": null,
+            "_model_module": "@jupyter-widgets/base",
+            "top": null,
+            "grid_column": null,
+            "overflow_y": null,
+            "overflow_x": null,
+            "grid_auto_flow": null,
+            "grid_area": null,
+            "grid_template_columns": null,
+            "flex": null,
+            "_model_name": "LayoutModel",
+            "justify_items": null,
+            "grid_row": null,
+            "max_height": null,
+            "align_content": null,
+            "visibility": null,
+            "align_self": null,
+            "height": null,
+            "min_height": null,
+            "padding": null,
+            "grid_auto_rows": null,
+            "grid_gap": null,
+            "max_width": null,
+            "order": null,
+            "_view_module_version": "1.2.0",
+            "grid_template_areas": null,
+            "object_position": null,
+            "object_fit": null,
+            "grid_auto_columns": null,
+            "margin": null,
+            "display": null,
+            "left": null
+          }
+        },
+        "a3b0759750904945b2ce929de4e8b41e": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "HTMLModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_view_name": "HTMLView",
+            "style": "IPY_MODEL_0cd0602da8774f05b5a42526dba8f3f2",
+            "_dom_classes": [],
+            "description": "",
+            "_model_name": "HTMLModel",
+            "placeholder": "​",
+            "_view_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "value": "Download file saved_model.pb: 100%",
+            "_view_count": null,
+            "_view_module_version": "1.5.0",
+            "description_tooltip": null,
+            "_model_module": "@jupyter-widgets/controls",
+            "layout": "IPY_MODEL_5fd167866b36458db7f442b788b56b3a"
+          }
+        },
+        "69e09e9596d0433c9a74af41395ed5cc": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "FloatProgressModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_view_name": "ProgressView",
+            "style": "IPY_MODEL_19ae74592d1641e5ba3de24076e9e991",
+            "_dom_classes": [],
+            "description": "",
+            "_model_name": "FloatProgressModel",
+            "bar_style": "success",
+            "max": 4904280,
+            "_view_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "value": 4904280,
+            "_view_count": null,
+            "_view_module_version": "1.5.0",
+            "orientation": "horizontal",
+            "min": 0,
+            "description_tooltip": null,
+            "_model_module": "@jupyter-widgets/controls",
+            "layout": "IPY_MODEL_1cf62197694449ab97357d571984f69a"
+          }
+        },
+        "2c4866f6af87406cb32a43d6f28dc0f6": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "HTMLModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_view_name": "HTMLView",
+            "style": "IPY_MODEL_e6dd14643b9e4c25bcb88d449aedba21",
+            "_dom_classes": [],
+            "description": "",
+            "_model_name": "HTMLModel",
+            "placeholder": "​",
+            "_view_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "value": " 4.68M/4.68M [00:01&lt;00:00, 4.11MB/s]",
+            "_view_count": null,
+            "_view_module_version": "1.5.0",
+            "description_tooltip": null,
+            "_model_module": "@jupyter-widgets/controls",
+            "layout": "IPY_MODEL_2d5b97766d004047a631f08ab75b609e"
+          }
+        },
+        "0cd0602da8774f05b5a42526dba8f3f2": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "DescriptionStyleModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_view_name": "StyleView",
+            "_model_name": "DescriptionStyleModel",
+            "description_width": "",
+            "_view_module": "@jupyter-widgets/base",
+            "_model_module_version": "1.5.0",
+            "_view_count": null,
+            "_view_module_version": "1.2.0",
+            "_model_module": "@jupyter-widgets/controls"
+          }
+        },
+        "5fd167866b36458db7f442b788b56b3a": {
+          "model_module": "@jupyter-widgets/base",
+          "model_name": "LayoutModel",
+          "model_module_version": "1.2.0",
+          "state": {
+            "_view_name": "LayoutView",
+            "grid_template_rows": null,
+            "right": null,
+            "justify_content": null,
+            "_view_module": "@jupyter-widgets/base",
+            "overflow": null,
+            "_model_module_version": "1.2.0",
+            "_view_count": null,
+            "flex_flow": null,
+            "width": null,
+            "min_width": null,
+            "border": null,
+            "align_items": null,
+            "bottom": null,
+            "_model_module": "@jupyter-widgets/base",
+            "top": null,
+            "grid_column": null,
+            "overflow_y": null,
+            "overflow_x": null,
+            "grid_auto_flow": null,
+            "grid_area": null,
+            "grid_template_columns": null,
+            "flex": null,
+            "_model_name": "LayoutModel",
+            "justify_items": null,
+            "grid_row": null,
+            "max_height": null,
+            "align_content": null,
+            "visibility": null,
+            "align_self": null,
+            "height": null,
+            "min_height": null,
+            "padding": null,
+            "grid_auto_rows": null,
+            "grid_gap": null,
+            "max_width": null,
+            "order": null,
+            "_view_module_version": "1.2.0",
+            "grid_template_areas": null,
+            "object_position": null,
+            "object_fit": null,
+            "grid_auto_columns": null,
+            "margin": null,
+            "display": null,
+            "left": null
+          }
+        },
+        "19ae74592d1641e5ba3de24076e9e991": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "ProgressStyleModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_view_name": "StyleView",
+            "_model_name": "ProgressStyleModel",
+            "description_width": "",
+            "_view_module": "@jupyter-widgets/base",
+            "_model_module_version": "1.5.0",
+            "_view_count": null,
+            "_view_module_version": "1.2.0",
+            "bar_color": null,
+            "_model_module": "@jupyter-widgets/controls"
+          }
+        },
+        "1cf62197694449ab97357d571984f69a": {
+          "model_module": "@jupyter-widgets/base",
+          "model_name": "LayoutModel",
+          "model_module_version": "1.2.0",
+          "state": {
+            "_view_name": "LayoutView",
+            "grid_template_rows": null,
+            "right": null,
+            "justify_content": null,
+            "_view_module": "@jupyter-widgets/base",
+            "overflow": null,
+            "_model_module_version": "1.2.0",
+            "_view_count": null,
+            "flex_flow": null,
+            "width": null,
+            "min_width": null,
+            "border": null,
+            "align_items": null,
+            "bottom": null,
+            "_model_module": "@jupyter-widgets/base",
+            "top": null,
+            "grid_column": null,
+            "overflow_y": null,
+            "overflow_x": null,
+            "grid_auto_flow": null,
+            "grid_area": null,
+            "grid_template_columns": null,
+            "flex": null,
+            "_model_name": "LayoutModel",
+            "justify_items": null,
+            "grid_row": null,
+            "max_height": null,
+            "align_content": null,
+            "visibility": null,
+            "align_self": null,
+            "height": null,
+            "min_height": null,
+            "padding": null,
+            "grid_auto_rows": null,
+            "grid_gap": null,
+            "max_width": null,
+            "order": null,
+            "_view_module_version": "1.2.0",
+            "grid_template_areas": null,
+            "object_position": null,
+            "object_fit": null,
+            "grid_auto_columns": null,
+            "margin": null,
+            "display": null,
+            "left": null
+          }
+        },
+        "e6dd14643b9e4c25bcb88d449aedba21": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "DescriptionStyleModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_view_name": "StyleView",
+            "_model_name": "DescriptionStyleModel",
+            "description_width": "",
+            "_view_module": "@jupyter-widgets/base",
+            "_model_module_version": "1.5.0",
+            "_view_count": null,
+            "_view_module_version": "1.2.0",
+            "_model_module": "@jupyter-widgets/controls"
+          }
+        },
+        "2d5b97766d004047a631f08ab75b609e": {
+          "model_module": "@jupyter-widgets/base",
+          "model_name": "LayoutModel",
+          "model_module_version": "1.2.0",
+          "state": {
+            "_view_name": "LayoutView",
+            "grid_template_rows": null,
+            "right": null,
+            "justify_content": null,
+            "_view_module": "@jupyter-widgets/base",
+            "overflow": null,
+            "_model_module_version": "1.2.0",
+            "_view_count": null,
+            "flex_flow": null,
+            "width": null,
+            "min_width": null,
+            "border": null,
+            "align_items": null,
+            "bottom": null,
+            "_model_module": "@jupyter-widgets/base",
+            "top": null,
+            "grid_column": null,
+            "overflow_y": null,
+            "overflow_x": null,
+            "grid_auto_flow": null,
+            "grid_area": null,
+            "grid_template_columns": null,
+            "flex": null,
+            "_model_name": "LayoutModel",
+            "justify_items": null,
+            "grid_row": null,
+            "max_height": null,
+            "align_content": null,
+            "visibility": null,
+            "align_self": null,
+            "height": null,
+            "min_height": null,
+            "padding": null,
+            "grid_auto_rows": null,
+            "grid_gap": null,
+            "max_width": null,
+            "order": null,
+            "_view_module_version": "1.2.0",
+            "grid_template_areas": null,
+            "object_position": null,
+            "object_fit": null,
+            "grid_auto_columns": null,
+            "margin": null,
+            "display": null,
+            "left": null
+          }
+        },
+        "33289e986b4d46999d01c5019349b6b8": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "HBoxModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_view_name": "HBoxView",
+            "_dom_classes": [],
+            "_model_name": "HBoxModel",
+            "_view_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_view_count": null,
+            "_view_module_version": "1.5.0",
+            "box_style": "",
+            "layout": "IPY_MODEL_dd6d3fb053a845f5a20d2dab82cb7400",
+            "_model_module": "@jupyter-widgets/controls",
+            "children": [
+              "IPY_MODEL_9e82a454487b48e7b00bfaffc14c88ca",
+              "IPY_MODEL_a0c789281db24e1fa4da6ec6295a41f0",
+              "IPY_MODEL_a5efea4a821a45cfa9cffbfb00f45547"
+            ]
+          }
+        },
+        "dd6d3fb053a845f5a20d2dab82cb7400": {
+          "model_module": "@jupyter-widgets/base",
+          "model_name": "LayoutModel",
+          "model_module_version": "1.2.0",
+          "state": {
+            "_view_name": "LayoutView",
+            "grid_template_rows": null,
+            "right": null,
+            "justify_content": null,
