{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.10.13","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"gpu","dataSources":[{"sourceType":"competition","sourceId":24800,"datasetId":1042002,"databundleVersionId":1831594},{"sourceType":"datasetVersion","sourceId":9355809,"datasetId":5671733,"databundleVersionId":9554368},{"sourceType":"datasetVersion","sourceId":9358252,"datasetId":5673625,"databundleVersionId":9557032},{"sourceType":"datasetVersion","sourceId":9363154,"datasetId":5677381,"databundleVersionId":9562337},{"sourceType":"datasetVersion","sourceId":9365277,"datasetId":5679044,"databundleVersionId":9564643},{"sourceType":"datasetVersion","sourceId":9388364,"datasetId":5696638,"databundleVersionId":9589649},{"sourceType":"datasetVersion","sourceId":9395486,"datasetId":5702280,"databundleVersionId":9597289},{"sourceType":"datasetVersion","sourceId":9445869,"datasetId":5740774,"databundleVersionId":9652120},{"sourceType":"datasetVersion","sourceId":9447841,"datasetId":5742248,"databundleVersionId":9654266},{"sourceType":"datasetVersion","sourceId":1810938,"datasetId":1075803,"databundleVersionId":1848422}],"dockerImageVersionId":30683,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":true}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"raw","source":"\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\ndDDdEdde# This Python 3 environment comes with many helpful analytics libraries installed\n# It is defined by the kaggle/python Docker image: https://github.com/kaggle/docker-python\n# For example, here's several helpful packages to load\n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n\n# Input data files are available in the read-only \"../input/\" directory\n# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\n\nimport os\n# for dirname, _, filenames in os.walk('/kaggle/input'):\n# for filename in filenames:\n# print(os.path.join(dirname, filename))\n\n# You can write up to 20GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using \"Save & Run All\" \n# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","execution":{"iopub.status.busy":"2024-09-19T07:24:27.470566Z","iopub.execute_input":"2024-09-19T07:24:27.471005Z","iopub.status.idle":"2024-09-19T07:24:28.599836Z","shell.execute_reply.started":"2024-09-19T07:24:27.470971Z","shell.execute_reply":"2024-09-19T07:24:28.598947Z"}}},{"cell_type":"code","source":"# Display generic output messages\n!pip install colorama\n\n# Library for visualizing bounding boxes\n!pip install bbox-visualizer\n\n# Install ONNX library, will be used to convert from pytorch model to a tf model\n!pip install onnx onnxruntime onnxsim onnx-tf","metadata":{"execution":{"iopub.status.busy":"2024-09-26T01:17:56.090748Z","iopub.execute_input":"2024-09-26T01:17:56.091045Z","iopub.status.idle":"2024-09-26T01:18:36.587069Z","shell.execute_reply.started":"2024-09-26T01:17:56.091018Z","shell.execute_reply":"2024-09-26T01:18:36.585969Z"},"trusted":true},"execution_count":1,"outputs":[{"name":"stdout","text":"Requirement already satisfied: colorama in /opt/conda/lib/python3.10/site-packages (0.4.6)\nCollecting bbox-visualizer\n Downloading bbox_visualizer-0.1.0-py2.py3-none-any.whl.metadata (4.2 kB)\nDownloading bbox_visualizer-0.1.0-py2.py3-none-any.whl (6.2 kB)\nInstalling collected packages: bbox-visualizer\nSuccessfully installed bbox-visualizer-0.1.0\nRequirement already satisfied: onnx in /opt/conda/lib/python3.10/site-packages (1.16.0)\nCollecting onnxruntime\n Downloading onnxruntime-1.19.2-cp310-cp310-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl.metadata (4.5 kB)\nCollecting onnxsim\n Downloading onnxsim-0.4.36-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (4.3 kB)\nCollecting onnx-tf\n Downloading onnx_tf-1.10.0-py3-none-any.whl.metadata (510 bytes)\nRequirement already satisfied: numpy>=1.20 in /opt/conda/lib/python3.10/site-packages (from onnx) (1.26.4)\nRequirement already satisfied: protobuf>=3.20.2 in /opt/conda/lib/python3.10/site-packages (from onnx) (3.20.3)\nCollecting coloredlogs (from onnxruntime)\n Downloading coloredlogs-15.0.1-py2.py3-none-any.whl.metadata (12 kB)\nRequirement already satisfied: flatbuffers in /opt/conda/lib/python3.10/site-packages (from onnxruntime) (23.5.26)\nRequirement already satisfied: packaging in /opt/conda/lib/python3.10/site-packages (from onnxruntime) (21.3)\nRequirement already satisfied: sympy in /opt/conda/lib/python3.10/site-packages (from onnxruntime) (1.12)\nRequirement already satisfied: rich in /opt/conda/lib/python3.10/site-packages (from onnxsim) (13.7.0)\nRequirement already satisfied: PyYAML in /opt/conda/lib/python3.10/site-packages (from onnx-tf) (6.0.1)\nCollecting tensorflow-addons (from onnx-tf)\n Downloading tensorflow_addons-0.23.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (1.8 kB)\nCollecting humanfriendly>=9.1 (from coloredlogs->onnxruntime)\n Downloading humanfriendly-10.0-py2.py3-none-any.whl.metadata (9.2 kB)\nRequirement already satisfied: pyparsing!=3.0.5,>=2.0.2 in /opt/conda/lib/python3.10/site-packages (from packaging->onnxruntime) (3.1.1)\nRequirement already satisfied: markdown-it-py>=2.2.0 in /opt/conda/lib/python3.10/site-packages (from rich->onnxsim) (3.0.0)\nRequirement already satisfied: pygments<3.0.0,>=2.13.0 in /opt/conda/lib/python3.10/site-packages (from rich->onnxsim) (2.17.2)\nRequirement already satisfied: mpmath>=0.19 in /opt/conda/lib/python3.10/site-packages (from sympy->onnxruntime) (1.3.0)\nCollecting typeguard<3.0.0,>=2.7 (from tensorflow-addons->onnx-tf)\n Downloading typeguard-2.13.3-py3-none-any.whl.metadata (3.6 kB)\nRequirement already satisfied: mdurl~=0.1 in /opt/conda/lib/python3.10/site-packages (from markdown-it-py>=2.2.0->rich->onnxsim) (0.1.2)\nDownloading onnxruntime-1.19.2-cp310-cp310-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl (13.2 MB)\n\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m13.2/13.2 MB\u001b[0m \u001b[31m81.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m:00:01\u001b[0m00:01\u001b[0m\n\u001b[?25hDownloading onnxsim-0.4.36-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (2.3 MB)\n\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m2.3/2.3 MB\u001b[0m \u001b[31m63.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m:00:01\u001b[0m\n\u001b[?25hDownloading onnx_tf-1.10.0-py3-none-any.whl (226 kB)\n\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m226.1/226.1 kB\u001b[0m \u001b[31m13.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n\u001b[?25hDownloading coloredlogs-15.0.1-py2.py3-none-any.whl (46 kB)\n\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m46.0/46.0 kB\u001b[0m \u001b[31m2.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n\u001b[?25hDownloading tensorflow_addons-0.23.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (611 kB)\n\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m611.8/611.8 kB\u001b[0m \u001b[31m32.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n\u001b[?25hDownloading humanfriendly-10.0-py2.py3-none-any.whl (86 kB)\n\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m86.8/86.8 kB\u001b[0m \u001b[31m6.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n\u001b[?25hDownloading typeguard-2.13.3-py3-none-any.whl (17 kB)\nInstalling collected packages: typeguard, humanfriendly, tensorflow-addons, coloredlogs, onnxsim, onnxruntime, onnx-tf\n Attempting uninstall: typeguard\n Found existing installation: typeguard 4.1.5\n Uninstalling typeguard-4.1.5:\n Successfully uninstalled typeguard-4.1.5\n\u001b[31mERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.\nydata-profiling 4.6.4 requires numpy<1.26,>=1.16.0, but you have numpy 1.26.4 which is incompatible.\nydata-profiling 4.6.4 requires typeguard<5,>=4.1.2, but you have typeguard 2.13.3 which is incompatible.\u001b[0m\u001b[31m\n\u001b[0mSuccessfully installed coloredlogs-15.0.1 humanfriendly-10.0 onnx-tf-1.10.0 onnxruntime-1.19.2 onnxsim-0.4.36 tensorflow-addons-0.23.0 typeguard-2.13.3\n","output_type":"stream"}]},{"cell_type":"code","source":"import bbox_visualizer as bbv\nimport cv2\nimport matplotlib.pyplot as plt\nimport numpy as np\nimport pandas as pd\nimport seaborn as sns\nimport shutil, os\nimport tensorflow as tf\nimport yaml\n\nfrom colorama import Fore, Back, Style\nfrom IPython.display import Image, display, clear_output\nfrom sklearn.model_selection import GroupShuffleSplit \nfrom tqdm.notebook import tqdm\nfrom typing import List","metadata":{"execution":{"iopub.status.busy":"2024-09-26T01:18:36.588972Z","iopub.execute_input":"2024-09-26T01:18:36.589268Z","iopub.status.idle":"2024-09-26T01:18:50.479286Z","shell.execute_reply.started":"2024-09-26T01:18:36.589238Z","shell.execute_reply":"2024-09-26T01:18:50.478277Z"},"trusted":true},"execution_count":2,"outputs":[{"name":"stderr","text":"2024-09-26 01:18:40.427745: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered\n2024-09-26 01:18:40.427847: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered\n2024-09-26 01:18:40.562762: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered\n","output_type":"stream"}]},{"cell_type":"code","source":"# !rm -rf /kaggle/working/data\n!mkdir -p /kaggle/working/data","metadata":{"execution":{"iopub.status.busy":"2024-09-26T01:18:50.480591Z","iopub.execute_input":"2024-09-26T01:18:50.481261Z","iopub.status.idle":"2024-09-26T01:18:51.496884Z","shell.execute_reply.started":"2024-09-26T01:18:50.481227Z","shell.execute_reply":"2024-09-26T01:18:51.495452Z"},"trusted":true},"execution_count":3,"outputs":[]},{"cell_type":"code","source":"!cp -r /kaggle/input/vinbigdata-chest-xray-resized-png-1024x1024/* /kaggle/working/data/","metadata":{"execution":{"iopub.status.busy":"2024-09-26T01:18:51.499643Z","iopub.execute_input":"2024-09-26T01:18:51.500008Z","iopub.status.idle":"2024-09-26T01:23:11.160602Z","shell.execute_reply.started":"2024-09-26T01:18:51.499976Z","shell.execute_reply":"2024-09-26T01:23:11.159315Z"},"trusted":true},"execution_count":4,"outputs":[]},{"cell_type":"code","source":"!cp /kaggle/input/vinbigdata-chest-xray-abnormalities-detection/train.csv /kaggle/working/data/","metadata":{"execution":{"iopub.status.busy":"2024-09-26T01:23:11.162042Z","iopub.execute_input":"2024-09-26T01:23:11.16236Z","iopub.status.idle":"2024-09-26T01:23:12.239601Z","shell.execute_reply.started":"2024-09-26T01:23:11.16233Z","shell.execute_reply":"2024-09-26T01:23:12.238114Z"},"trusted":true},"execution_count":5,"outputs":[]},{"cell_type":"code","source":"!cp /kaggle/input/lables/output.csv /kaggle/working/data/","metadata":{"execution":{"iopub.status.busy":"2024-09-26T01:23:12.241347Z","iopub.execute_input":"2024-09-26T01:23:12.242184Z","iopub.status.idle":"2024-09-26T01:23:13.292498Z","shell.execute_reply.started":"2024-09-26T01:23:12.242142Z","shell.execute_reply":"2024-09-26T01:23:13.291233Z"},"trusted":true},"execution_count":6,"outputs":[]},{"cell_type":"code","source":"# !cp /kaggle/input/lan2pt/lan2.pt /kaggle/working/","metadata":{"execution":{"iopub.status.busy":"2024-09-26T01:23:13.294494Z","iopub.execute_input":"2024-09-26T01:23:13.294864Z","iopub.status.idle":"2024-09-26T01:23:13.300392Z","shell.execute_reply.started":"2024-09-26T01:23:13.294822Z","shell.execute_reply":"2024-09-26T01:23:13.299197Z"},"trusted":true},"execution_count":7,"outputs":[]},{"cell_type":"code","source":"# !git clone https://github.com/WongKinYiu/yolov7.git","metadata":{"execution":{"iopub.status.busy":"2024-09-26T01:23:13.301957Z","iopub.execute_input":"2024-09-26T01:23:13.302375Z","iopub.status.idle":"2024-09-26T01:23:13.311761Z","shell.execute_reply.started":"2024-09-26T01:23:13.302334Z","shell.execute_reply":"2024-09-26T01:23:13.310605Z"},"trusted":true},"execution_count":8,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# # Clone the YoloV9 repository, install the libray, and obtain the model\n# !git clone https://github.com/WongKinYiu/yolov9.git\n# !wget https://github.com/WongKinYiu/yolov9/releases/download/v0.1/yolov9-e.pt","metadata":{"execution":{"iopub.status.busy":"2024-09-26T01:23:13.313032Z","iopub.execute_input":"2024-09-26T01:23:13.313353Z","iopub.status.idle":"2024-09-26T01:23:13.323405Z","shell.execute_reply.started":"2024-09-26T01:23:13.313318Z","shell.execute_reply":"2024-09-26T01:23:13.322488Z"},"trusted":true},"execution_count":9,"outputs":[]},{"cell_type":"code","source":"# !wget https://github.com/WongKinYiu/yolov9/releases/download/v0.1/yolov9-c.pt","metadata":{"execution":{"iopub.status.busy":"2024-09-26T01:23:13.324708Z","iopub.execute_input":"2024-09-26T01:23:13.325038Z","iopub.status.idle":"2024-09-26T01:23:13.334391Z","shell.execute_reply.started":"2024-09-26T01:23:13.325015Z","shell.execute_reply":"2024-09-26T01:23:13.333378Z"},"trusted":true},"execution_count":10,"outputs":[]},{"cell_type":"code","source":"# !wget https://github.com/WongKinYiu/yolov9/releases/download/v0.1/gelan-c.pt","metadata":{"execution":{"iopub.status.busy":"2024-09-26T01:23:13.3411Z","iopub.execute_input":"2024-09-26T01:23:13.341594Z","iopub.status.idle":"2024-09-26T01:23:13.347348Z","shell.execute_reply.started":"2024-09-26T01:23:13.341554Z","shell.execute_reply":"2024-09-26T01:23:13.346391Z"},"trusted":true},"execution_count":11,"outputs":[]},{"cell_type":"code","source":"# !pip install -r /kaggle/working/yolov9/requirements.txt","metadata":{"execution":{"iopub.status.busy":"2024-09-26T01:23:13.348455Z","iopub.execute_input":"2024-09-26T01:23:13.348859Z","iopub.status.idle":"2024-09-26T01:23:13.357532Z","shell.execute_reply.started":"2024-09-26T01:23:13.348834Z","shell.execute_reply":"2024-09-26T01:23:13.356535Z"},"trusted":true},"execution_count":12,"outputs":[]},{"cell_type":"code","source":"# !pip install -r yolov7/requirements.txt\n# !wget https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7.pt","metadata":{"execution":{"iopub.status.busy":"2024-09-26T01:23:13.35878Z","iopub.execute_input":"2024-09-26T01:23:13.359076Z","iopub.status.idle":"2024-09-26T01:23:13.366894Z","shell.execute_reply.started":"2024-09-26T01:23:13.359053Z","shell.execute_reply":"2024-09-26T01:23:13.366001Z"},"trusted":true},"execution_count":13,"outputs":[]},{"cell_type":"code","source":"IMAGE_SIZE = 1024\nTRAIN_IMAGES_DIRECTORY = '/kaggle/working/data/train/'\nTEST_IMAGES_DIRECTORY = '/kaggle/working/data/test/'\n\nTRAIN_IMAGES_PATH_REFACTORED = '/kaggle/working/refactored_data/images/train/'\nTRAIN_LABELS_PATH_REFACTORED = '/kaggle/working/refactored_data/labels/train/'\nVALID_IMAGES_PATH_REFACTORED = '/kaggle/working/refactored_data/images/val/'\nVALID_LABELS_PATH_REFACTORED = '/kaggle/working/refactored_data/labels/val/'","metadata":{"execution":{"iopub.status.busy":"2024-09-26T01:23:13.368346Z","iopub.execute_input":"2024-09-26T01:23:13.368611Z","iopub.status.idle":"2024-09-26T01:23:13.379072Z","shell.execute_reply.started":"2024-09-26T01:23:13.368589Z","shell.execute_reply":"2024-09-26T01:23:13.378119Z"},"trusted":true},"execution_count":14,"outputs":[]},{"cell_type":"code","source":"train_df = pd.read_csv('data/output.csv')\ntrain_df","metadata":{"execution":{"iopub.status.busy":"2024-09-26T01:23:13.380505Z","iopub.execute_input":"2024-09-26T01:23:13.381412Z","iopub.status.idle":"2024-09-26T01:23:13.464651Z","shell.execute_reply.started":"2024-09-26T01:23:13.381381Z","shell.execute_reply":"2024-09-26T01:23:13.463717Z"},"trusted":true},"execution_count":15,"outputs":[{"execution_count":15,"output_type":"execute_result","data":{"text/plain":" image_id class_id x_min y_min x_max y_max\n0 9a5094b2563a1ef3ff50dc5c7ff71345 3 339.7 593.0 816.0 787.3\n1 9a5094b2563a1ef3ff50dc5c7ff71345 10 880.0 757.0 923.0 873.0\n2 9a5094b2563a1ef3ff50dc5c7ff71345 11 880.0 757.0 923.0 873.0\n3 9a5094b2563a1ef3ff50dc5c7ff71345 0 517.0 313.0 639.0 423.0\n4 051132a778e61a86eb147c7c6f564dfe 3 423.7 463.7 907.7 594.3\n... ... ... ... ... ... ...\n22713 be53fe5a49231f1c1be020b0bdd8561f 7 216.0 388.0 282.0 451.0\n22714 380d07a94cc4b012812119370de47192 0 576.0 284.7 709.0 398.7\n22715 52951d7de2485aba8ed62629eee4d254 3 321.0 573.0 718.0 680.0\n22716 52951d7de2485aba8ed62629eee4d254 9 134.0 512.0 170.0 536.0\n22717 1224f07d895107573588225f692e94f9 0 515.3 314.0 638.3 441.3\n\n[22718 rows x 6 columns]","text/html":"
\n\n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
image_idclass_idx_miny_minx_maxy_max
09a5094b2563a1ef3ff50dc5c7ff713453339.7593.0816.0787.3
19a5094b2563a1ef3ff50dc5c7ff7134510880.0757.0923.0873.0
29a5094b2563a1ef3ff50dc5c7ff7134511880.0757.0923.0873.0
39a5094b2563a1ef3ff50dc5c7ff713450517.0313.0639.0423.0
4051132a778e61a86eb147c7c6f564dfe3423.7463.7907.7594.3
.....................
22713be53fe5a49231f1c1be020b0bdd8561f7216.0388.0282.0451.0
22714380d07a94cc4b012812119370de471920576.0284.7709.0398.7
2271552951d7de2485aba8ed62629eee4d2543321.0573.0718.0680.0
2271652951d7de2485aba8ed62629eee4d2549134.0512.0170.0536.0
227171224f07d895107573588225f692e94f90515.3314.0638.3441.3
\n

