{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "increased-pantyhose",
   "metadata": {},
   "source": [
    "# Quantization"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "magnetic-porter",
   "metadata": {},
   "source": [
    "<div class=\"alert alert-info\">\n",
    "\n",
    "This tutorial is available as an IPython notebook at [Malaya/example/quantization](https://github.com/huseinzol05/Malaya/tree/master/example/quantization).\n",
    "    \n",
    "</div>"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "outdoor-retailer",
   "metadata": {},
   "source": [
    "We provided Quantized model for all Malaya models, example, sentiment transformer models,"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "gothic-empty",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "INFO:root:tested on 20% test set.\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Size (MB)</th>\n",
       "      <th>Quantized Size (MB)</th>\n",
       "      <th>macro precision</th>\n",
       "      <th>macro recall</th>\n",
       "      <th>macro f1-score</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>bert</th>\n",
       "      <td>425.6</td>\n",
       "      <td>111.00</td>\n",
       "      <td>0.99330</td>\n",
       "      <td>0.99330</td>\n",
       "      <td>0.99329</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>tiny-bert</th>\n",
       "      <td>57.4</td>\n",
       "      <td>15.40</td>\n",
       "      <td>0.98774</td>\n",
       "      <td>0.98774</td>\n",
       "      <td>0.98774</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>albert</th>\n",
       "      <td>48.6</td>\n",
       "      <td>12.80</td>\n",
       "      <td>0.99227</td>\n",
       "      <td>0.99226</td>\n",
       "      <td>0.99226</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>tiny-albert</th>\n",
       "      <td>22.4</td>\n",
       "      <td>5.98</td>\n",
       "      <td>0.98554</td>\n",
       "      <td>0.98550</td>\n",
       "      <td>0.98551</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>xlnet</th>\n",
       "      <td>446.6</td>\n",
       "      <td>118.00</td>\n",
       "      <td>0.99353</td>\n",
       "      <td>0.99353</td>\n",
       "      <td>0.99353</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>alxlnet</th>\n",
       "      <td>46.8</td>\n",
       "      <td>13.30</td>\n",
       "      <td>0.99188</td>\n",
       "      <td>0.99188</td>\n",
       "      <td>0.99188</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "             Size (MB)  Quantized Size (MB)  macro precision  macro recall  \\\n",
       "bert             425.6               111.00          0.99330       0.99330   \n",
       "tiny-bert         57.4                15.40          0.98774       0.98774   \n",
       "albert            48.6                12.80          0.99227       0.99226   \n",
       "tiny-albert       22.4                 5.98          0.98554       0.98550   \n",
       "xlnet            446.6               118.00          0.99353       0.99353   \n",
       "alxlnet           46.8                13.30          0.99188       0.99188   \n",
       "\n",
       "             macro f1-score  \n",
       "bert                0.99329  \n",
       "tiny-bert           0.98774  \n",
       "albert              0.99226  \n",
       "tiny-albert         0.98551  \n",
       "xlnet               0.99353  \n",
       "alxlnet             0.99188  "
      ]
     },
     "execution_count": 1,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import malaya\n",
    "\n",
    "malaya.sentiment.available_transformer()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "positive-bracelet",
   "metadata": {},
   "source": [
    "Usually quantized model able to compress 4x of original size. This quantized model will convert all possible floating constants to quantized constants, and only stored mean, standard deviation of floating constants and quantized constants.\n",
    "\n",
    "Again, quantized model is not necessary faster, because tensorflow will cast back to FP32 during feed-forward for certain operations."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "functioning-youth",
   "metadata": {},
   "source": [
    "### Use quantized model\n",
    "\n",
    "Simply pass `quantized` parameter become `True`, default is `False`."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "better-religious",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "WARNING:root:Load quantized model will cause accuracy drop.\n",
      "INFO:root:running sentiment/albert-quantized using device /device:CPU:0\n",
      "INFO:root:running sentiment/albert using device /device:CPU:0\n"
     ]
    }
   ],
   "source": [
    "albert_quantized = malaya.sentiment.transformer(model = 'albert', quantized = True)\n",
    "albert = malaya.sentiment.transformer(model = 'albert')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "imposed-uganda",
   "metadata": {},
   "outputs": [],
   "source": [
    "string = 'saya masam awak pun masam'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "dietary-lottery",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "CPU times: user 171 ms, sys: 15.9 ms, total: 187 ms\n",
      "Wall time: 47.2 ms\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "['negative']"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "%%time\n",
    "\n",
    "albert.predict([string])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "trying-capability",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "CPU times: user 181 ms, sys: 41.1 ms, total: 223 ms\n",
      "Wall time: 53.8 ms\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "['negative']"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "%%time\n",
    "\n",
    "albert_quantized.predict([string])"
   ]
  }
 ],
 "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": "3.7.7"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}