tobacoo-industry/01_dataset_building.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": true,
    "pycharm": {
     "name": "#%% md\n"
    }
   },
   "source": [
    "# 数据集的制作"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "import pickle\n",
    "import cv2\n",
    "import numpy as np\n",
    "from utils import split_xy"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "# 一些参数\n",
    "blk_sz = 8\n",
    "sensitivity = 32\n",
    "selected_bands = [127, 201, 202, 294]\n",
    "# [76, 146, 216, 367, 383, 406]\n",
    "file_name, labeled_image_file = r\"F:\\zhouchao\\616\\calibrated1.raw\", \\\n",
    "r\"F:\\zhouchao\\616\\label1.bmp\"\n",
    "# file_name, labeled_image_file = \"./dataset/calibrated77.raw\", \"./dataset/label77.png\"\n",
    "dataset_file = f'./dataset/data_{blk_sz}x{blk_sz}_c{len(selected_bands)}_sen{sensitivity}_1.p'"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": false
   },
   "source": [
    "## 波长选择"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "with open(file_name, \"rb\") as f:\n",
    "    data = np.frombuffer(f.read(), dtype=np.float32).reshape((600, 448, 1024)).transpose(0, 2, 1)\n",
    "data = data[..., selected_bands]\n",
    "label = cv2.imread(labeled_image_file)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%% md\n"
    }
   },
   "source": [
    "## 块分割与数据存储"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "color_dict = {(0, 0, 255): 1, (255, 255, 255): 0, (0, 255, 0): 2, (255, 0, 0): 1, (0, 255, 255): 4,\n",
    "              (255, 255, 0): 5, (255, 0, 255): 6}\n",
    "x, y = split_xy(data, label, blk_sz, sensitivity=sensitivity, color_dict=color_dict)\n",
    "with open(dataset_file, 'wb') as f:\n",
    "    pickle.dump((x, y), f)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3.9.7 ('base')",
   "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": "3.9.7"
  },
  "vscode": {
   "interpreter": {
    "hash": "7f619fc91ee8bdab81d49e7c14228037474662e3f2d607687ae505108922fa06"
   }
  }
 },
 "nbformat": 4,
 "nbformat_minor": 0
}