Skip to content

Instantly share code, notes, and snippets.

@czynot

czynot/train_covid19.ipynb

Last active March 21, 2020 05:45
Show Gist options
  • Save czynot/79686ff13e28e985a27bd798b725b0f4 to your computer and use it in GitHub Desktop.
Save czynot/79686ff13e28e985a27bd798b725b0f4 to your computer and use it in GitHub Desktop.
Download ZIP
train_covid19.ipynb
Display the source blob
Display the rendered blob
Raw
train_covid19.ipynb
{
"nbformat": 4,
"nbformat_minor": 0,
"metadata": {
"colab": {
"name": "train_covid19.ipynb",
"provenance": [],
"collapsed_sections": [],
"toc_visible": true,
"mount_file_id": "120jl8kdg8TkwCcXGzyIZjUUvTW3b69a5",
"authorship_tag": "ABX9TyOHQj6ue4NhXERlYElJ1OrT",
"include_colab_link": true
},
"kernelspec": {
"name": "python3",
"display_name": "Python 3"
}
},
"cells": [
{
"cell_type": "markdown",
"metadata": {
"id": "view-in-github",
"colab_type": "text"
},
"source": [
"<a href=\"https://colab.research.google.com/gist/czynot/79686ff13e28e985a27bd798b725b0f4/train_covid19.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "cgTf_Ag3Rc3Z",
"colab_type": "text"
},
"source": [
"# **Detecting COVID-19 in X-ray images with Keras, TensorFlow, and Deep Learning**"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "BzlD3pibVFJb",
"colab_type": "text"
},
"source": [
"## Import Statements"
]
},
{
"cell_type": "code",
"metadata": {
"id": "gMJ05u24vFEY",
"colab_type": "code",
"colab": {}
},
"source": [
"# import the necessary packages\n",
"from tensorflow.keras.preprocessing.image import ImageDataGenerator\n",
"from tensorflow.keras.applications import VGG16\n",
"from tensorflow.keras.layers import AveragePooling2D\n",
"from tensorflow.keras.layers import Dropout\n",
"from tensorflow.keras.layers import Flatten\n",
"from tensorflow.keras.layers import Dense\n",
"from tensorflow.keras.layers import Input\n",
"from tensorflow.keras.models import Model\n",
"from tensorflow.keras.optimizers import Adam\n",
"from tensorflow.keras.utils import to_categorical\n",
"from sklearn.preprocessing import LabelBinarizer\n",
"from sklearn.model_selection import train_test_split\n",
"from sklearn.metrics import classification_report\n",
"from sklearn.metrics import confusion_matrix\n",
"from imutils import paths\n",
"import matplotlib.pyplot as plt\n",
"import numpy as np\n",
"import argparse\n",
"import cv2\n",
"import os"
],
"execution_count": 0,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "Dd10kT9dABn0",
"colab_type": "code",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 34
},
"outputId": "e09fe57b-3a43-4fb6-db20-70ffe54b623c"
},
"source": [
"# change direrctory to store and read data\n",
"cd ../covid-19/"
],
"execution_count": 94,
"outputs": [
{
"output_type": "stream",
"text": [
"/covid-19\n"
],
"name": "stdout"
}
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "Rtmd4a64W9rg",
"colab_type": "text"
},
"source": [
"## Download dataset from Google Drive"
]
},
{
"cell_type": "code",
"metadata": {
"id": "dIF4CfIZcZ14",
"colab_type": "code",
"colab": {}
},
"source": [
"# import pyDrive\n",
"from pydrive.auth import GoogleAuth\n",