22718 rows × 6 columns

\n
"},"metadata":{}}]},{"cell_type":"code","source":"train_base_df = pd.read_csv('data/train.csv')\ntrain_base_df #image_id,class_name,class_id,rad_id,x_min,y_min,x_max,y_max,width,height","metadata":{"execution":{"iopub.status.busy":"2024-09-26T01:23:13.466087Z","iopub.execute_input":"2024-09-26T01:23:13.466518Z","iopub.status.idle":"2024-09-26T01:23:13.58309Z","shell.execute_reply.started":"2024-09-26T01:23:13.466485Z","shell.execute_reply":"2024-09-26T01:23:13.582166Z"},"trusted":true},"execution_count":16,"outputs":[{"execution_count":16,"output_type":"execute_result","data":{"text/plain":" image_id class_name class_id rad_id \\\n0 50a418190bc3fb1ef1633bf9678929b3 No finding 14 R11 \n1 21a10246a5ec7af151081d0cd6d65dc9 No finding 14 R7 \n2 9a5094b2563a1ef3ff50dc5c7ff71345 Cardiomegaly 3 R10 \n3 051132a778e61a86eb147c7c6f564dfe Aortic enlargement 0 R10 \n4 063319de25ce7edb9b1c6b8881290140 No finding 14 R10 \n... ... ... ... ... \n67909 936fd5cff1c058d39817a08f58b72cae No finding 14 R1 \n67910 ca7e72954550eeb610fe22bf0244b7fa No finding 14 R1 \n67911 aa17d5312a0fb4a2939436abca7f9579 No finding 14 R8 \n67912 4b56bc6d22b192f075f13231419dfcc8 Cardiomegaly 3 R8 \n67913 5e272e3adbdaafb07a7e84a9e62b1a4c No finding 14 R16 \n\n x_min y_min x_max y_max \n0 NaN NaN NaN NaN \n1 NaN NaN NaN NaN \n2 691.0 1375.0 1653.0 1831.0 \n3 1264.0 743.0 1611.0 1019.0 \n4 NaN NaN NaN NaN \n... ... ... ... ... \n67909 NaN NaN NaN NaN \n67910 NaN NaN NaN NaN \n67911 NaN NaN NaN NaN \n67912 771.0 979.0 1680.0 1311.0 \n67913 NaN NaN NaN NaN \n\n[67914 rows x 8 columns]","text/html":"
\n\n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
image_idclass_nameclass_idrad_idx_miny_minx_maxy_max
050a418190bc3fb1ef1633bf9678929b3No finding14R11NaNNaNNaNNaN
121a10246a5ec7af151081d0cd6d65dc9No finding14R7NaNNaNNaNNaN
29a5094b2563a1ef3ff50dc5c7ff71345Cardiomegaly3R10691.01375.01653.01831.0
3051132a778e61a86eb147c7c6f564dfeAortic enlargement0R101264.0743.01611.01019.0
4063319de25ce7edb9b1c6b8881290140No finding14R10NaNNaNNaNNaN
...........................
67909936fd5cff1c058d39817a08f58b72caeNo finding14R1NaNNaNNaNNaN
67910ca7e72954550eeb610fe22bf0244b7faNo finding14R1NaNNaNNaNNaN
67911aa17d5312a0fb4a2939436abca7f9579No finding14R8NaNNaNNaNNaN
679124b56bc6d22b192f075f13231419dfcc8Cardiomegaly3R8771.0979.01680.01311.0
679135e272e3adbdaafb07a7e84a9e62b1a4cNo finding14R16NaNNaNNaNNaN
\n

67914 rows × 8 columns

\n
"},"metadata":{}}]},{"cell_type":"code","source":"# Tạo từ điển ánh xạ từ class_id đến class_name\nclass_id_to_name = dict(zip(train_base_df['class_id'], train_base_df['class_name']))\n\n# Thêm cột class_name vào new_df dựa trên class_id\ntrain_df['class_name'] = train_df['class_id'].map(class_id_to_name)\n\n# Kiểm tra new_df sau khi thêm cột\ntrain_df\n","metadata":{"execution":{"iopub.status.busy":"2024-09-26T01:23:13.584685Z","iopub.execute_input":"2024-09-26T01:23:13.585085Z","iopub.status.idle":"2024-09-26T01:23:13.624628Z","shell.execute_reply.started":"2024-09-26T01:23:13.585053Z","shell.execute_reply":"2024-09-26T01:23:13.62383Z"},"trusted":true},"execution_count":17,"outputs":[{"execution_count":17,"output_type":"execute_result","data":{"text/plain":" image_id class_id x_min y_min x_max y_max \\\n0 9a5094b2563a1ef3ff50dc5c7ff71345 3 339.7 593.0 816.0 787.3 \n1 9a5094b2563a1ef3ff50dc5c7ff71345 10 880.0 757.0 923.0 873.0 \n2 9a5094b2563a1ef3ff50dc5c7ff71345 11 880.0 757.0 923.0 873.0 \n3 9a5094b2563a1ef3ff50dc5c7ff71345 0 517.0 313.0 639.0 423.0 \n4 051132a778e61a86eb147c7c6f564dfe 3 423.7 463.7 907.7 594.3 \n... ... ... ... ... ... ... \n22713 be53fe5a49231f1c1be020b0bdd8561f 7 216.0 388.0 282.0 451.0 \n22714 380d07a94cc4b012812119370de47192 0 576.0 284.7 709.0 398.7 \n22715 52951d7de2485aba8ed62629eee4d254 3 321.0 573.0 718.0 680.0 \n22716 52951d7de2485aba8ed62629eee4d254 9 134.0 512.0 170.0 536.0 \n22717 1224f07d895107573588225f692e94f9 0 515.3 314.0 638.3 441.3 \n\n class_name \n0 Cardiomegaly \n1 Pleural effusion \n2 Pleural thickening \n3 Aortic enlargement \n4 Cardiomegaly \n... ... \n22713 Lung Opacity \n22714 Aortic enlargement \n22715 Cardiomegaly \n22716 Other lesion \n22717 Aortic enlargement \n\n[22718 rows x 7 columns]","text/html":"
\n\n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
image_idclass_idx_miny_minx_maxy_maxclass_name
09a5094b2563a1ef3ff50dc5c7ff713453339.7593.0816.0787.3Cardiomegaly
19a5094b2563a1ef3ff50dc5c7ff7134510880.0757.0923.0873.0Pleural effusion
29a5094b2563a1ef3ff50dc5c7ff7134511880.0757.0923.0873.0Pleural thickening
39a5094b2563a1ef3ff50dc5c7ff713450517.0313.0639.0423.0Aortic enlargement
4051132a778e61a86eb147c7c6f564dfe3423.7463.7907.7594.3Cardiomegaly
........................
22713be53fe5a49231f1c1be020b0bdd8561f7216.0388.0282.0451.0Lung Opacity
22714380d07a94cc4b012812119370de471920576.0284.7709.0398.7Aortic enlargement
2271552951d7de2485aba8ed62629eee4d2543321.0573.0718.0680.0Cardiomegaly
2271652951d7de2485aba8ed62629eee4d2549134.0512.0170.0536.0Other lesion
227171224f07d895107573588225f692e94f90515.3314.0638.3441.3Aortic enlargement
\n

22718 rows × 7 columns

\n
"},"metadata":{}}]},{"cell_type":"code","source":"path = 'data/train/'\nimg_path = []\nfor i in train_df['image_id']:\n img_path.append(path+i+'.png')\n\ntrain_df['img_path'] = img_path\ntrain_df","metadata":{"execution":{"iopub.status.busy":"2024-09-26T01:23:13.62562Z","iopub.execute_input":"2024-09-26T01:23:13.625907Z","iopub.status.idle":"2024-09-26T01:23:13.655662Z","shell.execute_reply.started":"2024-09-26T01:23:13.625885Z","shell.execute_reply":"2024-09-26T01:23:13.654838Z"},"trusted":true},"execution_count":18,"outputs":[{"execution_count":18,"output_type":"execute_result","data":{"text/plain":" image_id class_id x_min y_min x_max y_max \\\n0 9a5094b2563a1ef3ff50dc5c7ff71345 3 339.7 593.0 816.0 787.3 \n1 9a5094b2563a1ef3ff50dc5c7ff71345 10 880.0 757.0 923.0 873.0 \n2 9a5094b2563a1ef3ff50dc5c7ff71345 11 880.0 757.0 923.0 873.0 \n3 9a5094b2563a1ef3ff50dc5c7ff71345 0 517.0 313.0 639.0 423.0 \n4 051132a778e61a86eb147c7c6f564dfe 3 423.7 463.7 907.7 594.3 \n... ... ... ... ... ... ... \n22713 be53fe5a49231f1c1be020b0bdd8561f 7 216.0 388.0 282.0 451.0 \n22714 380d07a94cc4b012812119370de47192 0 576.0 284.7 709.0 398.7 \n22715 52951d7de2485aba8ed62629eee4d254 3 321.0 573.0 718.0 680.0 \n22716 52951d7de2485aba8ed62629eee4d254 9 134.0 512.0 170.0 536.0 \n22717 1224f07d895107573588225f692e94f9 0 515.3 314.0 638.3 441.3 \n\n class_name img_path \n0 Cardiomegaly data/train/9a5094b2563a1ef3ff50dc5c7ff71345.png \n1 Pleural effusion data/train/9a5094b2563a1ef3ff50dc5c7ff71345.png \n2 Pleural thickening data/train/9a5094b2563a1ef3ff50dc5c7ff71345.png \n3 Aortic enlargement data/train/9a5094b2563a1ef3ff50dc5c7ff71345.png \n4 Cardiomegaly data/train/051132a778e61a86eb147c7c6f564dfe.png \n... ... ... \n22713 Lung Opacity data/train/be53fe5a49231f1c1be020b0bdd8561f.png \n22714 Aortic enlargement data/train/380d07a94cc4b012812119370de47192.png \n22715 Cardiomegaly data/train/52951d7de2485aba8ed62629eee4d254.png \n22716 Other lesion data/train/52951d7de2485aba8ed62629eee4d254.png \n22717 Aortic enlargement data/train/1224f07d895107573588225f692e94f9.png \n\n[22718 rows x 8 columns]","text/html":"
\n\n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
image_idclass_idx_miny_minx_maxy_maxclass_nameimg_path
09a5094b2563a1ef3ff50dc5c7ff713453339.7593.0816.0787.3Cardiomegalydata/train/9a5094b2563a1ef3ff50dc5c7ff71345.png
19a5094b2563a1ef3ff50dc5c7ff7134510880.0757.0923.0873.0Pleural effusiondata/train/9a5094b2563a1ef3ff50dc5c7ff71345.png
29a5094b2563a1ef3ff50dc5c7ff7134511880.0757.0923.0873.0Pleural thickeningdata/train/9a5094b2563a1ef3ff50dc5c7ff71345.png
39a5094b2563a1ef3ff50dc5c7ff713450517.0313.0639.0423.0Aortic enlargementdata/train/9a5094b2563a1ef3ff50dc5c7ff71345.png
4051132a778e61a86eb147c7c6f564dfe3423.7463.7907.7594.3Cardiomegalydata/train/051132a778e61a86eb147c7c6f564dfe.png
...........................
22713be53fe5a49231f1c1be020b0bdd8561f7216.0388.0282.0451.0Lung Opacitydata/train/be53fe5a49231f1c1be020b0bdd8561f.png
22714380d07a94cc4b012812119370de471920576.0284.7709.0398.7Aortic enlargementdata/train/380d07a94cc4b012812119370de47192.png
2271552951d7de2485aba8ed62629eee4d2543321.0573.0718.0680.0Cardiomegalydata/train/52951d7de2485aba8ed62629eee4d254.png
2271652951d7de2485aba8ed62629eee4d2549134.0512.0170.0536.0Other lesiondata/train/52951d7de2485aba8ed62629eee4d254.png
227171224f07d895107573588225f692e94f90515.3314.0638.3441.3Aortic enlargementdata/train/1224f07d895107573588225f692e94f9.png
\n

