ISD Stable Diff

{
  "cells": [
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "WSoOPmCCVvwd",
        "outputId": "c10fe43d-b616-4d40-ace9-cd3426a72aba"
      },
      "outputs": [],
      "source": [
        "#@title Mount Google-Drive, needs to be approved manually\n",
        "from google.colab import drive\n",
        "drive.mount('/content/gdrive')"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": [
        "One weird thing w/ this colab:\n",
        "\n",
        "you must select a valid input image, even if it's out of the directory you're actually loading in and using- something to do with the structure of the img2img script on the compvis repo. I put this together as quick as I could to get it working so it's probably very easy to fix lol"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {},
      "outputs": [],
      "source": [
        "#colab variables\n",
        "model_ckpt = '/content/gdrive/My Drive/Colab Notebooks/models/model.ckpt' #@param {type:\"string\"}\n",
        "prompt = \"the delirious fruit god bust, colored pencil drawing\" #@param {type:\"string\"}\n",
        "outdir='/content/gdrive/MyDrive/SD/OUT/IMG_SEQ_021' #@param {type:\"string\"}\n",
        "ddim_steps = 75 #@param {type:\"number\"}\n",
        "ddim_eta = 0 #@param {type:\"number\"}\n",
        "n_iter = 2600 #@param {type:\"number\"}\n",
        "W=512 #@param {type:\"number\"}\n",
        "H=512 #@param {type:\"number\"}\n",
        "n_samples=1 #@param {type:\"number\"}\n",
        "scale=5.0 #@param {type:\"number\"}\n",
        "init_img_dir='/content/gdrive/MyDrive/INIT_IMG_DIR' #@param {type:\"string\"}\n",
        "plms=False #@param {type:\"boolean\"}\n",
        "n_rows=1 #@param {type:\"number\"}\n",
        "from_file=None #@param {type:\"string\"}\n",
        "strength=.52 #@param {type:\"number\"}\n",
        "precision=\"autocast\" #@param {type:\"string\"}\n",
        "skip_save=False #@param {type:\"boolean\"}\n",
        "skip_grid=True\n",
        "seed=2600\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 1000
        },
        "id": "NHgUAp48qwoG",
        "outputId": "042a9be5-56bb-497b-890a-bc8ab45bf7b9"
      },
      "outputs": [],
      "source": [
        "#@title Installation\n",
        "%cd /content/\n",
        "!pip install clip-by-openai\n",
        "!git clone https://github.com/CompVis/latent-diffusion.git\n",
        "!git clone https://github.com/CompVis/taming-transformers\n",
        "!git clone https://github.com/CompVis/stable-diffusion.git\n",
        "!pip install -e ./taming-transformers\n",
        "!pip install omegaconf>=2.0.0 pytorch-lightning>=1.0.8 torch-fidelity einops\n",
        "!pip install transformers\n",
        "!pip install kornia\n",
        "import sys\n",
        "sys.path.append(\".\")\n",
        "sys.path.append('./taming-transformers')\n",
        "from taming.models import vqgan \n",
        "!cp /content/stable-diffusion/ldm/modules/encoders/modules.py /content/latent-diffusion/ldm/modules/encoders/modules.py\n",
        "!nvidia-smi"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 1,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "fnGwQRhtyBhb",
        "outputId": "e3299938-b138-4e20-c522-497a23a76c5a"
      },
      "outputs": [
        {
          "name": "stdout",
          "output_type": "stream",
          "text": [
            "/content/stable-diffusion\n"
          ]
        }
      ],
      "source": [
        "#@title loading utils\n",
        "%cd /content/stable-diffusion/\n",
        "import torch\n",
        "from omegaconf import OmegaConf\n",
        "\n",
        "from ldm.util import instantiate_from_config\n",
        "\n",
        "\n",
        "def load_model_from_config(config, ckpt):\n",
        "    print(f\"Loading model from {ckpt}\")\n",
        "    pl_sd = torch.load(ckpt)#, map_location=\"cpu\")\n",
        "    sd = pl_sd[\"state_dict\"]\n",
        "    model = instantiate_from_config(config.model)\n",
        "    m, u = model.load_state_dict(sd, strict=False)\n",
        "    model.cuda()\n",
        "    model.eval()\n",
        "    return model\n",
        "\n",
        "\n",
        "def get_model():\n",
        "    config = OmegaConf.load(\"/content/stable-diffusion/configs/stable-diffusion/v1-inference.yaml\")  \n",
