make_good_supply_line_bad

make_good_supply_line_bad.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Requirement already satisfied: torch in c:\\users\\dixonjames\\documents\\chrp-demo\\.venv\\lib\\site-packages (2.5.1)\n",
      "Requirement already satisfied: torchvision in c:\\users\\dixonjames\\documents\\chrp-demo\\.venv\\lib\\site-packages (0.20.1)\n",
      "Requirement already satisfied: opencv-python in c:\\users\\dixonjames\\documents\\chrp-demo\\.venv\\lib\\site-packages (4.11.0.86)\n",
      "Requirement already satisfied: numpy in c:\\users\\dixonjames\\documents\\chrp-demo\\.venv\\lib\\site-packages (2.0.2)\n",
      "Requirement already satisfied: pillow in c:\\users\\dixonjames\\documents\\chrp-demo\\.venv\\lib\\site-packages (11.0.0)\n",
      "Requirement already satisfied: matplotlib in c:\\users\\dixonjames\\documents\\chrp-demo\\.venv\\lib\\site-packages (3.10.0)\n",
      "Requirement already satisfied: filelock in c:\\users\\dixonjames\\documents\\chrp-demo\\.venv\\lib\\site-packages (from torch) (3.16.1)\n",
      "Requirement already satisfied: typing-extensions>=4.8.0 in c:\\users\\dixonjames\\documents\\chrp-demo\\.venv\\lib\\site-packages (from torch) (4.12.2)\n",
      "Requirement already satisfied: networkx in c:\\users\\dixonjames\\documents\\chrp-demo\\.venv\\lib\\site-packages (from torch) (3.4.2)\n",
      "Requirement already satisfied: jinja2 in c:\\users\\dixonjames\\documents\\chrp-demo\\.venv\\lib\\site-packages (from torch) (3.1.4)\n",
      "Requirement already satisfied: fsspec in c:\\users\\dixonjames\\documents\\chrp-demo\\.venv\\lib\\site-packages (from torch) (2024.10.0)\n",
      "Requirement already satisfied: sympy==1.13.1 in c:\\users\\dixonjames\\documents\\chrp-demo\\.venv\\lib\\site-packages (from torch) (1.13.1)\n",
      "Requirement already satisfied: mpmath<1.4,>=1.1.0 in c:\\users\\dixonjames\\documents\\chrp-demo\\.venv\\lib\\site-packages (from sympy==1.13.1->torch) (1.3.0)\n",
      "Requirement already satisfied: contourpy>=1.0.1 in c:\\users\\dixonjames\\documents\\chrp-demo\\.venv\\lib\\site-packages (from matplotlib) (1.3.1)\n",
      "Requirement already satisfied: cycler>=0.10 in c:\\users\\dixonjames\\documents\\chrp-demo\\.venv\\lib\\site-packages (from matplotlib) (0.12.1)\n",
      "Requirement already satisfied: fonttools>=4.22.0 in c:\\users\\dixonjames\\documents\\chrp-demo\\.venv\\lib\\site-packages (from matplotlib) (4.55.5)\n",
      "Requirement already satisfied: kiwisolver>=1.3.1 in c:\\users\\dixonjames\\documents\\chrp-demo\\.venv\\lib\\site-packages (from matplotlib) (1.4.8)\n",
      "Requirement already satisfied: packaging>=20.0 in c:\\users\\dixonjames\\documents\\chrp-demo\\.venv\\lib\\site-packages (from matplotlib) (24.2)\n",
      "Requirement already satisfied: pyparsing>=2.3.1 in c:\\users\\dixonjames\\documents\\chrp-demo\\.venv\\lib\\site-packages (from matplotlib) (3.2.1)\n",
      "Requirement already satisfied: python-dateutil>=2.7 in c:\\users\\dixonjames\\documents\\chrp-demo\\.venv\\lib\\site-packages (from matplotlib) (2.9.0.post0)\n",
      "Requirement already satisfied: six>=1.5 in c:\\users\\dixonjames\\documents\\chrp-demo\\.venv\\lib\\site-packages (from python-dateutil>=2.7->matplotlib) (1.17.0)\n",
      "Requirement already satisfied: MarkupSafe>=2.0 in c:\\users\\dixonjames\\documents\\chrp-demo\\.venv\\lib\\site-packages (from jinja2->torch) (3.0.2)\n",
      "Note: you may need to restart the kernel to use updated packages.\n"
     ]
    }
   ],
   "source": [
    "%pip install torch torchvision opencv-python numpy pillow matplotlib"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "c:\\Users\\dixonjames\\Documents\\chrp-demo\\.venv\\Lib\\site-packages\\torchvision\\models\\_utils.py:208: UserWarning: The parameter 'pretrained' is deprecated since 0.13 and may be removed in the future, please use 'weights' instead.\n",
      "  warnings.warn(\n",
      "c:\\Users\\dixonjames\\Documents\\chrp-demo\\.venv\\Lib\\site-packages\\torchvision\\models\\_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and may be removed in the future. The current behavior is equivalent to passing `weights=MaskRCNN_ResNet50_FPN_Weights.COCO_V1`. You can also use `weights=MaskRCNN_ResNet50_FPN_Weights.DEFAULT` to get the most up-to-date weights.\n",
