{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "gf_Csp__upFO"
   },
   "source": [
    "### Using KDiffusion model, with t removed as baseline for future experiments"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "oFEJQaBsh-U9",
    "outputId": "158e8522-eb78-4522-cb53-280f3d017899"
   },
   "outputs": [],
   "source": [
    "#!pip install -q diffusers datasets wandb lpips timm"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "import os\n",
    "os.environ['CUDA_VISIBLE_DEVICES']='1'\n",
    "os.environ['OMP_NUM_THREADS']='1'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 69
    },
    "id": "Ddkidb9Fk6ZY",
    "outputId": "8c1ec8ab-26aa-4676-f1d6-d072d613cfb1"
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[34m\u001b[1mwandb\u001b[0m: Currently logged in as: \u001b[33mjantic\u001b[0m. Use \u001b[1m`wandb login --relogin`\u001b[0m to force relogin\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "True"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import wandb\n",
    "wandb.login()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "-pTR-1A-h7ks",
    "outputId": "5ce14582-76bf-4ec7-b03d-6c449ac786e3"
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "NOTE: Redirects are currently not supported in Windows or MacOs.\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Using device: cuda\n"
     ]
    }
   ],
   "source": [
    "#@title imports\n",
    "import wandb\n",
    "import torch\n",
    "import torchvision\n",
    "from torch import nn\n",
    "from torch import multiprocessing as mp\n",
    "from torch.utils import data\n",
    "from torchvision import datasets\n",
    "from torchvision import transforms as T\n",
    "from torchvision.transforms import functional as TF\n",
    "from fastai.data.all import *\n",
    "from fastai.vision.all import *\n",
    "from fastai.callback.wandb import *\n",
    "from timm.optim.rmsprop_tf import RMSpropTF\n",
    "from timm.optim.lookahead import Lookahead\n",
    "import accelerate\n",
    "from einops import rearrange\n",
    "from functools import partial\n",
    "import math\n",
    "from copy import deepcopy\n",
    "from pathlib import Path\n",
    "from tqdm.auto import trange, tqdm\n",
    "import k_diffusion as K\n",
    "from datasets import load_dataset\n",
    "\n",
    "device = torch.device(\"cuda\" if torch.cuda.is_available() else \"cpu\")\n",
    "print(f'Using device: {device}')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "ypA8A7pjuwI5"
   },
   "source": [
    "# Model and Training Setup"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "start_method = 'spawn' # the multiprocessing start method. Options: 'fork', 'forkserver', 'spawn'\n",
    "skip_stages = 0\n",
    "grad_accum_steps = 1\n",
    "mp.set_start_method(start_method)\n",
    "torch.backends.cuda.matmul.allow_tf32 = True"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Process 0 using device: cuda\n"
     ]
    }
   ],
   "source": [
    "ddp_kwargs = accelerate.DistributedDataParallelKwargs(find_unused_parameters=skip_stages > 0)\n",
    "accelerator = accelerate.Accelerator(kwargs_handlers=[ddp_kwargs], gradient_accumulation_steps=grad_accum_steps)\n",
    "device = accelerator.device\n",
    "print(f'Process {accelerator.process_index} using device: {device}', flush=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "sz = 28\n",
    "bs = 2048\n",
    "lr = 1e-3\n",
    "input_channels = 1\n",
    "augment_prob = 0.12\n",
    "sigma_data = 0.6162\n",
    "mean = 0.2859\n",
    "std = 0.353\n",
    "sigma_min = 1e-2\n",
    "sigma_max = 80\n",
    "has_variance=True\n",
    "sample_n = 64\n",
    "num_workers = 8"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "def normalize_img(x):\n",
    "    return (x-mean)/std\n",
    "\n",
    "def denormalize_img(x):\n",
    "    return (x*std)+mean"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "def RmsLookahead(params, alpha=0.5, k=6, *args, **kwargs):\n",
    "    rmsprop = RMSpropTF(params, *args, **kwargs)\n",
    "    return Lookahead(rmsprop, alpha, k)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "def make_sample_density(mean=-1.2, std=1.2):\n",
    "    #lognormal\n",
    "    return partial(K.utils.rand_log_normal, loc=mean, scale=std)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [],
   "source": [
    "def make_diffusion_model():\n",
    "    #Model Config\n",
    "    sz = 28\n",
    "    size = [sz,sz]\n",
    "    input_channels = 1\n",
    "    patch_size= 1\n",
    "    mapping_out= 256\n",
    "    depths= [2, 4, 4]\n",
    "    channels= [128, 128, 256]\n",
    "    self_attn_depths = [False, False, True]\n",
    "    cross_attn_depths = None\n",
    "    has_variance = True\n",
    "    dropout_rate = 0.05\n",
    "    augment_wrapper = True\n",
    "    skip_stages = 0\n",
    "\n",
    "    model = K.models.ImageDenoiserModelV1(\n",
    "        c_in=input_channels,\n",
    "        feats_in=mapping_out,\n",
    "        depths=depths,\n",
    "        channels=channels,\n",
    "        self_attn_depths=self_attn_depths,\n",
    "        cross_attn_depths=cross_attn_depths,\n",
    "        patch_size=patch_size,\n",