"from pydrive.drive import GoogleDrive\n",
"from google.colab import auth\n",
"from oauth2client.client import GoogleCredentials\n",
"\n",
"# authenticate and create the PyDrive client.\n",
"auth.authenticate_user()\n",
"gauth = GoogleAuth()\n",
"gauth.credentials = GoogleCredentials.get_application_default()\n",
"drive = GoogleDrive(gauth)"
],
"execution_count": 0,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "K3cXPEw_n1el",
"colab_type": "code",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 867
},
"outputId": "8639b313-ca8c-4a3e-fb5f-898b4a879398"
},
"source": [
"# choose a local (colab) directory to store the data for covid images\n",
"local_download_path = os.path.expanduser('dataset/covid')\n",
"try:\n",
" os.makedirs(local_download_path)\n",
"except: pass\n",
"\n",
"# auto-iterate using the query syntax\n",
"# https://developers.google.com/drive/v2/web/search-parameters\n",
"file_list = drive.ListFile(\n",
" # the parameter q is personal folder share id\n",
" {'q': \"'1mhFxCP2HB8VtXi3_ysxxDP854SehjvLe' in parents\"}).GetList()\n",
"\n",
"for f in file_list:\n",
" # create & download by id.\n",
" print('title: %s, id: %s' % (f['title'], f['id']))\n",
" fname = os.path.join(local_download_path, f['title'])\n",
" print('downloading to {}'.format(fname))\n",
" f_ = drive.CreateFile({'id': f['id']})\n",
" f_.GetContentFile(fname)"
],
"execution_count": 96,
"outputs": [
{
"output_type": "stream",
"text": [
"title: nejmoa2001191_f3-PA.jpeg, id: 1krdKPhjEAReg0Ba5yRKrA30V6OLUyUxt\n",
"downloading to dataset/covid/nejmoa2001191_f3-PA.jpeg\n",
"title: nejmoa2001191_f4.jpeg, id: 1qT3xg5wIO_6wTzfhKAZcEx46H0C_acuU\n",
"downloading to dataset/covid/nejmoa2001191_f4.jpeg\n",
"title: ryct.2020200034.fig5-day0.jpeg, id: 1dJierErYeDivOSKSZEpekg-IG3JLun7F\n",
"downloading to dataset/covid/ryct.2020200034.fig5-day0.jpeg\n",
"title: auntminnie-d-2020_01_28_23_51_6665_2020_01_28_Vietnam_coronavirus.jpeg, id: 1kRq4ii25X91_0gIk0yKIgJE3fjcbeRnO\n",
"downloading to dataset/covid/auntminnie-d-2020_01_28_23_51_6665_2020_01_28_Vietnam_coronavirus.jpeg\n",
"title: 1-s2.0-S0929664620300449-gr2_lrg-b.jpg, id: 1J07b9p_Aaof8FKOyLVgbrCilhTFCPXus\n",
"downloading to dataset/covid/1-s2.0-S0929664620300449-gr2_lrg-b.jpg\n",
"title: lancet-case2b.jpg, id: 1k0aXS9FIU1CDSmlScsJA0P56exijd8xo\n",
"downloading to dataset/covid/lancet-case2b.jpg\n",
"title: nejmoa2001191_f1-PA.jpeg, id: 1C7HWvQTyeUEQG5P8pyu4cHwiHIhfNpJx\n",
"downloading to dataset/covid/nejmoa2001191_f1-PA.jpeg\n",
"title: 1-s2.0-S0929664620300449-gr2_lrg-d.jpg, id: 1Sqkk_jy9dHaUMXfJ9o8OOGusXsoZM3GC\n",
"downloading to dataset/covid/1-s2.0-S0929664620300449-gr2_lrg-d.jpg\n",
"title: ryct.2020200034.fig5-day4.jpeg, id: 1elqC7dGzESqyN6PvyDgJ9iW9_dmD_vt6\n",
"downloading to dataset/covid/ryct.2020200034.fig5-day4.jpeg\n",
"title: lancet-case2a.jpg, id: 1VPBhlJfM4XH-ch5XJ1xW-mc37Gxv4zxZ\n",
"downloading to dataset/covid/lancet-case2a.jpg\n",
"title: ryct.2020200034.fig2.jpeg, id: 10hdXGSREW4ft028E1ueGwHnTQJqhXMlu\n",
"downloading to dataset/covid/ryct.2020200034.fig2.jpeg\n",
"title: nejmc2001573_f1a.jpeg, id: 19XShPsIufUx5DBwUzIIVIhtOYh6yHCuQ\n",
