{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Using TensorFlow backend.\n",
      "/home/haesun/github/GDL_code/env/lib/python3.7/site-packages/tensorflow/python/framework/dtypes.py:516: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.\n",
      "  _np_qint8 = np.dtype([(\"qint8\", np.int8, 1)])\n",
      "/home/haesun/github/GDL_code/env/lib/python3.7/site-packages/tensorflow/python/framework/dtypes.py:517: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.\n",
      "  _np_quint8 = np.dtype([(\"quint8\", np.uint8, 1)])\n",
      "/home/haesun/github/GDL_code/env/lib/python3.7/site-packages/tensorflow/python/framework/dtypes.py:518: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.\n",
      "  _np_qint16 = np.dtype([(\"qint16\", np.int16, 1)])\n",
      "/home/haesun/github/GDL_code/env/lib/python3.7/site-packages/tensorflow/python/framework/dtypes.py:519: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.\n",
      "  _np_quint16 = np.dtype([(\"quint16\", np.uint16, 1)])\n",
      "/home/haesun/github/GDL_code/env/lib/python3.7/site-packages/tensorflow/python/framework/dtypes.py:520: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.\n",
      "  _np_qint32 = np.dtype([(\"qint32\", np.int32, 1)])\n",
      "/home/haesun/github/GDL_code/env/lib/python3.7/site-packages/tensorflow/python/framework/dtypes.py:525: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.\n",
      "  np_resource = np.dtype([(\"resource\", np.ubyte, 1)])\n",
      "/home/haesun/github/GDL_code/env/lib/python3.7/site-packages/tensorboard/compat/tensorflow_stub/dtypes.py:541: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.\n",
      "  _np_qint8 = np.dtype([(\"qint8\", np.int8, 1)])\n",
      "/home/haesun/github/GDL_code/env/lib/python3.7/site-packages/tensorboard/compat/tensorflow_stub/dtypes.py:542: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.\n",
      "  _np_quint8 = np.dtype([(\"quint8\", np.uint8, 1)])\n",
      "/home/haesun/github/GDL_code/env/lib/python3.7/site-packages/tensorboard/compat/tensorflow_stub/dtypes.py:543: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.\n",
      "  _np_qint16 = np.dtype([(\"qint16\", np.int16, 1)])\n",
      "/home/haesun/github/GDL_code/env/lib/python3.7/site-packages/tensorboard/compat/tensorflow_stub/dtypes.py:544: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.\n",
      "  _np_quint16 = np.dtype([(\"quint16\", np.uint16, 1)])\n",
      "/home/haesun/github/GDL_code/env/lib/python3.7/site-packages/tensorboard/compat/tensorflow_stub/dtypes.py:545: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.\n",
      "  _np_qint32 = np.dtype([(\"qint32\", np.int32, 1)])\n",
      "/home/haesun/github/GDL_code/env/lib/python3.7/site-packages/tensorboard/compat/tensorflow_stub/dtypes.py:550: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.\n",
      "  np_resource = np.dtype([(\"resource\", np.ubyte, 1)])\n"
     ]
    }
   ],
   "source": [
    "import pickle as pkl\n",
    "import time\n",
    "import os\n",
    "import numpy as np\n",
    "import sys\n",
    "from music21 import instrument, note, stream, chord, duration\n",
    "from models.RNNAttention import create_network, sample_with_temp\n",
    "\n",
    "import matplotlib.pyplot as plt\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# 파라미터"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "# 실행 파라미터\n",
    "section = 'compose'\n",
    "run_id = '0006'\n",
    "music_name = 'cello'\n",
    "run_folder = 'run/{}/'.format(section)\n",
    "run_folder += '_'.join([run_id, music_name])\n",
    "\n",
    "# 하이퍼파라미터\n",
    "embed_size = 100\n",
    "rnn_units = 256\n",
    "use_attention = True"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 룩업 테이블 적재"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "store_folder = os.path.join(run_folder, 'store')\n",
    "\n",