    "        dropout_rate=dropout_rate,\n",
    "        mapping_cond_dim= 9 if augment_wrapper else 0,\n",
    "        unet_cond_dim = 0,\n",
    "        cross_cond_dim = 0,\n",
    "        skip_stages= skip_stages,\n",
    "        has_variance=has_variance,\n",
    "    )\n",
    "    if augment_wrapper:\n",
    "        model = K.augmentation.KarrasAugmentWrapper(model)\n",
    "    return model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "def make_denoiser_wrapper():\n",
    "    if not has_variance:\n",
    "        return partial(K.layers.Denoiser, sigma_data=sigma_data)\n",
    "    return partial(K.layers.DenoiserWithVariance, sigma_data=sigma_data)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "_vP7D_a4u0d9",
    "tags": []
   },
   "source": [
    "# Noise Classifier Training"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [],
   "source": [
    "class KarrasAugmentationPipelineCust(Transform):\n",
    "    def __init__(self):\n",
    "        self.pipeline = K.augmentation.KarrasAugmentationPipeline(augment_prob)\n",
    "        \n",
    "    def encodes(self, image):\n",
    "        return self.pipeline(image)[0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "tfm = T.transforms.Compose([\n",
    "    T.Resize(sz, interpolation=T.InterpolationMode.LANCZOS),\n",
    "    T.CenterCrop(sz),\n",
    "    #KarrasAugmentationPipelineCust()\n",
    "])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Number of items in dataset: 60000\n"
     ]
    }
   ],
   "source": [
    "dataset = datasets.FashionMNIST('data', train=True, download=True, transform=tfm)\n",
    "print('Number of items in dataset:', len(dataset))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [],
   "source": [
    "def get_scalings(sigma):\n",
    "    c_skip = sigma_data ** 2 / (sigma ** 2 + sigma_data ** 2)\n",
    "    c_out = sigma * sigma_data / (sigma ** 2 + sigma_data ** 2) ** 0.5\n",
    "    c_in = 1 / (sigma ** 2 + sigma_data ** 2) ** 0.5\n",
    "    return c_skip, c_out, c_in"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [],
   "source": [
    "sample_density = make_sample_density()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [],
   "source": [
    "def scale_model_input(input, sigma):\n",
    "    _, _, c_in = [K.utils.append_dims(x, input.ndim) for x in get_scalings(sigma)]\n",
    "    input = input * c_in \n",
    "    return input"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [],
   "source": [
    "sigmas_list = K.sampling.get_sigmas_karras(1000, sigma_min, sigma_max, rho=7., device=device)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [],
   "source": [
    "def crappify(input:TensorImage):\n",
    "    sigma_idx = torch.randint(low=0, high=len(sigmas_list)-1, size=(input.shape[0],))\n",
    "    sigma = torch.ones([input.shape[0]], device=device)*(sigmas_list[sigma_idx] + torch.randn([input.shape[0]], device=device))\n",
    "    \n",
    "    #print(sigma.shape)\n",
    "    #sigma = torch.rand([input.shape[0]], device=device) * (sigma_max - sigma_min) + sigma_min\n",
    "    #sigma = sample_density([input.shape[0]], device=device)\n",
    "    noise = torch.randn(input.shape).to(device) * K.utils.append_dims(sigma, input.ndim)\n",
    "    noised_input = input + noise\n",
    "    noised_input = noised_input\n",
    "    #noised_input = scale_model_input(noised_input, sigma)\n",
    "    return noised_input, sigma"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Due to IPython and Windows limitation, python multiprocessing isn't available now.\n",
      "So `number_workers` is changed to 0 to avoid getting stuck\n"
     ]
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 3000x2700 with 90 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "batch_tfms = aug_transforms()\n",
    "batch_tfms.append(Normalize.from_stats(0.5, 0.5))\n",
    "\n",
    "# Dataloader\n",
    "dblock = DataBlock(blocks=(ImageBlock(cls=PILImageBW), RegressionBlock),\n",
    "                   get_items=lambda pth: range(len(dataset)), # Gets the indexes\n",
    "                   get_x=[lambda idx: np.array(dataset[idx][0])],\n",
    "                   get_y=[lambda idx: sigma_max],\n",
    "                   batch_tfms=batch_tfms)\n",
    "dls = dblock.dataloaders('', bs=bs)\n",
    "dls.show_batch(max_n=90)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [],
   "source": [
    "class CrappificationCallback(Callback):\n",
    "    def before_batch(self):\n",
    "        x0 = self.learn.xb[0] # original images and labels\n",
    "        #print(x0.max(), x0.min())\n",
    "        xt, sigma = crappify(x0) # noise same shape as x0\n",
    "        self.learn.xb = (xt,) # input to our model is noisy image, timestep and label\n",
    "        self.learn.yb = (sigma,) # ground truth is the noise "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [],
   "source": [
    "import timm"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [],
   "source": [
    "arch = partial(timm.create_model, 'resnetrs200', pretrained=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {},
   "outputs": [],
   "source": [