+            "_view_module": "@jupyter-widgets/base",
+            "overflow": null,
+            "_model_module_version": "1.2.0",
+            "_view_count": null,
+            "flex_flow": null,
+            "width": null,
+            "min_width": null,
+            "border": null,
+            "align_items": null,
+            "bottom": null,
+            "_model_module": "@jupyter-widgets/base",
+            "top": null,
+            "grid_column": null,
+            "overflow_y": null,
+            "overflow_x": null,
+            "grid_auto_flow": null,
+            "grid_area": null,
+            "grid_template_columns": null,
+            "flex": null,
+            "_model_name": "LayoutModel",
+            "justify_items": null,
+            "grid_row": null,
+            "max_height": null,
+            "align_content": null,
+            "visibility": null,
+            "align_self": null,
+            "height": null,
+            "min_height": null,
+            "padding": null,
+            "grid_auto_rows": null,
+            "grid_gap": null,
+            "max_width": null,
+            "order": null,
+            "_view_module_version": "1.2.0",
+            "grid_template_areas": null,
+            "object_position": null,
+            "object_fit": null,
+            "grid_auto_columns": null,
+            "margin": null,
+            "display": null,
+            "left": null
+          }
+        },
+        "9e82a454487b48e7b00bfaffc14c88ca": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "HTMLModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_view_name": "HTMLView",
+            "style": "IPY_MODEL_e1447de1071f4d06b09b010a30d5b2ce",
+            "_dom_classes": [],
+            "description": "",
+            "_model_name": "HTMLModel",
+            "placeholder": "​",
+            "_view_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "value": "Download file keras_metadata.pb: 100%",
+            "_view_count": null,
+            "_view_module_version": "1.5.0",
+            "description_tooltip": null,
+            "_model_module": "@jupyter-widgets/controls",
+            "layout": "IPY_MODEL_c52dcedde03c4d0a890630ff2df2e479"
+          }
+        },
+        "a0c789281db24e1fa4da6ec6295a41f0": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "FloatProgressModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_view_name": "ProgressView",
+            "style": "IPY_MODEL_e7785eaa157248c092127fbf795e9ead",
+            "_dom_classes": [],
+            "description": "",
+            "_model_name": "FloatProgressModel",
+            "bar_style": "success",
+            "max": 36792,
+            "_view_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "value": 36792,
+            "_view_count": null,
+            "_view_module_version": "1.5.0",
+            "orientation": "horizontal",
+            "min": 0,
+            "description_tooltip": null,
+            "_model_module": "@jupyter-widgets/controls",
+            "layout": "IPY_MODEL_c31e0a9361be4ec69ac63c86ea153a6f"
+          }
+        },
+        "a5efea4a821a45cfa9cffbfb00f45547": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "HTMLModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_view_name": "HTMLView",
+            "style": "IPY_MODEL_ec8c8c3f9072409a8e9836afeb65f041",
+            "_dom_classes": [],
+            "description": "",
+            "_model_name": "HTMLModel",
+            "placeholder": "​",
+            "_view_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "value": " 35.9k/35.9k [00:01&lt;00:00, 32.6kB/s]",
+            "_view_count": null,
+            "_view_module_version": "1.5.0",
+            "description_tooltip": null,
+            "_model_module": "@jupyter-widgets/controls",
+            "layout": "IPY_MODEL_91bc7d27ce6140ebaa3cd794f99a68dd"
+          }
+        },
+        "e1447de1071f4d06b09b010a30d5b2ce": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "DescriptionStyleModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_view_name": "StyleView",
+            "_model_name": "DescriptionStyleModel",
+            "description_width": "",
+            "_view_module": "@jupyter-widgets/base",
+            "_model_module_version": "1.5.0",
+            "_view_count": null,
+            "_view_module_version": "1.2.0",
+            "_model_module": "@jupyter-widgets/controls"
+          }
+        },
+        "c52dcedde03c4d0a890630ff2df2e479": {
+          "model_module": "@jupyter-widgets/base",
+          "model_name": "LayoutModel",
+          "model_module_version": "1.2.0",
+          "state": {
+            "_view_name": "LayoutView",
+            "grid_template_rows": null,
+            "right": null,
+            "justify_content": null,
+            "_view_module": "@jupyter-widgets/base",
+            "overflow": null,
+            "_model_module_version": "1.2.0",
+            "_view_count": null,
+            "flex_flow": null,
+            "width": null,
+            "min_width": null,
+            "border": null,
+            "align_items": null,
+            "bottom": null,
+            "_model_module": "@jupyter-widgets/base",
+            "top": null,
+            "grid_column": null,
+            "overflow_y": null,
+            "overflow_x": null,
+            "grid_auto_flow": null,
+            "grid_area": null,
+            "grid_template_columns": null,
+            "flex": null,
+            "_model_name": "LayoutModel",
+            "justify_items": null,
+            "grid_row": null,
+            "max_height": null,
+            "align_content": null,
+            "visibility": null,
+            "align_self": null,
+            "height": null,
+            "min_height": null,
+            "padding": null,
+            "grid_auto_rows": null,
+            "grid_gap": null,