      "  warnings.warn(msg)\n",
      "Downloading: \"https://download.pytorch.org/models/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth\" to C:\\Users\\dixonjames/.cache\\torch\\hub\\checkpoints\\maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth\n",
      "100%|██████████| 170M/170M [00:05<00:00, 32.0MB/s] \n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "MaskRCNN(\n",
       "  (transform): GeneralizedRCNNTransform(\n",
       "      Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])\n",
       "      Resize(min_size=(800,), max_size=1333, mode='bilinear')\n",
       "  )\n",
       "  (backbone): BackboneWithFPN(\n",
       "    (body): IntermediateLayerGetter(\n",
       "      (conv1): Conv2d(3, 64, kernel_size=(7, 7), stride=(2, 2), padding=(3, 3), bias=False)\n",
       "      (bn1): FrozenBatchNorm2d(64, eps=0.0)\n",
       "      (relu): ReLU(inplace=True)\n",
       "      (maxpool): MaxPool2d(kernel_size=3, stride=2, padding=1, dilation=1, ceil_mode=False)\n",
       "      (layer1): Sequential(\n",
       "        (0): Bottleneck(\n",
       "          (conv1): Conv2d(64, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
       "          (bn1): FrozenBatchNorm2d(64, eps=0.0)\n",
       "          (conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
       "          (bn2): FrozenBatchNorm2d(64, eps=0.0)\n",
       "          (conv3): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
       "          (bn3): FrozenBatchNorm2d(256, eps=0.0)\n",
       "          (relu): ReLU(inplace=True)\n",
       "          (downsample): Sequential(\n",
       "            (0): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
       "            (1): FrozenBatchNorm2d(256, eps=0.0)\n",
       "          )\n",
       "        )\n",
       "        (1): Bottleneck(\n",
       "          (conv1): Conv2d(256, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
       "          (bn1): FrozenBatchNorm2d(64, eps=0.0)\n",
       "          (conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
       "          (bn2): FrozenBatchNorm2d(64, eps=0.0)\n",
       "          (conv3): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
       "          (bn3): FrozenBatchNorm2d(256, eps=0.0)\n",
       "          (relu): ReLU(inplace=True)\n",
       "        )\n",
       "        (2): Bottleneck(\n",
       "          (conv1): Conv2d(256, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
       "          (bn1): FrozenBatchNorm2d(64, eps=0.0)\n",
       "          (conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
       "          (bn2): FrozenBatchNorm2d(64, eps=0.0)\n",
       "          (conv3): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
       "          (bn3): FrozenBatchNorm2d(256, eps=0.0)\n",
       "          (relu): ReLU(inplace=True)\n",
       "        )\n",
       "      )\n",
       "      (layer2): Sequential(\n",
       "        (0): Bottleneck(\n",
       "          (conv1): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
       "          (bn1): FrozenBatchNorm2d(128, eps=0.0)\n",
       "          (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)\n",
       "          (bn2): FrozenBatchNorm2d(128, eps=0.0)\n",
       "          (conv3): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
       "          (bn3): FrozenBatchNorm2d(512, eps=0.0)\n",
       "          (relu): ReLU(inplace=True)\n",
       "          (downsample): Sequential(\n",
       "            (0): Conv2d(256, 512, kernel_size=(1, 1), stride=(2, 2), bias=False)\n",
       "            (1): FrozenBatchNorm2d(512, eps=0.0)\n",
       "          )\n",
       "        )\n",
       "        (1): Bottleneck(\n",
       "          (conv1): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
       "          (bn1): FrozenBatchNorm2d(128, eps=0.0)\n",
       "          (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
       "          (bn2): FrozenBatchNorm2d(128, eps=0.0)\n",