    "learn = vision_learner(dls, arch, loss_func=nn.L1Loss(), opt_func=partial(OptimWrapper, opt=RmsLookahead), n_in=1, n_out=1, y_range=(sigma_min, sigma_max), \n",
    "                       cbs=[CrappificationCallback()])       "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "\n",
       "<style>\n",
       "    /* Turns off some styling */\n",
       "    progress {\n",
       "        /* gets rid of default border in Firefox and Opera. */\n",
       "        border: none;\n",
       "        /* Needs to be in here for Safari polyfill so background images work as expected. */\n",
       "        background-size: auto;\n",
       "    }\n",
       "    progress:not([value]), progress:not([value])::-webkit-progress-bar {\n",
       "        background: repeating-linear-gradient(45deg, #7e7e7e, #7e7e7e 10px, #5c5c5c 10px, #5c5c5c 20px);\n",
       "    }\n",
       "    .progress-bar-interrupted, .progress-bar-interrupted::-webkit-progress-bar {\n",
       "        background: #F44336;\n",
       "    }\n",
       "</style>\n"
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\jsa16\\anaconda3\\envs\\course22p2\\lib\\site-packages\\torch\\_tensor.py:1121: UserWarning: Using a target size (torch.Size([2048])) that is different to the input size (torch.Size([2048, 1])). This will likely lead to incorrect results due to broadcasting. Please ensure they have the same size.\n",
      "  ret = func(*args, **kwargs)\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "SuggestedLRs(valley=0.00363078061491251)"
      ]
     },
     "execution_count": 26,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "learn.lr_find()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "\n",
       "<style>\n",
       "    /* Turns off some styling */\n",
       "    progress {\n",
       "        /* gets rid of default border in Firefox and Opera. */\n",
       "        border: none;\n",
       "        /* Needs to be in here for Safari polyfill so background images work as expected. */\n",
       "        background-size: auto;\n",
       "    }\n",
       "    progress:not([value]), progress:not([value])::-webkit-progress-bar {\n",
       "        background: repeating-linear-gradient(45deg, #7e7e7e, #7e7e7e 10px, #5c5c5c 10px, #5c5c5c 20px);\n",
       "    }\n",
       "    .progress-bar-interrupted, .progress-bar-interrupted::-webkit-progress-bar {\n",
       "        background: #F44336;\n",
       "    }\n",
       "</style>\n"
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: left;\">\n",
       "      <th>epoch</th>\n",
       "      <th>train_loss</th>\n",
       "      <th>valid_loss</th>\n",
       "      <th>time</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <td>0</td>\n",
       "      <td>22.939627</td>\n",
       "      <td>13.512413</td>\n",
       "      <td>01:20</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>"
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\jsa16\\anaconda3\\envs\\course22p2\\lib\\site-packages\\torch\\_tensor.py:1121: UserWarning: Using a target size (torch.Size([1760])) that is different to the input size (torch.Size([1760, 1])). This will likely lead to incorrect results due to broadcasting. Please ensure they have the same size.\n",
      "  ret = func(*args, **kwargs)\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "\n",
       "<style>\n",
       "    /* Turns off some styling */\n",
       "    progress {\n",
       "        /* gets rid of default border in Firefox and Opera. */\n",
       "        border: none;\n",
       "        /* Needs to be in here for Safari polyfill so background images work as expected. */\n",
       "        background-size: auto;\n",
       "    }\n",
       "    progress:not([value]), progress:not([value])::-webkit-progress-bar {\n",
       "        background: repeating-linear-gradient(45deg, #7e7e7e, #7e7e7e 10px, #5c5c5c 10px, #5c5c5c 20px);\n",
       "    }\n",
       "    .progress-bar-interrupted, .progress-bar-interrupted::-webkit-progress-bar {\n",
       "        background: #F44336;\n",
       "    }\n",
       "</style>\n"
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "\n",
       "    <div>\n",
       "      <progress value='37' class='' max='100' style='width:300px; height:20px; vertical-align: middle;'></progress>\n",
       "      37.00% [37/100 55:24&lt;1:34:21]\n",
       "    </div>\n",
       "    \n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: left;\">\n",
       "      <th>epoch</th>\n",
       "      <th>train_loss</th>\n",
       "      <th>valid_loss</th>\n",
       "      <th>time</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <td>0</td>\n",
       "      <td>13.864560</td>\n",
       "      <td>13.771007</td>\n",
       "      <td>01:29</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>1</td>\n",
       "      <td>13.918092</td>\n",
       "      <td>13.808266</td>\n",
       "      <td>01:29</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>2</td>\n",
       "      <td>13.997495</td>\n",
       "      <td>14.325958</td>\n",
       "      <td>01:30</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>3</td>\n",
       "      <td>13.894313</td>\n",
