{
  "cells": [
    {
      "cell_type": "markdown",
      "source": [
        "# Clone official repo"
      ],
      "metadata": {
        "id": "P1rhi9xgJR-x"
      },
      "id": "P1rhi9xgJR-x"
    },
    {
      "cell_type": "code",
      "source": [
        "! git clone https://github.com/xuebinqin/DIS\n",
        "\n",
        "%cd ./DIS/IS-Net\n",
        "\n",
        "!pip install gdown"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "wlRB0Pq0JIvF",
        "outputId": "3fbaf6b9-f65d-48b7-fdf0-8e3d0e8c5614"
      },
      "id": "wlRB0Pq0JIvF",
      "execution_count": 1,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Cloning into 'DIS'...\n",
            "remote: Enumerating objects: 355, done.\u001b[K\n",
            "remote: Counting objects: 100% (121/121), done.\u001b[K\n",
            "remote: Compressing objects: 100% (45/45), done.\u001b[K\n",
            "remote: Total 355 (delta 96), reused 85 (delta 76), pack-reused 234\u001b[K\n",
            "Receiving objects: 100% (355/355), 49.60 MiB | 27.31 MiB/s, done.\n",
            "Resolving deltas: 100% (172/172), done.\n",
            "/content/DIS/IS-Net\n",
            "Requirement already satisfied: gdown in /usr/local/lib/python3.10/dist-packages (4.6.6)\n",
            "Requirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from gdown) (3.13.1)\n",
            "Requirement already satisfied: requests[socks] in /usr/local/lib/python3.10/dist-packages (from gdown) (2.31.0)\n",
            "Requirement already satisfied: six in /usr/local/lib/python3.10/dist-packages (from gdown) (1.16.0)\n",
            "Requirement already satisfied: tqdm in /usr/local/lib/python3.10/dist-packages (from gdown) (4.66.1)\n",
            "Requirement already satisfied: beautifulsoup4 in /usr/local/lib/python3.10/dist-packages (from gdown) (4.11.2)\n",
            "Requirement already satisfied: soupsieve>1.2 in /usr/local/lib/python3.10/dist-packages (from beautifulsoup4->gdown) (2.5)\n",
            "Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests[socks]->gdown) (3.3.2)\n",
            "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests[socks]->gdown) (3.6)\n",
            "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests[socks]->gdown) (2.0.7)\n",
            "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests[socks]->gdown) (2023.11.17)\n",
            "Requirement already satisfied: PySocks!=1.5.7,>=1.5.6 in /usr/local/lib/python3.10/dist-packages (from requests[socks]->gdown) (1.7.1)\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "!mkdir ./saved_models"
      ],
      "metadata": {
        "id": "FRrZ5Z_krzr7"
      },
      "id": "FRrZ5Z_krzr7",
      "execution_count": 2,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "# Imports"
      ],
      "metadata": {
        "id": "RO0DY6O3Jqe9"
      },
      "id": "RO0DY6O3Jqe9"
    },
    {
      "cell_type": "code",
      "source": [
        "import numpy as np\n",
        "from PIL import Image\n",
        "import torch\n",
        "from torch.autograd import Variable\n",
        "from torchvision import transforms\n",
        "import torch.nn.functional as F\n",
        "import gdown\n",
        "import os\n",
        "\n",
        "import requests\n",
        "import matplotlib.pyplot as plt\n",
        "from io import BytesIO\n",
        "\n",
        "# project imports\n",
        "from data_loader_cache import normalize, im_reader, im_preprocess\n",
        "from models import *\n"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "9fFNd2X_Js0e",
        "outputId": "039dd0c1-a69b-4f13-e3bf-913681f6e87d"
      },
      "id": "9fFNd2X_Js0e",
      "execution_count": 3,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "/usr/local/lib/python3.10/dist-packages/torch/nn/_reduction.py:42: UserWarning: size_average and reduce args will be deprecated, please use reduction='mean' instead.\n",
            "  warnings.warn(warning.format(ret))\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "# Helpers"
      ],
      "metadata": {
        "id": "h1C9zSdkJgtF"
      },
      "id": "h1C9zSdkJgtF"
    },
    {
      "cell_type": "code",
      "source": [
        "drive_link = \"https://drive.google.com/uc?id=1XHIzgTzY5BQHw140EDIgwIb53K659ENH\"\n",
        "\n",
        "# Specify the local path and filename\n",