22718 rows × 8 columns

\n
"},"metadata":{}}]},{"cell_type":"code","source":"#x_min, y_min, x_max, y_max normalization값으로 update\ntrain_df['x_min'] = train_df.apply(lambda row: (row.x_min) /1024, axis =1)\ntrain_df['y_min'] = train_df.apply(lambda row: (row.y_min) /1024, axis =1)\n\ntrain_df['x_max'] = train_df.apply(lambda row: (row.x_max) /1024, axis =1)\ntrain_df['y_max'] = train_df.apply(lambda row: (row.y_max) /1024, axis =1)\n#x_mid, y_mid가 추가\ntrain_df['x_mid'] = train_df.apply(lambda row: (row.x_min + row.x_max)/2,axis =1)\ntrain_df['y_mid'] = train_df.apply(lambda row: (row.y_min + row.y_max)/2, axis =1)\n#normalization된 width & height 추가\ntrain_df['w'] = train_df.apply(lambda row: (row.x_max - row.x_min), axis = 1)\ntrain_df['h'] = train_df.apply(lambda row: (row.y_max - row.y_min), axis = 1)\n#area 추가\ntrain_df['area'] = train_df['w']*train_df['h']\ntrain_df","metadata":{"execution":{"iopub.status.busy":"2024-09-26T01:23:13.65681Z","iopub.execute_input":"2024-09-26T01:23:13.657135Z","iopub.status.idle":"2024-09-26T01:23:17.392676Z","shell.execute_reply.started":"2024-09-26T01:23:13.657103Z","shell.execute_reply":"2024-09-26T01:23:17.391757Z"},"trusted":true},"execution_count":19,"outputs":[{"execution_count":19,"output_type":"execute_result","data":{"text/plain":" image_id class_id x_min y_min \\\n0 9a5094b2563a1ef3ff50dc5c7ff71345 3 0.331738 0.579102 \n1 9a5094b2563a1ef3ff50dc5c7ff71345 10 0.859375 0.739258 \n2 9a5094b2563a1ef3ff50dc5c7ff71345 11 0.859375 0.739258 \n3 9a5094b2563a1ef3ff50dc5c7ff71345 0 0.504883 0.305664 \n4 051132a778e61a86eb147c7c6f564dfe 3 0.413770 0.452832 \n... ... ... ... ... \n22713 be53fe5a49231f1c1be020b0bdd8561f 7 0.210938 0.378906 \n22714 380d07a94cc4b012812119370de47192 0 0.562500 0.278027 \n22715 52951d7de2485aba8ed62629eee4d254 3 0.313477 0.559570 \n22716 52951d7de2485aba8ed62629eee4d254 9 0.130859 0.500000 \n22717 1224f07d895107573588225f692e94f9 0 0.503223 0.306641 \n\n x_max y_max class_name \\\n0 0.796875 0.768848 Cardiomegaly \n1 0.901367 0.852539 Pleural effusion \n2 0.901367 0.852539 Pleural thickening \n3 0.624023 0.413086 Aortic enlargement \n4 0.886426 0.580371 Cardiomegaly \n... ... ... ... \n22713 0.275391 0.440430 Lung Opacity \n22714 0.692383 0.389355 Aortic enlargement \n22715 0.701172 0.664062 Cardiomegaly \n22716 0.166016 0.523438 Other lesion \n22717 0.623340 0.430957 Aortic enlargement \n\n img_path x_mid y_mid \\\n0 data/train/9a5094b2563a1ef3ff50dc5c7ff71345.png 0.564307 0.673975 \n1 data/train/9a5094b2563a1ef3ff50dc5c7ff71345.png 0.880371 0.795898 \n2 data/train/9a5094b2563a1ef3ff50dc5c7ff71345.png 0.880371 0.795898 \n3 data/train/9a5094b2563a1ef3ff50dc5c7ff71345.png 0.564453 0.359375 \n4 data/train/051132a778e61a86eb147c7c6f564dfe.png 0.650098 0.516602 \n... ... ... ... \n22713 data/train/be53fe5a49231f1c1be020b0bdd8561f.png 0.243164 0.409668 \n22714 data/train/380d07a94cc4b012812119370de47192.png 0.627441 0.333691 \n22715 data/train/52951d7de2485aba8ed62629eee4d254.png 0.507324 0.611816 \n22716 data/train/52951d7de2485aba8ed62629eee4d254.png 0.148438 0.511719 \n22717 data/train/1224f07d895107573588225f692e94f9.png 0.563281 0.368799 \n\n w h area \n0 0.465137 0.189746 0.088258 \n1 0.041992 0.113281 0.004757 \n2 0.041992 0.113281 0.004757 \n3 0.119141 0.107422 0.012798 \n4 0.472656 0.127539 0.060282 \n... ... ... ... \n22713 0.064453 0.061523 0.003965 \n22714 0.129883 0.111328 0.014460 \n22715 0.387695 0.104492 0.040511 \n22716 0.035156 0.023438 0.000824 \n22717 0.120117 0.124316 0.014933 \n\n[22718 rows x 13 columns]","text/html":"
\n\n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
image_idclass_idx_miny_minx_maxy_maxclass_nameimg_pathx_midy_midwharea
09a5094b2563a1ef3ff50dc5c7ff7134530.3317380.5791020.7968750.768848Cardiomegalydata/train/9a5094b2563a1ef3ff50dc5c7ff71345.png0.5643070.6739750.4651370.1897460.088258
19a5094b2563a1ef3ff50dc5c7ff71345100.8593750.7392580.9013670.852539Pleural effusiondata/train/9a5094b2563a1ef3ff50dc5c7ff71345.png0.8803710.7958980.0419920.1132810.004757
29a5094b2563a1ef3ff50dc5c7ff71345110.8593750.7392580.9013670.852539Pleural thickeningdata/train/9a5094b2563a1ef3ff50dc5c7ff71345.png0.8803710.7958980.0419920.1132810.004757
39a5094b2563a1ef3ff50dc5c7ff7134500.5048830.3056640.6240230.413086Aortic enlargementdata/train/9a5094b2563a1ef3ff50dc5c7ff71345.png0.5644530.3593750.1191410.1074220.012798
4051132a778e61a86eb147c7c6f564dfe30.4137700.4528320.8864260.580371Cardiomegalydata/train/051132a778e61a86eb147c7c6f564dfe.png0.6500980.5166020.4726560.1275390.060282
..........................................
22713be53fe5a49231f1c1be020b0bdd8561f70.2109380.3789060.2753910.440430Lung Opacitydata/train/be53fe5a49231f1c1be020b0bdd8561f.png0.2431640.4096680.0644530.0615230.003965
22714380d07a94cc4b012812119370de4719200.5625000.2780270.6923830.389355Aortic enlargementdata/train/380d07a94cc4b012812119370de47192.png0.6274410.3336910.1298830.1113280.014460
2271552951d7de2485aba8ed62629eee4d25430.3134770.5595700.7011720.664062Cardiomegalydata/train/52951d7de2485aba8ed62629eee4d254.png0.5073240.6118160.3876950.1044920.040511
2271652951d7de2485aba8ed62629eee4d25490.1308590.5000000.1660160.523438Other lesiondata/train/52951d7de2485aba8ed62629eee4d254.png0.1484380.5117190.0351560.0234380.000824
227171224f07d895107573588225f692e94f900.5032230.3066410.6233400.430957Aortic enlargementdata/train/1224f07d895107573588225f692e94f9.png0.5632810.3687990.1201170.1243160.014933
\n

22718 rows × 13 columns

\n
"},"metadata":{}}]},{"cell_type":"code","source":"train_df['ori_x_min'] = (train_df['x_min']*1024).astype('int')\ntrain_df['ori_y_min'] = (train_df['y_min']*1024).astype('int')\ntrain_df['ori_x_max'] = (train_df['x_max']*1024).astype('int')\ntrain_df['ori_y_max'] = (train_df['y_max']*1024).astype('int')\n\ntrain_df['ori_x_mid'] = (train_df['x_mid']*1024).astype('int')\ntrain_df['ori_y_mid'] = (train_df['y_mid']*1024).astype('int')\ntrain_df['ori_w'] = (train_df['w']*1024).astype('int')\ntrain_df['ori_h'] = (train_df['h']*1024).astype('int')","metadata":{"execution":{"iopub.status.busy":"2024-09-26T01:23:17.393942Z","iopub.execute_input":"2024-09-26T01:23:17.394307Z","iopub.status.idle":"2024-09-26T01:23:17.408322Z","shell.execute_reply.started":"2024-09-26T01:23:17.39428Z","shell.execute_reply":"2024-09-26T01:23:17.407596Z"},"trusted":true},"execution_count":20,"outputs":[]},{"cell_type":"code","source":"final_df = train_df.copy()\nfinal_df = final_df[['image_id', 'class_name', 'class_id', 'ori_x_min', 'ori_y_min', 'ori_x_max', 'ori_y_max', 'ori_x_mid', 'ori_y_mid', 'ori_w', 'ori_h','img_path']]\nfinal_df","metadata":{"execution":{"iopub.status.busy":"2024-09-26T01:23:17.409583Z","iopub.execute_input":"2024-09-26T01:23:17.410965Z","iopub.status.idle":"2024-09-26T01:23:17.435405Z","shell.execute_reply.started":"2024-09-26T01:23:17.410931Z","shell.execute_reply":"2024-09-26T01:23:17.434572Z"},"trusted":true},"execution_count":21,"outputs":[{"execution_count":21,"output_type":"execute_result","data":{"text/plain":" image_id class_name class_id \\\n0 9a5094b2563a1ef3ff50dc5c7ff71345 Cardiomegaly 3 \n1 9a5094b2563a1ef3ff50dc5c7ff71345 Pleural effusion 10 \n2 9a5094b2563a1ef3ff50dc5c7ff71345 Pleural thickening 11 \n3 9a5094b2563a1ef3ff50dc5c7ff71345 Aortic enlargement 0 \n4 051132a778e61a86eb147c7c6f564dfe Cardiomegaly 3 \n... ... ... ... \n22713 be53fe5a49231f1c1be020b0bdd8561f Lung Opacity 7 \n22714 380d07a94cc4b012812119370de47192 Aortic enlargement 0 \n22715 52951d7de2485aba8ed62629eee4d254 Cardiomegaly 3 \n22716 52951d7de2485aba8ed62629eee4d254 Other lesion 9 \n22717 1224f07d895107573588225f692e94f9 Aortic enlargement 0 \n\n ori_x_min ori_y_min ori_x_max ori_y_max ori_x_mid ori_y_mid \\\n0 339 593 816 787 577 690 \n1 880 757 923 873 901 815 \n2 880 757 923 873 901 815 \n3 517 313 639 423 578 368 \n4 423 463 907 594 665 529 \n... ... ... ... ... ... ... \n22713 216 388 282 451 249 419 \n22714 576 284 709 398 642 341 \n22715 321 573 718 680 519 626 \n22716 134 512 170 536 152 524 \n22717 515 314 638 441 576 377 \n\n ori_w ori_h img_path \n0 476 194 data/train/9a5094b2563a1ef3ff50dc5c7ff71345.png \n1 43 116 data/train/9a5094b2563a1ef3ff50dc5c7ff71345.png \n2 43 116 data/train/9a5094b2563a1ef3ff50dc5c7ff71345.png \n3 122 110 data/train/9a5094b2563a1ef3ff50dc5c7ff71345.png \n4 484 130 data/train/051132a778e61a86eb147c7c6f564dfe.png \n... ... ... ... \n22713 66 63 data/train/be53fe5a49231f1c1be020b0bdd8561f.png \n22714 133 114 data/train/380d07a94cc4b012812119370de47192.png \n22715 397 107 data/train/52951d7de2485aba8ed62629eee4d254.png \n22716 36 24 data/train/52951d7de2485aba8ed62629eee4d254.png \n22717 123 127 data/train/1224f07d895107573588225f692e94f9.png \n\n[22718 rows x 12 columns]","text/html":"
\n\n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
image_idclass_nameclass_idori_x_minori_y_minori_x_maxori_y_maxori_x_midori_y_midori_wori_himg_path
09a5094b2563a1ef3ff50dc5c7ff71345Cardiomegaly3339593816787577690476194data/train/9a5094b2563a1ef3ff50dc5c7ff71345.png
19a5094b2563a1ef3ff50dc5c7ff71345Pleural effusion1088075792387390181543116data/train/9a5094b2563a1ef3ff50dc5c7ff71345.png
29a5094b2563a1ef3ff50dc5c7ff71345Pleural thickening1188075792387390181543116data/train/9a5094b2563a1ef3ff50dc5c7ff71345.png
39a5094b2563a1ef3ff50dc5c7ff71345Aortic enlargement0517313639423578368122110data/train/9a5094b2563a1ef3ff50dc5c7ff71345.png
4051132a778e61a86eb147c7c6f564dfeCardiomegaly3423463907594665529484130data/train/051132a778e61a86eb147c7c6f564dfe.png
.......................................
22713be53fe5a49231f1c1be020b0bdd8561fLung Opacity72163882824512494196663data/train/be53fe5a49231f1c1be020b0bdd8561f.png
22714380d07a94cc4b012812119370de47192Aortic enlargement0576284709398642341133114data/train/380d07a94cc4b012812119370de47192.png
2271552951d7de2485aba8ed62629eee4d254Cardiomegaly3321573718680519626397107data/train/52951d7de2485aba8ed62629eee4d254.png
2271652951d7de2485aba8ed62629eee4d254Other lesion91345121705361525243624data/train/52951d7de2485aba8ed62629eee4d254.png
227171224f07d895107573588225f692e94f9Aortic enlargement0515314638441576377123127data/train/1224f07d895107573588225f692e94f9.png
\n