       "      <td>12.943288</td>\n",
       "      <td>01:29</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4</td>\n",
       "      <td>13.617351</td>\n",
       "      <td>13.220692</td>\n",
       "      <td>01:29</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>5</td>\n",
       "      <td>13.371610</td>\n",
       "      <td>12.921383</td>\n",
       "      <td>01:29</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>6</td>\n",
       "      <td>13.291358</td>\n",
       "      <td>13.067586</td>\n",
       "      <td>01:30</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>7</td>\n",
       "      <td>13.252453</td>\n",
       "      <td>13.312786</td>\n",
       "      <td>01:29</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>8</td>\n",
       "      <td>13.259872</td>\n",
       "      <td>13.309431</td>\n",
       "      <td>01:29</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>9</td>\n",
       "      <td>13.155416</td>\n",
       "      <td>12.811332</td>\n",
       "      <td>01:29</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>10</td>\n",
       "      <td>13.189067</td>\n",
       "      <td>13.171445</td>\n",
       "      <td>01:30</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>11</td>\n",
       "      <td>13.212422</td>\n",
       "      <td>13.401793</td>\n",
       "      <td>01:29</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>12</td>\n",
       "      <td>13.186036</td>\n",
       "      <td>13.030722</td>\n",
       "      <td>01:30</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>13</td>\n",
       "      <td>13.237270</td>\n",
       "      <td>13.156294</td>\n",
       "      <td>01:29</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>14</td>\n",
       "      <td>13.265850</td>\n",
       "      <td>13.090401</td>\n",
       "      <td>01:29</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>15</td>\n",
       "      <td>13.203370</td>\n",
       "      <td>13.697763</td>\n",
       "      <td>01:29</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>16</td>\n",
       "      <td>13.137811</td>\n",
       "      <td>13.201479</td>\n",
       "      <td>01:28</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>17</td>\n",
       "      <td>13.181696</td>\n",
       "      <td>13.027193</td>\n",
       "      <td>01:29</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>18</td>\n",
       "      <td>13.194204</td>\n",
       "      <td>13.279347</td>\n",
       "      <td>01:29</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>19</td>\n",
       "      <td>13.214813</td>\n",
       "      <td>12.884426</td>\n",
       "      <td>01:29</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>20</td>\n",
       "      <td>13.171059</td>\n",
       "      <td>13.209190</td>\n",
       "      <td>01:29</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>21</td>\n",
       "      <td>13.202210</td>\n",
       "      <td>13.107743</td>\n",
       "      <td>01:30</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>22</td>\n",
       "      <td>13.238354</td>\n",
       "      <td>13.205649</td>\n",
       "      <td>01:29</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>23</td>\n",
       "      <td>13.240045</td>\n",
       "      <td>12.990332</td>\n",
       "      <td>01:29</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>24</td>\n",
       "      <td>13.211985</td>\n",
       "      <td>13.117427</td>\n",
       "      <td>01:30</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>25</td>\n",
       "      <td>13.236915</td>\n",
       "      <td>12.960276</td>\n",
       "      <td>01:30</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>26</td>\n",
       "      <td>13.244856</td>\n",
       "      <td>13.051888</td>\n",
       "      <td>01:29</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>27</td>\n",
       "      <td>13.196985</td>\n",
       "      <td>12.847483</td>\n",
       "      <td>01:30</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>28</td>\n",
       "      <td>13.195829</td>\n",
       "      <td>13.112218</td>\n",
       "      <td>01:30</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>29</td>\n",
       "      <td>13.246385</td>\n",
       "      <td>13.287416</td>\n",
       "      <td>01:29</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>30</td>\n",
       "      <td>13.187284</td>\n",
       "      <td>13.085998</td>\n",
       "      <td>01:29</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>31</td>\n",
       "      <td>13.129988</td>\n",
       "      <td>13.188730</td>\n",
       "      <td>01:30</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>32</td>\n",
       "      <td>13.176440</td>\n",
       "      <td>12.974963</td>\n",
       "      <td>01:30</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>33</td>\n",
       "      <td>13.177260</td>\n",
       "      <td>13.157208</td>\n",
       "      <td>01:30</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>34</td>\n",
       "      <td>13.151767</td>\n",
       "      <td>13.062047</td>\n",