+            "max_width": null,
+            "order": null,
+            "_view_module_version": "1.2.0",
+            "grid_template_areas": null,
+            "object_position": null,
+            "object_fit": null,
+            "grid_auto_columns": null,
+            "margin": null,
+            "display": null,
+            "left": null
+          }
+        },
+        "e7785eaa157248c092127fbf795e9ead": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "ProgressStyleModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_view_name": "StyleView",
+            "_model_name": "ProgressStyleModel",
+            "description_width": "",
+            "_view_module": "@jupyter-widgets/base",
+            "_model_module_version": "1.5.0",
+            "_view_count": null,
+            "_view_module_version": "1.2.0",
+            "bar_color": null,
+            "_model_module": "@jupyter-widgets/controls"
+          }
+        },
+        "c31e0a9361be4ec69ac63c86ea153a6f": {
+          "model_module": "@jupyter-widgets/base",
+          "model_name": "LayoutModel",
+          "model_module_version": "1.2.0",
+          "state": {
+            "_view_name": "LayoutView",
+            "grid_template_rows": null,
+            "right": null,
+            "justify_content": null,
+            "_view_module": "@jupyter-widgets/base",
+            "overflow": null,
+            "_model_module_version": "1.2.0",
+            "_view_count": null,
+            "flex_flow": null,
+            "width": null,
+            "min_width": null,
+            "border": null,
+            "align_items": null,
+            "bottom": null,
+            "_model_module": "@jupyter-widgets/base",
+            "top": null,
+            "grid_column": null,
+            "overflow_y": null,
+            "overflow_x": null,
+            "grid_auto_flow": null,
+            "grid_area": null,
+            "grid_template_columns": null,
+            "flex": null,
+            "_model_name": "LayoutModel",
+            "justify_items": null,
+            "grid_row": null,
+            "max_height": null,
+            "align_content": null,
+            "visibility": null,
+            "align_self": null,
+            "height": null,
+            "min_height": null,
+            "padding": null,
+            "grid_auto_rows": null,
+            "grid_gap": null,
+            "max_width": null,
+            "order": null,
+            "_view_module_version": "1.2.0",
+            "grid_template_areas": null,
+            "object_position": null,
+            "object_fit": null,
+            "grid_auto_columns": null,
+            "margin": null,
+            "display": null,
+            "left": null
+          }
+        },
+        "ec8c8c3f9072409a8e9836afeb65f041": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "DescriptionStyleModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_view_name": "StyleView",
+            "_model_name": "DescriptionStyleModel",
+            "description_width": "",
+            "_view_module": "@jupyter-widgets/base",
+            "_model_module_version": "1.5.0",
+            "_view_count": null,
+            "_view_module_version": "1.2.0",
+            "_model_module": "@jupyter-widgets/controls"
+          }
+        },
+        "91bc7d27ce6140ebaa3cd794f99a68dd": {
+          "model_module": "@jupyter-widgets/base",
+          "model_name": "LayoutModel",
+          "model_module_version": "1.2.0",
+          "state": {
+            "_view_name": "LayoutView",
+            "grid_template_rows": null,
+            "right": null,
+            "justify_content": null,
+            "_view_module": "@jupyter-widgets/base",
+            "overflow": null,
+            "_model_module_version": "1.2.0",
+            "_view_count": null,
+            "flex_flow": null,
+            "width": null,
+            "min_width": null,
+            "border": null,
+            "align_items": null,
+            "bottom": null,
+            "_model_module": "@jupyter-widgets/base",
+            "top": null,
+            "grid_column": null,
+            "overflow_y": null,
+            "overflow_x": null,
+            "grid_auto_flow": null,
+            "grid_area": null,
+            "grid_template_columns": null,
+            "flex": null,
+            "_model_name": "LayoutModel",
+            "justify_items": null,
+            "grid_row": null,
+            "max_height": null,
+            "align_content": null,
+            "visibility": null,
+            "align_self": null,
+            "height": null,
+            "min_height": null,
+            "padding": null,
+            "grid_auto_rows": null,
+            "grid_gap": null,
+            "max_width": null,
+            "order": null,
+            "_view_module_version": "1.2.0",
+            "grid_template_areas": null,
+            "object_position": null,
+            "object_fit": null,
+            "grid_auto_columns": null,
+            "margin": null,
+            "display": null,
+            "left": null
+          }
+        },
+        "d0557237d0984ff58db01e08fe7f4843": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "HBoxModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_view_name": "HBoxView",
+            "_dom_classes": [],
+            "_model_name": "HBoxModel",
+            "_view_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_view_count": null,
+            "_view_module_version": "1.5.0",
+            "box_style": "",
+            "layout": "IPY_MODEL_80ece29af820447fbc0d19f94b4638f7",
+            "_model_module": "@jupyter-widgets/controls",
+            "children": [
+              "IPY_MODEL_2ffca3af2668441a863396ade910ba17",
+              "IPY_MODEL_472fb9183fb849b6a9bd9a502cf9a002",
+              "IPY_MODEL_50e92d86e74d42cc8452e8d37978087f"
+            ]
+          }