        "    model = load_model_from_config(config, f\"{model_ckpt}\")\n",
        "    return model"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 2,
      "metadata": {
        "id": "BPnyd-XUKbfE"
      },
      "outputs": [],
      "source": [
        "#@title Import stuff\n",
        "import argparse, os, sys, glob\n",
        "import torch\n",
        "import numpy as np\n",
        "import PIL\n",
        "from omegaconf import OmegaConf\n",
        "from PIL import Image\n",
        "from tqdm.auto import tqdm, trange\n",
        "from einops import rearrange\n",
        "from torchvision.utils import make_grid\n",
        "import transformers\n",
        "import gc\n",
        "from ldm.util import instantiate_from_config\n",
        "from ldm.models.diffusion.ddim import DDIMSampler\n",
        "from tqdm import tqdm, trange\n",
        "from itertools import islice\n",
        "from einops import rearrange, repeat\n",
        "from torch import autocast\n",
        "from contextlib import nullcontext\n",
        "import time\n",
        "from pytorch_lightning import seed_everything\n",
        "from ldm.models.diffusion.plms import PLMSSampler\n",
        "from google.colab.patches import cv2_imshow\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 14,
      "metadata": {
        "id": "Z6OadItmKyCd"
      },
      "outputs": [],
      "source": [
        "\n",
        "INPUT_SIZE = (W,H)\n",
        "\n",
        "\n",
        "def chunk(it, size):\n",
        "    it = iter(it)\n",
        "    return iter(lambda: tuple(islice(it, size)), ())\n",
        "\n",
        "\n",
        "def load_model_from_config(config, ckpt, verbose=False):\n",
        "    print(f\"Loading model from {ckpt}\")\n",
        "    pl_sd = torch.load(ckpt, map_location=\"cpu\")\n",
        "    if \"global_step\" in pl_sd:\n",
        "        print(f\"Global Step: {pl_sd['global_step']}\")\n",
        "    sd = pl_sd[\"state_dict\"]\n",
        "    model = instantiate_from_config(config.model)\n",
        "    m, u = model.load_state_dict(sd, strict=False)\n",
        "    if len(m) > 0 and verbose:\n",
        "        print(\"missing keys:\")\n",
        "        print(m)\n",
        "    if len(u) > 0 and verbose:\n",
        "        print(\"unexpected keys:\")\n",
        "        print(u)\n",
        "\n",
        "    model.cuda()\n",
        "    model.eval()\n",
        "    return model\n",
        "\n",
        "\n",
        "def load_img(path):\n",
        "    image = Image.open(path).convert(\"RGB\")\n",
        "    image = image.resize((W,H), resample=PIL.Image.LANCZOS)\n",
        "    w, h = image.size\n",
        "    print(f\"loaded input image of size ({w}, {h}) from {path}\")\n",
        "    w, h = map(lambda x: x - x % 32, (w, h))  # resize to integer multiple of 32\n",
        "    # image = image.resize((w, h), resample=PIL.Image.LANCZOS)\n",
        "    image = np.array(image).astype(np.float32) / 255.0\n",
        "    image = image[None].transpose(0, 3, 1, 2)\n",
        "    image = torch.from_numpy(image)\n",
        "    return 2.*image - 1.\n",
        "\n",
        "def run(opt):\n",
        "    torch.cuda.empty_cache()\n",
        "    gc.collect()\n",
        "    prompt = opt.prompt,\n",
        "    outdir=opt.outdir,\n",
        "    ddim_steps = opt.ddim_steps,\n",
        "    ddim_eta = opt.ddim_eta,\n",
        "    n_iter = opt.n_iter,\n",
        "    W=opt.W,\n",
        "    H=opt.H,\n",
        "    n_samples=opt.n_samples,\n",
        "    scale=opt.scale,\n",
        "    init_img=opt.init_img,\n",
        "    init_img_dir=opt.init_img_dir\n",
        "    plms=opt.plms\n",
        "    n_rows=opt.n_rows,\n",
        "    from_file=opt.from_file\n",
        "    strength=opt.strength\n",
        "    precision=opt.precision\n",
        "    skip_save=opt.skip_save\n",
        "    skip_grid=opt.skip_grid\n",
        "    seed = opt.seed\n",
        "    # opt = parser.parse_args()\n",
        "    # seed_everything(opt.seed)\n",
        "\n",
        "    config = OmegaConf.load(\"/content/stable-diffusion/configs/stable-diffusion/v1-inference.yaml\")  # TODO: Optionally download from same location as ckpt and chnage this logic\n",
        "    model = load_model_from_config(config, \"/content/gdrive/MyDrive/SD/sd-v1-3-full-ema/sd-v1-3-full-ema.ckpt\")  # TODO: check path\n",
        "\n",
        "    device = torch.device(\"cuda\") if torch.cuda.is_available() else torch.device(\"cpu\")\n",
        "    model = model.to(device)\n",
        "\n",
        "    if opt.plms:\n",
        "        raise NotImplementedError(\"PLMS sampler not (yet) supported\")\n",
        "        sampler = PLMSSampler(model)\n",
        "    else:\n",
        "        sampler = DDIMSampler(model)\n",
        "\n",
        "    os.makedirs(opt.outdir, exist_ok=True)\n",
        "    outpath = opt.outdir\n",
        "\n",
        "    batch_size = opt.n_samples\n",
        "    n_rows = opt.n_rows if opt.n_rows > 0 else batch_size\n",
        "    if not opt.from_file:\n",
        "        prompt = opt.prompt\n",
        "        assert prompt is not None\n",
        "        data = [batch_size * [prompt]]\n",
        "\n",
        "    else:\n",
        "        print(f\"reading prompts from {opt.from_file}\")\n",
        "        with open(opt.from_file, \"r\") as f:\n",
        "            data = f.read().splitlines()\n",
        "            data = list(chunk(data, batch_size))\n",
        "\n",
        "    sample_path = os.path.join(outpath, \"samples\")\n",
        "    os.makedirs(sample_path, exist_ok=True)\n",
        "    base_count = len(os.listdir(sample_path))\n",
        "    grid_count = len(os.listdir(outpath)) - 1\n",
        "\n",
        "    \n",
        "    sampler.make_schedule(ddim_num_steps=opt.ddim_steps, ddim_eta=opt.ddim_eta, verbose=False)\n",
        "\n",
        "    assert 0. <= opt.strength <= 1., 'can only work with strength in [0.0, 1.0]'\n",
        "    t_enc = int(opt.strength * opt.ddim_steps)\n",
        "    print(f\"target t_enc is {t_enc} steps\")\n",
        "\n",
        "    precision_scope = autocast if opt.precision == \"autocast\" else nullcontext\n",
        "    with torch.no_grad():\n",
        "        with precision_scope(\"cuda\"):\n",
        "            with model.ema_scope():\n",
        "                tic = time.time()\n",
        "                all_samples = list()\n",
        "                for n in trange(opt.n_iter, desc=\"Sampling\"):\n",
        "                    current_input_frame=f\"{opt.init_img_dir}/{n+1:04}.png\"\n",
        "                                         # /content/gdrive/MyDrive/SD/IN/A/098.0.png\n",
        "                    #current_input_frame=f\"/content/gdrive/MyDrive/SD/IN/A/{n+1:03}.0.png\"\n",
        "                    assert os.path.isfile(current_input_frame)\n",
        "\n",
        "                    init_image_ref = load_img(current_input_frame).to(device)\n",
        "                    init_image = repeat(init_image_ref, '1 ... -> b ...', b=batch_size)\n",
        "                    \n",
        "                    init_latent = model.get_first_stage_encoding(model.encode_first_stage(init_image))  # move to latent space\n",
        "\n",
        "                    #BLEND PREV FRAME\n",
        "                    #UNCOMMENT TO BLEND\n",
        "                    # if n>1:\n",
        "                    #     previous_input_frame= f\"{opt.init_img_dir}/{n:04}.jpg\"\n",
        "                    #     assert os.path.isfile(previous_input_frame)\n",
        "                    #     _prev_frame_ref = load_img(previous_input_frame).to(device)\n",
        "                    #     init_image = blend_frames(init_image, _prev_frame_ref, strength=strength)\n",
        "                    #     init_latent = model.get_first_stage_encoding(model.encode_first_stage(init_image))  # move to latent space\n",
        "\n",
        "\n",
        "                    for prompts in tqdm(data, desc=\"data\"):\n",
        "                        uc = None\n",
        "                        if opt.scale != 1.0:\n",
        "                            uc = model.get_learned_conditioning(batch_size * [\"\"])\n",
        "                        if isinstance(prompts, tuple):\n",
        "                            prompts = list(prompts)\n",
