kiransair/image_recognition.ipynb Secret

## image_recognition.ipynb
{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "provenance": [],
      "authorship_tag": "ABX9TyOBL6iWPL3+DTNM5IEO0uNG",
      "include_colab_link": true
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    }
  },
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "view-in-github",
        "colab_type": "text"
      },
      "source": [
        "<a href=\"https://colab.research.google.com/gist/kiransair/7a939904394891e9f0b7da4c32ced7d3/image_recognition.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 1,
      "metadata": {
        "id": "ZjHcoyw_xKYy"
      },
      "outputs": [],
      "source": [
        "import tensorflow as tf"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "from tensorflow.keras import datasets, layers, models\n",
        "import matplotlib.pyplot as plt"
      ],
      "metadata": {
        "id": "zoRMHHiDyWz9"
      },
      "execution_count": 2,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "(train_images, train_labels), (test_images, test_labels) = datasets.cifar10.load_data()\n",
        "\n",
        "# Normalize pixel values to be between 0 and 1\n",
        "train_images, test_images = train_images / 255.0, test_images / 255.0"
      ],
      "metadata": {
        "id": "naph6z7s89H4",
        "outputId": "1759c125-c521-411c-933e-739362e1b8d4",
        "colab": {
          "base_uri": "https://localhost:8080/"
        }
      },
      "execution_count": 3,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Downloading data from https://www.cs.toronto.edu/~kriz/cifar-10-python.tar.gz\n",
            "170498071/170498071 [==============================] - 2s 0us/step\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "class_names = ['airplane', 'automobile', 'bird', 'cat', 'deer',\n",
        "               'dog', 'frog', 'horse', 'ship', 'truck']"
      ],
      "metadata": {
        "id": "PZEj9t_R9BoC"
      },
      "execution_count": 4,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "from tensorflow import keras"
      ],
      "metadata": {
        "id": "ANxzFZVMYqLC"
      },
      "execution_count": 5,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "model1=keras.Sequential([\n",
        "                        keras.Input(shape=(32,32,3),),\n",
        "                        keras.layers.Conv2D(32,kernel_size=(3,3),activation='relu',),\n",
        "                        keras.layers.MaxPooling2D(pool_size=(2,2)),\n",
        "                        keras.layers.Conv2D(64,kernel_size=(3,3),activation='relu'),\n",
        "                        keras.layers.MaxPooling2D(pool_size=(2,2)),\n",
        "                        keras.layers.Flatten(),\n",
        "                        keras.layers.Dropout(0.5),\n",
        "                        keras.layers.Dense(10,activation='softmax')])"
      ],
      "metadata": {
        "id": "EhO6uFD-YO6A"
      },
      "execution_count": 7,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "model1.compile(loss=\"sparse_categorical_crossentropy\", optimizer='adam',metrics=['accuracy'])"
      ],
      "metadata": {
        "id": "E6YPY2UDY8R9"
      },
      "execution_count": 8,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "train_images[0].shape"
      ],
      "metadata": {
        "id": "U_LZiEz_8YIc",
        "outputId": "25087ad6-90df-48f4-bf6f-6ad6f528fe6c",
        "colab": {
          "base_uri": "https://localhost:8080/"
        }
      },
      "execution_count": 11,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(32, 32, 3)"
            ]
          },
          "metadata": {},
          "execution_count": 11
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "train_labels[0].shape"
      ],
      "metadata": {
        "id": "dWkWILg28oMV",
        "outputId": "aa6323c8-bb0d-49b3-af00-f75fa6e1eb5d",
        "colab": {
          "base_uri": "https://localhost:8080/"
        }
      },
      "execution_count": 12,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(1,)"
            ]
          },
          "metadata": {},
          "execution_count": 12
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "model1.fit(train_images, train_labels, epochs=3)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "kquvqOEFYlRh",
        "outputId": "74059bf3-6b6b-4e9e-f214-c842c5eab49c"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Epoch 1/3\n",
            "1563/1563 [==============================] - 66s 42ms/step - loss: 1.5374 - accuracy: 0.4480\n",
            "Epoch 2/3\n",
            "1563/1563 [==============================] - 63s 40ms/step - loss: 1.2557 - accuracy: 0.5590\n",
            "Epoch 3/3\n",
            "1563/1563 [==============================] - 66s 43ms/step - loss: 1.1509 - accuracy: 0.5975\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "<keras.callbacks.History at 0x7f0b55085ee0>"
            ]
          },
          "metadata": {},
          "execution_count": 16
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "pred=model1.predict(test_images)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "34EDQnHLY4ad",
        "outputId": "931bf4c1-0bf7-40af-f794-e1dac54a7c46"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "313/313 [==============================] - 5s 15ms/step\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "import numpy as np"
      ],
      "metadata": {
        "id": "jJR6BuT4bfZm"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "np.argmax(pred[0])"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "lrUAK-TjbJdw",
        "outputId": "20888674-46c2-4b46-b59a-efa8e0604ea9"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "3"
            ]
          },
          "metadata": {},
          "execution_count": 20
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "plt.imshow(test_images[0])"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 284
        },
        "id": "F5B9NvWVbazh",
        "outputId": "b1cf969a-caa7-4d83-e6b8-3d2617ee8251"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "<matplotlib.image.AxesImage at 0x7f0b4f3ac6d0>"
            ]
          },
          "metadata": {},
          "execution_count": 23
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 432x288 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {
            "needs_background": "light"
          }
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "class_names[3]"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 37
        },
        "id": "8wxBgyq_boS3",
        "outputId": "1e176fe9-4b98-4fec-c9a4-d506bc8491bb"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "'cat'"
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "string"
            }
          },
          "metadata": {},
          "execution_count": 24
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [],
      "metadata": {
        "id": "SQQTahPub-3r"
      },
      "execution_count": null,
      "outputs": []
    }
  ]
}
	{
	"nbformat": 4,
	"nbformat_minor": 0,
	"metadata": {
	"colab": {
	"provenance": [],
	"authorship_tag": "ABX9TyOBL6iWPL3+DTNM5IEO0uNG",
	"include_colab_link": true
	},
	"kernelspec": {
	"name": "python3",
	"display_name": "Python 3"
	},
	"language_info": {
	"name": "python"
	}
	},
	"cells": [
	{
	"cell_type": "markdown",
	"metadata": {
	"id": "view-in-github",
	"colab_type": "text"
	},
	"source": [
	"<a href=\"https://colab.research.google.com/gist/kiransair/7a939904394891e9f0b7da4c32ced7d3/image_recognition.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
	]
	},
	{
	"cell_type": "code",
	"execution_count": 1,
	"metadata": {
	"id": "ZjHcoyw_xKYy"
	},
	"outputs": [],
	"source": [
	"import tensorflow as tf"
	]
	},
	{
	"cell_type": "code",
	"source": [
	"from tensorflow.keras import datasets, layers, models\n",
	"import matplotlib.pyplot as plt"
	],
	"metadata": {
	"id": "zoRMHHiDyWz9"
	},
	"execution_count": 2,
	"outputs": []
	},
	{
	"cell_type": "code",
	"source": [
	"(train_images, train_labels), (test_images, test_labels) = datasets.cifar10.load_data()\n",
	"\n",
	"# Normalize pixel values to be between 0 and 1\n",
	"train_images, test_images = train_images / 255.0, test_images / 255.0"
	],
	"metadata": {
	"id": "naph6z7s89H4",
	"outputId": "1759c125-c521-411c-933e-739362e1b8d4",
	"colab": {
	"base_uri": "https://localhost:8080/"
	}
	},
	"execution_count": 3,
	"outputs": [
	{
	"output_type": "stream",
	"name": "stdout",
	"text": [
	"Downloading data from https://www.cs.toronto.edu/~kriz/cifar-10-python.tar.gz\n",
	"170498071/170498071 [==============================] - 2s 0us/step\n"
	]
	}
	]
	},
	{
	"cell_type": "code",
	"source": [
	"class_names = ['airplane', 'automobile', 'bird', 'cat', 'deer',\n",
	" 'dog', 'frog', 'horse', 'ship', 'truck']"
	],
	"metadata": {
	"id": "PZEj9t_R9BoC"
	},
	"execution_count": 4,
	"outputs": []
	},
	{
	"cell_type": "code",
	"source": [
	"from tensorflow import keras"
	],
	"metadata": {
	"id": "ANxzFZVMYqLC"
	},
	"execution_count": 5,
	"outputs": []
	},
	{
	"cell_type": "code",
	"source": [
	"model1=keras.Sequential([\n",