        "local_path = \"/content/DIS/IS-Net/saved_models/isnet.pth\"\n",
        "\n",
        "# Download the file\n",
        "gdown.download(drive_link, local_path, quiet=False)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 105
        },
        "id": "D239BlYfo2cl",
        "outputId": "a4990760-18d6-4df6-9741-93f2e6e367d9"
      },
      "id": "D239BlYfo2cl",
      "execution_count": 4,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "Downloading...\n",
            "From: https://drive.google.com/uc?id=1XHIzgTzY5BQHw140EDIgwIb53K659ENH\n",
            "To: /content/DIS/IS-Net/saved_models/isnet.pth\n",
            "100%|██████████| 177M/177M [00:03<00:00, 57.9MB/s]\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "'/content/DIS/IS-Net/saved_models/isnet.pth'"
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "string"
            }
          },
          "metadata": {},
          "execution_count": 4
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "device = 'cuda' if torch.cuda.is_available() else 'cpu'\n",
        "\n",
        "# Download official weights\n",
        "\n",
        "\n",
        "\n",
        "class GOSNormalize(object):\n",
        "    '''\n",
        "    Normalize the Image using torch.transforms\n",
        "    '''\n",
        "    def __init__(self, mean=[0.485,0.456,0.406], std=[0.229,0.224,0.225]):\n",
        "        self.mean = mean\n",
        "        self.std = std\n",
        "\n",
        "    def __call__(self,image):\n",
        "        image = normalize(image,self.mean,self.std)\n",
        "        return image\n",
        "\n",
        "\n",
        "transform =  transforms.Compose([GOSNormalize([0.5,0.5,0.5],[1.0,1.0,1.0])])\n",
        "\n",
        "def load_image(im_path, hypar):\n",
        "    if im_path.startswith(\"http\"):\n",
        "        im_path = BytesIO(requests.get(im_path).content)\n",
        "\n",
        "    im = im_reader(im_path)\n",
        "    im, im_shp = im_preprocess(im, hypar[\"cache_size\"])\n",
        "    im = torch.divide(im,255.0)\n",
        "    shape = torch.from_numpy(np.array(im_shp))\n",
        "    return transform(im).unsqueeze(0), shape.unsqueeze(0) # make a batch of image, shape\n",
        "\n",
        "\n",
        "def build_model(hypar,device):\n",
        "    net = hypar[\"model\"]#GOSNETINC(3,1)\n",
        "\n",
        "    # convert to half precision\n",
        "    if(hypar[\"model_digit\"]==\"half\"):\n",
        "        net.half()\n",
        "        for layer in net.modules():\n",
        "            if isinstance(layer, nn.BatchNorm2d):\n",
        "                layer.float()\n",
        "\n",
        "    net.to(device)\n",
        "\n",
        "    if(hypar[\"restore_model\"]!=\"\"):\n",
        "        net.load_state_dict(torch.load(hypar[\"model_path\"]+\"/\"+hypar[\"restore_model\"],map_location=device))\n",
        "        net.to(device)\n",
        "    net.eval()\n",
        "    return net\n",
        "\n",
        "\n",
        "def predict(net,  inputs_val, shapes_val, hypar, device):\n",
        "    '''\n",
        "    Given an Image, predict the mask\n",
        "    '''\n",
        "    net.eval()\n",
        "\n",
        "    if(hypar[\"model_digit\"]==\"full\"):\n",
        "        inputs_val = inputs_val.type(torch.FloatTensor)\n",
        "    else:\n",
        "        inputs_val = inputs_val.type(torch.HalfTensor)\n",
        "\n",
        "\n",
        "    inputs_val_v = Variable(inputs_val, requires_grad=False).to(device) # wrap inputs in Variable\n",
        "\n",
        "    ds_val = net(inputs_val_v)[0] # list of 6 results\n",
        "\n",
        "    pred_val = ds_val[0][0,:,:,:] # B x 1 x H x W    # we want the first one which is the most accurate prediction\n",
        "\n",
        "    ## recover the prediction spatial size to the orignal image size\n",
        "    pred_val = torch.squeeze(F.upsample(torch.unsqueeze(pred_val,0),(shapes_val[0][0],shapes_val[0][1]),mode='bilinear'))\n",
        "\n",
        "    ma = torch.max(pred_val)\n",
        "    mi = torch.min(pred_val)\n",
        "    pred_val = (pred_val-mi)/(ma-mi) # max = 1\n",
        "\n",
        "    if device == 'cuda': torch.cuda.empty_cache()\n",
        "    return (pred_val.detach().cpu().numpy()*255).astype(np.uint8) # it is the mask we need"
      ],
      "metadata": {
