{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "1e40a88b",
   "metadata": {},
   "outputs": [],
   "source": [
    "%load_ext autoreload\n",
    "%autoreload 2\n",
    "\n",
    "%matplotlib inline\n",
    "import matplotlib.pyplot as plt\n",
    "import numpy as np\n",
    "from PIL import Image\n",
    "import torch\n",
    "from torch import nn\n",
    "from importlib.util import find_spec\n",
    "if find_spec(\"text_recognizer\") is None:\n",
    "    import sys\n",
    "    sys.path.append('..')\n",
    "    "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "d3a6146b-94b1-4618-a4e4-00f8e23ffdb0",
   "metadata": {},
   "outputs": [],
   "source": [
    "from hydra import compose, initialize\n",
    "from omegaconf import OmegaConf\n",
    "from hydra.utils import instantiate"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "6b722ca0-9c65-4f90-be4e-b7334ea81237",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "mapping:\n",
      "  _target_: text_recognizer.data.mappings.WordPieceMapping\n",
      "  num_features: 1000\n",
      "  tokens: iamdb_1kwp_tokens_1000.txt\n",
      "  lexicon: iamdb_1kwp_lex_1000.txt\n",
      "  data_dir: null\n",
      "  use_words: false\n",
      "  prepend_wordsep: false\n",
      "  special_tokens:\n",
      "  - <s>\n",
      "  - <e>\n",
      "  - <p>\n",
      "  extra_symbols:\n",
      "  - \\n\n",
      "_target_: text_recognizer.models.transformer.TransformerLitModel\n",
      "interval: step\n",
      "monitor: val/loss\n",
      "ignore_tokens:\n",
      "- <s>\n",
      "- <e>\n",
      "- <p>\n",
      "start_token: <s>\n",
      "end_token: <e>\n",
      "pad_token: <p>\n",
      "\n",
      "{'mapping': {'_target_': 'text_recognizer.data.mappings.WordPieceMapping', 'num_features': 1000, 'tokens': 'iamdb_1kwp_tokens_1000.txt', 'lexicon': 'iamdb_1kwp_lex_1000.txt', 'data_dir': None, 'use_words': False, 'prepend_wordsep': False, 'special_tokens': ['<s>', '<e>', '<p>'], 'extra_symbols': ['\\\\n']}, '_target_': 'text_recognizer.models.transformer.TransformerLitModel', 'interval': 'step', 'monitor': 'val/loss', 'ignore_tokens': ['<s>', '<e>', '<p>'], 'start_token': '<s>', 'end_token': '<e>', 'pad_token': '<p>'}\n"
     ]
    }
   ],
   "source": [
    "# context initialization\n",
    "with initialize(config_path=\"../training/conf/model/\", job_name=\"test_app\"):\n",
    "    cfg = compose(config_name=\"lit_transformer\")\n",
    "    print(OmegaConf.to_yaml(cfg))\n",
    "    print(cfg)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "9c797159-845e-42c6-bd65-1c976ad627cd",
   "metadata": {},
   "outputs": [],
   "source": [
    "# context initialization\n",
    "with initialize(config_path=\"../training/conf/network/\", job_name=\"test_app\"):\n",
    "    cfg = compose(config_name=\"conv_transformer\")\n",
    "    print(OmegaConf.to_yaml(cfg))\n",
    "    print(cfg)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "af2c8cfa-0b45-4681-b671-0f97ace62516",
   "metadata": {},
   "outputs": [],
   "source": [
    "net = instantiate(cfg)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "8f0742ad-5e2f-42d5-83e7-6e46398b4f0f",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "net"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "40be59bc-db79-4af1-9df4-e280f7a56481",
   "metadata": {},
   "outputs": [],
   "source": [
    "img = torch.rand(4, 1, 576, 640)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "d5a8f10b-edf5-4a18-9747-f016db72c384",
   "metadata": {},
   "outputs": [],
   "source": [
    "y = torch.randint(0, 1006, (4, 451))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "19423ef1-3d98-4af3-8748-fdd3bb817300",
   "metadata": {},
   "outputs": [],
   "source": [
    "y.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "0712ee7e-4f66-4fb1-bc91-d8a127eb7ac7",
   "metadata": {},
   "outputs": [],
   "source": [
    "net = net.cuda()\n",
    "img = img.cuda()\n",
    "y = y.cuda()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "719154b4-47db-4c91-bae4-8c572c4a4536",
   "metadata": {},
   "outputs": [],
   "source": [
    "net(img, y).shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "bcb7db0f-0afe-44eb-9bb7-b988fbead95a",
   "metadata": {},
   "outputs": [],
   "source": [
    "from torchsummary import summary"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "31af8ee1-28d3-46b8-a847-6506d29bc45c",
   "metadata": {},
   "outputs": [],
   "source": [
    "summary(net, [(1, 576, 640), (451,)], device=\"cpu\", depth=2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "4d6d836f-d169-48b4-92e6-ca17179e6f85",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": "3.9.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}