Created
April 19, 2021 22:53
-
-
Save nogawanogawa/3d79dcbf9ba216c5ab42761b06238730 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
{ | |
"cells": [ | |
{ | |
"cell_type": "code", | |
"execution_count": 1, | |
"id": "baf8897c", | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"from lib.feature.src.phash import *\n", | |
"from lib.feature.src.akaze import *\n", | |
"from PIL import Image\n", | |
"from os import listdir, path\n", | |
"import numpy as np\n", | |
"from pyclustering.cluster import gmeans,xmeans\n", | |
"import plotly.express as px\n", | |
"import plotly.graph_objects as go\n", | |
"from sklearn.decomposition import PCA\n", | |
"import itertools" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 2, | |
"id": "6f0ca11a", | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"def corpus_filenames(path):\n", | |
" \"\"\" pathの中のファイルをlistにして返す \"\"\"\n", | |
" labels = [] # *.txt\n", | |
" for y in listdir(path):\n", | |
" if not y.startswith('LICENSE'):\n", | |
" labels.append(y)\n", | |
" return labels" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 3, | |
"id": "c77b02c4", | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"filename = \"/app/images/Abyssinian_4.jpg\"" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 4, | |
"id": "99508ddb", | |
"metadata": {}, | |
"outputs": [ | |
{ | |
"data": { | |
"text/plain": [ | |
"64" | |
] | |
}, | |
"execution_count": 4, | |
"metadata": {}, | |
"output_type": "execute_result" | |
} | |
], | |
"source": [ | |
"len(get_hash(filename))" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 5, | |
"id": "33558b3a", | |
"metadata": { | |
"scrolled": true | |
}, | |
"outputs": [ | |
{ | |
"data": { | |
"text/plain": [ | |
"array([[199, 237, 191, ..., 6, 0, 24],\n", | |
" [192, 243, 1, ..., 10, 49, 32],\n", | |
" [224, 193, 15, ..., 99, 216, 62],\n", | |
" ...,\n", | |
" [ 0, 238, 5, ..., 252, 15, 0],\n", | |
" [225, 240, 11, ..., 115, 254, 63],\n", | |
" [ 65, 73, 11, ..., 121, 255, 62]], dtype=uint8)" | |
] | |
}, | |
"execution_count": 5, | |
"metadata": {}, | |
"output_type": "execute_result" | |
} | |
], | |
"source": [ | |
"get_akaze_featrue(filename)" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 6, | |
"id": "33f834e5", | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"PATH = \"/app/images\"\n", | |
"b = None\n", | |
"for filename in corpus_filenames(PATH):\n", | |
" filepath = path.join(PATH, filename)\n", | |
" try:\n", | |
" if b is None:\n", | |
" b = get_akaze_featrue(filepath)\n", | |
" else :\n", | |
" b = np.append(b, get_akaze_featrue(filepath), axis=0)\n", | |
" except:\n", | |
" pass\n" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 7, | |
"id": "6752b9fa", | |
"metadata": {}, | |
"outputs": [ | |
{ | |
"data": { | |
"text/plain": [ | |
"array([[ 11, 178, 252, ..., 0, 252, 62],\n", | |
" [161, 70, 7, ..., 95, 0, 53],\n", | |
" [ 64, 13, 8, ..., 254, 10, 37],\n", | |
" ...,\n", | |
" [ 8, 230, 3, ..., 255, 255, 63],\n", | |
" [117, 253, 79, ..., 143, 0, 48],\n", | |
" [ 65, 61, 236, ..., 65, 221, 60]], dtype=uint8)" | |
] | |
}, | |
"execution_count": 7, | |
"metadata": {}, | |
"output_type": "execute_result" | |
} | |
], | |
"source": [ | |
"b\n", | |
"\n", | |
"# akaze \n", | |
"# kmeans" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 8, | |
"id": "dca24173", | |
"metadata": {}, | |
"outputs": [ | |
{ | |
"data": { | |
"text/plain": [ | |
"2805623" | |
] | |
}, | |
"execution_count": 8, | |
"metadata": {}, | |
"output_type": "execute_result" | |
} | |
], | |
"source": [ | |
"len(b)" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 9, | |
"id": "276a1841", | |
"metadata": {}, | |
"outputs": [ | |
{ | |
"name": "stderr", | |
"output_type": "stream", | |
"text": [ | |
"/usr/local/lib/python3.7/site-packages/numpy/core/_asarray.py:102: VisibleDeprecationWarning: Creating an ndarray from ragged nested sequences (which is a list-or-tuple of lists-or-tuples-or ndarrays with different lengths or shapes) is deprecated. If you meant to do this, you must specify 'dtype=object' when creating the ndarray.\n", | |
" return array(a, dtype, copy=False, order=order)\n" | |
] | |
} | |
], | |
"source": [ | |
"# X-means\n", | |
"xmeans_instance = xmeans.xmeans(b).process()\n", | |
"\n", | |
"clusters = xmeans_instance.get_clusters()\n", | |
"centers = xmeans_instance.get_centers()\n", | |
"\n", | |
"labels_size = len(\n", | |
" list(itertools.chain.from_iterable(clusters))\n", | |
")\n", | |
"labels = np.zeros((1, labels_size))\n", | |
"for n, n_th_cluster in np.ndenumerate(clusters):\n", | |
" for img_num in n_th_cluster:\n", | |
" labels[0][img_num] = n[0]\n", | |
"labels = labels.ravel()\n" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 10, | |
"id": "07217d3d", | |
"metadata": {}, | |
"outputs": [ | |
{ | |
"data": { | |
"text/plain": [ | |
"0.0" | |
] | |
}, | |
"execution_count": 10, | |
"metadata": {}, | |
"output_type": "execute_result" | |
} | |
], | |
"source": [ | |
"min(labels)" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 11, | |
"id": "1e019069", | |
"metadata": {}, | |
"outputs": [ | |
{ | |
"data": { | |
"text/plain": [ | |
"19.0" | |
] | |
}, | |
"execution_count": 11, | |
"metadata": {}, | |
"output_type": "execute_result" | |
} | |
], | |
"source": [ | |
"max(labels)" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": null, | |
"id": "d8966add", | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"# G-means\n", | |
"\n", | |
"gmeans_instance = gmeans.gmeans(b).process()\n", | |
"\n", | |
"clusters = gmeans_instance.get_clusters()\n", | |
"centers = gmeans_instance.get_centers()\n", | |
"\n", | |
"labels_size = len(\n", | |
" list(itertools.chain.from_iterable(clusters))\n", | |
")\n", | |
"labels = np.zeros((1, labels_size))\n", | |
"for n, n_th_cluster in np.ndenumerate(clusters):\n", | |
" for img_num in n_th_cluster:\n", | |
" labels[0][img_num] = n[0]\n", | |
"labels = labels.ravel()" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": null, | |
"id": "b3f233a2", | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"min(labels)" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": null, | |
"id": "9da97557", | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"max(labels)" | |
] | |
} | |
], | |
"metadata": { | |
"kernelspec": { | |
"display_name": "Python 3", | |
"language": "python", | |
"name": "python3" | |
}, | |
"language_info": { | |
"codemirror_mode": { | |
"name": "ipython", | |
"version": 3 | |
}, | |
"file_extension": ".py", | |
"mimetype": "text/x-python", | |
"name": "python", | |
"nbconvert_exporter": "python", | |
"pygments_lexer": "ipython3", | |
"version": "3.7.8" | |
} | |
}, | |
"nbformat": 4, | |
"nbformat_minor": 5 | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment