Advanced Level Task 3 - Handwritten equation solver using CNN Part-2.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "import pickle\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {},
   "outputs": [],
   "source": [
    "df_train = pd.read_csv('C://Users//Asus//OneDrive//Desktop//LGMVIP//Advanced Level Task 3//train_final.csv', index_col=False)\n",
    "labels=df_train[['784']]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "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>0</th>\n",
       "      <th>1</th>\n",
       "      <th>2</th>\n",
       "      <th>3</th>\n",
       "      <th>4</th>\n",
       "      <th>5</th>\n",
       "      <th>6</th>\n",
       "      <th>7</th>\n",
       "      <th>8</th>\n",
       "      <th>9</th>\n",
       "      <th>...</th>\n",
       "      <th>774</th>\n",
       "      <th>775</th>\n",
       "      <th>776</th>\n",
       "      <th>777</th>\n",
       "      <th>778</th>\n",
       "      <th>779</th>\n",
       "      <th>780</th>\n",
       "      <th>781</th>\n",
       "      <th>782</th>\n",
       "      <th>783</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>255</td>\n",
       "      <td>255</td>\n",
       "      <td>255</td>\n",
       "      <td>255</td>\n",
       "      <td>255</td>\n",
       "      <td>255</td>\n",
       "      <td>255</td>\n",
       "      <td>255</td>\n",
       "      <td>255</td>\n",
       "      <td>255</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>255</td>\n",
       "      <td>255</td>\n",
       "      <td>255</td>\n",
       "      <td>255</td>\n",
       "      <td>255</td>\n",
       "      <td>255</td>\n",
       "      <td>255</td>\n",
       "      <td>255</td>\n",
       "      <td>255</td>\n",
       "      <td>255</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>255</td>\n",
       "      <td>255</td>\n",
       "      <td>255</td>\n",
       "      <td>255</td>\n",
       "      <td>255</td>\n",
       "      <td>255</td>\n",
       "      <td>255</td>\n",
       "      <td>255</td>\n",
       "      <td>255</td>\n",
       "      <td>255</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>255</td>\n",
       "      <td>255</td>\n",
       "      <td>255</td>\n",
       "      <td>255</td>\n",
       "      <td>255</td>\n",
       "      <td>255</td>\n",
       "      <td>255</td>\n",
       "      <td>255</td>\n",
       "      <td>255</td>\n",
       "      <td>255</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>255</td>\n",
       "      <td>255</td>\n",
       "      <td>255</td>\n",
       "      <td>255</td>\n",
       "      <td>255</td>\n",
       "      <td>255</td>\n",
       "      <td>255</td>\n",
       "      <td>255</td>\n",
       "      <td>255</td>\n",
       "      <td>255</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 784 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     0    1    2    3    4    5    6    7    8    9  ...  774  775  776  777  \\\n",
       "0  255  255  255  255  255  255  255  255  255  255  ...    0    0    0    0   \n",
       "1  255  255  255  255  255  255  255  255  255  255  ...    0    0    0    0   \n",
       "2  255  255  255  255  255  255  255  255  255  255  ...    0    0    0    0   \n",
       "3  255  255  255  255  255  255  255  255  255  255  ...    0    0    0    0   \n",
       "4  255  255  255  255  255  255  255  255  255  255  ...    0    0    0    0   \n",
       "\n",
       "   778  779  780  781  782  783  \n",
       "0    0    0    0    0    0    0  \n",
       "1    0    0    0    0    0    0  \n",
       "2    0    0    0    0    0    0  \n",
       "3    0    0    0    0    0    0  \n",
       "4    0    0    0    0    0    0  \n",
       "\n",
       "[5 rows x 784 columns]"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_train.drop(df_train.columns[[784]], axis=1, inplace=True)\n",
    "df_train.head()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'channels_last'"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from keras import backend as K\n",
    "from keras.utils import np_utils\n",
    "from keras.layers.convolutional import MaxPooling2D\n",
    "from keras.layers.convolutional import Conv2D\n",
    "from keras.layers import Flatten\n",
    "from keras.layers import Dropout\n",
    "from keras.layers import Dense\n",
    "from keras.models import Sequential\n",
    "from keras.layers import Input, Dense\n",
    "from keras import optimizers\n",
    "from keras.layers import *\n",
    "from keras.models import Model\n",
    "import keras\n",
    "np.random.seed(1212)\n",
    "K.image_data_format()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "labels=np.array(labels)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "from keras.utils.np_utils import to_categorical\n",
    "cat=to_categorical(labels,num_classes=13)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 1. 0. 0.]\n"
     ]
    }
   ],
   "source": [
    "print(cat[0])\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "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>0</th>\n",
       "      <th>1</th>\n",
       "      <th>2</th>\n",
       "      <th>3</th>\n",
       "      <th>4</th>\n",
       "      <th>5</th>\n",
       "      <th>6</th>\n",
       "      <th>7</th>\n",
       "      <th>8</th>\n",
       "      <th>9</th>\n",
       "      <th>...</th>\n",
       "      <th>774</th>\n",
       "      <th>775</th>\n",
       "      <th>776</th>\n",
       "      <th>777</th>\n",
       "      <th>778</th>\n",
       "      <th>779</th>\n",
       "      <th>780</th>\n",
       "      <th>781</th>\n",
       "      <th>782</th>\n",
       "      <th>783</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>255</td>\n",
       "      <td>255</td>\n",
       "      <td>255</td>\n",
       "      <td>255</td>\n",
       "      <td>255</td>\n",
       "      <td>255</td>\n",
       "      <td>255</td>\n",
       "      <td>255</td>\n",
       "      <td>255</td>\n",
       "      <td>255</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>255</td>\n",
       "      <td>255</td>\n",
       "      <td>255</td>\n",
       "      <td>255</td>\n",
       "      <td>255</td>\n",
       "      <td>255</td>\n",
       "      <td>255</td>\n",
       "      <td>255</td>\n",
       "      <td>255</td>\n",
       "      <td>255</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>255</td>\n",
       "      <td>255</td>\n",
       "      <td>255</td>\n",
       "      <td>255</td>\n",
       "      <td>255</td>\n",
       "      <td>255</td>\n",
       "      <td>255</td>\n",
       "      <td>255</td>\n",
       "      <td>255</td>\n",
       "      <td>255</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>255</td>\n",
       "      <td>255</td>\n",
       "      <td>255</td>\n",
       "      <td>255</td>\n",
       "      <td>255</td>\n",
       "      <td>255</td>\n",
       "      <td>255</td>\n",
       "      <td>255</td>\n",
       "      <td>255</td>\n",
       "      <td>255</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>255</td>\n",
       "      <td>255</td>\n",
       "      <td>255</td>\n",
       "      <td>255</td>\n",
       "      <td>255</td>\n",
       "      <td>255</td>\n",
       "      <td>255</td>\n",
       "      <td>255</td>\n",
       "      <td>255</td>\n",
       "      <td>255</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 784 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     0    1    2    3    4    5    6    7    8    9  ...  774  775  776  777  \\\n",
       "0  255  255  255  255  255  255  255  255  255  255  ...    0    0    0    0   \n",
       "1  255  255  255  255  255  255  255  255  255  255  ...    0    0    0    0   \n",
       "2  255  255  255  255  255  255  255  255  255  255  ...    0    0    0    0   \n",
       "3  255  255  255  255  255  255  255  255  255  255  ...    0    0    0    0   \n",
       "4  255  255  255  255  255  255  255  255  255  255  ...    0    0    0    0   \n",
       "\n",
       "   778  779  780  781  782  783  \n",
       "0    0    0    0    0    0    0  \n",
       "1    0    0    0    0    0    0  \n",
       "2    0    0    0    0    0    0  \n",
       "3    0    0    0    0    0    0  \n",
       "4    0    0    0    0    0    0  \n",
       "\n",
       "[5 rows x 784 columns]"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_train.head()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(184638, 784)"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_train.shape\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [],
   "source": [