+        },
+        "80ece29af820447fbc0d19f94b4638f7": {
+          "model_module": "@jupyter-widgets/base",
+          "model_name": "LayoutModel",
+          "model_module_version": "1.2.0",
+          "state": {
+            "_view_name": "LayoutView",
+            "grid_template_rows": null,
+            "right": null,
+            "justify_content": null,
+            "_view_module": "@jupyter-widgets/base",
+            "overflow": null,
+            "_model_module_version": "1.2.0",
+            "_view_count": null,
+            "flex_flow": null,
+            "width": null,
+            "min_width": null,
+            "border": null,
+            "align_items": null,
+            "bottom": null,
+            "_model_module": "@jupyter-widgets/base",
+            "top": null,
+            "grid_column": null,
+            "overflow_y": null,
+            "overflow_x": null,
+            "grid_auto_flow": null,
+            "grid_area": null,
+            "grid_template_columns": null,
+            "flex": null,
+            "_model_name": "LayoutModel",
+            "justify_items": null,
+            "grid_row": null,
+            "max_height": null,
+            "align_content": null,
+            "visibility": null,
+            "align_self": null,
+            "height": null,
+            "min_height": null,
+            "padding": null,
+            "grid_auto_rows": null,
+            "grid_gap": null,
+            "max_width": null,
+            "order": null,
+            "_view_module_version": "1.2.0",
+            "grid_template_areas": null,
+            "object_position": null,
+            "object_fit": null,
+            "grid_auto_columns": null,
+            "margin": null,
+            "display": null,
+            "left": null
+          }
+        },
+        "2ffca3af2668441a863396ade910ba17": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "HTMLModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_view_name": "HTMLView",
+            "style": "IPY_MODEL_2b8c22730dc3428b9d8087d15e698dac",
+            "_dom_classes": [],
+            "description": "",
+            "_model_name": "HTMLModel",
+            "placeholder": "​",
+            "_view_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "value": "Clean file keras_metadata.pb: 100%",
+            "_view_count": null,
+            "_view_module_version": "1.5.0",
+            "description_tooltip": null,
+            "_model_module": "@jupyter-widgets/controls",
+            "layout": "IPY_MODEL_c59caab0525948de98277bcdab4f039a"
+          }
+        },
+        "472fb9183fb849b6a9bd9a502cf9a002": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "FloatProgressModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_view_name": "ProgressView",
+            "style": "IPY_MODEL_5d11cedff5784ded90b15383a782b9ad",
+            "_dom_classes": [],
+            "description": "",
+            "_model_name": "FloatProgressModel",
+            "bar_style": "success",
+            "max": 36792,
+            "_view_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "value": 36792,
+            "_view_count": null,
+            "_view_module_version": "1.5.0",
+            "orientation": "horizontal",
+            "min": 0,
+            "description_tooltip": null,
+            "_model_module": "@jupyter-widgets/controls",
+            "layout": "IPY_MODEL_fa8812f859fe4c45aff1335cf85be76a"
+          }
+        },
+        "50e92d86e74d42cc8452e8d37978087f": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "HTMLModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_view_name": "HTMLView",
+            "style": "IPY_MODEL_16d5e64960454ac8bf12d2fb5531662e",
+            "_dom_classes": [],
+            "description": "",
+            "_model_name": "HTMLModel",
+            "placeholder": "​",
+            "_view_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "value": " 35.9k/35.9k [00:01&lt;00:00, 34.0kB/s]",
+            "_view_count": null,
+            "_view_module_version": "1.5.0",
+            "description_tooltip": null,
+            "_model_module": "@jupyter-widgets/controls",
+            "layout": "IPY_MODEL_277c23308a354c26a24caae56b8c0200"
+          }
+        },
+        "2b8c22730dc3428b9d8087d15e698dac": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "DescriptionStyleModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_view_name": "StyleView",
+            "_model_name": "DescriptionStyleModel",
+            "description_width": "",
+            "_view_module": "@jupyter-widgets/base",
+            "_model_module_version": "1.5.0",
+            "_view_count": null,
+            "_view_module_version": "1.2.0",
+            "_model_module": "@jupyter-widgets/controls"
+          }
+        },
+        "c59caab0525948de98277bcdab4f039a": {
+          "model_module": "@jupyter-widgets/base",
+          "model_name": "LayoutModel",
+          "model_module_version": "1.2.0",
+          "state": {
+            "_view_name": "LayoutView",
+            "grid_template_rows": null,
+            "right": null,
+            "justify_content": null,
+            "_view_module": "@jupyter-widgets/base",
+            "overflow": null,
+            "_model_module_version": "1.2.0",
+            "_view_count": null,
+            "flex_flow": null,
+            "width": null,
+            "min_width": null,
+            "border": null,
+            "align_items": null,
+            "bottom": null,
+            "_model_module": "@jupyter-widgets/base",
+            "top": null,
+            "grid_column": null,
+            "overflow_y": null,
+            "overflow_x": null,
+            "grid_auto_flow": null,
+            "grid_area": null,
+            "grid_template_columns": null,
+            "flex": null,
+            "_model_name": "LayoutModel",
