{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Training CoarseNet\n",
    "Code for FineNet in paper \"Robust Minutiae Extractor: Integrating Deep Networks and Fingerprint Domain Knowledge\" at ICB 2018: https://arxiv.org/pdf/1712.09401.pdf\n",
    "\n",
    "If you use whole or partial function in this code, please cite paper:\n",
    "\n",
    "    @inproceedings{Nguyen_MinutiaeNet,\n",
    "\tauthor    = {Dinh-Luan Nguyen and Kai Cao and Anil K. Jain},\n",
    "\ttitle     = {Robust Minutiae Extractor: Integrating Deep Networks and Fingerprint Domain Knowledge},\n",
    "\tbooktitle = {The 11th International Conference on Biometrics, 2018},\n",
    "\tyear      = {2018},\n",
    "\t}"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "To run this script, you need to prepare dataset as follows:\n",
    "`path/to/dataset/`:\n",
    "```Shell\n",
    " - img_files/*.bmp\n",
    " - mnt_files/*.mnt\n",
    " - seg_files/*.jpg\n",
    "```\n",
    "See example at `Dataset/CoarseNet_train/` (these images are example from NIST SD27)\n",
    " \n",
    "## CoarseNet can run with any image size\n",
    "See [CoarseNet_train.py](https://github.com/luannd/MinutiaeNet/blob/master/CoarseNet/CoarseNet_train.py) if running from command line.\n",
    "\n",
    "Log files, tensorboard, minutiae models can be seen from `output_CoarseNet` folder"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from __future__ import absolute_import\n",
    "from __future__ import division\n",
    "\n",
    "import sys, os\n",
    "sys.path.append(os.path.realpath('../CoarseNet'))\n",
    "\n",
    "os.environ['KERAS_BACKEND'] = 'tensorflow'\n",
    "\n",
    "from datetime import datetime\n",
    "from MinutiaeNet_utils import *\n",
    "\n",
    "from keras import backend as K\n",
    "from keras.optimizers import SGD, Adam\n",
    "\n",
    "from CoarseNet_utils import *\n",
    "from CoarseNet_model import *\n",
    "\n",
    "lr = 0.005\n",
    "\n",
    "os.environ[\"CUDA_VISIBLE_DEVICES\"] = '0'\n",
    "\n",
    "config = K.tf.ConfigProto(gpu_options=K.tf.GPUOptions(allow_growth=True))\n",
    "sess = K.tf.Session(config=config)\n",
    "K.set_session(sess)\n",
    "\n",
    "batch_size = 2\n",
    "use_multiprocessing = False\n",
    "input_size = 400\n",
    "\n",
    "# Can use multiple folders for training\n",
    "train_set = ['../Dataset/CoarseNet_train/',]\n",
    "validate_set = ['../path/to/your/data/',]\n",
    "\n",
    "pretrain_dir = '../Models/CoarseNet.h5'\n",
    "output_dir = '../output_CoarseNet/'+datetime.now().strftime('%Y%m%d-%H%M%S')\n",
    "FineNet_dir = '../Models/FineNet.h5'\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "\n",
    "output_dir = '../output_CoarseNet/trainResults/' + datetime.now().strftime('%Y%m%d-%H%M%S')\n",
    "logging = init_log(output_dir)\n",
    "logging.info(\"Learning rate = %s\", lr)\n",
    "logging.info(\"Pretrain dir = %s\", pretrain_dir)\n",
    "\n",
    "train(input_shape=(input_size, input_size), train_set=train_set, output_dir=output_dir,\n",
    "      pretrain_dir=pretrain_dir, batch_size=batch_size, test_set=validate_set,\n",
    "      learning_config=Adam(lr=float(lr), beta_1=0.9, beta_2=0.999, epsilon=1e-08, clipnorm=0.9),\n",
    "      logging=logging)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 2",
   "language": "python",
   "name": "python2"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 2
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython2",
   "version": "2.7.15"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}