       "          (conv3): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
       "          (bn3): FrozenBatchNorm2d(512, eps=0.0)\n",
       "          (relu): ReLU(inplace=True)\n",
       "        )\n",
       "        (2): Bottleneck(\n",
       "          (conv1): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
       "          (bn1): FrozenBatchNorm2d(128, eps=0.0)\n",
       "          (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
       "          (bn2): FrozenBatchNorm2d(128, eps=0.0)\n",
       "          (conv3): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
       "          (bn3): FrozenBatchNorm2d(512, eps=0.0)\n",
       "          (relu): ReLU(inplace=True)\n",
       "        )\n",
       "        (3): Bottleneck(\n",
       "          (conv1): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
       "          (bn1): FrozenBatchNorm2d(128, eps=0.0)\n",
       "          (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
       "          (bn2): FrozenBatchNorm2d(128, eps=0.0)\n",
       "          (conv3): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
       "          (bn3): FrozenBatchNorm2d(512, eps=0.0)\n",
       "          (relu): ReLU(inplace=True)\n",
       "        )\n",
       "      )\n",
       "      (layer3): Sequential(\n",
       "        (0): Bottleneck(\n",
       "          (conv1): Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
       "          (bn1): FrozenBatchNorm2d(256, eps=0.0)\n",
       "          (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)\n",
       "          (bn2): FrozenBatchNorm2d(256, eps=0.0)\n",
       "          (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
       "          (bn3): FrozenBatchNorm2d(1024, eps=0.0)\n",
       "          (relu): ReLU(inplace=True)\n",
       "          (downsample): Sequential(\n",
       "            (0): Conv2d(512, 1024, kernel_size=(1, 1), stride=(2, 2), bias=False)\n",
       "            (1): FrozenBatchNorm2d(1024, eps=0.0)\n",
       "          )\n",
       "        )\n",
       "        (1): Bottleneck(\n",
       "          (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
       "          (bn1): FrozenBatchNorm2d(256, eps=0.0)\n",
       "          (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
       "          (bn2): FrozenBatchNorm2d(256, eps=0.0)\n",
       "          (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
       "          (bn3): FrozenBatchNorm2d(1024, eps=0.0)\n",
       "          (relu): ReLU(inplace=True)\n",
       "        )\n",
       "        (2): Bottleneck(\n",
       "          (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
       "          (bn1): FrozenBatchNorm2d(256, eps=0.0)\n",
       "          (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
       "          (bn2): FrozenBatchNorm2d(256, eps=0.0)\n",
       "          (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
       "          (bn3): FrozenBatchNorm2d(1024, eps=0.0)\n",
       "          (relu): ReLU(inplace=True)\n",
       "        )\n",
       "        (3): Bottleneck(\n",
       "          (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
       "          (bn1): FrozenBatchNorm2d(256, eps=0.0)\n",
       "          (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
       "          (bn2): FrozenBatchNorm2d(256, eps=0.0)\n",
       "          (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
       "          (bn3): FrozenBatchNorm2d(1024, eps=0.0)\n",
       "          (relu): ReLU(inplace=True)\n",
       "        )\n",
       "        (4): Bottleneck(\n",
       "          (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
       "          (bn1): FrozenBatchNorm2d(256, eps=0.0)\n",
       "          (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
       "          (bn2): FrozenBatchNorm2d(256, eps=0.0)\n",
       "          (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
       "          (bn3): FrozenBatchNorm2d(1024, eps=0.0)\n",
       "          (relu): ReLU(inplace=True)\n",
       "        )\n",
       "        (5): Bottleneck(\n",