       "      <td>01:29</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>35</td>\n",
       "      <td>13.200571</td>\n",
       "      <td>13.479816</td>\n",
       "      <td>01:30</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>36</td>\n",
       "      <td>13.117564</td>\n",
       "      <td>13.070472</td>\n",
       "      <td>01:30</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table><p>\n",
       "\n",
       "    <div>\n",
       "      <progress value='10' class='' max='23' style='width:300px; height:20px; vertical-align: middle;'></progress>\n",
       "      43.48% [10/23 00:33&lt;00:43 13.1297]\n",
       "    </div>\n",
       "    "
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\n",
      "KeyboardInterrupt\n",
      "\n",
      "\u001b[34m\u001b[1mwandb\u001b[0m: While tearing down the service manager. The following error has occured: [WinError 10054] An existing connection was forcibly closed by the remote host\n"
     ]
    }
   ],
   "source": [
    "learn.fine_tune(100, base_lr=1e-2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "denoiser_name = 'denoiser_1'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "learn.save(denoiser_name)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "_vP7D_a4u0d9",
    "tags": []
   },
   "source": [
    "# Optimizer Based Sampling"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "def generate_random_noise(bs):\n",
    "    return torch.randn(bs, 1, sz, sz, device=device) * sigma_max\n",
    "\n",
    "def generate_random_noise_like(x):\n",
    "    return torch.randn_like(x, device=device) * sigma_max"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "learn.load(denoiser_name)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "sigma_model = learn.model.eval().to(device)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "checkpoints_dir = './checkpoints'\n",
    "model_ema_path = Path(checkpoints_dir +'/kdiff_34_fmnist_ema.pt')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "model_ema = make_denoiser_wrapper()( make_diffusion_model().to(device)).eval()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "model_ema.load_state_dict(torch.load(str(model_ema_path)))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "def sample_based_on_optimizer(model_ema, sigma_model, xt, optim_fn, n_steps, lr_max, pct_start):\n",
    "    with K.utils.eval_mode(model_ema):\n",
    "        div=100000.\n",
    "        div_final=1e5\n",
    "        lr_sched_fn = combined_cos(pct_start, lr_max/div, lr_max, lr_max/div_final)\n",
    "        optim = OptimWrapper(opt=optim_fn([xt], lr=lr_max))\n",
    "        prev_noise_var = 1e6\n",
    "        eps = None\n",
    "        xt.requires_grad = True\n",
    "        sigma = torch.ones([num_examples, 1], device=device) * sigma_max\n",
    "\n",
    "        for i in range(n_steps):\n",
    "            pos = i/(n_steps)\n",
    "            lr = lr_sched_fn(pos)\n",
    "            optim.set_hyper('lr', lr)\n",
    "            in_xt = xt\n",
    "\n",
    "            with torch.no_grad():\n",
    "                #print(sigma_model(in_xt)[0])\n",
    "                pred = model_ema(in_xt, sigma)\n",
    "                eps = in_xt-pred\n",
    "                sigma = sigma_model(pred)\n",
    "\n",
    "            # # Early stopping\n",
    "            #if (eps.float()).var() < 0.01 or i == n_steps-1:\n",
    "            #    print('Stopping at:', i)\n",
    "            #    return pred, eps\n",
    "\n",
    "            xt.grad = eps.float()\n",
    "            grad_mean = eps.mean()\n",
    "            prev_noise_var = eps.float().var()\n",
    "\n",
    "            #if i%10==0:\n",
    "            #    print(i, xt.grad.mean(), xt.grad.var(), xt.float().var(), lr) # Useful to watch the noise variance\n",
    "\n",
    "\n",
    "            optim.step()\n",
    "            optim.zero_grad() \n",
    "\n",
    "\n",
    "            #if i%10==0:\n",
    "            #    print('xt:', i, xt.mean(), xt.max(), xt.min())\n",
    "\n",
    "            #if grad_mean < 0.0:\n",
    "            #    return xt, eps\n",
    "\n",
    "        return xt, eps\n",
    "\n",
    "def generate_opt_based_samples(model_ema, sigma_model, xt):\n",
    "    sgd_optim_fn = partial(torch.optim.SGD, momentum=0.01)\n",
    "    xt = xt.clone()\n",
    "    xt, eps = sample_based_on_optimizer(model_ema, sigma_model, xt=xt, optim_fn=sgd_optim_fn, n_steps=40, lr_max=2e-2, pct_start=0.25)\n",
    "    #xt, eps = sample_based_on_optimizer(model_ema, sigma_model, xt=xt, optim_fn=sgd_optim_fn, n_steps=10, lr_max=3e-2, pct_start=0.5)\n",
    "    #xt, eps = sample_based_on_optimizer(model_ema, sigma_model, xt=xt,  optim_fn=RmsLookahead, n_steps=20, lr_max=5e-2, pct_start=0.25)\n",
    "    pred_image = xt\n",
    "    return pred_image, eps"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "torch.random.manual_seed(1000)\n",
    "num_examples = 80\n",
    "#xt = generate_random_noise(num_examples).to(device)\n",
    "xt = torch.randn([num_examples, input_channels, sz, sz], device=device) * sigma_max\n",
    "## Seem to get better results with 0.95 noise_amount rather than 1.0\n",
