Skip to content

Instantly share code, notes, and snippets.

@ravi07bec

ravi07bec/neuralnets_imagedetection.ipynb

Last active March 10, 2019 09:22
Show Gist options
  • Save ravi07bec/4fafe045d5237f964ae1ee680a878535 to your computer and use it in GitHub Desktop.
Save ravi07bec/4fafe045d5237f964ae1ee680a878535 to your computer and use it in GitHub Desktop.
Download ZIP
NeuralNets_ImageDetection.ipynb
Display the source blob
Display the rendered blob
Raw
neuralnets_imagedetection.ipynb
{
"nbformat": 4,
"nbformat_minor": 0,
"metadata": {
"colab": {
"name": "NeuralNets_ImageDetection.ipynb",
"version": "0.3.2",
"provenance": [],
"include_colab_link": true
},
"kernelspec": {
"name": "python3",
"display_name": "Python 3"
},
"accelerator": "GPU"
},
"cells": [
{
"cell_type": "markdown",
"metadata": {
"id": "view-in-github",
"colab_type": "text"
},
"source": [
"<a href=\"https://colab.research.google.com/gist/ravi07bec/4fafe045d5237f964ae1ee680a878535/neuralnets_imagedetection.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
]
},
{
"metadata": {
"id": "V6ZVM_10322d",
"colab_type": "code",
"outputId": "981004ac-7ed3-4d45-ede7-9fd1305ee367",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 51
}
},
"cell_type": "code",
"source": [
"from keras.datasets import mnist\n",
"#download mnist data and split into train and test sets\n",
"(X_train, y_train), (X_test, y_test) = mnist.load_data()\n"
],
"execution_count": 0,
"outputs": [
{
"output_type": "stream",
"text": [
"Downloading data from https://s3.amazonaws.com/img-datasets/mnist.npz\n",
"11493376/11490434 [==============================] - 0s 0us/step\n"
],
"name": "stdout"
}
]
},
{
"metadata": {
"id": "NtRfFDL835nh",
"colab_type": "code",
"outputId": "8dbb0cab-b5eb-4ea2-ea30-210ff0c5c95b",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 364
}
},
"cell_type": "code",
"source": [
"import matplotlib.pyplot as plt\n",
"#plot the first image in the dataset\n",
"plt.imshow(X_train[10])"
],
"execution_count": 0,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"<matplotlib.image.AxesImage at 0x7f48906446a0>"
]
},
"metadata": {
"tags": []
},
"execution_count": 5
},
{
"output_type": "display_data",
"data": {
"image/png": "iVBORw0KGgoAAAANSUhEUgAAAUsAAAFKCAYAAACU6307AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nF5A8IO3oN+s/AAAAAElFTkSuQmCC\n",
"text/plain": [
"<Figure size 576x396 with 1 Axes>"
]
},
"metadata": {
"tags": []
}
}
]
},
{
"metadata": {
"id": "op9S_eOd393h",
"colab_type": "code",
"outputId": "0f93ba75-c058-478b-86c5-9fbc2e6ef0e8",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 34
}
},
"cell_type": "code",
"source": [
"#check image shape\n",
"X_train[0].shape"
],
"execution_count": 0,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"(28, 28)"
]
},
"metadata": {
"tags": []
},
"execution_count": 6
}
]
},
{
"metadata": {
"id": "NkQ963r14Eyy",
"colab_type": "code",
"colab": {}
},
"cell_type": "code",
"source": [
"#reshape data to fit model\n",
"X_train = X_train.reshape(60000,28,28,1)\n",
"X_test = X_test.reshape(10000,28,28,1)\n"
],
"execution_count": 0,
"outputs": []
},
{
"metadata": {
"id": "Hby0SEnQ4HuQ",
"colab_type": "code",
"outputId": "9c9c81d8-7d8e-45a0-f9e5-51aa6b8b0a64",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 34
}
},
"cell_type": "code",
"source": [
"from keras.utils import to_categorical\n",
"#one-hot encode target column\n",
"y_train = to_categorical(y_train)\n",
"y_test = to_categorical(y_test)\n",
"y_train[0]"
],
"execution_count": 0,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"array([0., 0., 0., 0., 0., 1., 0., 0., 0., 0.], dtype=float32)"
]
},
"metadata": {
"tags": []
},
"execution_count": 8
}
]
},
{
"metadata": {
"id": "AiG29CuXPFwK",
"colab_type": "code",
"colab": {}
},
"cell_type": "code",
"source": [
"import keras\n",
"from keras.models import Sequential\n",
"from keras.layers import Dense, Conv2D, Flatten\n",
"#create model\n",
"model = Sequential()\n",
"#add model layers\n",
"model.add(Conv2D(64, kernel_size=3, activation='relu', input_shape=(28,28,1)))\n",
"model.add(Conv2D(32, kernel_size=3, activation='relu'))\n",
"model.add(Flatten())\n",
"model.add(Dense(10, activation='softmax'))"
],
"execution_count": 0,