+            "justify_items": null,
+            "grid_row": null,
+            "max_height": null,
+            "align_content": null,
+            "visibility": null,
+            "align_self": null,
+            "height": null,
+            "min_height": null,
+            "padding": null,
+            "grid_auto_rows": null,
+            "grid_gap": null,
+            "max_width": null,
+            "order": null,
+            "_view_module_version": "1.2.0",
+            "grid_template_areas": null,
+            "object_position": null,
+            "object_fit": null,
+            "grid_auto_columns": null,
+            "margin": null,
+            "display": null,
+            "left": null
+          }
+        },
+        "5d11cedff5784ded90b15383a782b9ad": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "ProgressStyleModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_view_name": "StyleView",
+            "_model_name": "ProgressStyleModel",
+            "description_width": "",
+            "_view_module": "@jupyter-widgets/base",
+            "_model_module_version": "1.5.0",
+            "_view_count": null,
+            "_view_module_version": "1.2.0",
+            "bar_color": null,
+            "_model_module": "@jupyter-widgets/controls"
+          }
+        },
+        "fa8812f859fe4c45aff1335cf85be76a": {
+          "model_module": "@jupyter-widgets/base",
+          "model_name": "LayoutModel",
+          "model_module_version": "1.2.0",
+          "state": {
+            "_view_name": "LayoutView",
+            "grid_template_rows": null,
+            "right": null,
+            "justify_content": null,
+            "_view_module": "@jupyter-widgets/base",
+            "overflow": null,
+            "_model_module_version": "1.2.0",
+            "_view_count": null,
+            "flex_flow": null,
+            "width": null,
+            "min_width": null,
+            "border": null,
+            "align_items": null,
+            "bottom": null,
+            "_model_module": "@jupyter-widgets/base",
+            "top": null,
+            "grid_column": null,
+            "overflow_y": null,
+            "overflow_x": null,
+            "grid_auto_flow": null,
+            "grid_area": null,
+            "grid_template_columns": null,
+            "flex": null,
+            "_model_name": "LayoutModel",
+            "justify_items": null,
+            "grid_row": null,
+            "max_height": null,
+            "align_content": null,
+            "visibility": null,
+            "align_self": null,
+            "height": null,
+            "min_height": null,
+            "padding": null,
+            "grid_auto_rows": null,
+            "grid_gap": null,
+            "max_width": null,
+            "order": null,
+            "_view_module_version": "1.2.0",
+            "grid_template_areas": null,
+            "object_position": null,
+            "object_fit": null,
+            "grid_auto_columns": null,
+            "margin": null,
+            "display": null,
+            "left": null
+          }
+        },
+        "16d5e64960454ac8bf12d2fb5531662e": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "DescriptionStyleModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_view_name": "StyleView",
+            "_model_name": "DescriptionStyleModel",
+            "description_width": "",
+            "_view_module": "@jupyter-widgets/base",
+            "_model_module_version": "1.5.0",
+            "_view_count": null,
+            "_view_module_version": "1.2.0",
+            "_model_module": "@jupyter-widgets/controls"
+          }
+        },
+        "277c23308a354c26a24caae56b8c0200": {
+          "model_module": "@jupyter-widgets/base",
+          "model_name": "LayoutModel",
+          "model_module_version": "1.2.0",
+          "state": {
+            "_view_name": "LayoutView",
+            "grid_template_rows": null,
+            "right": null,
+            "justify_content": null,
+            "_view_module": "@jupyter-widgets/base",
+            "overflow": null,
+            "_model_module_version": "1.2.0",
+            "_view_count": null,
+            "flex_flow": null,
+            "width": null,
+            "min_width": null,
+            "border": null,
+            "align_items": null,
+            "bottom": null,
+            "_model_module": "@jupyter-widgets/base",
+            "top": null,
+            "grid_column": null,
+            "overflow_y": null,
+            "overflow_x": null,
+            "grid_auto_flow": null,
+            "grid_area": null,
+            "grid_template_columns": null,
+            "flex": null,
+            "_model_name": "LayoutModel",
+            "justify_items": null,
+            "grid_row": null,
+            "max_height": null,
+            "align_content": null,
+            "visibility": null,
+            "align_self": null,
+            "height": null,
+            "min_height": null,
+            "padding": null,
+            "grid_auto_rows": null,
+            "grid_gap": null,
+            "max_width": null,
+            "order": null,
+            "_view_module_version": "1.2.0",
+            "grid_template_areas": null,
+            "object_position": null,
+            "object_fit": null,
+            "grid_auto_columns": null,
+            "margin": null,
+            "display": null,
+            "left": null
+          }
+        },
+        "ec063e2465c24cbbb2c2aba12b489258": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "HBoxModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_view_name": "HBoxView",
+            "_dom_classes": [],
+            "_model_name": "HBoxModel",
+            "_view_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_view_count": null,
+            "_view_module_version": "1.5.0",
+            "box_style": "",
