gistfile1.txt

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "%matplotlib inline\n",
    "import pandas as pd\n",
    "import matplotlib.pyplot as plt\n",
    "import numpy.random as rnd\n",
    "import numpy as np\n",
    "import matplotlib\n",
    "import seaborn as sns\n",
    "import numpy as np\n",
    "import chainer\n",
    "from chainer import cuda, Variable\n",
    "from chainer import Chain\n",
    "import chainer.functions as F\n",
    "import chainer.links as L\n",
    "import chainer.optimizers as O"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [],
   "source": [
    "logit = Variable(np.random.randn(5, 3))\n",
    "label1 = np.asarray([0,1,2,1,2], 'i')\n",
    "label2 = np.asarray([0,-1, -1, -1, -1], 'i')\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "variable(1.62515638)"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "F.softmax_cross_entropy(x=logit, t=label1, normalize=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "variable(0.81395807)"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "F.softmax_cross_entropy(x=logit, t=label2, normalize=False, ignore_label=-1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "variable(4.06979035)"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "F.softmax_cross_entropy(x=logit, t=label2, normalize=True, ignore_label=-1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "variable(4.06979035)"
      ]
     },
     "execution_count": 23,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "-F.log(F.softmax(logit)[0])[0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "variable([4.06979035, 0.        , 0.        , 0.        , 0.        ])"
      ]
     },
     "execution_count": 24,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "F.softmax_cross_entropy(x=logit, t=label2, normalize=False, ignore_label=-1, reduce='no')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "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": "3.6.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}