"outputs": []
},
{
"metadata": {
"id": "pjX77fP1PJbZ",
"colab_type": "code",
"outputId": "1ffcdb2d-93af-4b80-db3d-aeffd3f68c83",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 272
}
},
"cell_type": "code",
"source": [
"model.summary()"
],
"execution_count": 0,
"outputs": [
{
"output_type": "stream",
"text": [
"_________________________________________________________________\n",
"Layer (type) Output Shape Param # \n",
"=================================================================\n",
"conv2d_3 (Conv2D) (None, 26, 26, 64) 640 \n",
"_________________________________________________________________\n",
"conv2d_4 (Conv2D) (None, 24, 24, 32) 18464 \n",
"_________________________________________________________________\n",
"flatten_2 (Flatten) (None, 18432) 0 \n",
"_________________________________________________________________\n",
"dense_2 (Dense) (None, 10) 184330 \n",
"=================================================================\n",
"Total params: 203,434\n",
"Trainable params: 203,434\n",
"Non-trainable params: 0\n",
"_________________________________________________________________\n"
],
"name": "stdout"
}
]
},
{
"metadata": {
"id": "BcLXLeRpPPsE",
"colab_type": "code",
"colab": {}
},
"cell_type": "code",
"source": [
"#compile model using accuracy to measure model performance\n",
"model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])"
],
"execution_count": 0,
"outputs": []
},
{
"metadata": {
"id": "aEobJ4vR4V8e",
"colab_type": "code",
"outputId": "bd6f46bf-c8c0-44fc-8911-89e28b7fd59b",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 224
}
},
"cell_type": "code",
"source": [
"#train the model\n",
"model.fit(X_train, y_train, validation_data=(X_test, y_test), epochs=3)"
],
"execution_count": 0,
"outputs": [
{
"output_type": "stream",
"text": [
"WARNING:tensorflow:From /usr/local/lib/python3.6/dist-packages/tensorflow/python/ops/math_ops.py:3066: to_int32 (from tensorflow.python.ops.math_ops) is deprecated and will be removed in a future version.\n",
"Instructions for updating:\n",
"Use tf.cast instead.\n",
"Train on 60000 samples, validate on 10000 samples\n",
"Epoch 1/3\n",
"60000/60000 [==============================] - 20s 327us/step - loss: 10.8514 - acc: 0.3259 - val_loss: 9.9144 - val_acc: 0.3844\n",
"Epoch 2/3\n",
"60000/60000 [==============================] - 17s 289us/step - loss: 9.3920 - acc: 0.4170 - val_loss: 8.9451 - val_acc: 0.4449\n",
"Epoch 3/3\n",
"60000/60000 [==============================] - 17s 289us/step - loss: 8.4426 - acc: 0.4761 - val_loss: 8.3438 - val_acc: 0.4823\n"
],
"name": "stdout"
},
{
"output_type": "execute_result",
"data": {
"text/plain": [
"<keras.callbacks.History at 0x7f489036ceb8>"
]
},
"metadata": {
"tags": []
},
"execution_count": 13
}
]
},
{
"metadata": {
"id": "pH0BUyuo4Xgk",
"colab_type": "code",
"outputId": "55ac941f-2546-41be-a66c-8db5c4d679ee",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 85
}
},
"cell_type": "code",
"source": [
"#predict first 4 images in the test set\n",
"model.predict(X_test[:4])"
],
"execution_count": 0,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"array([[0., 0., 0., 0., 0., 0., 0., 1., 0., 0.],\n",
" [0., 0., 1., 0., 0., 0., 0., 0., 0., 0.],\n",
" [0., 1., 0., 0., 0., 0., 0., 0., 0., 0.],\n",
" [0., 0., 1., 0., 0., 0., 0., 0., 0., 0.]], dtype=float32)"
]
},
"metadata": {
"tags": []
},
"execution_count": 14
}
]
},
{
"metadata": {
"id": "ozhW5EfO4dux",
"colab_type": "code",
"outputId": "4df41053-0ef3-496b-e5ea-330f9dfe5398",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 85
}
},
"cell_type": "code",
"source": [
"#actual results for first 4 images in test set\n",
"y_test[:4]"
],
"execution_count": 0,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"array([[0., 0., 0., 0., 0., 0., 0., 1., 0., 0.],\n",
" [0., 0., 1., 0., 0., 0., 0., 0., 0., 0.],\n",
" [0., 1., 0., 0., 0., 0., 0., 0., 0., 0.],\n",
" [1., 0., 0., 0., 0., 0., 0., 0., 0., 0.]], dtype=float32)"
]
},
"metadata": {
"tags": []
},
"execution_count": 15
}
]
},
{
"metadata": {
"id": "ObG_iDt14hDb",
"colab_type": "code",
"colab": {}
},
"cell_type": "code",
"source": [
""
],
"execution_count": 0,
"outputs": []
}
]
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment