{"metadata":{"colab":{"name":"lesson-3-rsna-pneumonia-detection-challenge-kaggle","version":"0.3.2","provenance":[],"collapsed_sections":[]},"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"accelerator":"GPU","language_info":{"name":"python","version":"3.6.4","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"import os \nimport sys\nimport random\nimport math\nimport numpy as np\nimport cv2\nimport matplotlib.pyplot as plt\nimport json\nimport pydicom\nfrom imgaug import augmenters as iaa\nfrom tqdm import tqdm\nimport pandas as pd \nimport glob \nimport pandas as pd\n!pip install pillow","metadata":{"id":"4kjcC6QqywWl","colab_type":"code","colab":{},"_uuid":"40c67b3ff0fa04587dec508363308adaa3ceaf34","execution":{"iopub.status.busy":"2023-11-07T11:44:36.331056Z","iopub.execute_input":"2023-11-07T11:44:36.331466Z","iopub.status.idle":"2023-11-07T11:44:41.126856Z","shell.execute_reply.started":"2023-11-07T11:44:36.331399Z","shell.execute_reply":"2023-11-07T11:44:41.12552Z"},"trusted":true},"execution_count":49,"outputs":[{"name":"stdout","text":"Requirement already satisfied: pillow in /opt/conda/lib/python3.6/site-packages\nRequirement already satisfied: olefile in /opt/conda/lib/python3.6/site-packages (from pillow)\n\u001b[33mYou are using pip version 9.0.1, however version 23.3.1 is available.\nYou should consider upgrading via the 'pip install --upgrade pip' command.\u001b[0m\n","output_type":"stream"}]},{"cell_type":"code","source":"print( tf. __version__)","metadata":{"execution":{"iopub.status.busy":"2023-11-07T14:05:23.396Z","iopub.execute_input":"2023-11-07T14:05:23.396423Z","iopub.status.idle":"2023-11-07T14:05:23.621206Z","shell.execute_reply.started":"2023-11-07T14:05:23.396359Z","shell.execute_reply":"2023-11-07T14:05:23.61939Z"},"trusted":true},"execution_count":1,"outputs":[{"traceback":["\u001b[0;31m---------------------------------------------------------------------------\u001b[0m","\u001b[0;31mNameError\u001b[0m Traceback (most recent call last)","\u001b[0;32m\u001b[0m in \u001b[0;36m\u001b[0;34m()\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0mprint\u001b[0m\u001b[0;34m(\u001b[0m \u001b[0mtf\u001b[0m\u001b[0;34m.\u001b[0m \u001b[0m__version__\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m","\u001b[0;31mNameError\u001b[0m: name 'tf' is not defined"],"ename":"NameError","evalue":"name 'tf' is not defined","output_type":"error"}]},{"cell_type":"code","source":"","metadata":{"execution":{"iopub.status.busy":"2023-11-07T11:38:21.553918Z","iopub.execute_input":"2023-11-07T11:38:21.55438Z","iopub.status.idle":"2023-11-07T11:38:26.571054Z","shell.execute_reply.started":"2023-11-07T11:38:21.55433Z","shell.execute_reply":"2023-11-07T11:38:26.570032Z"},"trusted":true},"execution_count":43,"outputs":[{"name":"stdout","text":"Requirement already satisfied: pydicom in /opt/conda/lib/python3.6/site-packages\n\u001b[33mYou are using pip version 9.0.1, however version 23.3.1 is available.\nYou should consider upgrading via the 'pip install --upgrade pip' command.\u001b[0m\n","output_type":"stream"}]},{"cell_type":"code","source":"DATA_DIR = '/kaggle/input'\nROOT_DIR = '/kaggle/working'","metadata":{"id":"yP0XLJx_x_6o","colab_type":"code","colab":{},"_uuid":"6e5764759e6a0a9b698b44645658f66873edd807","execution":{"iopub.status.busy":"2023-11-07T11:28:54.223676Z","iopub.execute_input":"2023-11-07T11:28:54.224054Z","iopub.status.idle":"2023-11-07T11:28:54.22957Z","shell.execute_reply.started":"2023-11-07T11:28:54.22396Z","shell.execute_reply":"2023-11-07T11:28:54.2285Z"},"trusted":true},"execution_count":25,"outputs":[]},{"cell_type":"code","source":"!git clone https://www.github.com/matterport/Mask_RCNN.git","metadata":{"id":"KgllzLnDr7kF","colab_type":"code","colab":{"base_uri":"https://localhost:8080/","height":143},"outputId":"6c978df7-2013-437e-acd1-5011048dfb53","_uuid":"b37d22551d332f0f7b722cc7204eb614524b6c21","execution":{"iopub.status.busy":"2023-11-07T11:30:02.308585Z","iopub.execute_input":"2023-11-07T11:30:02.309659Z","iopub.status.idle":"2023-11-07T11:30:12.897137Z","shell.execute_reply.started":"2023-11-07T11:30:02.309584Z","shell.execute_reply":"2023-11-07T11:30:12.896069Z"},"trusted":true},"execution_count":33,"outputs":[{"name":"stdout","text":"Cloning into 'Mask_RCNN'...