{ "metadata": { "kernelspec": { "language": "python", "display_name": "Python 3", "name": "python3" }, "language_info": { "name": "python", "version": "3.10.12", "mimetype": "text/x-python", "codemirror_mode": { "name": "ipython", "version": 3 }, "pygments_lexer": "ipython3", "nbconvert_exporter": "python", "file_extension": ".py" }, "kaggle": { "accelerator": "nvidiaTeslaT4", "dataSources": [ { "sourceId": 1267593, "sourceType": "datasetVersion", "datasetId": 723383 }, { "sourceId": 1299795, "sourceType": "datasetVersion", "datasetId": 751906 } ], "dockerImageVersionId": 30823, "isInternetEnabled": true, "language": "python", "sourceType": "notebook", "isGpuEnabled": true } }, "nbformat_minor": 4, "nbformat": 4, "cells": [ { "cell_type": "code", "source": [ "import segmentation_models_pytorch as smp\n", "import os\n", "import matplotlib.pyplot as plt\n", "from PIL import Image\n", "import numpy as np\n", "import torch\n", "from torch.utils.data import Dataset, DataLoader\n", "from torchvision import transforms, utils\n", "import torch.nn as nn\n", "import torch.optim as optim\n", "from torch.optim import lr_scheduler\n", "import time\n", "import albumentations as Album\n", "import torch.nn.functional as Functional\n", "import pandas as pd\n", "import nibabel as nib\n", "from tqdm import tqdm" ], "metadata": { "_uuid": "8f2839f25d086af736a60e9eeb907d3b93b6e0e5", "_cell_guid": "b1076dfc-b9ad-4769-8c92-a6c4dae69d19", "trusted": true, "execution": { "iopub.status.busy": "2025-01-09T16:36:25.227303Z", "iopub.execute_input": "2025-01-09T16:36:25.227597Z", "iopub.status.idle": "2025-01-09T16:36:35.081281Z", "shell.execute_reply.started": "2025-01-09T16:36:25.227573Z", "shell.execute_reply": "2025-01-09T16:36:35.080659Z" }, "ExecuteTime": { "end_time": "2025-01-21T13:45:36.111460Z", "start_time": "2025-01-21T13:45:36.096955Z" } }, "outputs": [], "execution_count": 135 }, { "metadata": { "ExecuteTime": { "end_time": "2025-01-21T13:45:36.690308Z", "start_time": "2025-01-21T13:45:36.114962Z" } }, "cell_type": "code", "source": "! pip show albumentations", "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Name: albumentations\n", "Version: 1.1.0\n", "Summary: Fast image augmentation library and easy to use wrapper around other libraries\n", "Home-page: https://github.com/albumentations-team/albumentations\n", "Author: Buslaev Alexander, Alexander Parinov, Vladimir Iglovikov, Eugene Khvedchenya, Druzhinin Mikhail\n", "Author-email: \n", "License: MIT\n", "Location: c:\\users\\sammi\\anaconda3\\envs\\tensorflow-env\\lib\\site-packages\n", "Requires: numpy, opencv-python-headless, PyYAML, qudida, scikit-image, scipy\n", "Required-by: \n" ] } ], "execution_count": 136 }, { "cell_type": "code", "source": [ "training_df = pd.read_csv('data/archive/BraTS2020_TrainingData/MICCAI_BraTS2020_TrainingData/name_mapping.csv')\n", "root_df = 'data/archive/BraTS2020_TrainingData/MICCAI_BraTS2020_TrainingData'" ], "metadata": { "trusted": true, "execution": { "iopub.status.busy": "2025-01-09T16:36:48.478879Z", "iopub.execute_input": "2025-01-09T16:36:48.479196Z", "iopub.status.idle": "2025-01-09T16:36:48.500028Z", "shell.execute_reply.started": "2025-01-09T16:36:48.479170Z", "shell.execute_reply": "2025-01-09T16:36:48.499404Z" }, "ExecuteTime": { "end_time": "2025-01-21T13:45:36.737850Z", "start_time": "2025-01-21T13:45:36.722835Z" } }, "outputs": [], "execution_count": 137 }, { "cell_type": "code", "source": "training_df.head(10)", "metadata": { "trusted": true, "execution": { "iopub.status.busy": "2025-01-09T16:36:51.383835Z", "iopub.execute_input": "2025-01-09T16:36:51.384165Z", "iopub.status.idle": "2025-01-09T16:36:51.401352Z", "shell.execute_reply.started": "2025-01-09T16:36:51.384140Z", "shell.execute_reply": "2025-01-09T16:36:51.400713Z" }, "ExecuteTime": { "end_time": "2025-01-21T13:45:36.783839Z", "start_time": "2025-01-21T13:45:36.769373Z" } }, "outputs": [ { "data": { "text/plain": [ " Grade BraTS_2017_subject_ID BraTS_2018_subject_ID TCGA_TCIA_subject_ID \\\n", "0 HGG Brats17_CBICA_AAB_1 Brats18_CBICA_AAB_1 NaN \n", "1 HGG Brats17_CBICA_AAG_1 Brats18_CBICA_AAG_1 NaN \n", "2 HGG Brats17_CBICA_AAL_1 Brats18_CBICA_AAL_1 NaN \n", "3 HGG Brats17_CBICA_AAP_1 Brats18_CBICA_AAP_1 NaN \n", "4 HGG Brats17_CBICA_ABB_1 Brats18_CBICA_ABB_1 NaN \n", "5 HGG Brats17_CBICA_ABE_1 Brats18_CBICA_ABE_1 NaN \n", "6 HGG Brats17_CBICA_ABM_1 Brats18_CBICA_ABM_1 NaN \n", "7 HGG Brats17_CBICA_ABN_1 Brats18_CBICA_ABN_1 NaN \n", "8 HGG Brats17_CBICA_ABO_1 Brats18_CBICA_ABO_1 NaN \n", "9 HGG Brats17_CBICA_ABY_1 Brats18_CBICA_ABY_1 NaN \n", "\n", " BraTS_2019_subject_ID BraTS_2020_subject_ID \n", "0 BraTS19_CBICA_AAB_1 BraTS20_Training_001 \n", "1 BraTS19_CBICA_AAG_1 BraTS20_Training_002 \n", "2 BraTS19_CBICA_AAL_1 BraTS20_Training_003 \n", "3 BraTS19_CBICA_AAP_1 BraTS20_Training_004 \n", "4 BraTS19_CBICA_ABB_1 BraTS20_Training_005 \n", "5 BraTS19_CBICA_ABE_1 BraTS20_Training_006 \n", "6 BraTS19_CBICA_ABM_1 BraTS20_Training_007 \n", "7 BraTS19_CBICA_ABN_1 BraTS20_Training_008 \n", "8 BraTS19_CBICA_ABO_1 BraTS20_Training_009 \n", "9 BraTS19_CBICA_ABY_1 BraTS20_Training_010 " ], "text/html": [ "
\n", " | Grade | \n", "BraTS_2017_subject_ID | \n", "BraTS_2018_subject_ID | \n", "TCGA_TCIA_subject_ID | \n", "BraTS_2019_subject_ID | \n", "BraTS_2020_subject_ID | \n", "
---|---|---|---|---|---|---|
0 | \n", "HGG | \n", "Brats17_CBICA_AAB_1 | \n", "Brats18_CBICA_AAB_1 | \n", "NaN | \n", "BraTS19_CBICA_AAB_1 | \n", "BraTS20_Training_001 | \n", "
1 | \n", "HGG | \n", "Brats17_CBICA_AAG_1 | \n", "Brats18_CBICA_AAG_1 | \n", "NaN | \n", "BraTS19_CBICA_AAG_1 | \n", "BraTS20_Training_002 | \n", "
2 | \n", "HGG | \n", "Brats17_CBICA_AAL_1 | \n", "Brats18_CBICA_AAL_1 | \n", "NaN | \n", "BraTS19_CBICA_AAL_1 | \n", "BraTS20_Training_003 | \n", "
3 | \n", "HGG | \n", "Brats17_CBICA_AAP_1 | \n", "Brats18_CBICA_AAP_1 | \n", "NaN | \n", "BraTS19_CBICA_AAP_1 | \n", "BraTS20_Training_004 | \n", "
4 | \n", "HGG | \n", "Brats17_CBICA_ABB_1 | \n", "Brats18_CBICA_ABB_1 | \n", "NaN | \n", "BraTS19_CBICA_ABB_1 | \n", "BraTS20_Training_005 | \n", "
5 | \n", "HGG | \n", "Brats17_CBICA_ABE_1 | \n", "Brats18_CBICA_ABE_1 | \n", "NaN | \n", "BraTS19_CBICA_ABE_1 | \n", "BraTS20_Training_006 | \n", "
6 | \n", "HGG | \n", "Brats17_CBICA_ABM_1 | \n", "Brats18_CBICA_ABM_1 | \n", "NaN | \n", "BraTS19_CBICA_ABM_1 | \n", "BraTS20_Training_007 | \n", "
7 | \n", "HGG | \n", "Brats17_CBICA_ABN_1 | \n", "Brats18_CBICA_ABN_1 | \n", "NaN | \n", "BraTS19_CBICA_ABN_1 | \n", "BraTS20_Training_008 | \n", "
8 | \n", "HGG | \n", "Brats17_CBICA_ABO_1 | \n", "Brats18_CBICA_ABO_1 | \n", "NaN | \n", "BraTS19_CBICA_ABO_1 | \n", "BraTS20_Training_009 | \n", "
9 | \n", "HGG | \n", "Brats17_CBICA_ABY_1 | \n", "Brats18_CBICA_ABY_1 | \n", "NaN | \n", "BraTS19_CBICA_ABY_1 | \n", "BraTS20_Training_010 | \n", "