{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "3DR-eO17geWu"
   },
   "source": [
    "## Image Recognition Model With CNN"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "EMefrVPCg-60"
   },
   "source": [
    "### Importing the libraries"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {
    "id": "w3mybNcNuyRf"
   },
   "outputs": [],
   "source": [
    "import tensorflow as tf\n",
    "from keras.preprocessing.image import ImageDataGenerator"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 38
    },
    "id": "Gk81TsV3vNYv",
    "outputId": "ac51f686-a76e-4be8-ae56-5db116913a8b"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'2.15.0'"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "tf.__version__"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "oxQxCBWyoGPE"
   },
   "source": [
    "## Part 1 - Data Preprocessing"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "MvE-heJNo3GG"
   },
   "source": [
    "### Preprocessing the Training set"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "id": "IZPgIbSyzcZz"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Found 8000 images belonging to 2 classes.\n"
     ]
    }
   ],
   "source": [
    "train_datagen = ImageDataGenerator(rescale = 1./255,\n",
    "                                   shear_range = 0.2,\n",
    "                                   zoom_range = 0.2,\n",
    "                                   horizontal_flip = True)\n",
    "training_set = train_datagen.flow_from_directory('dataset/training_set',\n",
    "                                                 target_size = (64, 64),\n",
    "                                                 batch_size = 32,\n",
    "                                                 class_mode = 'binary')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "mrCMmGw9pHys"
   },
   "source": [
    "### Preprocessing the Test set"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "id": "qTwLxo10zn-P"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Found 2000 images belonging to 2 classes.\n"
     ]
    }
   ],
   "source": [
    "test_datagen = ImageDataGenerator(rescale = 1./255)\n",
    "test_set = test_datagen.flow_from_directory('dataset/test_set',\n",
    "                                            target_size = (64, 64),\n",
    "                                            batch_size = 32,\n",
    "                                            class_mode = 'binary')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "af8O4l90gk7B"
   },
   "source": [
    "## Part 2 - Building the CNN"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "ces1gXY2lmoX"
   },
   "source": [
    "### Initialising the CNN"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "id": "OywsP_gTz8VA"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "WARNING:tensorflow:From C:\\Users\\manik\\anaconda3\\Lib\\site-packages\\keras\\src\\backend.py:873: The name tf.get_default_graph is deprecated. Please use tf.compat.v1.get_default_graph instead.\n",
      "\n"
     ]
    }
   ],
   "source": [
    "cnn=tf.keras.models.Sequential()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "u5YJj_XMl5LF"
   },
   "source": [
    "### Step 1 - Convolution"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "id": "dkA5f15L0IRA"
   },
   "outputs": [],
   "source": [
    "cnn.add(tf.keras.layers.Conv2D(filters=32,kernel_size=3,activation='relu',input_shape=[64,64,3]))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "tf87FpvxmNOJ"
   },
   "source": [
    "### Step 2 - Pooling"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "id": "Khzh28Gj056f"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "WARNING:tensorflow:From C:\\Users\\manik\\anaconda3\\Lib\\site-packages\\keras\\src\\layers\\pooling\\max_pooling2d.py:161: The name tf.nn.max_pool is deprecated. Please use tf.nn.max_pool2d instead.\n",
      "\n"
     ]
    }
   ],
   "source": [
    "cnn.add(tf.keras.layers.MaxPool2D(pool_size=2,strides=2))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "xaTOgD8rm4mU"
   },
   "source": [
    "### Adding a second convolutional layer"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "id": "G7GvlV8W1zFv"
   },
   "outputs": [],
   "source": [
    "cnn.add(tf.keras.layers.Conv2D(filters=32,kernel_size=3,activation='relu'))\n",
    "cnn.add(tf.keras.layers.MaxPool2D(pool_size=2,strides=2))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "tmiEuvTunKfk"
   },
   "source": [
    "### Step 3 - Flattening"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {
    "id": "CgmlA6xs16ub"
   },
   "outputs": [],
   "source": [
    "cnn.add(tf.keras.layers.Flatten())"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "dAoSECOm203v"
   },
   "source": [
    "### Step 4 - Full Connection"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {
    "id": "1DXEM0C-2Cv6"
   },
   "outputs": [],
   "source": [
    "cnn.add(tf.keras.layers.Dense(units=128,activation='relu'))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "yTldFvbX28Na"
   },
   "source": [
    "### Step 5 - Output Layer"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {
    "id": "bM9tOMr02dTk"
   },
   "outputs": [],
   "source": [
    "cnn.add(tf.keras.layers.Dense(units=1,activation='sigmoid'))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "D6XkI90snSDl"
   },
   "source": [
    "## Part 3 - Training the CNN"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "vfrFQACEnc6i"
   },
   "source": [
    "### Compiling the CNN"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {
    "id": "QRSs7B252tM8"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "WARNING:tensorflow:From C:\\Users\\manik\\anaconda3\\Lib\\site-packages\\keras\\src\\optimizers\\__init__.py:309: The name tf.train.Optimizer is deprecated. Please use tf.compat.v1.train.Optimizer instead.\n",
      "\n"
     ]
    }
   ],
   "source": [
    "cnn.compile(optimizer='adam',loss='binary_crossentropy',metrics=['accuracy'])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "ehS-v3MIpX2h"
   },
   "source": [
    "### Training the CNN on the Training set and evaluating it on the Test set"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {
    "id": "ibgjSnzf3Mai"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 1/25\n",
      "WARNING:tensorflow:From C:\\Users\\manik\\anaconda3\\Lib\\site-packages\\keras\\src\\utils\\tf_utils.py:492: The name tf.ragged.RaggedTensorValue is deprecated. Please use tf.compat.v1.ragged.RaggedTensorValue instead.\n",
      "\n",
      "WARNING:tensorflow:From C:\\Users\\manik\\anaconda3\\Lib\\site-packages\\keras\\src\\engine\\base_layer_utils.py:384: The name tf.executing_eagerly_outside_functions is deprecated. Please use tf.compat.v1.executing_eagerly_outside_functions instead.\n",
      "\n",
      "250/250 [==============================] - 75s 298ms/step - loss: 0.6505 - accuracy: 0.6121 - val_loss: 0.5777 - val_accuracy: 0.7080\n",
      "Epoch 2/25\n",
      "250/250 [==============================] - 30s 121ms/step - loss: 0.5849 - accuracy: 0.6865 - val_loss: 0.5398 - val_accuracy: 0.7290\n",
      "Epoch 3/25\n",
      "250/250 [==============================] - 30s 121ms/step - loss: 0.5501 - accuracy: 0.7189 - val_loss: 0.5827 - val_accuracy: 0.6865\n",
      "Epoch 4/25\n",
      "250/250 [==============================] - 30s 122ms/step - loss: 0.5212 - accuracy: 0.7369 - val_loss: 0.5147 - val_accuracy: 0.7455\n",
      "Epoch 5/25\n",
      "250/250 [==============================] - 30s 119ms/step - loss: 0.4896 - accuracy: 0.7613 - val_loss: 0.5152 - val_accuracy: 0.7550\n",
      "Epoch 6/25\n",
      "250/250 [==============================] - 30s 120ms/step - loss: 0.4721 - accuracy: 0.7770 - val_loss: 0.4776 - val_accuracy: 0.7640\n",
      "Epoch 7/25\n",
      "250/250 [==============================] - 30s 121ms/step - loss: 0.4506 - accuracy: 0.7826 - val_loss: 0.4668 - val_accuracy: 0.7845\n",
      "Epoch 8/25\n",
      "250/250 [==============================] - 32s 126ms/step - loss: 0.4380 - accuracy: 0.7868 - val_loss: 0.4637 - val_accuracy: 0.7870\n",
      "Epoch 9/25\n",
      "250/250 [==============================] - 30s 121ms/step - loss: 0.4231 - accuracy: 0.8026 - val_loss: 0.4680 - val_accuracy: 0.7850\n",
      "Epoch 10/25\n",
      "250/250 [==============================] - 30s 120ms/step - loss: 0.4048 - accuracy: 0.8135 - val_loss: 0.5443 - val_accuracy: 0.7470\n",
      "Epoch 11/25\n",
      "250/250 [==============================] - 30s 120ms/step - loss: 0.3917 - accuracy: 0.8242 - val_loss: 0.4698 - val_accuracy: 0.7875\n",
      "Epoch 12/25\n",
      "250/250 [==============================] - 37s 148ms/step - loss: 0.3743 - accuracy: 0.8284 - val_loss: 0.4812 - val_accuracy: 0.7940\n",
      "Epoch 13/25\n",
      "250/250 [==============================] - 30s 120ms/step - loss: 0.3720 - accuracy: 0.8317 - val_loss: 0.4309 - val_accuracy: 0.8140\n",
      "Epoch 14/25\n",
      "250/250 [==============================] - 30s 120ms/step - loss: 0.3497 - accuracy: 0.8443 - val_loss: 0.4593 - val_accuracy: 0.7980\n",
      "Epoch 15/25\n",
      "250/250 [==============================] - 30s 121ms/step - loss: 0.3407 - accuracy: 0.8514 - val_loss: 0.4699 - val_accuracy: 0.7925\n",
      "Epoch 16/25\n",
      "250/250 [==============================] - 30s 121ms/step - loss: 0.3249 - accuracy: 0.8593 - val_loss: 0.4712 - val_accuracy: 0.8035\n",
      "Epoch 17/25\n",
      "250/250 [==============================] - 30s 122ms/step - loss: 0.3044 - accuracy: 0.8748 - val_loss: 0.4846 - val_accuracy: 0.8060\n",
      "Epoch 18/25\n",