       "          (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
       "          (bn1): FrozenBatchNorm2d(256, eps=0.0)\n",
       "          (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
       "          (bn2): FrozenBatchNorm2d(256, eps=0.0)\n",
       "          (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
       "          (bn3): FrozenBatchNorm2d(1024, eps=0.0)\n",
       "          (relu): ReLU(inplace=True)\n",
       "        )\n",
       "      )\n",
       "      (layer4): Sequential(\n",
       "        (0): Bottleneck(\n",
       "          (conv1): Conv2d(1024, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
       "          (bn1): FrozenBatchNorm2d(512, eps=0.0)\n",
       "          (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)\n",
       "          (bn2): FrozenBatchNorm2d(512, eps=0.0)\n",
       "          (conv3): Conv2d(512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
       "          (bn3): FrozenBatchNorm2d(2048, eps=0.0)\n",
       "          (relu): ReLU(inplace=True)\n",
       "          (downsample): Sequential(\n",
       "            (0): Conv2d(1024, 2048, kernel_size=(1, 1), stride=(2, 2), bias=False)\n",
       "            (1): FrozenBatchNorm2d(2048, eps=0.0)\n",
       "          )\n",
       "        )\n",
       "        (1): Bottleneck(\n",
       "          (conv1): Conv2d(2048, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
       "          (bn1): FrozenBatchNorm2d(512, eps=0.0)\n",
       "          (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
       "          (bn2): FrozenBatchNorm2d(512, eps=0.0)\n",
       "          (conv3): Conv2d(512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
       "          (bn3): FrozenBatchNorm2d(2048, eps=0.0)\n",
       "          (relu): ReLU(inplace=True)\n",
       "        )\n",
       "        (2): Bottleneck(\n",
       "          (conv1): Conv2d(2048, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
       "          (bn1): FrozenBatchNorm2d(512, eps=0.0)\n",
       "          (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
       "          (bn2): FrozenBatchNorm2d(512, eps=0.0)\n",
       "          (conv3): Conv2d(512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
       "          (bn3): FrozenBatchNorm2d(2048, eps=0.0)\n",
       "          (relu): ReLU(inplace=True)\n",
       "        )\n",
       "      )\n",
       "    )\n",
       "    (fpn): FeaturePyramidNetwork(\n",
       "      (inner_blocks): ModuleList(\n",
       "        (0): Conv2dNormActivation(\n",
       "          (0): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1))\n",
       "        )\n",
       "        (1): Conv2dNormActivation(\n",
       "          (0): Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1))\n",
       "        )\n",
       "        (2): Conv2dNormActivation(\n",
       "          (0): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1))\n",
       "        )\n",
       "        (3): Conv2dNormActivation(\n",
       "          (0): Conv2d(2048, 256, kernel_size=(1, 1), stride=(1, 1))\n",
       "        )\n",
       "      )\n",
       "      (layer_blocks): ModuleList(\n",
       "        (0-3): 4 x Conv2dNormActivation(\n",
       "          (0): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
       "        )\n",
       "      )\n",
       "      (extra_blocks): LastLevelMaxPool()\n",
       "    )\n",
       "  )\n",
       "  (rpn): RegionProposalNetwork(\n",
       "    (anchor_generator): AnchorGenerator()\n",
       "    (head): RPNHead(\n",
       "      (conv): Sequential(\n",
       "        (0): Conv2dNormActivation(\n",
       "          (0): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
       "          (1): ReLU(inplace=True)\n",
       "        )\n",
       "      )\n",
       "      (cls_logits): Conv2d(256, 3, kernel_size=(1, 1), stride=(1, 1))\n",
       "      (bbox_pred): Conv2d(256, 12, kernel_size=(1, 1), stride=(1, 1))\n",
       "    )\n",
       "  )\n",
       "  (roi_heads): RoIHeads(\n",
       "    (box_roi_pool): MultiScaleRoIAlign(featmap_names=['0', '1', '2', '3'], output_size=(7, 7), sampling_ratio=2)\n",
