pix2pix-for-roman2italic.ipynb

pix2pix-for-roman2italic.ipynb

{
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "view-in-github",
        "colab_type": "text"
      },
      "source": [
        "<a href=\"https://colab.research.google.com/gist/celestialphineas/859b87fe082b078d71811d1b5b64b3bc/pix2pix-for-roman2italic.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "7wNjDKdQy35h"
      },
      "source": [
        "# Install"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "TRm-USlsHgEV"
      },
      "outputs": [],
      "source": [
        "!git clone https://github.com/junyanz/pytorch-CycleGAN-and-pix2pix"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 3,
      "metadata": {
        "id": "Pt3igws3eiVp"
      },
      "outputs": [],
      "source": [
        "import os\n",
        "os.chdir('pytorch-CycleGAN-and-pix2pix/')"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "z1EySlOXwwoa"
      },
      "outputs": [],
      "source": [
        "!pip install -r requirements.txt"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "8daqlgVhw29P"
      },
      "source": [
        "# Datasets\n",
        "\n",
        "Download one of the official datasets with:\n",
        "\n",
        "-   `bash ./datasets/download_pix2pix_dataset.sh [cityscapes, night2day, edges2handbags, edges2shoes, facades, maps]`\n",
        "\n",
        "Or use your own dataset by creating the appropriate folders and adding in the images. Follow the instructions [here](https://github.com/junyanz/pytorch-CycleGAN-and-pix2pix/blob/master/docs/datasets.md#pix2pix-datasets)."
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "vrdOettJxaCc"
      },
      "outputs": [],
      "source": [
        "!wget https://github.com/celestialphineas/misc/releases/download/v0.0.1/roman2ital.zip -P ./datasets\n",
        "!(cd datasets && unzip -q roman2ital.zip)"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "yFw1kDQBx3LN"
      },
      "source": [
        "# Training\n",
        "\n",
        "-   `python train.py --dataroot ./datasets/facades --name facades_pix2pix --model pix2pix --direction BtoA`\n",
        "\n",
        "Change the `--dataroot` and `--name` to your own dataset's path and model's name. Use `--gpu_ids 0,1,..` to train on multiple GPUs and `--batch_size` to change the batch size. Add `--direction BtoA` if you want to train a model to transfrom from class B to A."
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "0sp7TCT2x9dB"
      },
      "outputs": [],
      "source": [
        "!python train.py --dataroot ./datasets/roman2ital --name roman2ital --model pix2pix\\\n",
        "  --use_wandb\\\n",
        "  --input_nc 3 --output_nc 3\\\n",
        "  --direction AtoB --load_size 256 --no_flip"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "9UkcaFZiyASl"
      },
      "source": [
        "# Testing\n",
        "\n",
        "-   `python test.py --dataroot ./datasets/facades --direction BtoA --model pix2pix --name facades_pix2pix`\n",
        "\n",
        "Change the `--dataroot`, `--name`, and `--direction` to be consistent with your trained model's configuration and how you want to transform images.\n",
        "\n",
        "> from https://github.com/junyanz/pytorch-CycleGAN-and-pix2pix:\n",
        "> Note that we specified --direction BtoA as Facades dataset's A to B direction is photos to labels.\n",
        "\n",
        "> If you would like to apply a pre-trained model to a collection of input images (rather than image pairs), please use --model test option. See ./scripts/test_single.sh for how to apply a model to Facade label maps (stored in the directory facades/testB).\n",
        "\n",
        "> See a list of currently available models at ./scripts/download_pix2pix_model.sh\n",
        "\n",
        "### **Note that we didn't provide test data for roman2ital.**"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "mey7o6j-0368"
      },
      "outputs": [],
      "source": [
        "!ls checkpoints/"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "uCsKkEq0yGh0"
      },
      "outputs": [],
      "source": [
        "!python test.py --dataroot ./datasets/roman2ital --direction AtoB --model pix2pix --name AtoB --use_wandb"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "OzSKIPUByfiN"
      },
      "source": [
        "# Visualize"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "9Mgg8raPyizq"
      },
      "outputs": [],
      "source": [
        "import matplotlib.pyplot as plt\n",
        "\n",
        "# img = plt.imread('./results/roman2ital/test_latest/images/xxxxxx_fake_B.png')\n",
        "# plt.imshow(img)"
      ]
    }
  ],
  "metadata": {
    "accelerator": "GPU",
    "colab": {
      "collapsed_sections": [],
      "provenance": [],
      "include_colab_link": true
    },
    "environment": {
      "name": "tf2-gpu.2-3.m74",
      "type": "gcloud",
      "uri": "gcr.io/deeplearning-platform-release/tf2-gpu.2-3:m74"
    },
    "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": "3.7.10"
    }
  },
  "nbformat": 4,
  "nbformat_minor": 0
}