{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "7c02ae76-b540-4b16-9492-e9210b3b9249",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "import os\n",
    "os.environ['CUDA_VISIBLE_DEVICE'] = ''\n",
    "import random\n",
    "\n",
    "%matplotlib inline\n",
    "import matplotlib.pyplot as plt\n",
    "\n",
    "import numpy as np\n",
    "from omegaconf import OmegaConf\n",
    "\n",
    "%load_ext autoreload\n",
    "%autoreload 2\n",
    "\n",
    "from importlib.util import find_spec\n",
    "if find_spec(\"text_recognizer\") is None:\n",
    "    import sys\n",
    "    sys.path.append('..')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "ccdb6dde-47e5-429a-88f2-0764fb7e259a",
   "metadata": {
    "tags": []
   },
   "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": "3cf50475-39f2-4642-a7d1-5bcbc0a036f7",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "path = \"../training/conf/network/convnext.yaml\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 64,
   "id": "e52ecb01-c975-4e55-925d-1182c7aea473",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "with open(path, \"rb\") as f:\n",
    "    cfg = OmegaConf.load(f)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 65,
   "id": "f939aa37-7b1d-45cc-885c-323c4540bda1",
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'_target_': 'text_recognizer.network.convnext.convnext.ConvNext', 'dim': 8, 'dim_mults': [2, 8], 'depths': [2, 2], 'attn': {'_target_': 'text_recognizer.network.convnext.transformer.Transformer', 'attn': {'_target_': 'text_recognizer.network.convnext.transformer.Attention', 'dim': 64, 'heads': 4, 'dim_head': 64, 'scale': 8}, 'ff': {'_target_': 'text_recognizer.network.convnext.transformer.FeedForward', 'dim': 64, 'mult': 4}}}"
      ]
     },
     "execution_count": 65,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "cfg"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 66,
   "id": "c9589350",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "net = instantiate(cfg)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 67,
   "id": "618b997c-e6a6-4487-b70c-9d260cb556d3",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "from torchinfo import summary"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 68,
   "id": "25759b7b-8deb-4163-b75d-a1357c9fe88f",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "====================================================================================================\n",
       "Layer (type:depth-idx)                             Output Shape              Param #\n",
       "====================================================================================================\n",
       "ConvNext                                           [2, 64, 14, 256]          --\n",
       "├─Conv2d: 1-1                                      [2, 8, 56, 1024]          400\n",
       "├─ModuleList: 1-2                                  --                        30,512\n",
       "├─Transformer: 1-3                                 [2, 64, 14, 256]          98,688\n",
       "├─LayerNorm: 1-4                                   [2, 64, 14, 256]          64\n",
       "====================================================================================================\n",
       "Total params: 129,664\n",
       "Trainable params: 129,664\n",
       "Non-trainable params: 0\n",
       "Total mult-adds (G): 2.00\n",
       "====================================================================================================\n",
       "Input size (MB): 0.46\n",
       "Forward/backward pass size (MB): 260.57\n",
       "Params size (MB): 0.52\n",
       "Estimated Total Size (MB): 261.55\n",
       "===================================================================================================="
      ]
     },
     "execution_count": 68,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "summary(net, (2, 1, 56, 1024), device=\"cpu\", depth=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "05c1d499",
   "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": "3.9.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}