        "                        c = model.get_learned_conditioning(prompts)\n",
        "\n",
        "                        # encode (scaled latent)\n",
        "                        z_enc = sampler.stochastic_encode(init_latent, torch.tensor([t_enc]*batch_size).to(device))\n",
        "                        # decode it\n",
        "                        samples = sampler.decode(z_enc, c, t_enc, unconditional_guidance_scale=opt.scale,\n",
        "                                                 unconditional_conditioning=uc,)\n",
        "\n",
        "                        x_samples = model.decode_first_stage(samples)\n",
        "                        x_samples = torch.clamp((x_samples + 1.0) / 2.0, min=0.0, max=1.0)\n",
        "\n",
        "                        if not opt.skip_save:\n",
        "                            for x_sample in x_samples:\n",
        "                                x_sample = 255. * rearrange(x_sample.cpu().numpy(), 'c h w -> h w c')\n",
        "                                #cv2_imshow(Image.fromarray(x_sample.astype(np.uint8)))\n",
        "                                Image.fromarray(x_sample.astype(np.uint8)).save(\n",
        "                                    os.path.join(sample_path, f\"{base_count:05}.jpg\"))\n",
        "                                base_count += 1\n",
        "                        all_samples.append(x_samples)\n",
        "\n",
        "                if not opt.skip_grid:\n",
        "                    # additionally, save as grid\n",
        "                    grid = torch.stack(all_samples, 0)\n",
        "                    grid = rearrange(grid, 'n b c h w -> (n b) c h w')\n",
        "                    grid = make_grid(grid, nrow=n_rows)\n",
        "\n",
        "                    # to image\n",
        "                    grid = 255. * rearrange(grid, 'c h w -> h w c').cpu().numpy()\n",
        "                    Image.fromarray(grid.astype(np.uint8)).save(os.path.join(outpath, f'grid-{grid_count:04}.png'))\n",
        "                    grid_count += 1\n",
        "\n",
        "                toc = time.time()\n",
        "\n",
        "    print(f\"Your samples are ready and waiting for you here: \\n{outpath} \\n\"\n",
        "          f\" \\nEnjoy.\")\n",
        "    \n",
        "def blend_frames(frame1, frame2, strength=0.5):\n",
        "    return (1-strength)*frame1 + strength*frame2\n",
        "    \n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 1000
        },
        "id": "s1ywvU-5LHC_",
        "outputId": "61557c4f-0186-42fc-a967-c303173833c4"
      },
      "outputs": [],
      "source": [
        "for i in range(4000):\n",
        "    args = argparse.Namespace(\n",
        "        prompt = prompt\n",
        "        outdir=outdir\n",
        "        ddim_steps = ddim_steps,\n",
        "        ddim_eta = ddim_eta,\n",
        "        n_iter = n_iter,\n",
        "        W=W,\n",
        "        H=H,\n",
        "        n_samples=n_samples,\n",
        "        scale=scale,\n",
        "        init_img_dir=init_img_dir,\n",
        "        init_img=init_img\n",
        "        plms=plms,\n",
        "        n_rows=n_rows,\n",
        "        from_file=from_file,\n",
        "        strength=.strength,\n",
        "        precision=precision,\n",
        "        skip_save=skip_save,\n",
        "        skip_grid=skip_grid,\n",
        "        seed=seed\n",
        "    )\n",
        "    run(args)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "l1BtLj8SBTay"
      },
      "outputs": [],
      "source": [
        "#Extras for YT-DL\n",
        "\n",
        "\n",
        "%pip install yt-dlp\n",
        "%pip install ffmpeg\n",
        "\n",
        "%sudo curl -L https://yt-dl.org/downloads/latest/youtube-dl -o /usr/local/bin/youtube-dl\n",
        "%sudo chmod a+rx /usr/local/bin/youtube-dl\n",
        "\n",
        "import os\n",
        "import subprocess\n",
        "import sys\n",
        "import cv2\n",
        "\n",
        "\n",
        "\n",
        "url = 'YT LINK'\n",
        "drive__output_path = '/content/gdrive/MyDrive/TYDL_OUT/'\n",
        "def download_video(url, path):\n",
        "    out1 = subprocess.check_output('youtube-dl -f mp4 ' + url + ' -o ' + path + '.mp4',shell=True)\n",