    "pred_image, eps = generate_opt_based_samples(model_ema, sigma_model, xt=xt)\n",
    "#pred_image = denormalize_img(pred_image).detach().cpu()\n",
    "pred_image = pred_image.detach().cpu()\n",
    "xt = xt.detach().cpu()\n",
    "eps = eps.detach().cpu()\n",
    "#pred_img = (pred_image).clip(0, 1)\n",
    "grid = torchvision.utils.make_grid(pred_image, nrow=8, padding=0)\n",
    "grid = K.utils.to_pil_image(grid)\n",
    "fig, ax = plt.subplots(1, 1, figsize=(12, 12))\n",
    "ax.imshow(grid)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "for i in range(100):\n",
    "    input = K.utils.from_pil_image(dataset[0][0]).unsqueeze(0).to(device)\n",
    "    sigma = sample_density([input.shape[0]], device=device)\n",
    "    noise = torch.randn(input.shape).to(device) * K.utils.append_dims(sigma, input.ndim)\n",
    "    noised_input = input + noise\n",
    "    pred = sigma_model(noised_input)\n",
    "    print(sigma[0], pred[0])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "@torch.no_grad()\n",
    "def sample_lms(model_ema, size):\n",
    "    with K.utils.eval_mode(model_ema):\n",
    "        n_per_proc = math.ceil(sample_n / accelerator.num_processes)\n",
    "        x = torch.randn([n_per_proc, input_channels, size[0], size[1]], device=device) * sigma_max\n",
    "        sigmas = K.sampling.get_sigmas_karras(50, sigma_min, sigma_max, rho=7., device=device)\n",
    "        print(x.max(), x.min())\n",
    "        pred_sigmas = sigma_model(x)\n",
    "        print(sigmas[0], pred_sigmas[0])\n",
    "        x_0 = K.sampling.sample_lms(model_ema, x, sigmas, disable=not accelerator.is_main_process)\n",
    "        x_0 = accelerator.gather(x_0)[:sample_n]\n",
    "        # For some reason the images are inverting...\n",
    "        x_0 = -x_0\n",
    "\n",
    "        grid = torchvision.utils.make_grid(x_0, nrow=math.ceil(sample_n ** 0.5), padding=0)\n",
    "        return K.utils.to_pil_image(grid)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "grid = sample_lms(model_ema, [sz,sz])\n",
    "fig, ax = plt.subplots(1, 1, figsize=(12, 12))\n",
    "ax.imshow(grid)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "accelerator": "GPU",
  "colab": {
   "collapsed_sections": [],
   "provenance": []
  },
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": "3.7.11"
  },
  "widgets": {
   "application/vnd.jupyter.widget-state+json": {
    "0abad3eee1904c2bb8a2f963fed5fba6": {
     "model_module": "@jupyter-widgets/controls",
     "model_module_version": "1.5.0",
     "model_name": "DescriptionStyleModel",
     "state": {
      "_model_module": "@jupyter-widgets/controls",
      "_model_module_version": "1.5.0",
      "_model_name": "DescriptionStyleModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/base",
      "_view_module_version": "1.2.0",
      "_view_name": "StyleView",
      "description_width": ""
     }
    },
    "13c327d321444b32aa4349ec81e98cde": {
     "model_module": "@jupyter-widgets/controls",
     "model_module_version": "1.5.0",
     "model_name": "ProgressStyleModel",
     "state": {
      "_model_module": "@jupyter-widgets/controls",
      "_model_module_version": "1.5.0",
      "_model_name": "ProgressStyleModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/base",
      "_view_module_version": "1.2.0",
      "_view_name": "StyleView",
      "bar_color": null,
      "description_width": ""
     }
    },
    "184b1cfa56be41c7845062a4e7c5fa59": {
     "model_module": "@jupyter-widgets/controls",
     "model_module_version": "1.5.0",
     "model_name": "DescriptionStyleModel",
     "state": {
      "_model_module": "@jupyter-widgets/controls",
      "_model_module_version": "1.5.0",
      "_model_name": "DescriptionStyleModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/base",
      "_view_module_version": "1.2.0",
      "_view_name": "StyleView",
      "description_width": ""
     }
    },
    "250c148b80734613a53fec26ab1b3db8": {
     "model_module": "@jupyter-widgets/base",
     "model_module_version": "1.2.0",
     "model_name": "LayoutModel",
     "state": {
      "_model_module": "@jupyter-widgets/base",
      "_model_module_version": "1.2.0",
      "_model_name": "LayoutModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/base",
      "_view_module_version": "1.2.0",
      "_view_name": "LayoutView",
      "align_content": null,
      "align_items": null,
      "align_self": null,
      "border": 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,
      "overflow_x": null,
      "overflow_y": null,
      "padding": null,
      "right": null,
      "top": null,
      "visibility": null,
      "width": null
     }
    },
    "33691922e1a0401890529b929d0169b7": {
     "model_module": "@jupyter-widgets/controls",
     "model_module_version": "1.5.0",
     "model_name": "ProgressStyleModel",
     "state": {
      "_model_module": "@jupyter-widgets/controls",
      "_model_module_version": "1.5.0",
      "_model_name": "ProgressStyleModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/base",
      "_view_module_version": "1.2.0",
      "_view_name": "StyleView",
      "bar_color": null,