\nremote: Enumerating objects: 956, done.\u001b[K\nremote: Total 956 (delta 0), reused 0 (delta 0), pack-reused 956\u001b[K\nReceiving objects: 100% (956/956), 137.67 MiB | 21.29 MiB/s, done.\nResolving deltas: 100% (558/558), done.\nChecking connectivity... done.\n","output_type":"stream"}]},{"cell_type":"code","source":"","metadata":{"execution":{"iopub.status.busy":"2023-11-07T11:30:37.648236Z","iopub.execute_input":"2023-11-07T11:30:37.648743Z","iopub.status.idle":"2023-11-07T11:30:47.684702Z","shell.execute_reply.started":"2023-11-07T11:30:37.64865Z","shell.execute_reply":"2023-11-07T11:30:47.683658Z"},"trusted":true},"execution_count":37,"outputs":[{"name":"stdout","text":"Collecting mrcnn\n Downloading https://files.pythonhosted.org/packages/80/3d/56e05c297a1f464a042b2c47bcd9e5f2d452ce0e5eca3894f7cbdcaee758/mrcnn-0.2.tar.gz (51kB)\n\u001b[K 100% |████████████████████████████████| 61kB 5.2MB/s ta 0:00:011\n\u001b[?25hBuilding wheels for collected packages: mrcnn\n Running setup.py bdist_wheel for mrcnn ... \u001b[?25ldone\n\u001b[?25h Stored in directory: /root/.cache/pip/wheels/11/ed/28/e550ddc897c04c336b923eae4eb35c9aae993d20ce39d9cc40\nSuccessfully built mrcnn\nInstalling collected packages: mrcnn\nSuccessfully installed mrcnn-0.2\n\u001b[33mYou are using pip version 9.0.1, however version 23.3.1 is available.\nYou should consider upgrading via the 'pip install --upgrade pip' command.\u001b[0m\n","output_type":"stream"}]},{"cell_type":"code","source":"sys.path.append(os.path.join(ROOT_DIR, 'Mask_RCNN')) \nfrom mrcnn.config import Config\nfrom mrcnn import utils\nimport mrcnn.model as modellib\nfrom mrcnn import visualize\nfrom mrcnn.model import log","metadata":{"id":"-KZXyWwhzOVU","colab_type":"code","colab":{"base_uri":"https://localhost:8080/","height":35},"outputId":"2576cc17-7484-4311-ad72-3c5643dcb5bb","_uuid":"3acbbbe055b6a409d3c50ae0f893acf51b5ae7ba","execution":{"iopub.status.busy":"2023-11-07T11:30:50.536668Z","iopub.execute_input":"2023-11-07T11:30:50.537102Z","iopub.status.idle":"2023-11-07T11:30:53.352469Z","shell.execute_reply.started":"2023-11-07T11:30:50.537015Z","shell.execute_reply":"2023-11-07T11:30:53.351428Z"},"trusted":true},"execution_count":38,"outputs":[{"name":"stderr","text":"/opt/conda/lib/python3.6/site-packages/h5py/__init__.py:36: FutureWarning: Conversion of the second argument of issubdtype from `float` to `np.floating` is deprecated. In future, it will be treated as `np.float64 == np.dtype(float).type`.\n from ._conv import register_converters as _register_converters\nUsing TensorFlow backend.\n","output_type":"stream"}]},{"cell_type":"code","source":"train_dicom_dir = os.path.join(DATA_DIR, 'stage_2_train_images')\ntest_dicom_dir = os.path.join(DATA_DIR, 'stage_2_test_images')","metadata":{"id":"FghMmiMjzOX2","colab_type":"code","colab":{},"_uuid":"50089cc61791871cdf6a5c0037dc4f28b7b7d7cc","execution":{"iopub.status.busy":"2023-11-07T11:31:08.315873Z","iopub.execute_input":"2023-11-07T11:31:08.316249Z","iopub.status.idle":"2023-11-07T11:31:08.321689Z","shell.execute_reply.started":"2023-11-07T11:31:08.316173Z","shell.execute_reply":"2023-11-07T11:31:08.320849Z"},"trusted":true},"execution_count":39,"outputs":[]},{"cell_type":"code","source":"","metadata":{"execution":{"iopub.status.busy":"2023-11-07T11:39:32.179827Z","iopub.execute_input":"2023-11-07T11:39:32.180267Z","iopub.status.idle":"2023-11-07T11:39:32.185272Z","shell.execute_reply.started":"2023-11-07T11:39:32.1802Z","shell.execute_reply":"2023-11-07T11:39:32.184151Z"},"trusted":true},"execution_count":46,"outputs":[]},{"cell_type":"code","source":"","metadata":{"execution":{"iopub.status.busy":"2023-11-07T11:46:09.512166Z","iopub.execute_input":"2023-11-07T11:46:09.512576Z","iopub.status.idle":"2023-11-07T11:46:10.042474Z","shell.execute_reply.started":"2023-11-07T11:46:09.512526Z","shell.execute_reply":"2023-11-07T11:46:10.040837Z"},"trusted":true},"execution_count":52,"outputs":[{"traceback":["\u001b[0;31m---------------------------------------------------------------------------\u001b[0m","\u001b[0;31mValueError\u001b[0m