    "temp=df_train.to_numpy()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [],
   "source": [
    "X_train = temp.reshape(temp.shape[0], 28, 28, 1)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "184638"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "temp.shape[0]\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(184638, 28, 28, 1)"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X_train.shape\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [],
   "source": [
    "l=[]\n",
    "for i in range(47504):\n",
    "    l.append(np.array(df_train[i:i+1]).reshape(1,28,28))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [],
   "source": [
    "np.random.seed(7)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "1"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "\n",
    "len(l[0])\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(184638, 28, 28, 1)"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X_train.shape\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [],
   "source": [
    "model = Sequential()\n",
    "model.add(Conv2D(32, (3, 3), input_shape=(28, 28, 1),\n",
    "          activation='relu', padding='same'))\n",
    "model.add(MaxPooling2D(pool_size=(2, 2)))\n",
    "model.add(Conv2D(15, (3, 3), activation='relu'))\n",
    "model.add(MaxPooling2D(pool_size=(2, 2)))\n",
    "model.add(Dropout(0.2))\n",
    "model.add(Flatten())\n",
    "model.add(Dense(128, activation='relu'))\n",
    "model.add(Dense(50, activation='relu'))\n",
    "model.add(Dense(13, activation='softmax'))\n",
    "# Compile model\n",
    "model.compile(loss='categorical_crossentropy',\n",
    "              optimizer='adam', metrics=['accuracy'])\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [],
   "source": [
    "from keras.models import model_from_json\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 1/10\n",
      "924/924 [==============================] - 62s 66ms/step - loss: 0.3673 - accuracy: 0.9039\n",
      "Epoch 2/10\n",
      "924/924 [==============================] - 58s 63ms/step - loss: 0.0882 - accuracy: 0.9667\n",
      "Epoch 3/10\n",
      "924/924 [==============================] - 57s 62ms/step - loss: 0.0612 - accuracy: 0.9735\n",
      "Epoch 4/10\n",
      "924/924 [==============================] - 57s 61ms/step - loss: 0.0517 - accuracy: 0.9757\n",
      "Epoch 5/10\n",
      "924/924 [==============================] - 56s 61ms/step - loss: 0.0453 - accuracy: 0.9771\n",
      "Epoch 6/10\n",
      "924/924 [==============================] - 56s 60ms/step - loss: 0.0416 - accuracy: 0.9784\n",
      "Epoch 7/10\n",
      "924/924 [==============================] - 57s 62ms/step - loss: 0.0388 - accuracy: 0.9789\n",
      "Epoch 8/10\n",
      "924/924 [==============================] - 59s 64ms/step - loss: 0.0367 - accuracy: 0.9797\n",
      "Epoch 9/10\n",
      "924/924 [==============================] - 54s 58ms/step - loss: 0.0351 - accuracy: 0.9801\n",
      "Epoch 10/10\n",
      "924/924 [==============================] - 49s 53ms/step - loss: 0.0329 - accuracy: 0.9809\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "<keras.callbacks.History at 0x1a5ce68dbe0>"
      ]
     },
     "execution_count": 21,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "model.fit(X_train, cat, epochs=10, batch_size=200,shuffle=True,verbose=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [],
   "source": [
    "\n",
    "model_json = model.to_json()\n",
    "with open(\"model_final.json\", \"w\") as json_file:\n",
    "    json_file.write(model_json)\n",
    "# serialize weights to HDF5\n",
    "model.save_weights(\"model_final.h5\")\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [],
   "source": [
    "import cv2\n",
    "import numpy\n",
    "from keras.datasets import mnist\n",
    "from keras.models import Sequential\n",
    "from keras.layers import Dense\n",
    "from keras.layers import Dropout\n",
    "from keras.layers import Flatten\n",
    "from keras.layers.convolutional import Conv2D\n",
    "from keras.layers.convolutional import MaxPooling2D\n",
    "from keras.utils import np_utils\n",
    "from keras import backend as K\n",
    "# K.set_image_dim_ordering('th')\n",
    "from keras.models import model_from_json\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [],