      "description_width": ""
     }
    },
    "3b7a1d8560004241b9b06700bcdb5b1c": {
     "model_module": "@jupyter-widgets/controls",
     "model_module_version": "1.5.0",
     "model_name": "FloatProgressModel",
     "state": {
      "_dom_classes": [],
      "_model_module": "@jupyter-widgets/controls",
      "_model_module_version": "1.5.0",
      "_model_name": "FloatProgressModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/controls",
      "_view_module_version": "1.5.0",
      "_view_name": "ProgressView",
      "bar_style": "success",
      "description": "",
      "description_tooltip": null,
      "layout": "IPY_MODEL_63c702b2fa6a4270b88479f5319a6ae2",
      "max": 1,
      "min": 0,
      "orientation": "horizontal",
      "style": "IPY_MODEL_33691922e1a0401890529b929d0169b7",
      "value": 1
     }
    },
    "4979c4212a1b46ceb5664a9a8680b665": {
     "model_module": "@jupyter-widgets/controls",
     "model_module_version": "1.5.0",
     "model_name": "DescriptionStyleModel",
     "state": {
      "_model_module": "@jupyter-widgets/controls",
      "_model_module_version": "1.5.0",
      "_model_name": "DescriptionStyleModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/base",
      "_view_module_version": "1.2.0",
      "_view_name": "StyleView",
      "description_width": ""
     }
    },
    "56f6e898da4248ea9a64658f6b284a3b": {
     "model_module": "@jupyter-widgets/base",
     "model_module_version": "1.2.0",
     "model_name": "LayoutModel",
     "state": {
      "_model_module": "@jupyter-widgets/base",
      "_model_module_version": "1.2.0",
      "_model_name": "LayoutModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/base",
      "_view_module_version": "1.2.0",
      "_view_name": "LayoutView",
      "align_content": null,
      "align_items": null,
      "align_self": null,
      "border": 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,
      "overflow_x": null,
      "overflow_y": null,
      "padding": null,
      "right": null,
      "top": null,
      "visibility": null,
      "width": null
     }
    },
    "60553a0615334106a03d52877861569a": {
     "model_module": "@jupyter-widgets/base",
     "model_module_version": "1.2.0",
     "model_name": "LayoutModel",
     "state": {
      "_model_module": "@jupyter-widgets/base",
      "_model_module_version": "1.2.0",
      "_model_name": "LayoutModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/base",
      "_view_module_version": "1.2.0",
      "_view_name": "LayoutView",
      "align_content": null,
      "align_items": null,
      "align_self": null,
      "border": 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,
      "overflow_x": null,
      "overflow_y": null,
      "padding": null,
      "right": null,
      "top": null,
      "visibility": null,
      "width": null
     }
    },
    "6172b7637810408ebe9e2118c5d02c04": {
     "model_module": "@jupyter-widgets/controls",
     "model_module_version": "1.5.0",
     "model_name": "HTMLModel",
     "state": {
      "_dom_classes": [],
      "_model_module": "@jupyter-widgets/controls",
      "_model_module_version": "1.5.0",
      "_model_name": "HTMLModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/controls",
      "_view_module_version": "1.5.0",
      "_view_name": "HTMLView",
      "description": "",
      "description_tooltip": null,
      "layout": "IPY_MODEL_250c148b80734613a53fec26ab1b3db8",
      "placeholder": "​",
      "style": "IPY_MODEL_0abad3eee1904c2bb8a2f963fed5fba6",
      "value": "100%"
     }
    },
    "63c702b2fa6a4270b88479f5319a6ae2": {
     "model_module": "@jupyter-widgets/base",
     "model_module_version": "1.2.0",
     "model_name": "LayoutModel",
     "state": {
      "_model_module": "@jupyter-widgets/base",
      "_model_module_version": "1.2.0",
      "_model_name": "LayoutModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/base",
      "_view_module_version": "1.2.0",
      "_view_name": "LayoutView",
      "align_content": null,
      "align_items": null,
      "align_self": null,
      "border": 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,
      "overflow_x": null,
      "overflow_y": null,
      "padding": null,
      "right": null,
      "top": null,
      "visibility": null,
      "width": null
     }
    },
    "6a7fe0a8c7d844c9b92ab9dab247ec79": {
     "model_module": "@jupyter-widgets/base",
     "model_module_version": "1.2.0",
     "model_name": "LayoutModel",
     "state": {
      "_model_module": "@jupyter-widgets/base",
      "_model_module_version": "1.2.0",
      "_model_name": "LayoutModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/base",
      "_view_module_version": "1.2.0",
      "_view_name": "LayoutView",
      "align_content": null,
      "align_items": null,
      "align_self": null,
      "border": 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,
      "overflow_x": null,
      "overflow_y": null,
      "padding": null,
      "right": null,
      "top": null,
      "visibility": null,
      "width": null
     }
    },
    "72f566c251ba4cf6a0282ed4340e1f08": {
     "model_module": "@jupyter-widgets/controls",
     "model_module_version": "1.5.0",