        "id": "BFVvxhZQJkEy"
      },
      "id": "BFVvxhZQJkEy",
      "execution_count": 5,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "# Set Parameters"
      ],
      "metadata": {
        "id": "H7OQxVqaOgtk"
      },
      "id": "H7OQxVqaOgtk"
    },
    {
      "cell_type": "code",
      "execution_count": 6,
      "id": "189b719a-c9a2-4048-8620-0501fd5653ec",
      "metadata": {
        "id": "189b719a-c9a2-4048-8620-0501fd5653ec"
      },
      "outputs": [],
      "source": [
        "hypar = {} # paramters for inferencing\n",
        "\n",
        "\n",
        "hypar[\"model_path\"] =\"./saved_models\" ## load trained weights from this path\n",
        "hypar[\"restore_model\"] = \"isnet.pth\" ## name of the to-be-loaded weights\n",
        "hypar[\"interm_sup\"] = False ## indicate if activate intermediate feature supervision\n",
        "\n",
        "##  choose floating point accuracy --\n",
        "hypar[\"model_digit\"] = \"full\" ## indicates \"half\" or \"full\" accuracy of float number\n",
        "hypar[\"seed\"] = 0\n",
        "\n",
        "hypar[\"cache_size\"] = [1024, 1024] ## cached input spatial resolution, can be configured into different size\n",
        "\n",
        "## data augmentation parameters ---\n",
        "hypar[\"input_size\"] = [1024, 1024] ## mdoel input spatial size, usually use the same value hypar[\"cache_size\"], which means we don't further resize the images\n",
        "hypar[\"crop_size\"] = [1024, 1024] ## random crop size from the input, it is usually set as smaller than hypar[\"cache_size\"], e.g., [920,920] for data augmentation\n",
        "\n",
        "hypar[\"model\"] = ISNetDIS()"
      ]
    },
    {
      "cell_type": "markdown",
      "id": "0af5269e-26a6-4370-8863-92b7381ee90f",
      "metadata": {
        "tags": [],
        "id": "0af5269e-26a6-4370-8863-92b7381ee90f"
      },
      "source": [
        "# Build Model"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 7,
      "id": "b23ea487-1f64-4443-95b4-7998b5345310",
      "metadata": {
        "id": "b23ea487-1f64-4443-95b4-7998b5345310"
      },
      "outputs": [],
      "source": [
        "net = build_model(hypar, device)"
      ]
    },
    {
      "cell_type": "markdown",
      "id": "8beb1f62-0345-4c82-a2e3-9a4db55a55a2",
      "metadata": {
        "id": "8beb1f62-0345-4c82-a2e3-9a4db55a55a2"
      },
      "source": [
        "# Predict Mask"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "gsheetid = \"1n9kk7IHyBzkw5e08wpjjt-Ry5aE_thqGrJ97rMeN-K4\"\n",
        "sheet_name = \"sarvm\""
      ],
      "metadata": {
        "id": "8g-9kgrFm4nW"
      },
      "id": "8g-9kgrFm4nW",
      "execution_count": 8,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "gsheet_url = \"https://docs.google.com/spreadsheets/d/{}/gviz/tq?tqx=out:csv&sheet={}\".format(gsheetid, sheet_name)"
      ],
      "metadata": {
        "id": "cPw0Wk86nFD2"
      },
      "id": "cPw0Wk86nFD2",
      "execution_count": 9,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "gsheet_url"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 36
        },
        "id": "vJuRGNA4nI0o",
        "outputId": "43d83b79-7e9b-4826-8dc9-6d94607f1e63"
      },
      "id": "vJuRGNA4nI0o",
      "execution_count": 10,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "'https://docs.google.com/spreadsheets/d/1n9kk7IHyBzkw5e08wpjjt-Ry5aE_thqGrJ97rMeN-K4/gviz/tq?tqx=out:csv&sheet=sarvm'"
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "string"
            }
          },
          "metadata": {},
          "execution_count": 10
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "import pandas as pd\n",
        "df = pd.read_csv(gsheet_url)"
      ],
      "metadata": {
        "id": "qbuIkaiRlYMt"
      },
      "id": "qbuIkaiRlYMt",
      "execution_count": 11,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "image_path = df.iloc[-1]['Image']"
      ],
      "metadata": {
        "id": "NJSO2jQNoIwb"
      },
      "id": "NJSO2jQNoIwb",
      "execution_count": 13,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "drive_link = \"https://drive.google.com/uc?id=132iFIWDU6NSzZy4oEUurGplQ2Z3tGGKb\"\n",
        "\n",
        "# Specify the local path and filename\n",
        "local_path = \"/content/DIS/IS-Net/saved_models/input2.jpg\"\n",
        "\n",
        "# Download the file\n",