   "source": [
    "json_file = open('model_final.json', 'r')\n",
    "loaded_model_json = json_file.read()\n",
    "json_file.close()\n",
    "loaded_model = model_from_json(loaded_model_json)\n",
    "# load weights into new model\n",
    "loaded_model.load_weights(\"model_final.h5\")\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [],
   "source": [
    "import cv2\n",
    "import numpy as np\n",
    "img = cv2.imread('test.jpg',cv2.IMREAD_GRAYSCALE)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {},
   "outputs": [],
   "source": [
    "img\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "metadata": {},
   "outputs": [],
   "source": [
    "if img is not None:\n",
    "    #images.append(img)\n",
    "    img = ~img\n",
    "    ret, thresh = cv2.threshold(img, 127, 255, cv2.THRESH_BINARY)\n",
    "    ctrs, ret = cv2.findContours(\n",
    "        thresh, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)\n",
    "    cnt = sorted(ctrs, key=lambda ctr: cv2.boundingRect(ctr)[0])\n",
    "    w = int(28)\n",
    "    h = int(28)\n",
    "    train_data = []\n",
    "    print(len(cnt))\n",
    "    rects = []\n",
    "    for c in cnt:\n",
    "        x, y, w, h = cv2.boundingRect(c)\n",
    "        rect = [x, y, w, h]\n",
    "        rects.append(rect)\n",
    "    print(rects)\n",
    "    bool_rect = []\n",
    "    for r in rects:\n",
    "        l = []\n",
    "        for rec in rects:\n",
    "            flag = 0\n",
    "            if rec != r:\n",
    "                if r[0] < (rec[0]+rec[2]+10) and rec[0] < (r[0]+r[2]+10) and r[1] < (rec[1]+rec[3]+10) and rec[1] < (r[1]+r[3]+10):\n",
    "                    flag = 1\n",
    "                l.append(flag)\n",
    "            if rec == r:\n",
    "                l.append(0)\n",
    "        bool_rect.append(l)\n",
    "    print(bool_rect)\n",
    "    dump_rect = []\n",
    "    for i in range(0, len(cnt)):\n",
    "        for j in range(0, len(cnt)):\n",
    "            if bool_rect[i][j] == 1:\n",
    "                area1 = rects[i][2]*rects[i][3]\n",
    "                area2 = rects[j][2]*rects[j][3]\n",
    "                if(area1 == min(area1, area2)):\n",
    "                    dump_rect.append(rects[i])\n",
    "    print(len(dump_rect))\n",
    "    final_rect = [i for i in rects if i not in dump_rect]\n",
    "    print(final_rect)\n",
    "    for r in final_rect:\n",
    "        x = r[0]\n",
    "        y = r[1]\n",
    "        w = r[2]\n",
    "        h = r[3]\n",
    "        im_crop = thresh[y:y+h+10, x:x+w+10]\n",
    "\n",
    "        im_resize = cv2.resize(im_crop, (28, 28))\n",
    "\n",
    "        im_resize = np.reshape(im_resize, (28, 28, 1))\n",
    "        train_data.append(im_resize)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n"
     ]
    }
   ],
   "source": [
    "s = ''\n",
    "for i in range(len(train_data)):\n",
    "    train_data[i] = np.array(train_data[i])\n",
    "    train_data[i] = train_data[i].reshape(1, 28, 28, 1)\n",
    "    #result=loaded_model.predict_classes(train_data[i])\n",
    "    result = np.argmax(loaded_model.predict(train_data[i]), axis=-1)\n",
    "    if(result[0] == 10):\n",
    "        s = s+'-'\n",
    "    if(result[0] == 11):\n",
    "        s = s+'+'\n",
    "    if(result[0] == 12):\n",
    "        s = s+'*'\n",
    "    if(result[0] == 0):\n",
    "        s = s+'0'\n",
    "    if(result[0] == 1):\n",
    "        s = s+'1'\n",
    "    if(result[0] == 2):\n",
    "        s = s+'2'\n",
    "    if(result[0] == 3):\n",
    "        s = s+'3'\n",
    "    if(result[0] == 4):\n",
    "        s = s+'4'\n",
    "    if(result[0] == 5):\n",
    "        s = s+'5'\n",
    "    if(result[0] == 6):\n",
    "        s = s+'6'\n",
    "    if(result[0] == 7):\n",
    "        s = s+'7'\n",
    "    if(result[0] == 8):\n",
    "        s = s+'8'\n",
    "    if(result[0] == 9):\n",
    "        s = s+'9'\n",
    "\n",
    "print(s)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3.9.12 ('base')",
   "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": "3.9.12"
  },
  "orig_nbformat": 4,
  "vscode": {
   "interpreter": {
    "hash": "ad2bdc8ecc057115af97d19610ffacc2b4e99fae6737bb82f5d7fb13d2f2c186"
   }
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}