{"cells":[{"metadata":{},"cell_type":"markdown","source":"# Use imgdupes for the detection of duplicates with exact neighbor searching using faiss\n1.  In the training set\n2. In the test set \n3. Between the above sets"},{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"# 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 in \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 \"../input/\" directory.\n# For example, running this (by clicking run or pressing Shift+Enter) will list the files in the input directory\n\nimport os\nprint(os.listdir(\"../input\"))\n\n# Any results you write to the current directory are saved as output.","execution_count":null,"outputs":[]},{"metadata":{"_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","trusted":true},"cell_type":"code","source":"! conda install -y faiss-gpu cudatoolkit=10.0 -c pytorch","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"!  pip install imgdupes","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"! ls -la ../input/","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"! imgdupes --recursive  --faiss-flat \"../input/test_images\" phash 1","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Let us see if these are really duplicates\n\n../input/test_images/01c31b10ab99.png\n../input/test_images/b29bd35acaf6.png\n\n../input/test_images/13e28ec4534a.png\n../input/test_images/6543b4168f98.png\n\n../input/test_images/1466c7e5936e.png\n../input/test_images/23c5eba92749.png\n\n../input/test_images/d00312c50737.png\n../input/test_images/1822b6c60784.png\n\n../input/test_images/2fb539602f57.png\n../input/test_images/80aa9b30d2f9.png\n\n../input/test_images/417d3908ee21.png\n../input/test_images/9d9de8c9afb5.png\n\n../input/test_images/4247b91698fc.png\n../input/test_images/a2319c2af727.png\n\n../input/test_images/aa381cb2abd2.png\n../input/test_images/9bd683e16325.png"},{"metadata":{"trusted":true},"cell_type":"code","source":"import matplotlib.pyplot as plt\nimport matplotlib.image as mpimg\nfrom matplotlib import rcParams\n\n%matplotlib inline\n\n# figure size in inches optional\nrcParams['figure.figsize'] = 15 ,15\ndef plotTwo(img_A,img_B):\n    # read images    \n    # display images\n    fig, ax = plt.subplots(1,2)\n    ax[0].imshow(img_A);\n    ax[1].imshow(img_B);","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"img_A = mpimg.imread('../input/test_images/01c31b10ab99.png')\nimg_B = mpimg.imread('../input/test_images/b29bd35acaf6.png')\nplotTwo (img_A,img_B)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"img_A = mpimg.imread('../input/test_images/417d3908ee21.png')\nimg_B = mpimg.imread('../input/test_images/9d9de8c9afb5.png')\nplotTwo (img_A,img_B)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# So you get the idea here. "},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]}],"metadata":{"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"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":4,"nbformat_minor":1}