        "gdown.download(drive_link, local_path, quiet=False)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 105
        },
        "id": "TbqbGK-ZtQ67",
        "outputId": "ea4b8748-d999-464e-9c2e-3057c965a4f8"
      },
      "id": "TbqbGK-ZtQ67",
      "execution_count": 15,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "Downloading...\n",
            "From: https://drive.google.com/uc?id=132iFIWDU6NSzZy4oEUurGplQ2Z3tGGKb\n",
            "To: /content/DIS/IS-Net/saved_models/input2.jpg\n",
            "100%|██████████| 27.7k/27.7k [00:00<00:00, 42.7MB/s]\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "'/content/DIS/IS-Net/saved_models/input2.jpg'"
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "string"
            }
          },
          "metadata": {},
          "execution_count": 15
        }
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 17,
      "id": "036b21e8-556b-43dd-b9fb-1ea085f7f0f1",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 708
        },
        "id": "036b21e8-556b-43dd-b9fb-1ea085f7f0f1",
        "outputId": "e5c6ae23-a03b-4c37-a96c-87439ff81aa4"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "/usr/local/lib/python3.10/dist-packages/torch/nn/functional.py:3769: UserWarning: nn.functional.upsample is deprecated. Use nn.functional.interpolate instead.\n",
            "  warnings.warn(\"nn.functional.upsample is deprecated. Use nn.functional.interpolate instead.\")\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 3500x2000 with 2 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ],
      "source": [
        "from google.colab.patches import cv2_imshow\n",
        "from PIL import Image\n",
        "image_path = \"/content/DIS/IS-Net/saved_models/input2.jpg\"\n",
        "# image_bytes = BytesIO(requests.get(image_path).content)\n",
        "# print(image_bytes)\n",
        "image_tensor, orig_size = load_image(image_path, hypar)\n",
        "mask = predict(net,image_tensor,orig_size, hypar, device)\n",
        "image = Image.open(image_path)\n",
        "\n",
        "f, ax = plt.subplots(1,2, figsize = (35,20))\n",
        "\n",
        "# ax[0].imshow(np.array(Image.open(image_bytes))) # Original image\n",
        "# cv2_imshow(image_path)\n",
        "\n",
        "ax[0].imshow(mask, cmap = 'gray') # retouched image\n",
        "\n",
        "# ax[0].set_title(\"Original Image\")\n",
        "ax[0].set_title(\"Mask\")\n",
        "\n",
        "plt.show()"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "import cv2\n",
        "image = cv2.imread(image_path)\n",
        "h, w , _ = image.shape\n",
        "# print(h)\n",
        "# print(w)\n",
        "# print(_)\n",
        "# print(image)\n",
        "h, w , _ = image.shape\n",
        "# print(h)\n",
        "# print(w)\n",
        "# print(_)\n",
        "# new_image = np.zeros_like(image)\n",
        "# new_image[mask] = image[mask]\n",
        "new_image = cv2.bitwise_and(image, image, mask=mask)\n",
        "transparent_bg = np.zeros((new_image.shape[0],new_image.shape[1], new_image.shape[2]+1) , dtype=np.uint8)\n",
        "\n",
        "# Apply the mask to the transparent background\n",
        "transparent_bg[:, :, :3] = new_image\n",
        "\n",
        "# Set the alpha channel using the mask\n",
        "transparent_bg[:, :, 3] = mask\n",
        "\n",
        "# Save the new image with a transparent background\n",
        "output_path = \"/content/output.png\"\n",
        "cv2.imwrite(output_path, transparent_bg)\n",
        "# Save the new image\n",
        "# output_path = \"/content/output.jpg\"\n",
        "# cv2.imwrite(output_path, new_image)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "xnLQbsHS7IF7",
        "outputId": "5c08d485-e617-4a7c-f714-6ec04c0543f5"
      },
      "id": "xnLQbsHS7IF7",
      "execution_count": 18,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "True"
            ]
          },
          "metadata": {},
          "execution_count": 18
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [],
      "metadata": {
        "id": "rJoaRMr8T5um"
      },
      "id": "rJoaRMr8T5um",
      "execution_count": null,
      "outputs": []
    }
  ],
  "metadata": {
    "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"
    },
    "colab": {
      "provenance": []
    }
  },
  "nbformat": 4,
  "nbformat_minor": 5
}