+            "layout": "IPY_MODEL_bdb9eb8e834043b6baf8d95d75ed372a",
+            "_model_module": "@jupyter-widgets/controls",
+            "children": [
+              "IPY_MODEL_cbd69a8c8fb04e7abc347cb8a855b73b",
+              "IPY_MODEL_cbb844064dd74e1aad7318ca6320e959",
+              "IPY_MODEL_9b090c77a53d45a19b1f9842c8fac8ed"
+            ]
+          }
+        },
+        "bdb9eb8e834043b6baf8d95d75ed372a": {
+          "model_module": "@jupyter-widgets/base",
+          "model_name": "LayoutModel",
+          "model_module_version": "1.2.0",
+          "state": {
+            "_view_name": "LayoutView",
+            "grid_template_rows": null,
+            "right": null,
+            "justify_content": null,
+            "_view_module": "@jupyter-widgets/base",
+            "overflow": null,
+            "_model_module_version": "1.2.0",
+            "_view_count": null,
+            "flex_flow": null,
+            "width": null,
+            "min_width": null,
+            "border": null,
+            "align_items": null,
+            "bottom": null,
+            "_model_module": "@jupyter-widgets/base",
+            "top": null,
+            "grid_column": null,
+            "overflow_y": null,
+            "overflow_x": null,
+            "grid_auto_flow": null,
+            "grid_area": null,
+            "grid_template_columns": null,
+            "flex": null,
+            "_model_name": "LayoutModel",
+            "justify_items": null,
+            "grid_row": null,
+            "max_height": null,
+            "align_content": null,
+            "visibility": null,
+            "align_self": null,
+            "height": null,
+            "min_height": null,
+            "padding": null,
+            "grid_auto_rows": null,
+            "grid_gap": null,
+            "max_width": null,
+            "order": null,
+            "_view_module_version": "1.2.0",
+            "grid_template_areas": null,
+            "object_position": null,
+            "object_fit": null,
+            "grid_auto_columns": null,
+            "margin": null,
+            "display": null,
+            "left": null
+          }
+        },
+        "cbd69a8c8fb04e7abc347cb8a855b73b": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "HTMLModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_view_name": "HTMLView",
+            "style": "IPY_MODEL_b3c9122465ea441f8320e037f0c83e31",
+            "_dom_classes": [],
+            "description": "",
+            "_model_name": "HTMLModel",
+            "placeholder": "​",
+            "_view_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "value": "Upload file saved_model.pb: 100%",
+            "_view_count": null,
+            "_view_module_version": "1.5.0",
+            "description_tooltip": null,
+            "_model_module": "@jupyter-widgets/controls",
+            "layout": "IPY_MODEL_af01adda7adc4e68b3785ce8b6a41036"
+          }
+        },
+        "cbb844064dd74e1aad7318ca6320e959": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "FloatProgressModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_view_name": "ProgressView",
+            "style": "IPY_MODEL_91611d3294fd4dfc8efac97843aab9ff",
+            "_dom_classes": [],
+            "description": "",
+            "_model_name": "FloatProgressModel",
+            "bar_style": "success",
+            "max": 4904275,
+            "_view_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "value": 4904275,
+            "_view_count": null,
+            "_view_module_version": "1.5.0",
+            "orientation": "horizontal",
+            "min": 0,
+            "description_tooltip": null,
+            "_model_module": "@jupyter-widgets/controls",
+            "layout": "IPY_MODEL_d6f241185c4243c5980036efbbdccd05"
+          }
+        },
+        "9b090c77a53d45a19b1f9842c8fac8ed": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "HTMLModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_view_name": "HTMLView",
+            "style": "IPY_MODEL_5727b4324c44423fa259b16360da0d73",
+            "_dom_classes": [],
+            "description": "",
+            "_model_name": "HTMLModel",
+            "placeholder": "​",
+            "_view_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "value": " 4.68M/4.68M [00:03&lt;00:00, 1.75MB/s]",
+            "_view_count": null,
+            "_view_module_version": "1.5.0",
+            "description_tooltip": null,
+            "_model_module": "@jupyter-widgets/controls",
+            "layout": "IPY_MODEL_8e581a2bd3a44195ba98b6f77461716e"
+          }
+        },
+        "b3c9122465ea441f8320e037f0c83e31": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "DescriptionStyleModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_view_name": "StyleView",
+            "_model_name": "DescriptionStyleModel",
+            "description_width": "",
+            "_view_module": "@jupyter-widgets/base",
+            "_model_module_version": "1.5.0",
+            "_view_count": null,
+            "_view_module_version": "1.2.0",
+            "_model_module": "@jupyter-widgets/controls"
+          }
+        },
+        "af01adda7adc4e68b3785ce8b6a41036": {
+          "model_module": "@jupyter-widgets/base",
+          "model_name": "LayoutModel",
+          "model_module_version": "1.2.0",
+          "state": {
+            "_view_name": "LayoutView",
+            "grid_template_rows": null,
+            "right": null,
+            "justify_content": null,
+            "_view_module": "@jupyter-widgets/base",
+            "overflow": null,
+            "_model_module_version": "1.2.0",
+            "_view_count": null,
+            "flex_flow": null,
+            "width": null,
+            "min_width": null,
+            "border": null,
+            "align_items": null,
+            "bottom": null,
+            "_model_module": "@jupyter-widgets/base",