Traceback (most recent call last)","\u001b[0;32m/opt/conda/lib/python3.6/site-packages/pydicom/tag.py\u001b[0m in \u001b[0;36mtag_in_exception\u001b[0;34m(tag)\u001b[0m\n\u001b[1;32m 29\u001b[0m \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 30\u001b[0;31m \u001b[0;32myield\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 31\u001b[0m \u001b[0;32mexcept\u001b[0m \u001b[0mException\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0mex\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n","\u001b[0;32m/opt/conda/lib/python3.6/site-packages/pydicom/filewriter.py\u001b[0m in \u001b[0;36mwrite_dataset\u001b[0;34m(fp, dataset, parent_encoding)\u001b[0m\n\u001b[1;32m 460\u001b[0m \u001b[0;31m# XXX for writing raw tags without converting to DataElement\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 461\u001b[0;31m \u001b[0mwrite_data_element\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mfp\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mdataset\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mtag\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mdataset_encoding\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 462\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n","\u001b[0;32m/opt/conda/lib/python3.6/site-packages/pydicom/filewriter.py\u001b[0m in \u001b[0;36mwrite_data_element\u001b[0;34m(fp, data_element, encoding)\u001b[0m\n\u001b[1;32m 424\u001b[0m not val.startswith(b'\\xff\\xfe\\xe0\\x00')):\n\u001b[0;32m--> 425\u001b[0;31m raise ValueError('Pixel Data with undefined length must '\n\u001b[0m\u001b[1;32m 426\u001b[0m 'start with an item tag')\n","\u001b[0;31mValueError\u001b[0m: Pixel Data with undefined length must start with an item tag","\nDuring handling of the above exception, another exception occurred:\n","\u001b[0;31mValueError\u001b[0m Traceback (most recent call last)","\u001b[0;32m\u001b[0m in \u001b[0;36m\u001b[0;34m()\u001b[0m\n\u001b[1;32m 13\u001b[0m \u001b[0mds\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mPixelRepresentation\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;36m0\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 14\u001b[0m \u001b[0mds\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mPixelData\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mnp_image\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mtobytes\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 15\u001b[0;31m \u001b[0mds\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msave_as\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mi\u001b[0m\u001b[0;34m+\u001b[0m\u001b[0;34m'.dcm'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m","\u001b[0;32m/opt/conda/lib/python3.6/site-packages/pydicom/dataset.py\u001b[0m in \u001b[0;36msave_as\u001b[0;34m(self, filename, write_like_original)\u001b[0m\n\u001b[1;32m 956\u001b[0m \"saving.\".format(self.__class__.__name__))\n\u001b[1;32m 957\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 958\u001b[0;31m \u001b[0mpydicom\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mdcmwrite\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mfilename\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mwrite_like_original\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 959\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 960\u001b[0m \u001b[0;32mdef\u001b[0m \u001b[0m__setattr__\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mname\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mvalue\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n","\u001b[0;32m/opt/conda/lib/python3.6/site-packages/pydicom/filewriter.py\u001b[0m in \u001b[0;36mdcmwrite\u001b[0;34m(filename, dataset, write_like_original)\u001b[0m\n\u001b[1;32m 848\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 849\u001b[0m \u001b[0;31m# Write non-Command Set elements now\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 