       "    (box_head): TwoMLPHead(\n",
       "      (fc6): Linear(in_features=12544, out_features=1024, bias=True)\n",
       "      (fc7): Linear(in_features=1024, out_features=1024, bias=True)\n",
       "    )\n",
       "    (box_predictor): FastRCNNPredictor(\n",
       "      (cls_score): Linear(in_features=1024, out_features=91, bias=True)\n",
       "      (bbox_pred): Linear(in_features=1024, out_features=364, bias=True)\n",
       "    )\n",
       "    (mask_roi_pool): MultiScaleRoIAlign(featmap_names=['0', '1', '2', '3'], output_size=(14, 14), sampling_ratio=2)\n",
       "    (mask_head): MaskRCNNHeads(\n",
       "      (0): Conv2dNormActivation(\n",
       "        (0): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
       "        (1): ReLU(inplace=True)\n",
       "      )\n",
       "      (1): Conv2dNormActivation(\n",
       "        (0): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
       "        (1): ReLU(inplace=True)\n",
       "      )\n",
       "      (2): Conv2dNormActivation(\n",
       "        (0): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
       "        (1): ReLU(inplace=True)\n",
       "      )\n",
       "      (3): Conv2dNormActivation(\n",
       "        (0): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
       "        (1): ReLU(inplace=True)\n",
       "      )\n",
       "    )\n",
       "    (mask_predictor): MaskRCNNPredictor(\n",
       "      (conv5_mask): ConvTranspose2d(256, 256, kernel_size=(2, 2), stride=(2, 2))\n",
       "      (relu): ReLU(inplace=True)\n",
       "      (mask_fcn_logits): Conv2d(256, 91, kernel_size=(1, 1), stride=(1, 1))\n",
       "    )\n",
       "  )\n",
       ")"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import torch\n",
    "import torchvision\n",
    "import torchvision.transforms as T\n",
    "import numpy as np\n",
    "import cv2\n",
    "from PIL import Image\n",
    "import matplotlib.pyplot as plt\n",
    "\n",
    "model = torchvision.models.detection.maskrcnn_resnet50_fpn(pretrained=True)\n",
    "model.eval()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "image_path = \"1-Good-Supply Line\\image_Good_Supply Line_1158401.jpg\"  #image_Good_Supply Line_1158476 #image_Good_Supply Line_1158401.jpg\n",
    "image = Image.open(image_path).convert(\"RGB\")\n",
    "\n",
    "plt.imshow(image)\n",
    "plt.axis(\"off\")\n",
    "plt.show()\n",
    "\n",
    "transform = T.Compose([T.ToTensor(),])\n",
    "input_tensor = transform(image).unsqueeze(0)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Detected Labels: [32 32 32 86 48 49 16 48 28 87 86]\n",
      "Confidence Scores: [0.44318357 0.3729521  0.16937003 0.16769741 0.11933742 0.11223593\n",
      " 0.08532872 0.07628033 0.0616294  0.06011672 0.05636086]\n"
     ]
    }
   ],
   "source": [
    "\n",
    "with torch.no_grad():\n",
    "    predictions = model(input_tensor)\n",
    "\n",
    "pred_boxes = predictions[0][\"boxes\"].cpu().numpy()  \n",
    "pred_masks = predictions[0][\"masks\"].cpu().numpy()  \n",
    "pred_labels = predictions[0][\"labels\"].cpu().numpy() \n",
    "pred_scores = predictions[0][\"scores\"].cpu().numpy()\n",
    "\n",
    "print(\"Detected Labels:\", pred_labels)\n",
    "print(\"Confidence Scores:\", pred_scores)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Pipe detected with confidence: 0.44\n"
     ]
    }
   ],
   "source": [
    "confidence_threshold = 0.25\n",
    "\n",
    "best_idx = np.argmax(pred_scores) if len(pred_scores) > 0 else None\n",
    "\n",
    "if best_idx is not None and pred_scores[best_idx] > confidence_threshold:\n",
    "    pipe_mask = pred_masks[best_idx][0]  \n",
    "    pipe_box = pred_boxes[best_idx]  \n",
    "    print(f\"Pipe detected with confidence: {pred_scores[best_idx]:.2f}\")\n",
    "else:\n",
    "    print(\"No pipe detected with high confidence.\")\n",
    "    pipe_mask = None\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "if pipe_mask is not None:\n",
    "\n",
    "    image_np = np.array(image)\n",
    "\n",
    "    pipe_mask_resized = cv2.resize(pipe_mask, (image.width, image.height), interpolation=cv2.INTER_NEAREST)\n",
    "\n",
    "    rust_texture = cv2.imread(\"rust_texture.jpg\")\n",
    "    rust_texture = cv2.cvtColor(rust_texture, cv2.COLOR_BGR2RGB)\n",
    "    rust_texture = cv2.resize(rust_texture, (image.width, image.height))\n",
    "\n",
    "    pipe_mask_3d = np.stack([pipe_mask_resized] * 3, axis=-1)\n",
    "\n",
    "    alpha = 0.5\n",
    "    rusted_pipe = image_np * (1 - pipe_mask_3d) + rust_texture * pipe_mask_3d * alpha\n",
    "\n",
    "    plt.imshow(rusted_pipe.astype(np.uint8))\n",
    "    plt.axis(\"off\")\n",
    "    plt.show()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Requirement already satisfied: torch in c:\\users\\dixonjames\\documents\\chrp-demo\\.venv\\lib\\site-packages (2.5.1)\n",
      "Requirement already satisfied: transformers in c:\\users\\dixonjames\\documents\\chrp-demo\\.venv\\lib\\site-packages (4.47.0)\n",
      "Requirement already satisfied: pillow in c:\\users\\dixonjames\\documents\\chrp-demo\\.venv\\lib\\site-packages (11.0.0)\n",
      "Requirement already satisfied: numpy in c:\\users\\dixonjames\\documents\\chrp-demo\\.venv\\lib\\site-packages (2.0.2)\n",
      "Requirement already satisfied: filelock in c:\\users\\dixonjames\\documents\\chrp-demo\\.venv\\lib\\site-packages (from torch) (3.16.1)\n",
      "Requirement already satisfied: typing-extensions>=4.8.0 in c:\\users\\dixonjames\\documents\\chrp-demo\\.venv\\lib\\site-packages (from torch) (4.12.2)\n",
      "Requirement already satisfied: networkx in c:\\users\\dixonjames\\documents\\chrp-demo\\.venv\\lib\\site-packages (from torch) (3.4.2)\n",
      "Requirement already satisfied: jinja2 in c:\\users\\dixonjames\\documents\\chrp-demo\\.venv\\lib\\site-packages (from torch) (3.1.4)\n",
      "Requirement already satisfied: fsspec in c:\\users\\dixonjames\\documents\\chrp-demo\\.venv\\lib\\site-packages (from torch) (2024.10.0)\n",
      "Requirement already satisfied: sympy==1.13.1 in c:\\users\\dixonjames\\documents\\chrp-demo\\.venv\\lib\\site-packages (from torch) (1.13.1)\n",
      "Requirement already satisfied: mpmath<1.4,>=1.1.0 in c:\\users\\dixonjames\\documents\\chrp-demo\\.venv\\lib\\site-packages (from sympy==1.13.1->torch) (1.3.0)\n",
      "Requirement already satisfied: huggingface-hub<1.0,>=0.24.0 in c:\\users\\dixonjames\\documents\\chrp-demo\\.venv\\lib\\site-packages (from transformers) (0.27.0)\n",
      "Requirement already satisfied: packaging>=20.0 in c:\\users\\dixonjames\\documents\\chrp-demo\\.venv\\lib\\site-packages (from transformers) (24.2)\n",
      "Requirement already satisfied: pyyaml>=5.1 in c:\\users\\dixonjames\\documents\\chrp-demo\\.venv\\lib\\site-packages (from transformers) (6.0.2)\n",
      "Requirement already satisfied: regex!=2019.12.17 in c:\\users\\dixonjames\\documents\\chrp-demo\\.venv\\lib\\site-packages (from transformers) (2024.11.6)\n",
      "Requirement already satisfied: requests in c:\\users\\dixonjames\\documents\\chrp-demo\\.venv\\lib\\site-packages (from transformers) (2.32.3)\n",
      "Requirement already satisfied: tokenizers<0.22,>=0.21 in c:\\users\\dixonjames\\documents\\chrp-demo\\.venv\\lib\\site-packages (from transformers) (0.21.0)\n",
      "Requirement already satisfied: safetensors>=0.4.1 in c:\\users\\dixonjames\\documents\\chrp-demo\\.venv\\lib\\site-packages (from transformers) (0.4.5)\n",
      "Requirement already satisfied: tqdm>=4.27 in c:\\users\\dixonjames\\documents\\chrp-demo\\.venv\\lib\\site-packages (from transformers) (4.67.1)\n",
      "Requirement already satisfied: colorama in c:\\users\\dixonjames\\documents\\chrp-demo\\.venv\\lib\\site-packages (from tqdm>=4.27->transformers) (0.4.6)\n",
      "Requirement already satisfied: MarkupSafe>=2.0 in c:\\users\\dixonjames\\documents\\chrp-demo\\.venv\\lib\\site-packages (from jinja2->torch) (3.0.2)\n",
      "Requirement already satisfied: charset-normalizer<4,>=2 in c:\\users\\dixonjames\\documents\\chrp-demo\\.venv\\lib\\site-packages (from requests->transformers) (3.4.0)\n",
      "Requirement already satisfied: idna<4,>=2.5 in c:\\users\\dixonjames\\documents\\chrp-demo\\.venv\\lib\\site-packages (from requests->transformers) (3.10)\n",