        "    print(out1)\n",
        "    return path\n",
        "\n",
        "import cv2\n",
        "def extract_every_nth_frame(video,path, n):\n",
        "    cap = cv2.VideoCapture(video)\n",
        "    i = 0\n",
        "    #remove all existing png files in dir\n",
        "    for the_file in os.listdir(path):\n",
        "        file_path = os.path.join(path, the_file)\n",
        "        try:\n",
        "            if os.path.isfile(file_path):\n",
        "                os.unlink(file_path)\n",
        "        except Exception as e:\n",
        "            print(e)\n",
        "            \n",
        "    while(cap.isOpened()):\n",
        "        ret, frame = cap.read()\n",
        "        if ret == False:\n",
        "            break\n",
        "        if i % n == 0:\n",
        "            cv2.imwrite(f'{path}/{1+(i/n):05}' + '.png', frame)\n",
        "        i += 1\n",
        "    cap.release()\n",
        "    cv2.destroyAllWindows()\n",
        "\n",
        "\n",
        "extract_every_nth_frame(download_video(url),  3)\n"
      ]
    }
  ],
  "metadata": {
    "accelerator": "GPU",
    "colab": {
      "collapsed_sections": [],
      "machine_shape": "hm",
      "name": "StableDiff_2",
      "provenance": []
    },
    "gpuClass": "standard",
    "kernelspec": {
      "display_name": "Python 3.10.2 64-bit",
      "language": "python",
      "name": "python3"
    },
    "language_info": {
      "name": "python",
      "version": "3.10.2"
    },
    "vscode": {
      "interpreter": {
        "hash": "6a57af3429fe39f1db95ae52500f0dc20b0d5b033a19c06462446e07082bc71c"
      }
    },
    "widgets": {
      "application/vnd.jupyter.widget-state+json": {
        "1a862bf1077a41029a3c6934fc306c24": {
          "model_module": "@jupyter-widgets/controls",
          "model_module_version": "2.0.0",
          "model_name": "HTMLModel",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "2.0.0",
            "_model_name": "HTMLModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "2.0.0",
            "_view_name": "HTMLView",
            "description": "",
            "description_allow_html": false,
            "layout": "IPY_MODEL_a81d0ff2fad64602b9d7ec04692e082d",
            "placeholder": "​",
            "style": "IPY_MODEL_26030a13461d420586db56729a6f939f",
            "tabbable": null,
            "tooltip": null,
            "value": " 4/420 [05:30&lt;9:21:05, 80.93s/it]"
          }
        },
        "26030a13461d420586db56729a6f939f": {
          "model_module": "@jupyter-widgets/controls",
          "model_module_version": "2.0.0",
          "model_name": "HTMLStyleModel",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "2.0.0",
            "_model_name": "HTMLStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "2.0.0",
            "_view_name": "StyleView",
            "background": null,
            "description_width": "",
            "font_size": null,
            "text_color": null
          }
        },
        "3e8a7e84e83e4846b2df78df756b5f5b": {
          "model_module": "@jupyter-widgets/controls",
          "model_module_version": "2.0.0",
          "model_name": "HBoxModel",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "2.0.0",
            "_model_name": "HBoxModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "2.0.0",
            "_view_name": "HBoxView",
            "box_style": "",
            "children": [
              "IPY_MODEL_a644e33e55674207929f1b88fd93d9bf",
              "IPY_MODEL_6a78d0ade9b846a3887f68fca592fb16",
              "IPY_MODEL_1a862bf1077a41029a3c6934fc306c24"
            ],
            "layout": "IPY_MODEL_c413cbf82d5441a79a2636fc49d090ac",
            "tabbable": null,
            "tooltip": null
          }
        },
        "5869dca9f06242c3af67bfc2ce980159": {
          "model_module": "@jupyter-widgets/controls",
          "model_module_version": "2.0.0",
          "model_name": "HTMLStyleModel",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "2.0.0",
            "_model_name": "HTMLStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "2.0.0",
            "_view_name": "StyleView",
            "background": null,