850\u001b[0;31m \u001b[0mwrite_dataset\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mfp\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mdataset\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;36m0x00010000\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 851\u001b[0m \u001b[0;32mfinally\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 852\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0mcaller_owns_file\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n","\u001b[0;32m/opt/conda/lib/python3.6/site-packages/pydicom/filewriter.py\u001b[0m in \u001b[0;36mwrite_dataset\u001b[0;34m(fp, dataset, parent_encoding)\u001b[0m\n\u001b[1;32m 459\u001b[0m \u001b[0;31m# write_data_element(fp, dataset.get_item(tag), dataset_encoding)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 460\u001b[0m \u001b[0;31m# XXX for writing raw tags without converting to DataElement\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 461\u001b[0;31m \u001b[0mwrite_data_element\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mfp\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mdataset\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mtag\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mdataset_encoding\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 462\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 463\u001b[0m \u001b[0;32mreturn\u001b[0m \u001b[0mfp\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mtell\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;34m-\u001b[0m \u001b[0mfpStart\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n","\u001b[0;32m/opt/conda/lib/python3.6/contextlib.py\u001b[0m in \u001b[0;36m__exit__\u001b[0;34m(self, type, value, traceback)\u001b[0m\n\u001b[1;32m 97\u001b[0m \u001b[0mvalue\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mtype\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 98\u001b[0m \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 99\u001b[0;31m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mgen\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mthrow\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mtype\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mvalue\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mtraceback\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 100\u001b[0m \u001b[0;32mexcept\u001b[0m \u001b[0mStopIteration\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0mexc\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 101\u001b[0m \u001b[0;31m# Suppress StopIteration *unless* it's the same exception that\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n","\u001b[0;32m/opt/conda/lib/python3.6/site-packages/pydicom/tag.py\u001b[0m in \u001b[0;36mtag_in_exception\u001b[0;34m(tag)\u001b[0m\n\u001b[1;32m 35\u001b[0m \u001b[0mstr\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mex\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 36\u001b[0m stack_trace)\n\u001b[0;32m---> 37\u001b[0;31m \u001b[0;32mraise\u001b[0m \u001b[0mtype\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mex\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mmsg\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 38\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 39\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n","\u001b[0;31mValueError\u001b[0m: With tag (7fe0, 0010) got exception: Pixel Data with undefined length must start with an item tag\nTraceback (most recent call last):\n File \"/opt/conda/lib/python3.6/site-packages/pydicom/tag.py\", line 30, in tag_in_exception\n yield\n File \"/opt/conda/lib/python3.6/site-packages/pydicom/filewriter.py\", line 461, in write_dataset\n write_data_element(fp, dataset[tag], dataset_encoding)\n File \"/opt/conda/lib/python3.6/site-packages/pydicom/filewriter.py\", line 425, in write_data_element\n raise ValueError('Pixel Data with undefined length must '\nValueError: Pixel Data with undefined length must start with an item tag\n"],"ename":"ValueError","evalue":"With tag (7fe0, 0010) got exception: Pixel