	" keras.Input(shape=(32,32,3),),\n",
	" keras.layers.Conv2D(32,kernel_size=(3,3),activation='relu',),\n",
	" keras.layers.MaxPooling2D(pool_size=(2,2)),\n",
	" keras.layers.Conv2D(64,kernel_size=(3,3),activation='relu'),\n",
	" keras.layers.MaxPooling2D(pool_size=(2,2)),\n",
	" keras.layers.Flatten(),\n",
	" keras.layers.Dropout(0.5),\n",
	" keras.layers.Dense(10,activation='softmax')])"
	],
	"metadata": {
	"id": "EhO6uFD-YO6A"
	},
	"execution_count": 7,
	"outputs": []
	},
	{
	"cell_type": "code",
	"source": [
	"model1.compile(loss=\"sparse_categorical_crossentropy\", optimizer='adam',metrics=['accuracy'])"
	],
	"metadata": {
	"id": "E6YPY2UDY8R9"
	},
	"execution_count": 8,
	"outputs": []
	},
	{
	"cell_type": "code",
	"source": [
	"train_images[0].shape"
	],
	"metadata": {
	"id": "U_LZiEz_8YIc",
	"outputId": "25087ad6-90df-48f4-bf6f-6ad6f528fe6c",
	"colab": {
	"base_uri": "https://localhost:8080/"
	}
	},
	"execution_count": 11,
	"outputs": [
	{
	"output_type": "execute_result",
	"data": {
	"text/plain": [
	"(32, 32, 3)"
	]
	},
	"metadata": {},
	"execution_count": 11
	}
	]
	},
	{
	"cell_type": "code",
	"source": [
	"train_labels[0].shape"
	],
	"metadata": {
	"id": "dWkWILg28oMV",
	"outputId": "aa6323c8-bb0d-49b3-af00-f75fa6e1eb5d",
	"colab": {
	"base_uri": "https://localhost:8080/"
	}
	},
	"execution_count": 12,
	"outputs": [
	{
	"output_type": "execute_result",
	"data": {
	"text/plain": [
	"(1,)"
	]
	},
	"metadata": {},
	"execution_count": 12
	}
	]
	},
	{
	"cell_type": "code",
	"source": [
	"model1.fit(train_images, train_labels, epochs=3)"
	],
	"metadata": {
	"colab": {
	"base_uri": "https://localhost:8080/"
	},
	"id": "kquvqOEFYlRh",
	"outputId": "74059bf3-6b6b-4e9e-f214-c842c5eab49c"
	},
	"execution_count": null,
	"outputs": [
	{
	"output_type": "stream",
	"name": "stdout",
	"text": [
	"Epoch 1/3\n",
	"1563/1563 [==============================] - 66s 42ms/step - loss: 1.5374 - accuracy: 0.4480\n",
	"Epoch 2/3\n",
	"1563/1563 [==============================] - 63s 40ms/step - loss: 1.2557 - accuracy: 0.5590\n",
	"Epoch 3/3\n",
	"1563/1563 [==============================] - 66s 43ms/step - loss: 1.1509 - accuracy: 0.5975\n"
	]
	},
	{
	"output_type": "execute_result",
	"data": {
	"text/plain": [
	"<keras.callbacks.History at 0x7f0b55085ee0>"
	]
	},
	"metadata": {},
	"execution_count": 16
	}
	]
	},
	{
	"cell_type": "code",
	"source": [
	"pred=model1.predict(test_images)"
	],
	"metadata": {
	"colab": {
	"base_uri": "https://localhost:8080/"
	},
	"id": "34EDQnHLY4ad",
	"outputId": "931bf4c1-0bf7-40af-f794-e1dac54a7c46"
	},
	"execution_count": null,
	"outputs": [
	{
	"output_type": "stream",
	"name": "stdout",
	"text": [
	"313/313 [==============================] - 5s 15ms/step\n"
	]
	}
	]
	},
	{
	"cell_type": "code",
	"source": [
	"import numpy as np"
	],
	"metadata": {
	"id": "jJR6BuT4bfZm"
	},
	"execution_count": null,
	"outputs": []
	},
	{
	"cell_type": "code",
	"source": [
	"np.argmax(pred[0])"
	],
	"metadata": {
	"colab": {
	"base_uri": "https://localhost:8080/"
	},
	"id": "lrUAK-TjbJdw",
	"outputId": "20888674-46c2-4b46-b59a-efa8e0604ea9"
	},
	"execution_count": null,
	"outputs": [
	{
	"output_type": "execute_result",
	"data": {
	"text/plain": [
	"3"
	]
	},
	"metadata": {},
	"execution_count": 20
	}
	]
	},
	{
	"cell_type": "code",
	"source": [
	"plt.imshow(test_images[0])"
	],
	"metadata": {
	"colab": {
	"base_uri": "https://localhost:8080/",
	"height": 284
	},
	"id": "F5B9NvWVbazh",
	"outputId": "b1cf969a-caa7-4d83-e6b8-3d2617ee8251"
	},
	"execution_count": null,
	"outputs": [
	{
	"output_type": "execute_result",
	"data": {
	"text/plain": [
	"<matplotlib.image.AxesImage at 0x7f0b4f3ac6d0>"
	]
	},
	"metadata": {},
	"execution_count": 23
	},
	{
	"output_type": "display_data",
	"data": {
	"text/plain": [
	"<Figure size 432x288 with 1 Axes>"
	],
	"image/png": "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\n"
	},
	"metadata": {
	"needs_background": "light"
	}
	}
	]
	},
	{
	"cell_type": "code",
	"source": [
	"class_names[3]"
	],
	"metadata": {
	"colab": {
	"base_uri": "https://localhost:8080/",
	"height": 37
	},
	"id": "8wxBgyq_boS3",
	"outputId": "1e176fe9-4b98-4fec-c9a4-d506bc8491bb"
	},
	"execution_count": null,
	"outputs": [
	{
	"output_type": "execute_result",
	"data": {
	"text/plain": [
	"'cat'"
	],
	"application/vnd.google.colaboratory.intrinsic+json": {
	"type": "string"
	}
	},
	"metadata": {},
	"execution_count": 24
	}
	]
	},
	{
	"cell_type": "code",
	"source": [],
	"metadata": {
	"id": "SQQTahPub-3r"
	},
	"execution_count": null,
	"outputs": []
	}
	]
	}