      "Requirement already satisfied: urllib3<3,>=1.21.1 in c:\\users\\dixonjames\\documents\\chrp-demo\\.venv\\lib\\site-packages (from requests->transformers) (2.2.3)\n",
      "Requirement already satisfied: certifi>=2017.4.17 in c:\\users\\dixonjames\\documents\\chrp-demo\\.venv\\lib\\site-packages (from requests->transformers) (2024.12.14)\n",
      "Note: you may need to restart the kernel to use updated packages.\n"
     ]
    }
   ],
   "source": [
    "%pip install torch transformers pillow numpy\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [],
   "source": [
    "import torch\n",
    "from transformers import CLIPModel, CLIPProcessor\n",
    "from PIL import Image\n",
    "import numpy as np\n",
    "\n",
    "model = CLIPModel.from_pretrained(\"openai/clip-vit-base-patch32\")\n",
    "processor = CLIPProcessor.from_pretrained(\"openai/clip-vit-base-patch32\")\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [],
   "source": [
    "if not isinstance(image, Image.Image):\n",
    "    original_image = Image.fromarray(image.astype(np.uint8))\n",
    "\n",
    "if not isinstance(rusted_pipe, Image.Image):\n",
    "    rusted_image = Image.fromarray(rusted_pipe.astype(np.uint8))\n",
    "\n",
    "device = \"cuda\" if torch.cuda.is_available() else \"cpu\"\n",
    "model = model.to(device)\n",
    "\n",
    "inputs_original = processor(images=original_image, return_tensors=\"pt\").to(device)\n",
    "inputs_rusted = processor(images=rusted_image, return_tensors=\"pt\").to(device)\n",
    "\n",
    "with torch.no_grad():\n",
    "    original_embedding = model.get_image_features(**inputs_original)\n",
    "    rusted_embedding = model.get_image_features(**inputs_rusted)\n",
    "\n",
    "original_embedding = original_embedding / original_embedding.norm(p=2, dim=-1, keepdim=True)\n",
    "rusted_embedding = rusted_embedding / rusted_embedding.norm(p=2, dim=-1, keepdim=True)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Cosine Similarity: 0.8703\n",
      "Euclidean Distance: 0.5093\n"
     ]
    }
   ],
   "source": [
    "from torch.nn.functional import cosine_similarity\n",
    "\n",
    "similarity = cosine_similarity(original_embedding, rusted_embedding)\n",
    "print(f\"Cosine Similarity: {similarity.item():.4f}\")\n",
    "\n",
    "distance = torch.norm(original_embedding - rusted_embedding, p=2).item()\n",
    "print(f\"Euclidean Distance: {distance:.4f}\")\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {},
   "outputs": [],
   "source": [
    "import torch\n",
    "import seaborn as sns\n",
    "import matplotlib.pyplot as plt\n",
    "import numpy as np\n",
    "from torch.nn.functional import cosine_similarity\n",
    "\n",
    "similarity_score = cosine_similarity(original_embedding, rusted_embedding).cpu().numpy()\n",
    "similarity_matrix = similarity_score.reshape(1, 1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 500x400 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "import seaborn as sns\n",
    "import matplotlib.pyplot as plt\n",
    "\n",
    "plt.figure(figsize=(5, 4))\n",
    "sns.heatmap(similarity_matrix, annot=True, cmap=\"coolwarm\", linewidths=0.5, vmin=0, vmax=1)\n",
    "\n",
    "plt.xlabel(\"Rusted Pipe\")\n",
    "plt.ylabel(\"Original Pipe\")\n",
    "plt.title(\"Cosine Similarity Heatmap (Original vs. Rusted Pipe)\")\n",
    "\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 600x500 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "difference_matrix = np.abs(original_embedding.cpu().numpy() - rusted_embedding.cpu().numpy())\n",
    "\n",
    "plt.figure(figsize=(6, 5))\n",
    "sns.heatmap(difference_matrix, annot=False, cmap=\"viridis\", linewidths=0.5)\n",
    "\n",
    "plt.xlabel(\"Rusted Pipe Embedding\")\n",
    "plt.ylabel(\"Original Pipe Embedding\")\n",
    "plt.title(\"Difference Heatmap (Feature Change Due to Rust)\")\n",
    "plt.show()"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": ".venv",
   "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": "3.11.9"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}