Data with undefined length must start with an item tag\nTraceback (most recent call last):\n File \"/opt/conda/lib/python3.6/site-packages/pydicom/tag.py\", line 30, in tag_in_exception\n yield\n File \"/opt/conda/lib/python3.6/site-packages/pydicom/filewriter.py\", line 461, in write_dataset\n write_data_element(fp, dataset[tag], dataset_encoding)\n File \"/opt/conda/lib/python3.6/site-packages/pydicom/filewriter.py\", line 425, in write_data_element\n raise ValueError('Pixel Data with undefined length must '\nValueError: Pixel Data with undefined length must start with an item tag\n","output_type":"error"}]},{"cell_type":"code","source":"def get_dicom_fps(dicom_dir):\n dicom_fps = glob.glob(dicom_dir+'/'+'*.dcm')\n return list(set(dicom_fps))\n\ndef parse_dataset(dicom_dir, anns): \n image_fps = get_dicom_fps(dicom_dir)\n image_annotations = {fp: [] for fp in image_fps}\n for index, row in anns.iterrows(): \n fp = os.path.join(dicom_dir, row['patientId']+'.dcm')\n image_annotations[fp].append(row)\n return image_fps, image_annotations ","metadata":{"id":"ivqC4cnszOaM","colab_type":"code","colab":{},"_uuid":"778cb19865d7cc63440491aef9202b71c61e8bb2","execution":{"iopub.status.busy":"2023-11-07T11:32:32.500892Z","iopub.execute_input":"2023-11-07T11:32:32.50134Z","iopub.status.idle":"2023-11-07T11:32:32.51739Z","shell.execute_reply.started":"2023-11-07T11:32:32.501267Z","shell.execute_reply":"2023-11-07T11:32:32.51641Z"},"trusted":true},"execution_count":40,"outputs":[]},{"cell_type":"code","source":"class DetectorConfig(Config):\n NAME = 'builing'\n GPU_COUNT = 1\n IMAGES_PER_GPU = 8 \n BACKBONE = 'resnet50'\n NUM_CLASSES = 2 \n IMAGE_MIN_DIM = 256\n IMAGE_MAX_DIM = 256\n RPN_ANCHOR_SCALES = (32, 64, 128, 256)\n TRAIN_ROIS_PER_IMAGE = 32\n MAX_GT_INSTANCES = 3\n DETECTION_MAX_INSTANCES = 3\n DETECTION_MIN_CONFIDENCE = 0.9\n DETECTION_NMS_THRESHOLD = 0.1\n STEPS_PER_EPOCH = 100\nconfig = DetectorConfig()\nconfig.display()","metadata":{"id":"_SfzTa-1zOck","colab_type":"code","colab":{"base_uri":"https://localhost:8080/","height":917},"outputId":"91ae8935-bccb-4b8e-9a7e-aa690f95fd9b","_uuid":"dfcffc4eaa94a41497717851dee9f702d8a2a73b","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"class DetectorDataset(utils.Dataset):\n def __init__(self, image_fps, image_annotations, orig_height, orig_width):\n super().__init__(self)\n self.add_class('pneumonia', 1, 'Lung Opacity')\n for i, fp in enumerate(image_fps):\n annotations = image_annotations[fp]\n self.add_image('pneumonia', image_id=i, path=fp, \n annotations=annotations, orig_height=orig_height, orig_width=orig_width)\n def image_reference(self, image_id):\n info = self.image_info[image_id]\n return info['path']\n def load_image(self, image_id):\n info = self.image_info[image_id]\n fp = info['path']\n ds = pydicom.read_file(fp)\n image = ds.pixel_array\n if len(image.shape) != 3 or image.shape[2] != 3:\n image = np.stack((image,) * 3, -1)\n return image\n def load_mask(self, image_id):\n info = self.image_info[image_id]\n annotations = info['annotations']\n count = len(annotations)\n if count == 0:\n mask = np.zeros((info['orig_height'], info['orig_width'], 1), dtype=np.uint8)\n class_ids = np.zeros((1,), dtype=np.int32)\n else:\n mask = np.zeros((info['orig_height'], info['orig_width'], count), dtype=np.uint8)\n class_ids = np.zeros((count,), dtype=np.int32)\n for i, a in enumerate(annotations):\n if a['Target'] == 1:\n x = int(a['x'])\n y = int(a['y'])\n w = int(a['width'])\n h = int(a['height'])\n mask_instance = mask[:, :, i].copy()\n cv2.rectangle(mask_instance, (x, y), (x+w, y+h), 255, -1)\n mask[:, :, i] = mask_instance\n class_ids[i] = 1\n return mask.astype(np.bool), class_ids.astype(np.int32)","metadata":{"id":"8EBVA1M60yAj","colab_type":"code","colab":{},"_uuid":"52bd3ffbdde0173a363055482d675da51c2aba99","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import pandas as pd\nanns = pd.read_csv(\"/kaggle/input/rsna-pneumonia-detection-challenge/stage_2_train_labels.csv\")\nanns.tail()","metadata":{"id":"EdhUEFDr0yDA","colab_type":"code","colab":{"base_uri":"https://localhost:8080/","height":235},"outputId":"1715a5df-a577-41fd-bf20-f1a27aadb28c","_uuid":"793b1c6c6ba4e5f0d51e130080aa799f230b5ef6","execution":{"iopub.status.busy":"2023-11-07T10:45:35.950849Z","iopub.execute_input":"2023-11-07T10:45:35.951274Z","iopub.status.idle":"2023-11-07T10:45:36.063945Z","shell.execute_reply.started":"2023-11-07T10:45:35.951221Z","shell.execute_reply":"2023-11-07T10:45:36.063161Z"},"trusted":true},"execution_count":5,"outputs":[{"execution_count":5,"output_type":"execute_result","data":{"text/plain":" patientId x y width height \\\n30222 c1ec14ff-f6d7-4b38-b0cb-fe07041cbdc8 185.0 298.0 228.0 379.0 \n30223 c1edf42b-5958-47ff-a1e7-4f23d99583ba NaN NaN NaN NaN \n30224 c1f6b555-2eb1-4231-98f6-50a963976431 NaN NaN NaN NaN \n30225 c1f7889a-9ea9-4acb-b64c-b737c929599a 570.0 393.0 261.0 345.0 \n30226 c1f7889a-9ea9-4acb-b64c-b737c929599a 233.0 424.0 201.0 356.0 \n\n Target \n30222 1 \n30223 0 \n30224 0 \n30225 1 \n30226 1 ","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
patientIdxywidthheightTarget
30222c1ec14ff-f6d7-4b38-b0cb-fe07041cbdc8185.0298.0228.0379.01
30223c1edf42b-5958-47ff-a1e7-4f23d99583baNaNNaNNaNNaN0
30224c1f6b555-2eb1-4231-98f6-50a963976431NaNNaNNaNNaN0
30225c1f7889a-9ea9-4acb-b64c-b737c929599a570.0393.0261.0345.01
30226c1f7889a-9ea9-4acb-b64c-b737c929599a233.0424.0201.0356.01
\n
"},"metadata":{}}]},{"cell_type":"code","source":"import json\nimport os\njson_path = os.path.join('/kaggle/input/synthetic-word-ocr/annotation.json')\nwith open(json_path, 'r') as f:\n annot_data = json.load(f)","metadata":{"execution":{"iopub.status.busy":"2023-11-07T10:44:02.015372Z","iopub.execute_input":"2023-11-07T10:44:02.015805Z","iopub.status.idle":"2023-11-07T10:44:37.757126Z","shell.execute_reply.started":"2023-11-07T10:44:02.015712Z","shell.execute_reply":"2023-11-07T10:44:37.75622Z"},"trusted":true},"execution_count":3,"outputs":[]},{"cell_type":"code","source":"image_fps, image_annotations = parse_dataset(train_dicom_dir, anns=anns)","metadata":{"id":"Mxz-pNbt5txY","colab_type":"code","colab":{},"_uuid":"7aebc88f910b232e3b8759421914a007c6ffed94","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"ds = pydicom.read_file(image_fps[0]) \nimage = ds.pixel_array","metadata":{"id":"YPqjEIXWRhSf","colab_type":"code","colab":{},"_uuid":"6c386dcef041b972f6209dd19e247d547c3c349f","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"ds","metadata":{"id":"81lovwF2Ro5R","colab_type":"code","colab":{"base_uri":"https://localhost:8080/","height":647},"outputId":"e2263fe2-1a32-432a-ec75-b9220a24e697","_uuid":"0ef68a41cf1a5e842e86a219b6392e3695004720","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"ORIG_SIZE = 300","metadata":{"id":"gYNSd1AhRqOV","colab_type":"code","colab":{},"_uuid":"74277ae9af4a3b044e62b664d10d76b23848bb43","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"image_fps_list = list(image_fps[:1000]) \nsorted(image_fps_list)\nrandom.seed(42)\nrandom.shuffle(image_fps_list)\nvalidation_split = 0.1\nsplit_index = int((1 - validation_split) * len(image_fps_list))\nimage_fps_train = image_fps_list[:split_index]\nimage_fps_val = image_fps_list[split_index:]\nprint(len(image_fps_train), len(image_fps_val))","metadata":{"id":"7jByVCZt-ZOC","colab_type":"code","colab":{"base_uri":"https://localhost:8080/","height":35},"outputId":"f1aa267d-7530-4620-ffc5-2f7aa39083bb","_uuid":"6175c72e73639e3190e127f67783988eadced9ba","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"dataset_train = DetectorDataset(image_fps_train, image_annotations, ORIG_SIZE, ORIG_SIZE)\ndataset_train.prepare()","metadata":{"id":"jwMkhotP0yFf","colab_type":"code","colab":{},"_uuid":"86c3333d4dfb8b7d00ce1f401693d0df4e6254e1","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test_fp = random.choice(image_fps_train)\nimage_annotations[test_fp]","metadata":{"id":"0xEc47Jz59x5","colab_type":"code","colab":{"base_uri":"https://localhost:8080/","height":251},"outputId":"129edfbc-cf9d-46c7-b569-d804a50cd12d","_uuid":"93da5a58731ad483a4bd2b20543f2b1df4b8ad74","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"dataset_val = DetectorDataset(image_fps_val, image_annotations, ORIG_SIZE, ORIG_SIZE)\ndataset_val.prepare()","metadata":{"id":"K1TkWuGP0yHl","colab_type":"code","colab":{},"_uuid":"313347d838fa8321a714858c8073f98c50c5be26","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"image_id = dataset_train.image_ids[290]\nimage_fp = dataset_train.image_reference(image_id)\nimage = dataset_train.load_image(image_id)\nmask, class_ids = dataset_train.load_mask(image_id)\nprint(image.shape)\nplt.figure(figsize=(10, 10))\nplt.subplot(1, 2, 1)\nplt.imshow(image[:, :, 0], cmap='gray')\nplt.axis('off')\nplt.subplot(1, 2, 2)\nmasked = np.zeros(image.shape[:2])\nfor i in range(mask.shape[2]):\n masked += image[:, :, 0] * mask[:, :, i]\nplt.imshow(masked, cmap='gray')\nplt.axis('off')\nprint(image_fp)\nprint(class_ids)","metadata":{"id":"4xwsrf9G1lHR","colab_type":"code","colab":{"base_uri":"https://localhost:8080/","height":359},"outputId":"a13386d3-a918-41fe-8824-13625c9d7b08","_uuid":"491b78ec96d28fcdbbf8e2d7f9320a05d64c9249","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"model = modellib.MaskRCNN(mode='training', config=config, model_dir=ROOT_DIR)","metadata":{"id":"geTvh0sU1lJo","colab_type":"code","colab":{},"_uuid":"ac5e11c89daeaa4e73af6a4967a4a375cddf284c","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Image augmentation \naugmentation = iaa.SomeOf((0, 1), [\n iaa.Fliplr(0.5),\n iaa.Affine(\n scale={\"x\": (0.8, 1.2), \"y\": (0.8, 1.2)},\n translate_percent={\"x\": (-0.2, 0.2), \"y\": (-0.2, 0.2)},\n rotate=(-25, 25),\n shear=(-8, 8)\n ),\n iaa.Multiply((0.9, 1.1))\n])","metadata":{"id":"STZnQTE61lME","colab_type":"code","colab":{},"_uuid":"4ab9d6086ce611a46f189c047956c43b29783e6d","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"NUM_EPOCHS = 1\nimport warnings \nwarnings.filterwarnings(\"ignore\")\nmodel.train(dataset_train, dataset_val, \n learning_rate=config.LEARNING_RATE, \n epochs=NUM_EPOCHS, \n layers='all',\n augmentation=augmentation)","metadata":{"id":"RVgNhHjl1lOS","colab_type":"code","colab":{"base_uri":"https://localhost:8080/","height":2575},"outputId":"2cba9efc-eeea-472d-d155-3c3d856585bf","_uuid":"64cce2581ffdb8c2b1cb07948ada4a93f64874b0","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"dir_names = next(os.walk(model.model_dir))[1]\nkey = config.NAME.lower()\ndir_names = filter(lambda f: f.startswith(key), dir_names)\ndir_names = sorted(dir_names)\n\nif not dir_names:\n import errno\n raise FileNotFoundError(\n errno.ENOENT,\n \"Could not find model directory under {}\".format(self.model_dir))\n \nfps = []\nfor d in dir_names: \n dir_name = os.path.join(model.model_dir, d)\n checkpoints = next(os.walk(dir_name))[2]\n checkpoints = filter(lambda f: f.startswith(\"mask_rcnn\"), checkpoints)\n checkpoints = sorted(checkpoints)\n if not checkpoints:\n print('No weight files in {}'.format(dir_name))\n else: \n \n checkpoint = os.path.join(dir_name, checkpoints[-1])\n fps.append(checkpoint)\n\nmodel_path = sorted(fps)[-1]\nprint('Found model {}'.format(model_path))","metadata":{"id":"eraRlzgPmmIZ","colab_type":"code","colab":{"base_uri":"https://localhost:8080/","height":35},"outputId":"de9e688c-ba4f-4b62-f842-dbcf00ce397c","_uuid":"db5c10d3f7da099e5751a04a6e6d49819882ecd4","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"class InferenceConfig(DetectorConfig):\n GPU_COUNT = 1\n IMAGES_PER_GPU = 1\ninference_config = InferenceConfig()\nmodel = modellib.MaskRCNN(mode='inference', \n config=inference_config,\n model_dir=ROOT_DIR)\nassert model_path != \"\", \"Provide path to trained weights\"\nprint(\"Loading weights from \", model_path)\nmodel.load_weights(model_path, by_name=True)","metadata":{"id":"TgpT9AzC2Bgz","colab_type":"code","colab":{"base_uri":"https://localhost:8080/","height":53},"outputId":"60f5a175-4666-497d-b4e8-0bdab39a92d0","_uuid":"52138636b2ae5bf444bba808518cd8313bde65cd","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def get_colors_for_class_ids(class_ids):\n colors = []\n for class_id in class_ids:\n if class_id == 1:\n colors.append((.941, .204, .204))\n