            "description_width": "",
            "font_size": null,
            "text_color": null
          }
        },
        "6a78d0ade9b846a3887f68fca592fb16": {
          "model_module": "@jupyter-widgets/controls",
          "model_module_version": "2.0.0",
          "model_name": "FloatProgressModel",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "2.0.0",
            "_model_name": "FloatProgressModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "2.0.0",
            "_view_name": "ProgressView",
            "bar_style": "danger",
            "description": "",
            "description_allow_html": false,
            "layout": "IPY_MODEL_df608b7bf0084ebca2b3601147d1fa1b",
            "max": 420,
            "min": 0,
            "orientation": "horizontal",
            "style": "IPY_MODEL_9ec62b96d900460a8e43e0dcaf99c975",
            "tabbable": null,
            "tooltip": null,
            "value": 4
          }
        },
        "9ec62b96d900460a8e43e0dcaf99c975": {
          "model_module": "@jupyter-widgets/controls",
          "model_module_version": "2.0.0",
          "model_name": "ProgressStyleModel",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "2.0.0",
            "_model_name": "ProgressStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "2.0.0",
            "_view_name": "StyleView",
            "bar_color": null,
            "description_width": ""
          }
        },
        "a644e33e55674207929f1b88fd93d9bf": {
          "model_module": "@jupyter-widgets/controls",
          "model_module_version": "2.0.0",
          "model_name": "HTMLModel",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "2.0.0",
            "_model_name": "HTMLModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "2.0.0",
            "_view_name": "HTMLView",
            "description": "",
            "description_allow_html": false,
            "layout": "IPY_MODEL_f1723874edc140dd970191fac8d1d45d",
            "placeholder": "​",
            "style": "IPY_MODEL_5869dca9f06242c3af67bfc2ce980159",
            "tabbable": null,
            "tooltip": null,
            "value": "Sampling:   1%"
          }
        },
        "a81d0ff2fad64602b9d7ec04692e082d": {
          "model_module": "@jupyter-widgets/base",
          "model_module_version": "2.0.0",
          "model_name": "LayoutModel",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "2.0.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "2.0.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border_bottom": null,
            "border_left": null,
            "border_right": null,
            "border_top": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "c413cbf82d5441a79a2636fc49d090ac": {
          "model_module": "@jupyter-widgets/base",
          "model_module_version": "2.0.0",
          "model_name": "LayoutModel",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "2.0.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "2.0.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border_bottom": null,
            "border_left": null,
            "border_right": null,
            "border_top": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "df608b7bf0084ebca2b3601147d1fa1b": {
          "model_module": "@jupyter-widgets/base",
          "model_module_version": "2.0.0",
          "model_name": "LayoutModel",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "2.0.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "2.0.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border_bottom": null,
            "border_left": null,
            "border_right": null,
            "border_top": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "f1723874edc140dd970191fac8d1d45d": {
          "model_module": "@jupyter-widgets/base",
          "model_module_version": "2.0.0",
          "model_name": "LayoutModel",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "2.0.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "2.0.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border_bottom": null,
            "border_left": null,
            "border_right": null,
            "border_top": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        }
      }
    }
  },
  "nbformat": 4,
  "nbformat_minor": 0
}