{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Computer Vision models zoo"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "hide_input": true
   },
   "outputs": [],
   "source": [
    "from fastai.gen_doc.nbdoc import *\n",
    "from fastai.vision.models.darknet import Darknet\n",
    "from fastai.vision.models.wrn import wrn_22, WideResNet"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "On top of the models offered by [torchivision](https://pytorch.org/docs/stable/torchvision/models.html), the fastai library has implementations for the following models:\n",
    "\n",
    "- Darknet architecture, which is the base of [Yolo v3](https://pjreddie.com/media/files/papers/YOLOv3.pdf)\n",
    "- Unet architecture based on a pretrained model. The original unet is described [here](https://arxiv.org/abs/1505.04597), the model implementation is detailed in [`models.unet`](/vision.models.unet.html#vision.models.unet)\n",
    "- Wide resnets architectures, as introduced in [this article](https://arxiv.org/abs/1605.07146)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "hide_input": true
   },
   "outputs": [
    {
     "data": {
      "text/markdown": [
       "<h2 id=\"Darknet\"><code>class</code> <code>Darknet</code><a href=\"https://github.com/fastai/fastai/blob/master/fastai/vision/models/darknet.py#L16\" class=\"source_link\">[source]</a></h2>\n",
       "\n",
       "> <code>Darknet</code>(`num_blocks`:`Collection`\\[`int`\\], `num_classes`:`int`, `nf`=`32`) :: [`Module`](https://pytorch.org/docs/stable/nn.html#torch.nn.Module)"
      ],
      "text/plain": [
       "<IPython.core.display.Markdown object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "show_doc(Darknet, doc_string=False)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Create a Darknet with blocks of sizes given in `num_blocks`, ending with `num_classes` and using `nf` initial features. Darknet53 uses `num_blocks = [1,2,8,8,4]`. "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "hide_input": true
   },
   "outputs": [
    {
     "data": {
      "text/markdown": [
       "<h2 id=\"WideResNet\"><code>class</code> <code>WideResNet</code><a href=\"https://github.com/fastai/fastai/blob/master/fastai/vision/models/wrn.py#L37\" class=\"source_link\">[source]</a></h2>\n",
       "\n",
       "> <code>WideResNet</code>(`num_groups`:`int`, `N`:`int`, `num_classes`:`int`, `k`:`int`=`1`, `drop_p`:`float`=`0.0`, `start_nf`:`int`=`16`) :: [`Module`](https://pytorch.org/docs/stable/nn.html#torch.nn.Module)"
      ],
      "text/plain": [
       "<IPython.core.display.Markdown object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "show_doc(WideResNet, doc_string=False)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Create a wide resnet with blocks `num_groups` groups, each containing blocks of size `N`. `k` is the width of the resnet, `start_nf` the initial number of features. Dropout of `drop_p` is applied at the end of each block."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "hide_input": true
   },
   "outputs": [
    {
     "data": {
      "text/markdown": [
       "<h4 id=\"wrn_22\"><code>wrn_22</code><a href=\"https://github.com/fastai/fastai/blob/master/fastai/vision/models/wrn.py#L54\" class=\"source_link\">[source]</a></h4>\n",
       "\n",
       "> <code>wrn_22</code>()"
      ],
      "text/plain": [
       "<IPython.core.display.Markdown object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "show_doc(wrn_22)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Creates a wide resnet for CIFAR-10 with `num_groups=3`, `N=3`, `k=6` and `drop_p=0.`."
   ]
  }
 ],
 "metadata": {
  "jekyll": {
   "keywords": "fastai",
   "summary": "Overview of the models used for CV in fastai",
   "title": "vision.models"
  },
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}