return colors","metadata":{"id":"9mTBig7D2BjU","colab_type":"code","colab":{},"_uuid":"e13c61bee23b791c61ecf1256f7512295cd4d9ab","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"dataset = dataset_val\nfig = plt.figure(figsize=(10, 30))\nfor i in range(4):\n\n image_id = random.choice(dataset.image_ids)\n \n original_image, image_meta, gt_class_id, gt_bbox, gt_mask =\\\n modellib.load_image_gt(dataset_val, inference_config, \n image_id, use_mini_mask=False)\n print(original_image.shape)\n plt.subplot(6, 2, 2*i + 1)\n visualize.display_instances(original_image, gt_bbox, gt_mask, gt_class_id, \n dataset.class_names,\n colors=get_colors_for_class_ids(gt_class_id), ax=fig.axes[-1])\n plt.subplot(6, 2, 2*i + 2)\n results = model.detect([original_image]) \n r = results[0]\n visualize.display_instances(original_image, r['rois'], r['masks'], r['class_ids'], \n dataset.class_names, r['scores'], \n colors=get_colors_for_class_ids(r['class_ids']), ax=fig.axes[-1])","metadata":{"id":"irheTbrW2Bl0","colab_type":"code","colab":{"base_uri":"https://localhost:8080/","height":1394},"outputId":"56041ad4-173d-45ab-af67-f54e8333511e","_uuid":"186412199e25b98719f71cfe5e8869abcce516c4","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test_image_fps = get_dicom_fps(test_dicom_dir)","metadata":{"id":"qRWBVJKYNdWM","colab_type":"code","colab":{},"_uuid":"fd9f53fa319a425693e07fe4898ddeeaa5d07f99","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def predict(image_fps, filepath='submission.csv', min_conf=0.95): \n resize_factor = ORIG_SIZE / config.IMAGE_SHAPE[0]\n #resize_factor = ORIG_SIZE \n with open(filepath, 'w') as file:\n for image_id in tqdm(image_fps): \n ds = pydicom.read_file(image_id)\n image = ds.pixel_array\n if len(image.shape) != 3 or image.shape[2] != 3:\n image = np.stack((image,) * 3, -1) \n image, window, scale, padding, crop = utils.resize_image(\n image,\n min_dim=config.IMAGE_MIN_DIM,\n min_scale=config.IMAGE_MIN_SCALE,\n max_dim=config.IMAGE_MAX_DIM,\n mode=config.IMAGE_RESIZE_MODE)\n \n patient_id = os.path.splitext(os.path.basename(image_id))[0]\n\n results = model.detect([image])\n r = results[0]\n\n out_str = \"\"\n out_str += patient_id \n out_str += \",\"\n assert( len(r['rois']) == len(r['class_ids']) == len(r['scores']) )\n if len(r['rois']) == 0: \n pass\n else: \n num_instances = len(r['rois'])\n for i in range(num_instances): \n if r['scores'][i] > min_conf: \n out_str += ' '\n out_str += str(round(r['scores'][i], 2))\n out_str += ' '\n x1 = r['rois'][i][1]\n y1 = r['rois'][i][0]\n width = r['rois'][i][3] - x1 \n height = r['rois'][i][2] - y1 \n bboxes_str = \"{} {} {} {}\".format(x1*resize_factor, y1*resize_factor, \\\n width*resize_factor, height*resize_factor) \n file.write(out_str+\"\\n\")","metadata":{"id":"C6UWVrbM2Bob","colab_type":"code","colab":{},"_uuid":"4a5c0c6134408ddbf5a34496d7e9d7be5692e9a1","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def visualize(): \n image_id = random.choice(test_image_fps)\n ds = pydicom.read_file(image_id)\n image = ds.pixel_array\n resize_factor = ORIG_SIZE / config.IMAGE_SHAPE[0]\n if len(image.shape) != 3 or image.shape[2] != 3:\n image = np.stack((image,) * 3, -1) \n resized_image, window, scale, padding, crop = utils.resize_image(\n image,\n min_dim=config.IMAGE_MIN_DIM,\n min_scale=config.IMAGE_MIN_SCALE,\n max_dim=config.IMAGE_MAX_DIM,\n mode=config.IMAGE_RESIZE_MODE)\n patient_id = os.path.splitext(os.path.basename(image_id))[0]\n print(patient_id)\n results = model.detect([resized_image])\n r = results[0]\n for bbox in r['rois']: \n print(bbox)\n x1 = int(bbox[1] * resize_factor)\n y1 = int(bbox[0] * resize_factor)\n x2 = int(bbox[3] * resize_factor)\n y2 = int(bbox[2] * resize_factor)\n cv2.rectangle(image, (x1,y1), (x2,y2), (77, 255, 9), 3, 1)\n width = x2 - x1 \n height = y2 - y1 \n print(\"x {} y {} h {} w {}\".format(x1, y1, width, height))\n plt.figure() \n plt.imshow(image, cmap=plt.cm.gist_gray)\n\nvisualize()","metadata":{"_uuid":"ea110f197abc2acb1c3435383f7259079dc0eb0e","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}