From bae522ba61d217ae5dd585511d331b393a22d17d Mon Sep 17 00:00:00 2001 From: nawnie <106923464+nawnie@users.noreply.github.com> Date: Sun, 11 Dec 2022 13:13:38 -0600 Subject: [PATCH] Other Scripts added to cells --- EveryDream_Tools.ipynb | 372 +++++++++++++++++++++++++++++++++++++++++ 1 file changed, 372 insertions(+) create mode 100644 EveryDream_Tools.ipynb diff --git a/EveryDream_Tools.ipynb b/EveryDream_Tools.ipynb new file mode 100644 index 0000000..d2114b2 --- /dev/null +++ b/EveryDream_Tools.ipynb @@ -0,0 +1,372 @@ +{ + "cells": [ + { + "cell_type": "markdown", + "metadata": { + "id": "view-in-github", + "colab_type": "text" + }, + "source": [ + "\"Open" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "uJfwih4wAVgw" + }, + "source": [ + "# Please read the documentation here before you start.\n", + "\n", + "I suggest reading this doc before you connect to your runtime to avoid using credits or being charged while you figure it out.\n", + "\n", + "[Auto Captioning Readme](doc/AUTO_CAPTION.md)\n", + "\n", + "This notebook requires an Nvidia GPU instance. Any will do, you don't need anything power. As low as 4GB should be fine.\n", + "\n", + "Only colab has automatic file transfers at this time. If you are using another platform, you will need to manually download your output files." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "lWGx2LuU8Q_I" + }, + "outputs": [], + "source": [ + "#download repo\n", + "!git clone https://github.com/victorchall/EveryDream.git\n", + "# Set working directory\n", + "%cd EveryDream" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "RJxfSai-8pkD" + }, + "outputs": [], + "source": [ + "# install requirements\n", + "!pip install torch=='1.12.1+cu113' 'torchvision==0.13.1+cu113' --extra-index-url https://download.pytorch.org/whl/cu113\n", + "!pip install pandas>='1.3.5'\n", + "!git clone https://github.com/salesforce/BLIP scripts/BLIP\n", + "!pip install timm\n", + "!pip install fairscale=='0.4.4'\n", + "!pip install transformers=='4.19.2'\n", + "!pip install timm\n", + "!pip install aiofiles" + ] + }, + { + "cell_type": "markdown", + "source": [ + "#Extract Frames from video\n", + "\n", + "Here we will use the folder input_vid and upload in the same way we did our images" + ], + "metadata": { + "id": "huQSI8Y-Bboz" + } + }, + { + "cell_type": "code", + "source": [ + "!python /scripts/extract_video_frames.py \\\n", + "--vid_dir input_vid \\\n", + "--out_dir output/vid \\\n", + "--format png \\\n", + "--interval 10 " + ], + "metadata": { + "id": "RDuBL4k8Avz-" + }, + "execution_count": null, + "outputs": [] + }, + { + "cell_type": "markdown", + "source": [ + "Move the extracted frames to the input directory for captions" + ], + "metadata": { + "id": "iqcUzcRuCTLR" + } + }, + { + "cell_type": "code", + "source": [ + "!cp -r output/vid input" + ], + "metadata": { + "id": "Uv8wAHSQAvrm" + }, + "execution_count": null, + "outputs": [] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "sbeUIVXJ-EVf" + }, + "source": [ + "# Upload your input images into the EveryDream/input folder\n", + "\n", + "![upload to input](https://github.com/victorchall/EveryDream/blob/main/demo/upload_images_caption.png?raw=1)" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "bscWH13SAVgz" + }, + "source": [ + "## Please read the documentation for information on the parameters\n", + "\n", + "[Auto Captioning](doc/AUTO_CAPTION.md)\n", + "\n", + "*You cannot have commented lines between uncommented lines. If you uncomment a line below, move it above any other commented lines.*\n", + "\n", + "*!python must remain the first line.*\n", + "\n", + "Default params should work fairly well." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "4TAICahl-RPn" + }, + "outputs": [], + "source": [ + "!python scripts/auto_caption.py \\\n", + "--img_dir input \\\n", + "--out_dir output \\\n", + "#--format mrwho \\\n", + "#--min_length 34 \\\n", + "#--q_factor 1.3 \\\n", + "#--nucleus \\\n", + "\n", + "## mutiple files can be targeted in succession\n", + "\n", + "#!python scripts/auto_caption.py \\\n", + "#--img_dir input/subfolder \\\n", + "#--out_dir output/subfolder \\\n", + "#--format mrwho \\\n", + "#--min_length 34 \\\n", + "#--q_factor 1.3 \\\n", + "#--nucleus \\" + ] + }, + { + "cell_type": "markdown", + "source": [ + "# Laion Downloader\n", + "\n", + "* --laion_dir: directory with laion parquet files, default is ./laion\n", + "\n", + "* --search_text: csv of words with AND logic, ex \\\"photo,man,dog\\\"\n", + "\n", + "* --out_dir: directory to download files to, ive defaulted this to inputs so they can be captioned \n", + "\n", + "* --log_dir: directory for logs, if ommitted will not log, logs may be large!