22718 rows × 12 columns

\n
"},"metadata":{}}]},{"cell_type":"code","source":"import pandas as pd\nimport cv2\nimport numpy as np\nfrom tqdm import tqdm\nimport os\n\n# Đọc dữ liệu từ final_df (giả sử final_df đã được định nghĩa trước đó)\nfiltered_df = final_df[final_df['class_id'].isin([1, 12])].copy()\n\n# Hàm để cập nhật bounding box sau khi tăng cường\ndef update_bounding_box(bbox, transform_matrix):\n \"\"\"\n Cập nhật bounding box sau khi áp dụng ma trận biến đổi.\n \n Args:\n bbox (list): Danh sách chứa các tọa độ bounding box [x_min, y_min, x_max, y_max].\n transform_matrix (np.array): Ma trận biến đổi affine 2x3.\n \n Returns:\n tuple: Tọa độ bounding box mới [x_min, y_min, x_max, y_max].\n \"\"\"\n ori_x_min, ori_y_min, ori_x_max, ori_y_max = bbox\n \n # Tạo mảng các điểm của bounding box\n points = np.array([\n [ori_x_min, ori_y_min], # Góc trên bên trái\n [ori_x_max, ori_y_min], # Góc trên bên phải\n [ori_x_max, ori_y_max], # Góc dưới bên phải\n [ori_x_min, ori_y_max] # Góc dưới bên trái\n ])\n \n # Chuyển đổi điểm bằng ma trận biến đổi\n # Thay đổi transform_matrix thành dạng 3x3 để dễ tính toán\n # Thêm hàng thứ ba [0, 0, 1] vào ma trận biến đổi để phù hợp với tọa độ đồng nhất\n transform_matrix_3x3 = np.vstack([transform_matrix, [0, 0, 1]])\n \n # Thêm hàng thứ ba [1] vào các điểm để phù hợp với tọa độ đồng nhất\n points_homogeneous = np.hstack([points, np.ones((points.shape[0], 1))])\n \n # Áp dụng ma trận biến đổi\n transformed_points = np.dot(points_homogeneous, transform_matrix_3x3.T)\n \n # Chuyển đổi trở lại tọa độ không đồng nhất\n transformed_points[:, 0] /= transformed_points[:, 2]\n transformed_points[:, 1] /= transformed_points[:, 2]\n \n # Tìm giá trị min và max cho các trục x và y\n ori_x_min = transformed_points[:, 0].min()\n ori_y_min = transformed_points[:, 1].min()\n ori_x_max = transformed_points[:, 0].max()\n ori_y_max = transformed_points[:, 1].max()\n \n return ori_x_min, ori_y_min, ori_x_max, ori_y_max\n\n# Thực hiện tăng cường dữ liệu và lưu thông số mới vào CSV\nnew_rows = []\n\nfor index, row in tqdm(filtered_df.iterrows(), total=filtered_df.shape[0]):\n image_path = row['img_path']\n bbox = [row['ori_x_min'], row['ori_y_min'], row['ori_x_max'], row['ori_y_max']]\n image_id = row['image_id']\n class_name = row['class_name']\n class_id = row['class_id']\n ori_x_mid = row['ori_x_mid']\n ori_y_mid = row['ori_y_mid']\n ori_w = row['ori_w']\n ori_h = row['ori_h']\n \n # Đọc ảnh\n image = cv2.imread(image_path)\n if image is None:\n continue\n \n # Ví dụ về một biến đổi: xoay ảnh 90 độ\n height, width = image.shape[:2]\n M = cv2.getRotationMatrix2D((width / 2, height / 2), 90, 1)\n rotated_image = cv2.warpAffine(image, M, (width, height))\n \n # Cập nhật bounding box\n new_bbox = update_bounding_box(bbox, M)\n \n # Lưu ảnh mới\n new_image_path = os.path.splitext(image_path)[0] + '_rotated.png'\n cv2.imwrite(new_image_path, rotated_image)\n \n # Tạo một dòng mới với thông số cập nhật\n new_row = row.copy()\n new_row['img_path'] = new_image_path\n new_row['ori_x_min'], new_row['ori_y_min'], new_row['ori_x_max'], new_row['ori_y_max'] = new_bbox\n new_row['image_id'] = image_id + '_rotated'\n new_row['class_name'] = class_name\n new_row['class_id'] = class_id\n new_row['ori_x_mid'] = ori_x_mid\n new_row['ori_y_mid'] = ori_y_mid\n new_row['ori_w'] = ori_w\n new_row['ori_h'] = ori_h\n new_rows.append(new_row)\n\n# Tạo DataFrame từ các dòng mới\nnew5_df = pd.DataFrame(new_rows)\n\n# # Gộp dữ liệu mới vào DataFrame gốc\n# augmented_df = pd.concat([final_df, new_df], ignore_index=True)\n\n# # Lưu DataFrame đã cập nhật vào file CSV mới\n# augmented_df.to_csv('/kaggle/working/data/train_augmented.csv', index=False)\n","metadata":{"execution":{"iopub.status.busy":"2024-09-26T01:23:17.436516Z","iopub.execute_input":"2024-09-26T01:23:17.436815Z","iopub.status.idle":"2024-09-26T01:23:42.994979Z","shell.execute_reply.started":"2024-09-26T01:23:17.436792Z","shell.execute_reply":"2024-09-26T01:23:42.993857Z"},"trusted":true},"execution_count":22,"outputs":[{"name":"stderr","text":"100%|██████████| 354/354 [00:25<00:00, 13.88it/s]\n","output_type":"stream"}]},{"cell_type":"code","source":"def flip_image(image_path, bbox):\n \"\"\"\n Lật ảnh theo chiều ngang và cập nhật bounding box.\n\n Args:\n image_path (str): Đường dẫn đến ảnh gốc.\n bbox (list): Danh sách chứa các tọa độ bounding box [x_min, y_min, x_max, y_max].\n\n Returns:\n tuple: Đường dẫn ảnh mới và bounding box đã được cập nhật.\n \"\"\"\n # Đọc ảnh gốc\n image = cv2.imread(image_path)\n if image is None:\n return None, None\n\n # Lật ảnh theo chiều ngang\n flipped_image = cv2.flip(image, 1)\n\n # Cập nhật bounding box\n width = image.shape[1]\n flipped_bbox = [\n width - bbox[2], bbox[1], # x_max -> new_x_min, y_min\n width - bbox[0], bbox[3] # x_min -> new_x_max, y_max\n ]\n\n # Lưu ảnh mới\n new_image_path = os.path.splitext(image_path)[0] + '_flip.png'\n cv2.imwrite(new_image_path, flipped_image)\n \n return new_image_path, flipped_bbox\n","metadata":{"execution":{"iopub.status.busy":"2024-09-26T01:23:42.996647Z","iopub.execute_input":"2024-09-26T01:23:42.997102Z","iopub.status.idle":"2024-09-26T01:23:43.007814Z","shell.execute_reply.started":"2024-09-26T01:23:42.997061Z","shell.execute_reply":"2024-09-26T01:23:43.006454Z"},"trusted":true},"execution_count":23,"outputs":[]},{"cell_type":"code","source":"def flip_images_in_df(df):\n \"\"\"\n Lật ảnh cho các lớp cụ thể và cập nhật thông tin bounding box trong DataFrame.\n\n Args:\n df (pd.DataFrame): DataFrame chứa thông tin về ảnh và bounding box.\n\n Returns:\n pd.DataFrame: DataFrame đã được cập nhật với ảnh lật và bounding box mới.\n \"\"\"\n filtered_df = final_df[final_df['class_id'].isin([1, 12,2,4])].copy()\n new_rows = []\n\n for index, row in tqdm(df.iterrows(), total=df.shape[0]):\n image_path = row['img_path']\n bbox = [row['ori_x_min'], row['ori_y_min'], row['ori_x_max'], row['ori_y_max']]\n image_id = row['image_id']\n class_name = row['class_name']\n class_id = row['class_id']\n ori_x_mid = row['ori_x_mid']\n ori_y_mid = row['ori_y_mid']\n ori_w = row['ori_w']\n ori_h = row['ori_h']\n \n # Lật ảnh và cập nhật bounding box\n new_image_path, new_bbox = flip_image(image_path, bbox)\n \n if new_image_path is None:\n continue\n \n # Tạo một dòng mới với thông số cập nhật\n new_row = row.copy()\n new_row['img_path'] = new_image_path\n new_row['ori_x_min'], new_row['ori_y_min'], new_row['ori_x_max'], new_row['ori_y_max'] = new_bbox\n new_row['image_id'] = image_id + '_flip'\n new_row['class_name'] = class_name\n new_row['class_id'] = class_id\n new_row['ori_x_mid'] = ori_x_mid\n new_row['ori_y_mid'] = ori_y_mid\n new_row['ori_w'] = ori_w\n new_row['ori_h'] = ori_h\n new_rows.append(new_row)\n\n # Tạo DataFrame từ các dòng mới\n new_df = pd.DataFrame(new_rows)\n\n return new_df\n","metadata":{"execution":{"iopub.status.busy":"2024-09-26T01:23:43.009271Z","iopub.execute_input":"2024-09-26T01:23:43.009601Z","iopub.status.idle":"2024-09-26T01:23:43.130881Z","shell.execute_reply.started":"2024-09-26T01:23:43.009572Z","shell.execute_reply":"2024-09-26T01:23:43.129992Z"},"trusted":true},"execution_count":24,"outputs":[]},{"cell_type":"code","source":"new5_df","metadata":{"execution":{"iopub.status.busy":"2024-09-26T01:23:43.131995Z","iopub.execute_input":"2024-09-26T01:23:43.132318Z","iopub.status.idle":"2024-09-26T01:23:43.160392Z","shell.execute_reply.started":"2024-09-26T01:23:43.132288Z","shell.execute_reply":"2024-09-26T01:23:43.159484Z"},"trusted":true},"execution_count":25,"outputs":[{"execution_count":25,"output_type":"execute_result","data":{"text/plain":" image_id class_name class_id \\\n59 80caa435b6ab5edaff4a0a758ffaec6e_rotated Atelectasis 1 \n60 80caa435b6ab5edaff4a0a758ffaec6e_rotated Atelectasis 1 \n61 80caa435b6ab5edaff4a0a758ffaec6e_rotated Atelectasis 1 \n71 80caa435b6ab5edaff4a0a758ffaec6e_rotated Atelectasis 1 \n103 c394eadea89e5795c8037280492d116d_rotated Pneumothorax 12 \n... ... ... ... \n22400 2f3264d3c0a52bb2e280855bcfd35733_rotated Atelectasis 1 \n22557 7253800842122c9e6e95878b46008f54_rotated Atelectasis 1 \n22577 06efcd37617307118fd48b3a493c133b_rotated Atelectasis 1 \n22578 06efcd37617307118fd48b3a493c133b_rotated Atelectasis 1 \n22688 afa4de6570c31504ba4b77978377ccc9_rotated Pneumothorax 12 \n\n ori_x_min ori_y_min ori_x_max ori_y_max ori_x_mid ori_y_mid \\\n59 91.0 622.0 288.0 805.0 310 189 \n60 129.0 614.0 461.0 778.0 328 295 \n61 152.0 552.0 779.0 912.0 292 465 \n71 105.0 222.0 267.0 392.0 717 186 \n103 221.0 580.0 694.0 902.0 283 457 \n... ... ... ... ... ... ... \n22400 519.0 248.0 546.0 303.0 748 532 \n22557 443.0 134.0 510.0 324.0 795 477 \n22577 685.0 70.0 712.0 126.0 926 698 \n22578 639.0 44.0 755.0 162.0 921 697 \n22688 157.0 547.0 616.0 788.0 357 386 \n\n ori_w ori_h img_path \n59 183 197 data/train/80caa435b6ab5edaff4a0a758ffaec6e_ro... \n60 164 332 data/train/80caa435b6ab5edaff4a0a758ffaec6e_ro... \n61 360 627 data/train/80caa435b6ab5edaff4a0a758ffaec6e_ro... \n71 170 162 data/train/80caa435b6ab5edaff4a0a758ffaec6e_ro... \n103 322 473 data/train/c394eadea89e5795c8037280492d116d_ro... \n... ... ... ... \n22400 55 27 data/train/2f3264d3c0a52bb2e280855bcfd35733_ro... \n22557 190 67 data/train/7253800842122c9e6e95878b46008f54_ro... \n22577 56 27 data/train/06efcd37617307118fd48b3a493c133b_ro... \n22578 118 116 data/train/06efcd37617307118fd48b3a493c133b_ro... \n22688 241 459 data/train/afa4de6570c31504ba4b77978377ccc9_ro... \n\n[354 rows x 12 columns]","text/html":"
\n\n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
image_idclass_nameclass_idori_x_minori_y_minori_x_maxori_y_maxori_x_midori_y_midori_wori_himg_path
5980caa435b6ab5edaff4a0a758ffaec6e_rotatedAtelectasis191.0622.0288.0805.0310189183197data/train/80caa435b6ab5edaff4a0a758ffaec6e_ro...
6080caa435b6ab5edaff4a0a758ffaec6e_rotatedAtelectasis1129.0614.0461.0778.0328295164332data/train/80caa435b6ab5edaff4a0a758ffaec6e_ro...
6180caa435b6ab5edaff4a0a758ffaec6e_rotatedAtelectasis1152.0552.0779.0912.0292465360627data/train/80caa435b6ab5edaff4a0a758ffaec6e_ro...
7180caa435b6ab5edaff4a0a758ffaec6e_rotatedAtelectasis1105.0222.0267.0392.0717186170162data/train/80caa435b6ab5edaff4a0a758ffaec6e_ro...
103c394eadea89e5795c8037280492d116d_rotatedPneumothorax12221.0580.0694.0902.0283457322473data/train/c394eadea89e5795c8037280492d116d_ro...
.......................................
224002f3264d3c0a52bb2e280855bcfd35733_rotatedAtelectasis1519.0248.0546.0303.07485325527data/train/2f3264d3c0a52bb2e280855bcfd35733_ro...
225577253800842122c9e6e95878b46008f54_rotatedAtelectasis1443.0134.0510.0324.079547719067data/train/7253800842122c9e6e95878b46008f54_ro...
2257706efcd37617307118fd48b3a493c133b_rotatedAtelectasis1685.070.0712.0126.09266985627data/train/06efcd37617307118fd48b3a493c133b_ro...
2257806efcd37617307118fd48b3a493c133b_rotatedAtelectasis1639.044.0755.0162.0921697118116data/train/06efcd37617307118fd48b3a493c133b_ro...
22688afa4de6570c31504ba4b77978377ccc9_rotatedPneumothorax12157.0547.0616.0788.0357386241459data/train/afa4de6570c31504ba4b77978377ccc9_ro...
\n

354 rows × 12 columns

\n
"},"metadata":{}}]},{"cell_type":"code","source":"filtered_df = final_df[final_df['class_id'].isin([1, 12])].copy()\nnew1_df = flip_images_in_df(filtered_df)","metadata":{"execution":{"iopub.status.busy":"2024-09-26T01:23:43.161606Z","iopub.execute_input":"2024-09-26T01:23:43.161991Z","iopub.status.idle":"2024-09-26T01:24:06.020329Z","shell.execute_reply.started":"2024-09-26T01:23:43.161964Z","shell.execute_reply":"2024-09-26T01:24:06.01943Z"},"trusted":true},"execution_count":26,"outputs":[{"name":"stderr","text":"100%|██████████| 354/354 [00:22<00:00, 15.51it/s]\n","output_type":"stream"}]},{"cell_type":"code","source":"import pandas as pd\nimport cv2\nimport numpy as np\nimport imgaug.augmenters as iaa\nfrom tqdm import tqdm\nimport os\n\ndef zoom_image(image_path, bbox, zoom_factor):\n \"\"\"\n Zoom ảnh và cập nhật bounding box.\n\n Args:\n image_path (str): Đường dẫn đến ảnh gốc.\n bbox (list): Danh sách chứa các tọa độ bounding box [x_min, y_min, x_max, y_max].\n zoom_factor (float): Hệ số zoom.\n\n Returns:\n tuple: Đường dẫn ảnh mới và bounding box đã được cập nhật.\n \"\"\"\n # Đọc ảnh gốc\n image = cv2.imread(image_path)\n if image is None:\n return None, None\n\n # Tăng cường zoom\n augment_img_zoom = iaa.Affine(scale=(zoom_factor))\n zoomed_image = augment_img_zoom.augment_image(image)\n\n # Cập nhật bounding box\n height, width = image.shape[:2]\n new_width, new_height = int(width * zoom_factor), int(height * zoom_factor)\n\n # Tính toán offset để điều chỉnh bounding box\n offset_x = (new_width - width) / 2\n offset_y = (new_height - height) / 2\n\n new_bbox = [\n bbox[0] * zoom_factor - offset_x, # x_min\n bbox[1] * zoom_factor - offset_y, # y_min\n bbox[2] * zoom_factor - offset_x, # x_max\n bbox[3] * zoom_factor - offset_y # y_max\n ]\n\n # Lưu ảnh mới\n new_image_path = os.path.splitext(image_path)[0] + '_zoom.png'\n cv2.imwrite(new_image_path, zoomed_image)\n \n return new_image_path, new_bbox\n","metadata":{"execution":{"iopub.status.busy":"2024-09-26T01:24:06.021849Z","iopub.execute_input":"2024-09-26T01:24:06.022163Z","iopub.status.idle":"2024-09-26T01:24:06.356965Z","shell.execute_reply.started":"2024-09-26T01:24:06.022139Z","shell.execute_reply":"2024-09-26T01:24:06.356018Z"},"trusted":true},"execution_count":27,"outputs":[]},{"cell_type":"code","source":"def zoom_images_in_df(df, zoom_factor):\n \"\"\"\n Thực hiện zoom cho các ảnh thuộc lớp cụ thể và cập nhật thông tin bounding box trong DataFrame.\n\n Args:\n df (pd.DataFrame): DataFrame chứa thông tin về ảnh và bounding box.\n zoom_factor (float): Hệ số zoom.\n\n Returns:\n pd.DataFrame: DataFrame đã được cập nhật với ảnh zoom và bounding box mới.\n \"\"\"\n new_rows = []\n\n for index, row in tqdm(df.iterrows(), total=df.shape[0]):\n image_path = row['img_path']\n bbox = [row['ori_x_min'], row['ori_y_min'], row['ori_x_max'], row['ori_y_max']]\n image_id = row['image_id']\n class_name = row['class_name']\n class_id = row['class_id']\n ori_x_mid = row['ori_x_mid']\n ori_y_mid = row['ori_y_mid']\n ori_w = row['ori_w']\n ori_h = row['ori_h']\n \n # Zoom ảnh và cập nhật bounding box\n new_image_path, new_bbox = zoom_image(image_path, bbox, zoom_factor)\n \n if new_image_path is None:\n continue\n \n # Tạo một dòng mới với thông số cập nhật\n new_row = row.copy()\n new_row['img_path'] = new_image_path\n new_row['ori_x_min'], new_row['ori_y_min'], new_row['ori_x_max'], new_row['ori_y_max'] = new_bbox\n new_row['image_id'] = image_id + '_zoom'\n new_row['class_name'] = class_name\n new_row['class_id'] = class_id\n new_row['ori_x_mid'] = ori_x_mid\n new_row['ori_y_mid'] = ori_y_mid\n new_row['ori_w'] = ori_w\n new_row['ori_h'] = ori_h\n new_rows.append(new_row)\n\n # Tạo DataFrame từ các dòng mới\n new_df = pd.DataFrame(new_rows)\n\n return new_df\n","metadata":{"execution":{"iopub.status.busy":"2024-09-26T01:24:06.3582Z","iopub.execute_input":"2024-09-26T01:24:06.358934Z","iopub.status.idle":"2024-09-26T01:24:06.368787Z","shell.execute_reply.started":"2024-09-26T01:24:06.358901Z","shell.execute_reply":"2024-09-26T01:24:06.367609Z"},"trusted":true},"execution_count":28,"outputs":[]},{"cell_type":"code","source":"filtered_df = final_df[final_df['class_id'].isin([1, 12])].copy()\n\n# Áp dụng hàm zoom ảnh cho DataFrame đã lọc với hệ số zoom là 10% (1.1)\nnew3_df = zoom_images_in_df(filtered_df, zoom_factor=1.1)","metadata":{"execution":{"iopub.status.busy":"2024-09-26T01:24:06.369922Z","iopub.execute_input":"2024-09-26T01:24:06.370241Z","iopub.status.idle":"2024-09-26T01:24:30.910036Z","shell.execute_reply.started":"2024-09-26T01:24:06.370211Z","shell.execute_reply":"2024-09-26T01:24:30.909116Z"},"trusted":true},"execution_count":29,"outputs":[{"name":"stderr","text":"100%|██████████| 354/354 [00:24<00:00, 14.45it/s]\n","output_type":"stream"}]},{"cell_type":"code","source":"import cv2\nimport os\n\ndef clahe_image(image_list):\n \"\"\"\n Áp dụng CLAHE cho ảnh và lưu ảnh đã được tăng cường.\n\n Args:\n image_list (list): Danh sách các đường dẫn đến các ảnh cần áp dụng CLAHE.\n \"\"\"\n clahe = cv2.createCLAHE(clipLimit=2.0, tileGridSize=(8, 8))\n \n for path in image_list:\n img = cv2.imread(path, cv2.IMREAD_GRAYSCALE)\n if img is None:\n continue\n clahe_img = clahe.apply(img)\n img_name = os.path.basename(path).split('.')[0]\n new_image_path = f'{os.path.splitext(path)[0]}_clahe.png'\n cv2.imwrite(new_image_path, clahe_img)\n","metadata":{"execution":{"iopub.status.busy":"2024-09-26T01:24:30.911351Z","iopub.execute_input":"2024-09-26T01:24:30.91173Z","iopub.status.idle":"2024-09-26T01:24:30.918545Z","shell.execute_reply.started":"2024-09-26T01:24:30.911682Z","shell.execute_reply":"2024-09-26T01:24:30.917689Z"},"trusted":true},"execution_count":30,"outputs":[]},{"cell_type":"code","source":"import pandas as pd\nfrom tqdm import tqdm\n\n# Lọc DataFrame chỉ chứa các lớp có class_id là 1 và 12\nfiltered_df = final_df[final_df['class_id'].isin([1, 12,4])].copy()\n\n# Tạo danh sách các đường dẫn ảnh\nimage_list = filtered_df['img_path'].tolist()\n\n# Thực hiện CLAHE cho các ảnh\nclahe_image(image_list)\n\n# Cập nhật DataFrame với ảnh mới đã áp dụng CLAHE\ndef update_df_with_clahe(df):\n new_rows = []\n\n for index, row in tqdm(df.iterrows(), total=df.shape[0]):\n image_path = row['img_path']\n img_name = os.path.basename(image_path).split('.')[0]\n new_image_path = f'{os.path.splitext(image_path)[0]}_clahe.png'\n\n # Tạo một dòng mới với đường dẫn ảnh CLAHE\n new_row = row.copy()\n new_row['img_path'] = new_image_path\n new_row['image_id'] = row['image_id'] + '_clahe'\n new_rows.append(new_row)\n\n # Tạo DataFrame từ các dòng mới\n new_df = pd.DataFrame(new_rows)\n \n return new_df\n\n# Áp dụng hàm cập nhật DataFrame\nnew4_df = update_df_with_clahe(filtered_df)\n\n","metadata":{"execution":{"iopub.status.busy":"2024-09-26T01:24:30.919843Z","iopub.execute_input":"2024-09-26T01:24:30.920106Z","iopub.status.idle":"2024-09-26T01:24:58.346566Z","shell.execute_reply.started":"2024-09-26T01:24:30.920084Z","shell.execute_reply":"2024-09-26T01:24:58.345736Z"},"trusted":true},"execution_count":31,"outputs":[{"name":"stderr","text":"100%|██████████| 782/782 [00:00<00:00, 8052.13it/s]\n","output_type":"stream"}]},{"cell_type":"code","source":"import cv2\nimport os\n\ndef equ_image(image_list):\n \"\"\"\n Áp dụng EqualizeHist cho ảnh và lưu ảnh đã được tăng cường.\n\n Args:\n image_list (list): Danh sách các đường dẫn đến các ảnh cần áp dụng EqualizeHist.\n \"\"\"\n for path in image_list:\n img = cv2.imread(path, cv2.IMREAD_GRAYSCALE)\n if img is None:\n continue\n equ_img = cv2.equalizeHist(img)\n img_name = os.path.basename(path).split('.')[0]\n new_image_path = f'{os.path.splitext(path)[0]}_equ.png'\n cv2.imwrite(new_image_path, equ_img)\n","metadata":{"execution":{"iopub.status.busy":"2024-09-26T01:24:58.35333Z","iopub.execute_input":"2024-09-26T01:24:58.353646Z","iopub.status.idle":"2024-09-26T01:24:58.359575Z","shell.execute_reply.started":"2024-09-26T01:24:58.35362Z","shell.execute_reply":"2024-09-26T01:24:58.358649Z"},"trusted":true},"execution_count":32,"outputs":[]},{"cell_type":"code","source":"import pandas as pd\nfrom tqdm import tqdm\n\n# Lọc DataFrame chỉ chứa các lớp có class_id là 1 và 12\nfiltered_df = final_df[final_df['class_id'].isin([1, 12,4,5,2,6])].copy()\n\n# Tạo danh sách các đường dẫn ảnh\nimage_list = filtered_df['img_path'].tolist()\n\n# Thực hiện EqualizeHist cho các ảnh\nequ_image(image_list)\n\n# Cập nhật DataFrame với ảnh mới đã áp dụng EqualizeHist\ndef update_df_with_equ(df):\n new_rows = []\n\n for index, row in tqdm(df.iterrows(), total=df.shape[0]):\n image_path = row['img_path']\n img_name = os.path.basename(image_path).split('.')[0]\n new_image_path = f'{os.path.splitext(image_path)[0]}_equ.png'\n\n # Tạo một dòng mới với đường dẫn ảnh EqualizeHist\n new_row = row.copy()\n new_row['img_path'] = new_image_path\n new_row['image_id'] = row['image_id'] + '_equ'\n new_rows.append(new_row)\n\n # Tạo DataFrame từ các dòng mới\n new_df = pd.DataFrame(new_rows)\n \n return new_df\n\n# Áp dụng hàm cập nhật DataFrame\n\n\n\n","metadata":{"execution":{"iopub.status.busy":"2024-09-26T01:24:58.360773Z","iopub.execute_input":"2024-09-26T01:24:58.361133Z","iopub.status.idle":"2024-09-26T01:26:42.998456Z","shell.execute_reply.started":"2024-09-26T01:24:58.361109Z","shell.execute_reply":"2024-09-26T01:26:42.996884Z"},"trusted":true},"execution_count":33,"outputs":[]},{"cell_type":"code","source":"new2_df=update_df_with_equ(filtered_df)","metadata":{"execution":{"iopub.status.busy":"2024-09-26T01:26:43.000117Z","iopub.execute_input":"2024-09-26T01:26:43.000508Z","iopub.status.idle":"2024-09-26T01:26:43.781281Z","shell.execute_reply.started":"2024-09-26T01:26:43.000475Z","shell.execute_reply":"2024-09-26T01:26:43.780492Z"},"trusted":true},"execution_count":34,"outputs":[{"name":"stderr","text":"100%|██████████| 3114/3114 [00:00<00:00, 7960.19it/s]\n","output_type":"stream"}]},{"cell_type":"code","source":"new_train_df = pd.concat([new5_df, new1_df, new2_df, new4_df,new3_df, final_df], ignore_index=True)","metadata":{"execution":{"iopub.status.busy":"2024-09-26T01:26:43.782355Z","iopub.execute_input":"2024-09-26T01:26:43.78265Z","iopub.status.idle":"2024-09-26T01:26:43.789617Z","shell.execute_reply.started":"2024-09-26T01:26:43.782625Z","shell.execute_reply":"2024-09-26T01:26:43.788609Z"},"trusted":true},"execution_count":35,"outputs":[]},{"cell_type":"code","source":"new_train_df","metadata":{"execution":{"iopub.status.busy":"2024-09-26T01:26:43.790871Z","iopub.execute_input":"2024-09-26T01:26:43.791143Z","iopub.status.idle":"2024-09-26T01:26:43.812985Z","shell.execute_reply.started":"2024-09-26T01:26:43.791121Z","shell.execute_reply":"2024-09-26T01:26:43.812222Z"},"trusted":true},"execution_count":36,"outputs":[{"execution_count":36,"output_type":"execute_result","data":{"text/plain":" image_id class_name class_id \\\n0 80caa435b6ab5edaff4a0a758ffaec6e_rotated Atelectasis 1 \n1 80caa435b6ab5edaff4a0a758ffaec6e_rotated Atelectasis 1 \n2 80caa435b6ab5edaff4a0a758ffaec6e_rotated Atelectasis 1 \n3 80caa435b6ab5edaff4a0a758ffaec6e_rotated Atelectasis 1 \n4 c394eadea89e5795c8037280492d116d_rotated Pneumothorax 12 \n... ... ... ... \n27671 be53fe5a49231f1c1be020b0bdd8561f Lung Opacity 7 \n27672 380d07a94cc4b012812119370de47192 Aortic enlargement 0 \n27673 52951d7de2485aba8ed62629eee4d254 Cardiomegaly 3 \n27674 52951d7de2485aba8ed62629eee4d254 Other lesion 9 \n27675 1224f07d895107573588225f692e94f9 Aortic enlargement 0 \n\n ori_x_min ori_y_min ori_x_max ori_y_max ori_x_mid ori_y_mid \\\n0 91.0 622.0 288.0 805.0 310 189 \n1 129.0 614.0 461.0 778.0 328 295 \n2 152.0 552.0 779.0 912.0 292 465 \n3 105.0 222.0 267.0 392.0 717 186 \n4 221.0 580.0 694.0 902.0 283 457 \n... ... ... ... ... ... ... \n27671 216.0 388.0 282.0 451.0 249 419 \n27672 576.0 284.0 709.0 398.0 642 341 \n27673 321.0 573.0 718.0 680.0 519 626 \n27674 134.0 512.0 170.0 536.0 152 524 \n27675 515.0 314.0 638.0 441.0 576 377 \n\n ori_w ori_h img_path \n0 183 197 data/train/80caa435b6ab5edaff4a0a758ffaec6e_ro... \n1 164 332 data/train/80caa435b6ab5edaff4a0a758ffaec6e_ro... \n2 360 627 data/train/80caa435b6ab5edaff4a0a758ffaec6e_ro... \n3 170 162 data/train/80caa435b6ab5edaff4a0a758ffaec6e_ro... \n4 322 473 data/train/c394eadea89e5795c8037280492d116d_ro... \n... ... ... ... \n27671 66 63 data/train/be53fe5a49231f1c1be020b0bdd8561f.png \n27672 133 114 data/train/380d07a94cc4b012812119370de47192.png \n27673 397 107 data/train/52951d7de2485aba8ed62629eee4d254.png \n27674 36 24 data/train/52951d7de2485aba8ed62629eee4d254.png \n27675 123 127 data/train/1224f07d895107573588225f692e94f9.png \n\n[27676 rows x 12 columns]","text/html":"
\n\n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
image_idclass_nameclass_idori_x_minori_y_minori_x_maxori_y_maxori_x_midori_y_midori_wori_himg_path
080caa435b6ab5edaff4a0a758ffaec6e_rotatedAtelectasis191.0622.0288.0805.0310189183197data/train/80caa435b6ab5edaff4a0a758ffaec6e_ro...
180caa435b6ab5edaff4a0a758ffaec6e_rotatedAtelectasis1129.0614.0461.0778.0328295164332data/train/80caa435b6ab5edaff4a0a758ffaec6e_ro...
280caa435b6ab5edaff4a0a758ffaec6e_rotatedAtelectasis1152.0552.0779.0912.0292465360627data/train/80caa435b6ab5edaff4a0a758ffaec6e_ro...
380caa435b6ab5edaff4a0a758ffaec6e_rotatedAtelectasis1105.0222.0267.0392.0717186170162data/train/80caa435b6ab5edaff4a0a758ffaec6e_ro...
4c394eadea89e5795c8037280492d116d_rotatedPneumothorax12221.0580.0694.0902.0283457322473data/train/c394eadea89e5795c8037280492d116d_ro...
.......................................
27671be53fe5a49231f1c1be020b0bdd8561fLung Opacity7216.0388.0282.0451.02494196663data/train/be53fe5a49231f1c1be020b0bdd8561f.png
27672380d07a94cc4b012812119370de47192Aortic enlargement0576.0284.0709.0398.0642341133114data/train/380d07a94cc4b012812119370de47192.png
2767352951d7de2485aba8ed62629eee4d254Cardiomegaly3321.0573.0718.0680.0519626397107data/train/52951d7de2485aba8ed62629eee4d254.png
2767452951d7de2485aba8ed62629eee4d254Other lesion9134.0512.0170.0536.01525243624data/train/52951d7de2485aba8ed62629eee4d254.png
276751224f07d895107573588225f692e94f9Aortic enlargement0515.0314.0638.0441.0576377123127data/train/1224f07d895107573588225f692e94f9.png
\n

27676 rows × 12 columns

\n
"},"metadata":{}}]},{"cell_type":"code","source":"import pandas as pd\n\n# Giả sử new_train_df đã tồn tại\n# Ví dụ:\n# new_train_df = pd.DataFrame(...)\n\n# Tạo một bản sao của new_train_df để xử lý\nnew_df = new_train_df.copy()\n\n# Đổi tên các cột liên quan\nnew_df.rename(columns={\n 'ori_x_min': 'x_min',\n 'ori_y_min': 'y_min',\n 'ori_x_max': 'x_max',\n 'ori_y_max': 'y_max'\n}, inplace=True)\n\n# Chuyển đổi giá trị các cột x_min, x_max, y_min, y_max\nnew_df['x_min'] = new_df['x_min'] / 1024\nnew_df['y_min'] = new_df['y_min'] / 1024\nnew_df['x_max'] = new_df['x_max'] / 1024\nnew_df['y_max'] = new_df['y_max'] / 1024\n\n# Chỉ giữ lại các cột x_min, x_max, y_min, y_max\nnew_df = new_df[['image_id','class_id','class_name','x_min', 'x_max', 'y_min', 'y_max']]\nnew_df['x_center'] = (new_df['x_max'] + new_df['x_min']) / 2\nnew_df['y_center'] = (new_df['y_max'] + new_df['y_min']) / 2\n\nnew_df['w'] = (new_df['x_max'] - new_df['x_min'])\nnew_df['h'] = (new_df['y_max'] - new_df['y_min'])\n# Hiển thị kết quả\nnew_df\n","metadata":{"execution":{"iopub.status.busy":"2024-09-26T01:26:43.814132Z","iopub.execute_input":"2024-09-26T01:26:43.814393Z","iopub.status.idle":"2024-09-26T01:26:43.848162Z","shell.execute_reply.started":"2024-09-26T01:26:43.814371Z","shell.execute_reply":"2024-09-26T01:26:43.847289Z"},"trusted":true},"execution_count":37,"outputs":[{"execution_count":37,"output_type":"execute_result","data":{"text/plain":" image_id class_id class_name \\\n0 80caa435b6ab5edaff4a0a758ffaec6e_rotated 1 Atelectasis \n1 80caa435b6ab5edaff4a0a758ffaec6e_rotated 1 Atelectasis \n2 80caa435b6ab5edaff4a0a758ffaec6e_rotated 1 Atelectasis \n3 80caa435b6ab5edaff4a0a758ffaec6e_rotated 1 Atelectasis \n4 c394eadea89e5795c8037280492d116d_rotated 12 Pneumothorax \n... ... ... ... \n27671 be53fe5a49231f1c1be020b0bdd8561f 7 Lung Opacity \n27672 380d07a94cc4b012812119370de47192 0 Aortic enlargement \n27673 52951d7de2485aba8ed62629eee4d254 3 Cardiomegaly \n27674 52951d7de2485aba8ed62629eee4d254 9 Other lesion \n27675 1224f07d895107573588225f692e94f9 0 Aortic enlargement \n\n x_min x_max y_min y_max x_center y_center w \\\n0 0.088867 0.281250 0.607422 0.786133 0.185059 0.696777 0.192383 \n1 0.125977 0.450195 0.599609 0.759766 0.288086 0.679688 0.324219 \n2 0.148437 0.760742 0.539062 0.890625 0.454590 0.714844 0.612305 \n3 0.102539 0.260742 0.216797 0.382812 0.181641 0.299805 0.158203 \n4 0.215820 0.677734 0.566406 0.880859 0.446777 0.723633 0.461914 \n... ... ... ... ... ... ... ... \n27671 0.210938 0.275391 0.378906 0.440430 0.243164 0.409668 0.064453 \n27672 0.562500 0.692383 0.277344 0.388672 0.627441 0.333008 0.129883 \n27673 0.313477 0.701172 0.559570 0.664062 0.507324 0.611816 0.387695 \n27674 0.130859 0.166016 0.500000 0.523438 0.148438 0.511719 0.035156 \n27675 0.502930 0.623047 0.306641 0.430664 0.562988 0.368652 0.120117 \n\n h \n0 0.178711 \n1 0.160156 \n2 0.351562 \n3 0.166016 \n4 0.314453 \n... ... \n27671 0.061523 \n27672 0.111328 \n27673 0.104492 \n27674 0.023438 \n27675 0.124023 \n\n[27676 rows x 11 columns]","text/html":"
\n\n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
image_idclass_idclass_namex_minx_maxy_miny_maxx_centery_centerwh
080caa435b6ab5edaff4a0a758ffaec6e_rotated1Atelectasis0.0888670.2812500.6074220.7861330.1850590.6967770.1923830.178711
180caa435b6ab5edaff4a0a758ffaec6e_rotated1Atelectasis0.1259770.4501950.5996090.7597660.2880860.6796880.3242190.160156
280caa435b6ab5edaff4a0a758ffaec6e_rotated1Atelectasis0.1484370.7607420.5390620.8906250.4545900.7148440.6123050.351562
380caa435b6ab5edaff4a0a758ffaec6e_rotated1Atelectasis0.1025390.2607420.2167970.3828120.1816410.2998050.1582030.166016
4c394eadea89e5795c8037280492d116d_rotated12Pneumothorax0.2158200.6777340.5664060.8808590.4467770.7236330.4619140.314453
....................................
27671be53fe5a49231f1c1be020b0bdd8561f7Lung Opacity0.2109380.2753910.3789060.4404300.2431640.4096680.0644530.061523
27672380d07a94cc4b012812119370de471920Aortic enlargement0.5625000.6923830.2773440.3886720.6274410.3330080.1298830.111328
2767352951d7de2485aba8ed62629eee4d2543Cardiomegaly0.3134770.7011720.5595700.6640620.5073240.6118160.3876950.104492
2767452951d7de2485aba8ed62629eee4d2549Other lesion0.1308590.1660160.5000000.5234380.1484380.5117190.0351560.023438
276751224f07d895107573588225f692e94f90Aortic enlargement0.5029300.6230470.3066410.4306640.5629880.3686520.1201170.124023
\n

27676 rows × 11 columns

\n
"},"metadata":{}}]},{"cell_type":"code","source":"new_df['class_id'].value_counts()","metadata":{"execution":{"iopub.status.busy":"2024-09-26T01:26:43.84921Z","iopub.execute_input":"2024-09-26T01:26:43.849479Z","iopub.status.idle":"2024-09-26T01:26:43.857986Z","shell.execute_reply.started":"2024-09-26T01:26:43.849457Z","shell.execute_reply":"2024-09-26T01:26:43.857011Z"},"trusted":true},"execution_count":38,"outputs":[{"execution_count":38,"output_type":"execute_result","data":{"text/plain":"class_id\n11 3793\n0 3203\n13 3125\n3 2336\n7 1941\n6 1828\n8 1826\n9 1776\n10 1604\n2 1454\n5 1382\n1 1356\n4 1284\n12 768\nName: count, dtype: int64"},"metadata":{}}]},{"cell_type":"code","source":"# ncount = len(new_df) #sample의 개수\n# plt.figure(figsize = (12,8))\n# #Seaborn으로 class name기준으로 bar chart 그리기\n# ax = sns.countplot(x = 'class_name', data = new_df, order = new_df.class_name.value_counts().index)\n# plt.title('Distribution of class names')\n# ax.set_xticklabels(ax.get_xticklabels(), rotation = 45, ha ='right')\n# #x축만 공유하고 y축은 따로 쓰는 'twinx()'\n# ax2 = ax.twinx()\n# # tick: 축에 간격을 구분하기 위해 표시하는 눈금\n# # ax는 오른쪽, ax2는 왼쪽\n# ax2.yaxis.tick_left() \n# ax.yaxis.tick_right() \n\n# ax.yaxis.set_label_position('right')\n# ax2.yaxis.set_label_position('left')\n\n# ax2.set_ylabel('Frequency [%]')\n# # patches 모듈은 (x, y, width, height)의 형태로 도형으로 시각화 하는 방법\n# for p in ax.patches:\n# x = p.get_bbox().get_points()[:,0] # get_points: bbox의 점을 [[x0,y0],[x1,y1]]형식의 numpy배열로 직접가져옴\n# y = p.get_bbox().get_points()[1,1]\n# # annotate: 주석달기. (주석 내용, 좌표는 필수로 전달해야함)\n# # ha = horizontal alignmnet, va = vertical alignment\n# ax.annotate('{:.1f}%'.format(100.*y/ncount), (x.mean(), y), ha = 'center', va = 'bottom')\n\n# # linearlocator: min에서 max까지 균일 분포 눈금.\n# ax.yaxis.set_major_locator(ticker.LinearLocator(11))\n# # y값의 limitation\n# ax2.set_ylim(0,100)\n# ax.set_ylim(0,ncount)\n# # multiplelocator: 눈금과 범위는 모두 base의 배수\n# ax2.yaxis.set_major_locator(ticker.MultipleLocator(10))\n\n# ax2.grid(None)","metadata":{"execution":{"iopub.status.busy":"2024-09-26T01:26:43.859257Z","iopub.execute_input":"2024-09-26T01:26:43.859602Z","iopub.status.idle":"2024-09-26T01:26:43.867246Z","shell.execute_reply.started":"2024-09-26T01:26:43.859571Z","shell.execute_reply":"2024-09-26T01:26:43.866556Z"},"trusted":true},"execution_count":39,"outputs":[]},{"cell_type":"code","source":"import os\nimport numpy as np\nimport shutil\nimport yaml\nfrom sklearn.model_selection import GroupShuffleSplit\nfrom tqdm import tqdm\n\n# Training/validation splitting\nsplitter = GroupShuffleSplit(test_size=0.1)\nsplit = splitter.split(new_df, groups=new_df['image_id'])\ntrain_inds, valid_inds = next(split)\n\nvalid_df = new_df.iloc[valid_inds]\ntrain_df = new_df.iloc[train_inds]\n\n# Create images and labels directories for both training and validation\nfor folder in [\n TRAIN_IMAGES_PATH_REFACTORED,\n TRAIN_LABELS_PATH_REFACTORED,\n VALID_IMAGES_PATH_REFACTORED,\n VALID_LABELS_PATH_REFACTORED,\n]:\n os.makedirs(folder, exist_ok=True)\n\n# Copy training images to its designated directory, and create a txt file for each image denoting its classes and their positions\nfor image in tqdm(train_df['image_id'].unique()):\n records = train_df[train_df['image_id'] == image]\n attributes = records[['class_id', 'x_center', 'y_center', 'w', 'h']].values\n np.savetxt(\n os.path.join(TRAIN_LABELS_PATH_REFACTORED, f'{image}.txt'),\n attributes,\n fmt=['%d', '%f', '%f', '%f', '%f']\n )\n shutil.copy(\n os.path.join(TRAIN_IMAGES_DIRECTORY, f'{image}.png'),\n TRAIN_IMAGES_PATH_REFACTORED\n )\n\n# Copy validation images to its designated directory, and create a txt file for each image denoting its classes and their positions\nfor image in tqdm(valid_df['image_id'].unique()):\n records = valid_df[valid_df['image_id'] == image]\n attributes = records[['class_id', 'x_center', 'y_center', 'w', 'h']].values\n np.savetxt(\n os.path.join(VALID_LABELS_PATH_REFACTORED, f'{image}.txt'),\n attributes,\n fmt=['%d', '%f', '%f', '%f', '%f']\n )\n shutil.copy(\n os.path.join(TRAIN_IMAGES_DIRECTORY, f'{image}.png'),\n VALID_IMAGES_PATH_REFACTORED\n )\n\n# Order the classes based on the class ID numerical value (in an ascending order)\nclass_ids, class_names = list(zip(*set(zip(new_df['class_id'], new_df['class_name']))))\nclasses = list(np.array(class_names)[np.argsort(class_ids)])\nclasses = list(map(lambda x: str(x), classes))\n\n# Store a list containing the path of each training image in a TXT file\nwith open('train.txt', 'w') as f:\n for path in os.listdir(TRAIN_IMAGES_PATH_REFACTORED):\n f.write(f'{TRAIN_IMAGES_PATH_REFACTORED}{path}\\n')\n\n# Store a list containing the path of each validation image in a TXT file\nwith open('valid.txt', 'w') as f:\n for path in os.listdir(VALID_IMAGES_PATH_REFACTORED):\n f.write(f'{VALID_IMAGES_PATH_REFACTORED}{path}\\n')\n\n# Create a dictionary containing the necessary configurations to run YOLO\ndata = dict(\n train='train.txt',\n val='valid.txt',\n nc=14, # Assuming 14 classes, adjust if needed\n names=classes\n)\n\n# Store the configurations in a YAML file, to be absorbed later by YOLO\nwith open('yolo.yaml', 'w') as outfile:\n yaml.dump(data, outfile, default_flow_style=False)\n\n# Return train dataframe and the original dataframe loaded from a CSV (assuming the CSV path is '/kaggle/working/data/train.csv')\n# return [pd.read_csv('/kaggle/working/data/train.csv'), train_df]\n","metadata":{"execution":{"iopub.status.busy":"2024-09-26T01:26:43.868526Z","iopub.execute_input":"2024-09-26T01:26:43.869032Z","iopub.status.idle":"2024-09-26T01:27:31.331855Z","shell.execute_reply.started":"2024-09-26T01:26:43.868998Z","shell.execute_reply":"2024-09-26T01:27:31.330856Z"},"trusted":true},"execution_count":40,"outputs":[{"name":"stderr","text":"100%|██████████| 6547/6547 [00:45<00:00, 145.31it/s]\n100%|██████████| 728/728 [00:02<00:00, 313.76it/s]\n","output_type":"stream"}]},{"cell_type":"code","source":"# def train_model(\n# train_step: int = 2, # Chọn lần huấn luyện (1 cho lần 1, 2 cho lần 2)\n# visualize: bool = False,\n# export_as_onnx: bool = False,\n# export_as_tf: bool = False,\n# export_as_tflite: bool = False,\n# conf_thres: float = 0.3,\n# iou_thres: float = 0.4,\n# ):\n\n\n# if train_step == 1:\n# # Train lần 1\n# print(\"Training lần 1...\")\n# !torchrun --nproc_per_node=2 --master_port 9527 /kaggle/working/yolov9/train_dual.py --device 0,1 --sync-bn --img {IMAGE_SIZE} --cfg /kaggle/working/yolov9/models/detect/yolov9-c.yaml --batch-size 8 --epochs 10 --data yolo.yaml --weights /kaggle/working/yolov9-c.pt --hyp /kaggle/working/yolov9/data/hyps/hyp.scratch-high.yaml --min-items 0 --close-mosaic 15\n\n# # Lưu trọng số sau lần train 1 vào /kaggle/outputs\n# print(\"Lưu mô hình sau lần 1...\")\n# !cp /kaggle/working/yolov9/runs/train/exp/weights/last.pt /kaggle/working/yolov9-c-lan1.pt\n\n# print(\"Đã hoàn thành lần huấn luyện 1. Lưu mô hình và dừng lại.\")\n\n# return # Dừng lại ngay sau khi huấn luyện lần 1 hoàn thành\n\n# elif train_step == 2:\n# # Load mô hình từ lần train 1 và tiếp tục train lần 2\n# print(\"Training lần 2...\")\n# !torchrun --nproc_per_node=2 --master_port 9527 /kaggle/working/yolov9/train_dual.py --device 0,1 --sync-bn --img {IMAGE_SIZE} --cfg /kaggle/working/yolov9/models/detect/yolov9-c.yaml --batch-size 8 --epochs 20 --data yolo.yaml --weights /kaggle/working/last.pt \n\n# if visualize:\n# # Visualize các kết quả sau lần huấn luyện\n# plt.rcParams.update({\n# 'figure.figsize': (15, 8),\n# 'axes.spines.left': False,\n# 'axes.spines.right': False,\n# 'axes.spines.bottom': False,\n# 'axes.spines.top': False,\n# 'xtick.bottom': False,\n# 'xtick.labelbottom': False,\n# 'ytick.labelleft': False,\n# 'ytick.left': False,\n# })\n\n# for img_name in ['results.png', 'PR_curve.png', 'confusion_matrix.png']:\n# img_path = f'runs/train/exp/{img_name}'\n# plt.figure(figsize=(15, 8))\n# plt.imshow(plt.imread(img_path))\n# plt.title(f\"{img_name} (conf_thres={conf_thres}, iou_thres={iou_thres})\")\n# plt.axis('off')\n\n# plt.rcParams.update(plt.rcParamsDefault)\n# plt.rcParams.update({'figure.figsize': (15, 8)})\n\n# if export_as_onnx or export_as_tf or export_as_tflite:\n# print(\"Exporting mô hình...\")\n# !python yolov9/export.py --weights yolov9-c.pt --img-size {IMAGE_SIZE} {IMAGE_SIZE} --max-wh {IMAGE_SIZE} --grid --end2end --simplify\n\n# if export_as_tf or export_as_tflite:\n# !onnx-tf convert -i yolov9.onnx -o ./\n\n# if export_as_tflite:\n# converter = tf.lite.TFLiteConverter.from_saved_model('./')\n# tflite_model = converter.convert()\n# with open('yolov9.tflite', 'wb') as f:\n# f.write(tflite_model)\n","metadata":{"execution":{"iopub.status.busy":"2024-09-26T01:27:31.333035Z","iopub.execute_input":"2024-09-26T01:27:31.333326Z","iopub.status.idle":"2024-09-26T01:27:31.340333Z","shell.execute_reply.started":"2024-09-26T01:27:31.333301Z","shell.execute_reply":"2024-09-26T01:27:31.339411Z"},"trusted":true},"execution_count":41,"outputs":[]},{"cell_type":"code","source":"# def train_model(\n# train_step: int = 1,\n# visualize: bool = True,\n# export_as_onnx: bool = True,\n# export_as_tf: bool = True,\n# export_as_tflite: bool = True,\n# ):\n# if train_step == 1:\n# # Train lần 1\n# print(\"Training lần 1...\")\n# !python /kaggle/working/yolov7/train.py --workers 0 --device 0 --img {IMAGE_SIZE} --batch-size 20 --epochs 30 --data /kaggle/working/yolo.yaml --weights /kaggle/working/yolov7.pt --hyp /kaggle/working/yolov7/data/hyp.scratch.p5.yaml\n# # Lưu trọng số sau lần train 1 vào /kaggle/outputs\n# print(\"Lưu mô hình sau lần 1...\")\n\n# print(\"Đã hoàn thành lần huấn luyện 1. Lưu mô hình và dừng lại.\")\n\n# return # Dừng lại ngay sau khi huấn luyện lần 1 hoàn thành\n\n# elif train_step == 2:\n# # Load mô hình từ lần train 1 và tiếp tục train lần 2\n# print(\"Training lần 2...\")\n# !torchrun --nproc_per_node=2 --master_port 9527 /kaggle/working/yolov9/train_dual.py --device 0,1 --sync-bn --img {IMAGE_SIZE} --cfg /kaggle/working/yolov9/models/detect/yolov9-c.yaml --batch-size 16 --epochs 40 --data yolo.yaml --weights /kaggle/working/last.pt \n\n\n# if visualize:\n# # Modify matplotlib figure size, and remove axis lines and ticks\n# plt.rcParams.update({\n# 'figure.figsize': (15, 8),\n# 'axes.spines.left': False,\n# 'axes.spines.right': False,\n# 'axes.spines.bottom': False,\n# 'axes.spines.top': False,\n# 'xtick.bottom': False,\n# 'xtick.labelbottom': False,\n# 'ytick.labelleft': False,\n# 'ytick.left': False,\n# })\n\n# plt.imshow(plt.imread('runs/train/exp/results.png'))\n# plt.imshow(plt.imread('runs/train/exp/PR_curve.png'))\n# plt.imshow(plt.imread('runs/train/exp/confusion_matrix.png'))\n\n# plt.rcParams.update(plt.rcParamsDefault)\n# plt.rcParams.update({'figure.figsize': (15, 8)})\n\n# if export_as_onnx or export_as_tf or export_as_tflite:\n# !python yolov7/export.py --weights yolov7.pt --img-size {IMAGE_SIZE} {IMAGE_SIZE} --max-wh {IMAGE_SIZE} --grid --end2end --simplify\n\n# if export_as_tf or export_as_tflite:\n# !onnx-tf convert -i yolov7.onnx -o ./\n\n# if export_as_tflite:\n# converter = tf.lite.TFLiteConverter.from_saved_model('./')\n# tflite_model = converter.convert()\n# with open('yolov7.tflite', 'wb') as f:\n# f.write(tflite_model)","metadata":{"execution":{"iopub.status.busy":"2024-09-26T01:27:31.341837Z","iopub.execute_input":"2024-09-26T01:27:31.342164Z","iopub.status.idle":"2024-09-26T01:27:31.358403Z","shell.execute_reply.started":"2024-09-26T01:27:31.342135Z","shell.execute_reply":"2024-09-26T01:27:31.357623Z"},"trusted":true},"execution_count":42,"outputs":[]},{"cell_type":"code","source":"!pip install ultralytics","metadata":{"execution":{"iopub.status.busy":"2024-09-26T01:27:31.359536Z","iopub.execute_input":"2024-09-26T01:27:31.360052Z","iopub.status.idle":"2024-09-26T01:27:45.074244Z","shell.execute_reply.started":"2024-09-26T01:27:31.36002Z","shell.execute_reply":"2024-09-26T01:27:45.073219Z"},"trusted":true},"execution_count":43,"outputs":[{"name":"stdout","text":"Collecting ultralytics\n Downloading ultralytics-8.2.101-py3-none-any.whl.metadata (39 kB)\nRequirement already satisfied: numpy<2.0.0,>=1.23.0 in /opt/conda/lib/python3.10/site-packages (from ultralytics) (1.26.4)\nRequirement already satisfied: matplotlib>=3.3.0 in /opt/conda/lib/python3.10/site-packages (from ultralytics) (3.7.5)\nRequirement already satisfied: opencv-python>=4.6.0 in /opt/conda/lib/python3.10/site-packages (from ultralytics) (4.9.0.80)\nRequirement already satisfied: pillow>=7.1.2 in /opt/conda/lib/python3.10/site-packages (from ultralytics) (9.5.0)\nRequirement already satisfied: pyyaml>=5.3.1 in /opt/conda/lib/python3.10/site-packages (from ultralytics) (6.0.1)\nRequirement already satisfied: requests>=2.23.0 in /opt/conda/lib/python3.10/site-packages (from ultralytics) (2.31.0)\nRequirement already satisfied: scipy>=1.4.1 in /opt/conda/lib/python3.10/site-packages (from ultralytics) (1.11.4)\nRequirement already satisfied: torch>=1.8.0 in /opt/conda/lib/python3.10/site-packages (from ultralytics) (2.1.2)\nRequirement already satisfied: torchvision>=0.9.0 in /opt/conda/lib/python3.10/site-packages (from ultralytics) (0.16.2)\nRequirement already satisfied: tqdm>=4.64.0 in /opt/conda/lib/python3.10/site-packages (from ultralytics) (4.66.1)\nRequirement already satisfied: psutil in /opt/conda/lib/python3.10/site-packages (from ultralytics) (5.9.3)\nRequirement already satisfied: py-cpuinfo in /opt/conda/lib/python3.10/site-packages (from ultralytics) (9.0.0)\nRequirement already satisfied: pandas>=1.1.4 in /opt/conda/lib/python3.10/site-packages (from ultralytics) (2.1.4)\nRequirement already satisfied: seaborn>=0.11.0 in /opt/conda/lib/python3.10/site-packages (from ultralytics) (0.12.2)\nCollecting ultralytics-thop>=2.0.0 (from ultralytics)\n Downloading ultralytics_thop-2.0.8-py3-none-any.whl.metadata (9.3 kB)\nRequirement already satisfied: contourpy>=1.0.1 in /opt/conda/lib/python3.10/site-packages (from matplotlib>=3.3.0->ultralytics) (1.2.0)\nRequirement already satisfied: cycler>=0.10 in /opt/conda/lib/python3.10/site-packages (from matplotlib>=3.3.0->ultralytics) (0.12.1)\nRequirement already satisfied: fonttools>=4.22.0 in /opt/conda/lib/python3.10/site-packages (from matplotlib>=3.3.0->ultralytics) (4.47.0)\nRequirement already satisfied: kiwisolver>=1.0.1 in /opt/conda/lib/python3.10/site-packages (from matplotlib>=3.3.0->ultralytics) (1.4.5)\nRequirement already satisfied: packaging>=20.0 in /opt/conda/lib/python3.10/site-packages (from matplotlib>=3.3.0->ultralytics) (21.3)\nRequirement