    "with open(os.path.join(store_folder, 'distincts'), 'rb') as filepath:\n",
    "    distincts = pkl.load(filepath)\n",
    "    note_names, n_notes, duration_names, n_durations = distincts\n",
    "\n",
    "with open(os.path.join(store_folder, 'lookups'), 'rb') as filepath:\n",
    "    lookups = pkl.load(filepath)\n",
    "    note_to_int, int_to_note, duration_to_int, int_to_duration = lookups"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 모델 만들기"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "WARNING: Logging before flag parsing goes to stderr.\n",
      "W0923 21:55:11.495095 139658663503680 deprecation_wrapper.py:119] From /home/haesun/github/GDL_code/env/lib/python3.7/site-packages/keras/backend/tensorflow_backend.py:74: The name tf.get_default_graph is deprecated. Please use tf.compat.v1.get_default_graph instead.\n",
      "\n",
      "W0923 21:55:11.504162 139658663503680 deprecation_wrapper.py:119] From /home/haesun/github/GDL_code/env/lib/python3.7/site-packages/keras/backend/tensorflow_backend.py:517: The name tf.placeholder is deprecated. Please use tf.compat.v1.placeholder instead.\n",
      "\n",
      "W0923 21:55:11.506637 139658663503680 deprecation_wrapper.py:119] From /home/haesun/github/GDL_code/env/lib/python3.7/site-packages/keras/backend/tensorflow_backend.py:4138: The name tf.random_uniform is deprecated. Please use tf.random.uniform instead.\n",
      "\n",
      "W0923 21:55:11.947371 139658663503680 deprecation_wrapper.py:119] From /home/haesun/github/GDL_code/env/lib/python3.7/site-packages/keras/optimizers.py:790: The name tf.train.Optimizer is deprecated. Please use tf.compat.v1.train.Optimizer instead.\n",
      "\n",
      "W0923 21:55:11.953456 139658663503680 deprecation_wrapper.py:119] From /home/haesun/github/GDL_code/env/lib/python3.7/site-packages/keras/backend/tensorflow_backend.py:3295: The name tf.log is deprecated. Please use tf.math.log instead.\n",
      "\n",
      "W0923 21:55:11.994368 139658663503680 deprecation_wrapper.py:119] From /home/haesun/github/GDL_code/env/lib/python3.7/site-packages/keras/backend/tensorflow_backend.py:174: The name tf.get_default_session is deprecated. Please use tf.compat.v1.get_default_session instead.\n",
      "\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "__________________________________________________________________________________________________\n",
      "Layer (type)                    Output Shape         Param #     Connected to                     \n",
      "==================================================================================================\n",
      "input_1 (InputLayer)            (None, None)         0                                            \n",
      "__________________________________________________________________________________________________\n",
      "input_2 (InputLayer)            (None, None)         0                                            \n",
      "__________________________________________________________________________________________________\n",
      "embedding_1 (Embedding)         (None, None, 100)    3300        input_1[0][0]                    \n",
      "__________________________________________________________________________________________________\n",
      "embedding_2 (Embedding)         (None, None, 100)    700         input_2[0][0]                    \n",
      "__________________________________________________________________________________________________\n",
      "concatenate_1 (Concatenate)     (None, None, 200)    0           embedding_1[0][0]                \n",
      "                                                                 embedding_2[0][0]                \n",
      "__________________________________________________________________________________________________\n",
      "lstm_1 (LSTM)                   (None, None, 256)    467968      concatenate_1[0][0]              \n",
