{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "6312daad",
   "metadata": {},
   "source": [
    "# variational-autoencoders"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "ba0c701f",
   "metadata": {},
   "source": [
    "A model skeleton for Variational Auto-Encoders (VAE). It was first introduced in the paper titled *[Auto-Encoding Variational Bayes]*(https://arxiv.org/abs/1312.6114) by Diederik P Kingma and Max Welling."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "a6ddd815",
   "metadata": {},
   "source": [
    "> In machine learning, a variational autoencoder, also known as VAE, is the artificial neural network architecture belonging to the families of probabilistic graphical models and variational Bayesian methods.\n",
    "\n",
    "> It is often associated with the autoencoder model because of its architectural affinity, but there are significant differences both in the goal and in the mathematical formulation. Variational autoencoders are meant to compress the input information into a constrained multivariate latent distribution (encoding) to reconstruct it as accurately as possible (decoding). Although this type of model was initially designed for unsupervised learning, its effectiveness has been proven in other domains of machine learning such as semi-supervised learning or supervised learning. - *WikiPedia*"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "de7b27bc",
   "metadata": {},
   "outputs": [],
   "source": [
    "%load_ext autoreload\n",
    "%autoreload"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "1753d7e2",
   "metadata": {},
   "source": [
    "## usage"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "af3b496b",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2022-01-03T21:33:05.773384Z",
     "iopub.status.busy": "2022-01-03T21:33:05.772674Z",
     "iopub.status.idle": "2022-01-03T21:33:28.873989Z",
     "shell.execute_reply": "2022-01-03T21:33:28.874242Z"
    },
    "scrolled": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "type <class 'type'>\n"
     ]
    },
    {
     "ename": "TypeError",
     "evalue": "isinstance expected 2 arguments, got 1",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mTypeError\u001b[0m                                 Traceback (most recent call last)",
      "\u001b[0;32m<ipython-input-2-2d5d37d7540f>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[1;32m      1\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mdeeply\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      2\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 3\u001b[0;31m \u001b[0mvae\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mdeeply\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mhub\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"convolutional-variational-autoencoder\"\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mx\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;36m28\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m      4\u001b[0m \u001b[0mvae\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mplot\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/dev/deeply/src/deeply/deeply.py\u001b[0m in \u001b[0;36mhub\u001b[0;34m(name, *args, **kwargs)\u001b[0m\n\u001b[1;32m     11\u001b[0m     \u001b[0;31m#     kwargs[\"weights\"]     = kwargs.get(\"weights\", DEFAULT[\"weights\"])\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     12\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 13\u001b[0;31m     \u001b[0mmodel\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mModelFactory\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mget\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mname\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m     14\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     15\u001b[0m     \u001b[0;32mreturn\u001b[0m \u001b[0mmodel\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/dev/deeply/src/deeply/model/factory.py\u001b[0m in \u001b[0;36mget\u001b[0;34m(name, *args, **kwargs)\u001b[0m\n\u001b[1;32m     25\u001b[0m         \u001b[0mmodel_class\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mmodel\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m\"model_class\"\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     26\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 27\u001b[0;31m         \u001b[0;32mreturn\u001b[0m \u001b[0mmodel_class\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
      "\u001b[0;32m~/dev/deeply/src/deeply/model/vae.py\u001b[0m in \u001b[0;36mConvolutionalVAE\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m    584\u001b[0m     \u001b[0;34m>>\u001b[0m\u001b[0;34m>\u001b[0m \u001b[0mmodel\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mdeeply\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mhub\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"convolutional-variational-autoencoder\"\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    585\u001b[0m     \"\"\"\n\u001b[0;32m--> 586\u001b[0;31m     model = VAE(\n\u001b[0m\u001b[1;32m    587\u001b[0m         \u001b[0mname\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m\"convolutional-vae\"\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    588\u001b[0m         \u001b[0mlayer_block\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mConvBlock\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/dev/deeply/src/deeply/model/vae.py\u001b[0m in \u001b[0;36mVAE\u001b[0;34m(x, y, channels, init_units, layer_growth_rate, layer_depth, n_dense, latent_dim, activation, batch_norm, dropout_rate, final_activation, kernel_initializer, name, backbone, backbone_weights, weights, layer_block, kernel_size, strides, n_classes, padding, final_conv_size, final_unit_size, attention_gate, freeze_backbone, *args, **kwargs)\u001b[0m\n\u001b[1;32m    302\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    303\u001b[0m     \u001b[0mprint\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"type\"\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mtype\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mlayer_block\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 304\u001b[0;31m     \u001b[0mprint\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0misinstance\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mlayer_block\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    305\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    306\u001b[0m     layer_block_args = dict(activation = activation, dropout_rate = dropout_rate, width = n_dense,\n",
      "\u001b[0;31mTypeError\u001b[0m: isinstance expected 2 arguments, got 1"
     ]
    }
   ],
   "source": [
    "import deeply\n",
    "\n",
    "vae = deeply.hub(\"convolutional-variational-autoencoder\", x = 28)\n",
    "vae.plot()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "59c60b6a",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "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": "3.8.9"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}