already satisfied: pyparsing>=2.3.1 in /opt/conda/lib/python3.10/site-packages (from matplotlib>=3.3.0->ultralytics) (3.1.1)\nRequirement already satisfied: python-dateutil>=2.7 in /opt/conda/lib/python3.10/site-packages (from matplotlib>=3.3.0->ultralytics) (2.9.0.post0)\nRequirement already satisfied: pytz>=2020.1 in /opt/conda/lib/python3.10/site-packages (from pandas>=1.1.4->ultralytics) (2023.3.post1)\nRequirement already satisfied: tzdata>=2022.1 in /opt/conda/lib/python3.10/site-packages (from pandas>=1.1.4->ultralytics) (2023.4)\nRequirement already satisfied: charset-normalizer<4,>=2 in /opt/conda/lib/python3.10/site-packages (from requests>=2.23.0->ultralytics) (3.3.2)\nRequirement already satisfied: idna<4,>=2.5 in /opt/conda/lib/python3.10/site-packages (from requests>=2.23.0->ultralytics) (3.6)\nRequirement already satisfied: urllib3<3,>=1.21.1 in /opt/conda/lib/python3.10/site-packages (from requests>=2.23.0->ultralytics) (1.26.18)\nRequirement already satisfied: certifi>=2017.4.17 in /opt/conda/lib/python3.10/site-packages (from requests>=2.23.0->ultralytics) (2024.2.2)\nRequirement already satisfied: filelock in /opt/conda/lib/python3.10/site-packages (from torch>=1.8.0->ultralytics) (3.13.1)\nRequirement already satisfied: typing-extensions in /opt/conda/lib/python3.10/site-packages (from torch>=1.8.0->ultralytics) (4.9.0)\nRequirement already satisfied: sympy in /opt/conda/lib/python3.10/site-packages (from torch>=1.8.0->ultralytics) (1.12)\nRequirement already satisfied: networkx in /opt/conda/lib/python3.10/site-packages (from torch>=1.8.0->ultralytics) (3.2.1)\nRequirement already satisfied: jinja2 in /opt/conda/lib/python3.10/site-packages (from torch>=1.8.0->ultralytics) (3.1.2)\nRequirement already satisfied: fsspec in /opt/conda/lib/python3.10/site-packages (from torch>=1.8.0->ultralytics) (2024.2.0)\nRequirement already satisfied: six>=1.5 in /opt/conda/lib/python3.10/site-packages (from python-dateutil>=2.7->matplotlib>=3.3.0->ultralytics) (1.16.0)\nRequirement already satisfied: MarkupSafe>=2.0 in /opt/conda/lib/python3.10/site-packages (from jinja2->torch>=1.8.0->ultralytics) (2.1.3)\nRequirement already satisfied: mpmath>=0.19 in /opt/conda/lib/python3.10/site-packages (from sympy->torch>=1.8.0->ultralytics) (1.3.0)\nDownloading ultralytics-8.2.101-py3-none-any.whl (874 kB)\n\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m874.1/874.1 kB\u001b[0m \u001b[31m18.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m00:01\u001b[0m\n\u001b[?25hDownloading ultralytics_thop-2.0.8-py3-none-any.whl (26 kB)\nInstalling collected packages: ultralytics-thop, ultralytics\nSuccessfully installed ultralytics-8.2.101 ultralytics-thop-2.0.8\n","output_type":"stream"}]},{"cell_type":"code","source":"import ultralytics\nultralytics.checks()","metadata":{"execution":{"iopub.status.busy":"2024-09-26T01:27:45.075665Z","iopub.execute_input":"2024-09-26T01:27:45.076025Z","iopub.status.idle":"2024-09-26T01:27:51.228069Z","shell.execute_reply.started":"2024-09-26T01:27:45.075993Z","shell.execute_reply":"2024-09-26T01:27:51.227037Z"},"trusted":true},"execution_count":44,"outputs":[{"name":"stdout","text":"Ultralytics YOLOv8.2.101 🚀 Python-3.10.13 torch-2.1.2 CUDA:0 (Tesla P100-PCIE-16GB, 16269MiB)\nSetup complete ✅ (4 CPUs, 31.4 GB RAM, 5889.5/8062.4 GB disk)\n","output_type":"stream"}]},{"cell_type":"code","source":"rm -rf /kaggle/working/data","metadata":{"execution":{"iopub.status.busy":"2024-09-26T01:27:51.229204Z","iopub.execute_input":"2024-09-26T01:27:51.230004Z","iopub.status.idle":"2024-09-26T01:27:53.810537Z","shell.execute_reply.started":"2024-09-26T01:27:51.229977Z","shell.execute_reply":"2024-09-26T01:27:53.808848Z"},"trusted":true},"execution_count":45,"outputs":[]},{"cell_type":"code","source":"!wget https://github.com/THU-MIG/yolov10/releases/download/v1.1/yolov10n.pt","metadata":{"execution":{"iopub.status.busy":"2024-09-26T01:27:53.812987Z","iopub.execute_input":"2024-09-26T01:27:53.813512Z","iopub.status.idle":"2024-09-26T01:27:55.490226Z","shell.execute_reply.started":"2024-09-26T01:27:53.813459Z","shell.execute_reply":"2024-09-26T01:27:55.489127Z"},"trusted":true},"execution_count":46,"outputs":[{"name":"stdout","text":"--2024-09-26 01:27:54-- https://github.com/THU-MIG/yolov10/releases/download/v1.1/yolov10n.pt\nResolving github.com (github.com)... 140.82.116.3\nConnecting to github.com (github.com)|140.82.116.3|:443... connected.\nHTTP request sent, awaiting response... 302 Found\nLocation: https://objects.githubusercontent.com/github-production-release-asset-2e65be/804788522/411e0d4f-1023-40ad-bfdd-c99f0dddb73b?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Credential=releaseassetproduction%2F20240926%2Fus-east-1%2Fs3%2Faws4_request&X-Amz-Date=20240926T012754Z&X-Amz-Expires=300&X-Amz-Signature=09d1593d6249bc8454bb05c0d8c2959fc0817383f106657458fd44a282dd8539&X-Amz-SignedHeaders=host&response-content-disposition=attachment%3B%20filename%3Dyolov10n.pt&response-content-type=application%2Foctet-stream [following]\n--2024-09-26 01:27:54-- https://objects.githubusercontent.com/github-production-release-asset-2e65be/804788522/411e0d4f-1023-40ad-bfdd-c99f0dddb73b?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Credential=releaseassetproduction%2F20240926%2Fus-east-1%2Fs3%2Faws4_request&X-Amz-Date=20240926T012754Z&X-Amz-Expires=300&X-Amz-Signature=09d1593d6249bc8454bb05c0d8c2959fc0817383f106657458fd44a282dd8539&X-Amz-SignedHeaders=host&response-content-disposition=attachment%3B%20filename%3Dyolov10n.pt&response-content-type=application%2Foctet-stream\nResolving objects.githubusercontent.com (objects.githubusercontent.com)... 185.199.111.133, 185.199.110.133, 185.199.108.133, ...\nConnecting to objects.githubusercontent.com (objects.githubusercontent.com)|185.199.111.133|:443... connected.\nHTTP request sent, awaiting response... 200 OK\nLength: 11448431 (11M) [application/octet-stream]\nSaving to: 'yolov10n.pt'\n\nyolov10n.pt 100%[===================>] 10.92M --.-KB/s in 0.1s \n\n2024-09-26 01:27:55 (87.7 MB/s) - 'yolov10n.pt' saved [11448431/11448431]\n\n","output_type":"stream"}]},{"cell_type":"code","source":"!yolo detect train data=/kaggle/working/yolo.yaml model=yolov10n.pt epochs=150 batch=24 imgsz=1024 device=0","metadata":{"execution":{"iopub.status.busy":"2024-09-26T01:27:55.491794Z","iopub.execute_input":"2024-09-26T01:27:55.492083Z"},"trusted":true},"execution_count":null,"outputs":[{"name":"stdout","text":"Ultralytics YOLOv8.2.101 🚀 Python-3.10.13 torch-2.1.2 CUDA:0 (Tesla P100-PCIE-16GB, 16269MiB)\n\u001b[34m\u001b[1mengine/trainer: \u001b[0mtask=detect, mode=train, model=yolov10n.pt, data=/kaggle/working/yolo.yaml, epochs=150, time=None, patience=100, batch=24, imgsz=1024, save=True, save_period=-1, cache=False, device=0, workers=8, project=None, name=train, exist_ok=False, pretrained=True, optimizer=auto, verbose=True, seed=0, deterministic=True, single_cls=False, rect=False, cos_lr=False, close_mosaic=10, resume=False, amp=True, fraction=1.0, profile=False, freeze=None, multi_scale=False, overlap_mask=True, mask_ratio=4, dropout=0.0, val=True, split=val, save_json=False, save_hybrid=False, conf=None, iou=0.7, max_det=300, half=False, dnn=False, plots=True, source=None, vid_stride=1, stream_buffer=False, visualize=False, augment=False, agnostic_nms=False, classes=None, retina_masks=False, embed=None, show=False, save_frames=False, save_txt=False, save_conf=False, save_crop=False, show_labels=True, show_conf=True, show_boxes=True, line_width=None, format=torchscript, keras=False, optimize=False, int8=False, dynamic=False, simplify=True, opset=None, workspace=4, nms=False, lr0=0.01, lrf=0.01, momentum=0.937, weight_decay=0.0005, warmup_epochs=3.0, warmup_momentum=0.8, warmup_bias_lr=0.1, box=7.5, cls=0.5, dfl=1.5, pose=12.0, kobj=1.0, label_smoothing=0.0, nbs=64, hsv_h=0.015, hsv_s=0.7, hsv_v=0.4, degrees=0.0, translate=0.1, scale=0.5, shear=0.0, perspective=0.0, flipud=0.0, fliplr=0.5, bgr=0.0, mosaic=1.0, mixup=0.0, copy_paste=0.0, auto_augment=randaugment, erasing=0.4, crop_fraction=1.0, cfg=None, tracker=botsort.yaml, save_dir=runs/detect/train\nDownloading https://ultralytics.com/assets/Arial.ttf to '/root/.config/Ultralytics/Arial.ttf'...\n100%|████████████████████████████████████████| 755k/755k [00:00<00:00, 19.7MB/s]\nOverriding model.yaml nc=80 with nc=14\n\n from n params module arguments \n 0 -1 1 464 ultralytics.nn.modules.conv.Conv [3, 16, 3, 2] \n 1 -1 1 4672 ultralytics.nn.modules.conv.Conv [16, 32, 3, 2] \n 2 -1 1 7360 ultralytics.nn.modules.block.C2f [32, 32, 1, True] \n 3 -1 1 18560 ultralytics.nn.modules.conv.Conv [32, 64, 3, 2] \n 4 -1 2 49664 ultralytics.nn.modules.block.C2f [64, 64, 2, True] \n 5 -1 1 9856 ultralytics.nn.modules.block.SCDown [64, 128, 3, 2] \n 6 -1 2 197632 ultralytics.nn.modules.block.C2f [128, 128, 2, True] \n 7 -1 1 36096 ultralytics.nn.modules.block.SCDown [128, 256, 3, 2] \n 8 -1 1 460288 ultralytics.nn.modules.block.C2f [256, 256, 1, True] \n 9 -1 1 164608 ultralytics.nn.modules.block.SPPF [256, 256, 5] \n 10 -1 1 249728 ultralytics.nn.modules.block.PSA [256, 256] \n 11 -1 1 0 torch.nn.modules.upsampling.Upsample [None, 2, 'nearest'] \n 12 [-1, 6] 1 0 ultralytics.nn.modules.conv.Concat [1] \n 13 -1 1 148224 ultralytics.nn.modules.block.C2f [384, 128, 1] \n 14 -1 1 0 torch.nn.modules.upsampling.Upsample [None, 2, 'nearest'] \n 15 [-1, 4] 1 0 ultralytics.nn.modules.conv.Concat [1] \n 16 -1 1 37248 ultralytics.nn.modules.block.C2f [192, 64, 1] \n 17 -1 1 36992 ultralytics.nn.modules.conv.Conv [64, 64, 3, 2] \n 18 [-1, 13] 1 0 ultralytics.nn.modules.conv.Concat [1] \n 19 -1 1 123648 ultralytics.nn.modules.block.C2f [192, 128, 1] \n 20 -1 1 18048 ultralytics.nn.modules.block.SCDown [128, 128, 3, 2] \n 21 [-1, 10] 1 0 ultralytics.nn.modules.conv.Concat [1] \n 22 -1 1 282624 ultralytics.nn.modules.block.C2fCIB [384, 256, 1, True, True] \n 23 [16, 19, 22] 1 866788 ultralytics.nn.modules.head.v10Detect [14, [64, 128, 256]] \nYOLOv10n summary: 385 layers, 2,712,500 parameters, 2,712,484 gradients, 8.4 GFLOPs\n\nTransferred 493/595 items from pretrained weights\n\u001b[34m\u001b[1mTensorBoard: \u001b[0mStart with 'tensorboard --logdir runs/detect/train', view at http://localhost:6006/\nFreezing layer 'model.23.dfl.conv.weight'\n\u001b[34m\u001b[1mAMP: \u001b[0mrunning Automatic Mixed Precision (AMP) checks with YOLOv8n...\nDownloading https://github.com/ultralytics/assets/releases/download/v8.2.0/yolov8n.pt to 'yolov8n.pt'...\n100%|██████████████████████████████████████| 6.25M/6.25M [00:00<00:00, 98.4MB/s]\n\u001b[34m\u001b[1mAMP: \u001b[0mchecks passed ✅\n\u001b[34m\u001b[1mtrain: \u001b[0mScanning /kaggle/working/refactored_data/labels/train... 6547 images, 0 b\u001b[0m\n\u001b[34m\u001b[1mtrain: \u001b[0mNew cache created: /kaggle/working/refactored_data/labels/train.cache\n\u001b[34m\u001b[1malbumentations: \u001b[0mBlur(p=0.01, blur_limit=(3, 7)), MedianBlur(p=0.01, blur_limit=(3, 7)), ToGray(p=0.01), CLAHE(p=0.01, clip_limit=(1, 4.0), tile_grid_size=(8, 8))\n\u001b[34m\u001b[1mval: \u001b[0mScanning /kaggle/working/refactored_data/labels/val... 728 images, 0 backgr\u001b[0m\n\u001b[34m\u001b[1mval: \u001b[0mNew cache created: /kaggle/working/refactored_data/labels/val.cache\nPlotting labels to runs/detect/train/labels.jpg... \n\u001b[34m\u001b[1moptimizer:\u001b[0m 'optimizer=auto' found, ignoring 'lr0=0.01' and 'momentum=0.937' and determining best 'optimizer', 'lr0' and 'momentum' automatically... \n\u001b[34m\u001b[1moptimizer:\u001b[0m SGD(lr=0.01, momentum=0.9) with parameter groups 95 weight(decay=0.0), 108 weight(decay=0.0005625000000000001), 107 bias(decay=0.0)\n\u001b[34m\u001b[1mTensorBoard: \u001b[0mmodel graph visualization added ✅\nImage sizes 1024 train, 1024 val\nUsing 4 dataloader workers\nLogging results to \u001b[1mruns/detect/train\u001b[0m\nStarting training for 150 epochs...\n\n Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n 1/150 13.5G 4.05 13.9 4.009 83 1024: 1\n Class Images Instances Box(P R mAP50 m\n all 728 2845 0.899 0.0175 0.0332 0.0192\n\n Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n 2/150 11.8G 3.639 10.74 3.52 114 1024: ","output_type":"stream"}]},{"cell_type":"code","source":"# from ultralytics import YOLOv10\n\n# model = YOLOv10()\n# # If you want to finetune the model with pretrained weights, you could load the \n# # pretrained weights like below\n# # model = YOLOv10.from_pretrained('jameslahm/yolov10{n/s/m/b/l/x}')\n# # or\n# # wget https://github.com/THU-MIG/yolov10/releases/download/v1.1/yolov10{n/s/m/b/l/x}.pt\n# # model = YOLOv10('yolov10{n/s/m/b/l/x}.pt')\n\n# model.train(data='yolo.yaml', epochs=150, batch=24, imgsz=1024)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# !WANDB_MODE=\"dryrun\" python train_dual.py \n# !yolo train model=yolov10n.pt workers=10 device=0 batch=24 data = /kaggle/working/yolo.yaml imgsz = 1024 epochs = 150","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# raw_df, preprocessed_df = prime_dataset()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"!pip uninstall -y wandb","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# !cp /kaggle/working/valid.txt /kaggle/working/yolov7/valid.txt\n# !cp /kaggle/working/train.txt /kaggle/working/yolov7/train.txt","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# rm -rf /kaggle/working/runs","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# rm -rf /kaggle/working/yolov8n.pt","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# rm -rf /kaggle/working/exp.zip","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# train_model()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"!cp /kaggle/working/yolov9/runs/train/exp/weights/last.pt /kaggle/working/yolov7_lan1.pt","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"%cd /kaggle/working/\nfrom IPython.display import FileLink\nFileLink(r'train.zip')","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"!cp -r /kaggle/working/yolov7/runs/train/exp /kaggle/working/","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import shutil\nfrom IPython.display import FileLink\n\n# Đường dẫn đến thư mục cần nén\nsource_dir = '/kaggle/working/runs/detect/train'\n\n# Nén thư mục 'runs' thành file 'runs.zip'\nshutil.make_archive('/kaggle/working/train', 'zip', source_dir)\n\n# Tạo liên kết tải về cho file nén\nFileLink(r'/kaggle/working/train.zip')","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"rm -rf /kaggle/working/exp.zip","metadata":{"trusted":true},"execution_count":null,"outputs":[]}]}