      "250/250 [==============================] - 30s 120ms/step - loss: 0.3082 - accuracy: 0.8608 - val_loss: 0.4750 - val_accuracy: 0.8040\n",
      "Epoch 19/25\n",
      "250/250 [==============================] - 30s 121ms/step - loss: 0.2860 - accuracy: 0.8752 - val_loss: 0.4533 - val_accuracy: 0.8180\n",
      "Epoch 20/25\n",
      "250/250 [==============================] - 30s 120ms/step - loss: 0.2761 - accuracy: 0.8792 - val_loss: 0.5786 - val_accuracy: 0.7975\n",
      "Epoch 21/25\n",
      "250/250 [==============================] - 30s 120ms/step - loss: 0.2634 - accuracy: 0.8861 - val_loss: 0.4989 - val_accuracy: 0.8085\n",
      "Epoch 22/25\n",
      "250/250 [==============================] - 30s 120ms/step - loss: 0.2491 - accuracy: 0.8946 - val_loss: 0.5098 - val_accuracy: 0.8160\n",
      "Epoch 23/25\n",
      "250/250 [==============================] - 31s 124ms/step - loss: 0.2385 - accuracy: 0.8981 - val_loss: 0.5296 - val_accuracy: 0.8115\n",
      "Epoch 24/25\n",
      "250/250 [==============================] - 30s 120ms/step - loss: 0.2260 - accuracy: 0.9040 - val_loss: 0.5117 - val_accuracy: 0.8105\n",
      "Epoch 25/25\n",
      "250/250 [==============================] - 30s 121ms/step - loss: 0.2117 - accuracy: 0.9146 - val_loss: 0.5145 - val_accuracy: 0.8180\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "<keras.src.callbacks.History at 0x1f3d5467610>"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "cnn.fit(x=training_set,validation_data=test_set,epochs=25)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "U3PZasO0006Z"
   },
   "source": [
    "## Part 4 - Making a single prediction"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {
    "id": "PQGfPACq3mGS"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "1/1 [==============================] - 0s 107ms/step\n"
     ]
    }
   ],
   "source": [
    "import numpy as np\n",
    "from keras.preprocessing import image\n",
    "test_image=image.load_img('dataset/single_prediction/cat_or_dog_1.jpg',target_size=(64,64))\n",
    "test_image=image.img_to_array(test_image)\n",
    "test_image=np.expand_dims(test_image,axis=0)\n",
    "result=cnn.predict(test_image)\n",
    "training_set.class_indices\n",
    "if result[0][0]==1:\n",
    "  prediction='dog'\n",
    "else:\n",
    "  prediction='cat'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {
    "id": "xMvlNcFN5yEX"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "dog\n"
     ]
    }
   ],
   "source": [
    "print(prediction)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "1/1 [==============================] - 0s 25ms/step\n"
     ]
    }
   ],
   "source": [
    "import numpy as np\n",
    "from keras.preprocessing import image\n",
    "test_image=image.load_img('dataset/single_prediction/cat_or_dog_2.jpg',target_size=(64,64))\n",
    "test_image=image.img_to_array(test_image)\n",
    "test_image=np.expand_dims(test_image,axis=0)\n",
    "result=cnn.predict(test_image)\n",
    "training_set.class_indices\n",
    "if result[0][0]==1:\n",
    "  prediction='dog'\n",
    "else:\n",
    "  prediction='cat'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "cat\n"
     ]
    }
   ],
   "source": [
    "print(prediction)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "1/1 [==============================] - 0s 26ms/step\n"
     ]
    }
   ],
   "source": [
    "import numpy as np\n",
    "from keras.preprocessing import image\n",
    "test_image=image.load_img('dataset/single_prediction/cat_or_dog_3.jpg',target_size=(64,64))\n",
    "test_image=image.img_to_array(test_image)\n",
    "test_image=np.expand_dims(test_image,axis=0)\n",
    "result=cnn.predict(test_image)\n",
    "training_set.class_indices\n",
    "if result[0][0]==1:\n",
    "  prediction='dog'\n",
    "else:\n",
    "  prediction='cat'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "cat\n"
     ]
    }
   ],
   "source": [
    "print(prediction)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "1/1 [==============================] - 0s 25ms/step\n"
     ]
    }
   ],
   "source": [
    "import numpy as np\n",
    "from keras.preprocessing import image\n",
    "test_image=image.load_img('dataset/single_prediction/cat_or_dog_4.jpg',target_size=(64,64))\n",
    "test_image=image.img_to_array(test_image)\n",
    "test_image=np.expand_dims(test_image,axis=0)\n",
    "result=cnn.predict(test_image)\n",
    "training_set.class_indices\n",
    "if result[0][0]==1:\n",
    "  prediction='dog'\n",
    "else:\n",
    "  prediction='cat'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "dog\n"
     ]
    }
   ],
   "source": [
    "print(prediction)"
   ]
  }
 ],
 "metadata": {
  "colab": {
   "provenance": []
  },
  "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": "3.11.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 1
}