     "model_name": "HTMLModel",
     "state": {
      "_dom_classes": [],
      "_model_module": "@jupyter-widgets/controls",
      "_model_module_version": "1.5.0",
      "_model_name": "HTMLModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/controls",
      "_view_module_version": "1.5.0",
      "_view_name": "HTMLView",
      "description": "",
      "description_tooltip": null,
      "layout": "IPY_MODEL_56f6e898da4248ea9a64658f6b284a3b",
      "placeholder": "​",
      "style": "IPY_MODEL_184b1cfa56be41c7845062a4e7c5fa59",
      "value": " 1/1 [00:00&lt;00:00, 27.33it/s]"
     }
    },
    "8f31a65e904f4bde91cc6fea6636c0a8": {
     "model_module": "@jupyter-widgets/controls",
     "model_module_version": "1.5.0",
     "model_name": "FloatProgressModel",
     "state": {
      "_dom_classes": [],
      "_model_module": "@jupyter-widgets/controls",
      "_model_module_version": "1.5.0",
      "_model_name": "FloatProgressModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/controls",
      "_view_module_version": "1.5.0",
      "_view_name": "ProgressView",
      "bar_style": "",
      "description": "",
      "description_tooltip": null,
      "layout": "IPY_MODEL_60553a0615334106a03d52877861569a",
      "max": 1,
      "min": 0,
      "orientation": "horizontal",
      "style": "IPY_MODEL_13c327d321444b32aa4349ec81e98cde",
      "value": 1
     }
    },
    "a4e5d6ce3657424eada1a68d0ff884b1": {
     "model_module": "@jupyter-widgets/controls",
     "model_module_version": "1.5.0",
     "model_name": "LabelModel",
     "state": {
      "_dom_classes": [],
      "_model_module": "@jupyter-widgets/controls",
      "_model_module_version": "1.5.0",
      "_model_name": "LabelModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/controls",
      "_view_module_version": "1.5.0",
      "_view_name": "LabelView",
      "description": "",
      "description_tooltip": null,
      "layout": "IPY_MODEL_d99f9f7346f34b1cbaaa865b0106a952",
      "placeholder": "​",
      "style": "IPY_MODEL_4979c4212a1b46ceb5664a9a8680b665",
      "value": "139.511 MB of 139.511 MB uploaded (0.000 MB deduped)\r"
     }
    },
    "aa9daced7eee485a918d1e398d228f51": {
     "model_module": "@jupyter-widgets/controls",
     "model_module_version": "1.5.0",
     "model_name": "HBoxModel",
     "state": {
      "_dom_classes": [],
      "_model_module": "@jupyter-widgets/controls",
      "_model_module_version": "1.5.0",
      "_model_name": "HBoxModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/controls",
      "_view_module_version": "1.5.0",
      "_view_name": "HBoxView",
      "box_style": "",
      "children": [
       "IPY_MODEL_6172b7637810408ebe9e2118c5d02c04",
       "IPY_MODEL_3b7a1d8560004241b9b06700bcdb5b1c",
       "IPY_MODEL_72f566c251ba4cf6a0282ed4340e1f08"
      ],
      "layout": "IPY_MODEL_6a7fe0a8c7d844c9b92ab9dab247ec79"
     }
    },
    "c76eba57c2af4a40b73731dc10b74c57": {
     "model_module": "@jupyter-widgets/base",
     "model_module_version": "1.2.0",
     "model_name": "LayoutModel",
     "state": {
      "_model_module": "@jupyter-widgets/base",
      "_model_module_version": "1.2.0",
      "_model_name": "LayoutModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/base",
      "_view_module_version": "1.2.0",
      "_view_name": "LayoutView",
      "align_content": null,
      "align_items": null,
      "align_self": null,
      "border": 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,
      "overflow_x": null,
      "overflow_y": null,
      "padding": null,
      "right": null,
      "top": null,
      "visibility": null,
      "width": null
     }
    },
    "d99f9f7346f34b1cbaaa865b0106a952": {
     "model_module": "@jupyter-widgets/base",
     "model_module_version": "1.2.0",
     "model_name": "LayoutModel",
     "state": {
      "_model_module": "@jupyter-widgets/base",
      "_model_module_version": "1.2.0",
      "_model_name": "LayoutModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/base",
      "_view_module_version": "1.2.0",
      "_view_name": "LayoutView",
      "align_content": null,
      "align_items": null,
      "align_self": null,
      "border": 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,
      "overflow_x": null,
      "overflow_y": null,
      "padding": null,
      "right": null,
      "top": null,
      "visibility": null,
      "width": null
     }
    },
    "dee95d2f12434f91b42f903656cc1ae8": {
     "model_module": "@jupyter-widgets/controls",
     "model_module_version": "1.5.0",
     "model_name": "VBoxModel",
     "state": {
      "_dom_classes": [],
      "_model_module": "@jupyter-widgets/controls",
      "_model_module_version": "1.5.0",
      "_model_name": "VBoxModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/controls",
      "_view_module_version": "1.5.0",
      "_view_name": "VBoxView",
      "box_style": "",
      "children": [
       "IPY_MODEL_a4e5d6ce3657424eada1a68d0ff884b1",
       "IPY_MODEL_8f31a65e904f4bde91cc6fea6636c0a8"
      ],
      "layout": "IPY_MODEL_c76eba57c2af4a40b73731dc10b74c57"
     }
    }
   }
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}