      "__________________________________________________________________________________________________\n",
      "lstm_2 (LSTM)                   (None, None, 256)    525312      lstm_1[0][0]                     \n",
      "__________________________________________________________________________________________________\n",
      "dense_1 (Dense)                 (None, None, 1)      257         lstm_2[0][0]                     \n",
      "__________________________________________________________________________________________________\n",
      "reshape_1 (Reshape)             (None, None)         0           dense_1[0][0]                    \n",
      "__________________________________________________________________________________________________\n",
      "activation_1 (Activation)       (None, None)         0           reshape_1[0][0]                  \n",
      "__________________________________________________________________________________________________\n",
      "repeat_vector_1 (RepeatVector)  (None, 256, None)    0           activation_1[0][0]               \n",
      "__________________________________________________________________________________________________\n",
      "permute_1 (Permute)             (None, None, 256)    0           repeat_vector_1[0][0]            \n",
      "__________________________________________________________________________________________________\n",
      "multiply_1 (Multiply)           (None, None, 256)    0           lstm_2[0][0]                     \n",
      "                                                                 permute_1[0][0]                  \n",
      "__________________________________________________________________________________________________\n",
      "lambda_1 (Lambda)               (None, 256)          0           multiply_1[0][0]                 \n",
      "__________________________________________________________________________________________________\n",
      "pitch (Dense)                   (None, 33)           8481        lambda_1[0][0]                   \n",
      "__________________________________________________________________________________________________\n",
      "duration (Dense)                (None, 7)            1799        lambda_1[0][0]                   \n",
      "==================================================================================================\n",
      "Total params: 1,007,817\n",
      "Trainable params: 1,007,817\n",
      "Non-trainable params: 0\n",
      "__________________________________________________________________________________________________\n"
     ]
    }
   ],
   "source": [
    "weights_folder = os.path.join(run_folder, 'weights')\n",
    "weights_file = 'weights.h5'\n",
    "\n",
    "model, att_model = create_network(n_notes, n_durations, embed_size, rnn_units, use_attention)\n",
    "\n",
    "# 각 노드에 가중치 적재하기\n",
    "weight_source = os.path.join(weights_folder,weights_file)\n",
    "model.load_weights(weight_source)\n",
    "model.summary()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 자신만의 악절 만들기"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "# 예측용 파라미터\n",
    "notes_temp=0.5\n",
    "duration_temp = 0.5\n",
    "max_extra_notes = 50\n",
    "max_seq_len = 32\n",
    "seq_len = 32\n",
    "\n",
    "# notes = ['START', 'D3', 'D3', 'E3', 'D3', 'G3', 'F#3','D3', 'D3', 'E3', 'D3', 'G3', 'F#3','D3', 'D3', 'E3', 'D3', 'G3', 'F#3','D3', 'D3', 'E3', 'D3', 'G3', 'F#3']\n",
    "# durations = [0, 0.75, 0.25, 1, 1, 1, 2, 0.75, 0.25, 1, 1, 1, 2, 0.75, 0.25, 1, 1, 1, 2, 0.75, 0.25, 1, 1, 1, 2]\n",
    "\n",
    "\n",
    "# notes = ['START', 'F#3', 'G#3', 'F#3', 'E3', 'F#3', 'G#3', 'F#3', 'E3', 'F#3', 'G#3', 'F#3', 'E3','F#3', 'G#3', 'F#3', 'E3', 'F#3', 'G#3', 'F#3', 'E3', 'F#3', 'G#3', 'F#3', 'E3']\n",
    "# durations = [0, 0.75, 0.25, 1, 1, 1, 2, 0.75, 0.25, 1, 1, 1, 2, 0.75, 0.25, 1, 1, 1, 2, 0.75, 0.25, 1, 1, 1, 2]\n",
    "\n",
    "\n",
    "notes = ['START']\n",
    "durations = [0]\n",
    "\n",
    "if seq_len is not None:\n",
    "    notes = ['START'] * (seq_len - len(notes)) + notes\n",
    "    durations = [0] * (seq_len - len(durations)) + durations\n",
    "\n",
    "\n",
    "sequence_length = len(notes)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 악보 시퀀스를 기반으로 신경망에서 악보 생성하기"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Generated sequence of 82 notes\n"
     ]
    }
   ],
   "source": [
    "prediction_output = []\n",
    "notes_input_sequence = []\n",
    "durations_input_sequence = []\n",
    "\n",
    "overall_preds = []\n",
    "\n",
    "for n, d in zip(notes,durations):\n",
    "    note_int = note_to_int[n]\n",
    "    duration_int = duration_to_int[d]\n",
    "    \n",
    "    notes_input_sequence.append(note_int)\n",
    "    durations_input_sequence.append(duration_int)\n",
    "    \n",
    "    prediction_output.append([n, d])\n",
    "    \n",
    "    if n != 'START':\n",
    "        midi_note = note.Note(n)\n",
    "\n",
    "        new_note = np.zeros(128)\n",
    "        new_note[midi_note.pitch.midi] = 1\n",
    "        overall_preds.append(new_note)\n",
    "\n",
    "\n",
    "att_matrix = np.zeros(shape = (max_extra_notes+sequence_length, max_extra_notes))\n",
    "\n",
    "for note_index in range(max_extra_notes):\n",
    "\n",
    "    prediction_input = [\n",
    "        np.array([notes_input_sequence])\n",
    "        , np.array([durations_input_sequence])\n",
    "       ]\n",
    "\n",
    "    notes_prediction, durations_prediction = model.predict(prediction_input, verbose=0)\n",
    "    if use_attention:\n",
    "        att_prediction = att_model.predict(prediction_input, verbose=0)[0]\n",
    "        att_matrix[(note_index-len(att_prediction)+sequence_length):(note_index+sequence_length), note_index] = att_prediction\n",
    "    \n",
    "    new_note = np.zeros(128)\n",
    "    \n",
    "    for idx, n_i in enumerate(notes_prediction[0]):\n",
    "        try:\n",
    "            note_name = int_to_note[idx]\n",
    "            midi_note = note.Note(note_name)\n",
    "            new_note[midi_note.pitch.midi] = n_i\n",
    "            \n",
    "        except:\n",
    "            pass\n",
    "        \n",
    "    overall_preds.append(new_note)\n",
    "            \n",
    "    \n",
    "    i1 = sample_with_temp(notes_prediction[0], notes_temp)\n",
    "    i2 = sample_with_temp(durations_prediction[0], duration_temp)\n",
    "    \n",
    "\n",
    "    note_result = int_to_note[i1]\n",
    "    duration_result = int_to_duration[i2]\n",
    "    \n",
    "    prediction_output.append([note_result, duration_result])\n",
    "\n",
    "    notes_input_sequence.append(i1)\n",
    "    durations_input_sequence.append(i2)\n",
    "    \n",
    "    if len(notes_input_sequence) > max_seq_len:\n",
    "        notes_input_sequence = notes_input_sequence[1:]\n",
    "        durations_input_sequence = durations_input_sequence[1:]\n",
    "        \n",
    "#     print(note_result)\n",
    "#     print(duration_result)\n",
    "        \n",
    "    if note_result == 'START':\n",
    "        break\n",
    "\n",
    "overall_preds = np.transpose(np.array(overall_preds)) \n",
    "print('Generated sequence of {} notes'.format(len(prediction_output)))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.image.AxesImage at 0x7f044011d940>"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1080x1080 with 1 Axes>"
      ]
     },
     "metadata": {
      "image/png": {
       "height": 618,
       "width": 877
      },
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "fig, ax = plt.subplots(figsize=(15,15))\n",
    "ax.set_yticks([int(j) for j in range(35,70)])\n",
    "\n",
    "plt.imshow(overall_preds[35:70,:], origin=\"lower\", cmap='coolwarm', vmin = -0.5, vmax = 0.5, extent=[0, max_extra_notes, 35,70]\n",
    "          \n",
    "          )"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 예측 출력을 악보로 변환하고 악보에서 미디 파일 만들기"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'run/compose/0006_cello/output/output-20190923-215515.mid'"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "output_folder = os.path.join(run_folder, 'output')\n",
    "\n",
    "midi_stream = stream.Stream()\n",
    "\n",
    "# 모델이 생성한 값을 기반으로 악보와 화음 객체 만들기\n",
    "for pattern in prediction_output:\n",
    "    note_pattern, duration_pattern = pattern\n",
    "    # 패턴이 화음일 경우\n",
    "    if ('.' in note_pattern):\n",
    "        notes_in_chord = note_pattern.split('.')\n",
    "        chord_notes = []\n",
    "        for current_note in notes_in_chord:\n",
    "            new_note = note.Note(current_note)\n",
    "            new_note.duration = duration.Duration(duration_pattern)\n",
    "            new_note.storedInstrument = instrument.Violoncello()\n",
    "            chord_notes.append(new_note)\n",
    "        new_chord = chord.Chord(chord_notes)\n",
    "        midi_stream.append(new_chord)\n",
    "    elif note_pattern == 'rest':\n",
    "    # 패턴이 쉼표일 경우\n",
    "        new_note = note.Rest()\n",
    "        new_note.duration = duration.Duration(duration_pattern)\n",
    "        new_note.storedInstrument = instrument.Violoncello()\n",
    "        midi_stream.append(new_note)\n",
    "    elif note_pattern != 'START':\n",
    "    # 패턴이 하나의 음표일 경우\n",
    "        new_note = note.Note(note_pattern)\n",
    "        new_note.duration = duration.Duration(duration_pattern)\n",
    "        new_note.storedInstrument = instrument.Violoncello()\n",
    "        midi_stream.append(new_note)\n",
    "\n",
    "\n",
    "\n",
    "midi_stream = midi_stream.chordify()\n",
    "timestr = time.strftime(\"%Y%m%d-%H%M%S\")\n",
    "midi_stream.write('midi', fp=os.path.join(output_folder, 'output-' + timestr + '.mid'))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1440x1440 with 1 Axes>"
      ]
     },
     "metadata": {
      "image/png": {
       "height": 1132,
       "width": 1101
      },
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "## 어텐션 그래프\n",
    "if use_attention:\n",
    "    fig, ax = plt.subplots(figsize=(20,20))\n",
    "\n",
    "    im = ax.imshow(att_matrix[(seq_len-2):,], cmap='coolwarm', interpolation='nearest')\n",
    "\n",
    "\n",
    "    \n",
    "\n",
    "    # Minor ticks\n",
    "    ax.set_xticks(np.arange(-.5, len(prediction_output)- seq_len, 1), minor=True);\n",
    "    ax.set_yticks(np.arange(-.5, len(prediction_output)- seq_len, 1), minor=True);\n",
    "\n",
    "    # Gridlines based on minor ticks\n",
    "    ax.grid(which='minor', color='black', linestyle='-', linewidth=1)\n",
    "    \n",
    "    \n",
    "    \n",
    "    \n",
    "    # We want to show all ticks...\n",
    "    ax.set_xticks(np.arange(len(prediction_output) - seq_len))\n",
    "    ax.set_yticks(np.arange(len(prediction_output)- seq_len+2))\n",
    "    # ... and label them with the respective list entries\n",
    "    ax.set_xticklabels([n[0] for n in prediction_output[(seq_len):]])\n",
    "    ax.set_yticklabels([n[0] for n in prediction_output[(seq_len - 2):]])\n",
    "\n",
    "    # ax.grid(color='black', linestyle='-', linewidth=1)\n",
    "\n",
    "    ax.xaxis.tick_top()\n",
    "\n",
    "\n",
    "    \n",
    "    plt.setp(ax.get_xticklabels(), rotation=90, ha=\"left\", va = \"center\",\n",
    "             rotation_mode=\"anchor\")\n",
    "\n",
    "    plt.show()"
   ]
  }
 ],
 "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": "3.7.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}