+            "top": null,
+            "grid_column": null,
+            "overflow_y": null,
+            "overflow_x": null,
+            "grid_auto_flow": null,
+            "grid_area": null,
+            "grid_template_columns": null,
+            "flex": null,
+            "_model_name": "LayoutModel",
+            "justify_items": null,
+            "grid_row": null,
+            "max_height": null,
+            "align_content": null,
+            "visibility": null,
+            "align_self": null,
+            "height": null,
+            "min_height": null,
+            "padding": null,
+            "grid_auto_rows": null,
+            "grid_gap": null,
+            "max_width": null,
+            "order": null,
+            "_view_module_version": "1.2.0",
+            "grid_template_areas": null,
+            "object_position": null,
+            "object_fit": null,
+            "grid_auto_columns": null,
+            "margin": null,
+            "display": null,
+            "left": null
+          }
+        },
+        "91611d3294fd4dfc8efac97843aab9ff": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "ProgressStyleModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_view_name": "StyleView",
+            "_model_name": "ProgressStyleModel",
+            "description_width": "",
+            "_view_module": "@jupyter-widgets/base",
+            "_model_module_version": "1.5.0",
+            "_view_count": null,
+            "_view_module_version": "1.2.0",
+            "bar_color": null,
+            "_model_module": "@jupyter-widgets/controls"
+          }
+        },
+        "d6f241185c4243c5980036efbbdccd05": {
+          "model_module": "@jupyter-widgets/base",
+          "model_name": "LayoutModel",
+          "model_module_version": "1.2.0",
+          "state": {
+            "_view_name": "LayoutView",
+            "grid_template_rows": null,
+            "right": null,
+            "justify_content": null,
+            "_view_module": "@jupyter-widgets/base",
+            "overflow": null,
+            "_model_module_version": "1.2.0",
+            "_view_count": null,
+            "flex_flow": null,
+            "width": null,
+            "min_width": null,
+            "border": null,
+            "align_items": null,
+            "bottom": null,
+            "_model_module": "@jupyter-widgets/base",
+            "top": null,
+            "grid_column": null,
+            "overflow_y": null,
+            "overflow_x": null,
+            "grid_auto_flow": null,
+            "grid_area": null,
+            "grid_template_columns": null,
+            "flex": null,
+            "_model_name": "LayoutModel",
+            "justify_items": null,
+            "grid_row": null,
+            "max_height": null,
+            "align_content": null,
+            "visibility": null,
+            "align_self": null,
+            "height": null,
+            "min_height": null,
+            "padding": null,
+            "grid_auto_rows": null,
+            "grid_gap": null,
+            "max_width": null,
+            "order": null,
+            "_view_module_version": "1.2.0",
+            "grid_template_areas": null,
+            "object_position": null,
+            "object_fit": null,
+            "grid_auto_columns": null,
+            "margin": null,
+            "display": null,
+            "left": null
+          }
+        },
+        "5727b4324c44423fa259b16360da0d73": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "DescriptionStyleModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_view_name": "StyleView",
+            "_model_name": "DescriptionStyleModel",
+            "description_width": "",
+            "_view_module": "@jupyter-widgets/base",
+            "_model_module_version": "1.5.0",
+            "_view_count": null,
+            "_view_module_version": "1.2.0",
+            "_model_module": "@jupyter-widgets/controls"
+          }
+        },
+        "8e581a2bd3a44195ba98b6f77461716e": {
+          "model_module": "@jupyter-widgets/base",
+          "model_name": "LayoutModel",
+          "model_module_version": "1.2.0",
+          "state": {
+            "_view_name": "LayoutView",
+            "grid_template_rows": null,
+            "right": null,
+            "justify_content": null,
+            "_view_module": "@jupyter-widgets/base",
+            "overflow": null,
+            "_model_module_version": "1.2.0",
+            "_view_count": null,
+            "flex_flow": null,
+            "width": null,
+            "min_width": null,
+            "border": null,
+            "align_items": null,
+            "bottom": null,
+            "_model_module": "@jupyter-widgets/base",
+            "top": null,
+            "grid_column": null,
+            "overflow_y": null,
+            "overflow_x": null,
+            "grid_auto_flow": null,
+            "grid_area": null,
+            "grid_template_columns": null,
+            "flex": null,
+            "_model_name": "LayoutModel",
+            "justify_items": null,
+            "grid_row": null,
+            "max_height": null,
+            "align_content": null,
+            "visibility": null,
+            "align_self": null,
+            "height": null,
+            "min_height": null,
+            "padding": null,
+            "grid_auto_rows": null,
+            "grid_gap": null,
+            "max_width": null,
+            "order": null,
+            "_view_module_version": "1.2.0",
+            "grid_template_areas": null,
+            "object_position": null,
+            "object_fit": null,
+            "grid_auto_columns": null,
+            "margin": null,
+            "display": null,
+            "left": null
+          }
+        }
+      }
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 0
+}
\ No newline at end of file