\n", + "\n", + "* --column:column to search for matches, defaults is 'TEXT', but you could use 'URL' if you wanted\",\n", + "\n", + "* --limit: max number of matching images to download, warning: may be slightly imprecise due to concurrency and http errors, defaults is 100\n", + "\n", + "* --min_hw: min height AND width of image to download, default is 512\n", + " \n", + "* --force: forces a full download of all images, even if no search is provided, USE CAUTION!\n", + "\n", + "* --parquet_skip: skips the first n parquet files on disk, useful to resume\n", + " \n", + "* --verbose: additional logging of URL and TEXT \n", + " \n", + "* --test: skips downloading, for checking filters, use with \"--verbose\"\n" + ], + "metadata": { + "id": "wY2f2LkPGSVa" + } + }, + { + "cell_type": "code", + "source": [ + "!python scripts/download_laion.py \\\n", + "--laion_dir ./laion \\\n", + "--search_text \"photo,man,dog\" \\\n", + "#--out_dir input \\\n", + "#--log_dir logs \\\n", + "#--column TEXT \\\n", + "#--limit 100 \\\n", + "#--min_hw 512 \\\n", + "#--force False \\\n", + "#--parquet_skip 0 \\\n", + "#--Verbose False \\\n", + "#--test not \\\n" + ], + "metadata": { + "id": "cxw60TTmEy2C" + }, + "execution_count": null, + "outputs": [] + }, + { + "cell_type": "markdown", + "source": [ + "Here we can take our now captioned images and replace generic terms with our subjects\n", + "\n", + "* --find: will search for a word in this case man\n", + "\n", + "* --replace: will replace our found word with in this case VictorChall\n", + "\n", + "* --append_only: this will allow us to add a tag at he end " + ], + "metadata": { + "id": "EBdLelNpDjYc" + } + }, + { + "cell_type": "code", + "source": [ + "!python scripts/filename_replace.py \\\n", + "--img_dir output \\\n", + "--find \"man\" \\\n", + "--replace \"VictorChall\"" + ], + "metadata": { + "id": "6Y1md3OHAvhw" + }, + "execution_count": null, + "outputs": [] + }, + { + "cell_type": "markdown", + "source": [ + "Now we can chose to create text files based on our file names, this is usefull for images with very long discriptions or tag list, windows has a limit of 256 characters, and files will not transfer correctly to a windows program if they are longer, moving these files in a zip is fine however and causes no issues\n" + ], + "metadata": { + "id": "W0MspWmXJQuc" + } + }, + { + "cell_type": "code", + "source": [ + "!python scripts/createtxtfromfilename.py" + ], + "metadata": { + "id": "BpvenvyQJr9b" + }, + "execution_count": null, + "outputs": [] + }, + { + "cell_type": "markdown", + "source": [ + "Compress our images " + ], + "metadata": { + "id": "boVkDsiWJ_-P" + } + }, + { + "cell_type": "code", + "source": [ + "/content/EveryDream/scripts/compress_img.py \\\n", + "--img_dir output \\\n", + "--out_dir output/compressed_images \\\n", + "--max_mp 1.5 \n", + "#--overwrite False \\\n", + "#--Quality 95 \\\n", + "#--noresize False \\\n", + "#--delete \\" + ], + "metadata": { + "id": "F6QYfylhKAII" + }, + "execution_count": null, + "outputs": [] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "HBrWnu1C_lN9" + }, + "source": [ + "## Download your DataSet from EveryDream/output\n", + "\n", + "If you're on a colab you can use the cell below to push your output to your Gdrive." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "ldW2sDLcAVgz" + }, + "outputs": [], + "source": [ + "from google.colab import drive\n", + "drive.mount('/content/drive')\n", + "\n", + "!mkdir /content/drive/MyDrive/Auto_Data_sets\n", + "!cp -r output/ /content/drive/MyDrive/Auto_Data_sets" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "B-HFqbP4AVgz" + }, + "source": [ + "## If not on colab/gdrive, the following will zip up your files for extraction\n", + "\n", + "You'll still need to use your runtime's own download feature to download the zip.\n", + "\n", + "![output zip](https://github.com/victorchall/EveryDream/blob/main/demo/output_zip.png?raw=1)" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "SVa80mrKAVg0" + }, + "outputs": [], + "source": [ + "!pip install patool\n", + "\n", + "import patoolib\n", + "\n", + "!mkdir output/zip\n", + "\n", + "!zip -r output/zip/output.zip output" + ] + } + ], + "metadata": { + "colab": { + "provenance": [], + "include_colab_link": true + }, + "kernelspec": { + "display_name": "Python 3.10.5 ('.venv': venv)", + "language": "python", + "name": "python3" + }, + "language_info": { + "name": "python", + "version": "3.10.5" + }, + "vscode": { + "interpreter": { + "hash": "faf4a6abb601e3a9195ce3e9620411ceec233a951446de834cdf28542d2d93b4" + } + } + }, + "nbformat": 4, + "nbformat_minor": 0 +} \ No newline at end of file