"downloading to dataset/covid/nejmc2001573_f1a.jpeg\n",
"title: radiol.2020200490.fig3.jpeg, id: 1dxuXzRlvdM7gqoqwVt_YGOT2bti0zVy1\n",
"downloading to dataset/covid/radiol.2020200490.fig3.jpeg\n",
"title: nejmc2001573_f1b.jpeg, id: 1CtxJJs7-IE4xUeZmxfTNCuHNUQbLT4sm\n",
"downloading to dataset/covid/nejmc2001573_f1b.jpeg\n",
"title: nCoV-radiol.2020200269.fig1-day7.jpeg, id: 1IV1GPVvZ470tD4pC9KoBwicIe3SoXyvo\n",
"downloading to dataset/covid/nCoV-radiol.2020200269.fig1-day7.jpeg\n",
"title: nejmoa2001191_f5-PA.jpeg, id: 1Vmrk4w_6r5COS2xNU1Xi4sQTx1_MwozE\n",
"downloading to dataset/covid/nejmoa2001191_f5-PA.jpeg\n",
"title: ryct.2020200034.fig5-day7.jpeg, id: 1MRjEydM0SFSjIyFz-vF_PYJ-77NzUpA1\n",
"downloading to dataset/covid/ryct.2020200034.fig5-day7.jpeg\n",
"title: 1-s2.0-S0929664620300449-gr2_lrg-c.jpg, id: 118BEuCGLM6JVZPzWy22y90R4tnDyGPKp\n",
"downloading to dataset/covid/1-s2.0-S0929664620300449-gr2_lrg-c.jpg\n",
"title: radiopedia-covid-19-pneumonia-2.jpg, id: 1_WuUvwmVVQaD4tXTZt1nHDVbbeZz1NBR\n",
"downloading to dataset/covid/radiopedia-covid-19-pneumonia-2.jpg\n",
"title: 1-s2.0-S0929664620300449-gr2_lrg-a.jpg, id: 19_Im59Y5anF-4jM7TkA3fcAb3ULxCKQ9\n",
"downloading to dataset/covid/1-s2.0-S0929664620300449-gr2_lrg-a.jpg\n",
"title: 1-s2.0-S0140673620303706-fx1_lrg.jpg, id: 1D_3kqC6YrtR13eCLeM67AKgqC1tlXrBf\n",
"downloading to dataset/covid/1-s2.0-S0140673620303706-fx1_lrg.jpg\n",
"title: ryct.2020200028.fig1a.jpeg, id: 1sPXtxFm5hUNu5BFCMUQVkZTQGJcAK1Zh\n",
"downloading to dataset/covid/ryct.2020200028.fig1a.jpeg\n",
"title: auntminnie-c-2020_01_28_23_51_6665_2020_01_28_Vietnam_coronavirus.jpeg, id: 1PCKJ-_YmG2GDoDVeXM1OkL7-oIvz8eSg\n",
"downloading to dataset/covid/auntminnie-c-2020_01_28_23_51_6665_2020_01_28_Vietnam_coronavirus.jpeg\n",
"title: auntminnie-a-2020_01_28_23_51_6665_2020_01_28_Vietnam_coronavirus.jpeg, id: 1SYpiZYHiBdXqHf1iJwuihJaIo6XQnrr1\n",
"downloading to dataset/covid/auntminnie-a-2020_01_28_23_51_6665_2020_01_28_Vietnam_coronavirus.jpeg\n",
"title: auntminnie-b-2020_01_28_23_51_6665_2020_01_28_Vietnam_coronavirus.jpeg, id: 1b2hbvAdffpU-wKmErJ1ESShASTHF-OS7\n",
"downloading to dataset/covid/auntminnie-b-2020_01_28_23_51_6665_2020_01_28_Vietnam_coronavirus.jpeg\n"
],
"name": "stdout"
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "W8KT5cpmI9O7",
"colab_type": "code",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 867
},
"outputId": "9e720577-f723-4299-ca59-dabac7de3945"
},
"source": [
"# choose a local (colab) directory to store the data for normal images\n",
"local_download_path = os.path.expanduser('dataset/normal')\n",
"try:\n",
" os.makedirs(local_download_path)\n",
"except: pass\n",
"\n",
"# auto-iterate using the query syntax\n",
"# https://developers.google.com/drive/v2/web/search-parameters\n",
"file_list = drive.ListFile(\n",
" # the parameter q is personal folder share id\n",
" {'q': \"'1VhOrJE3gFhj1SJHvuZepFftPDxa0bjFU' in parents\"}).GetList()\n",
"\n",
"for f in file_list:\n",
" # create & download by id.\n",
" print('title: %s, id: %s' % (f['title'], f['id']))\n",
" fname = os.path.join(local_download_path, f['title'])\n",
" print('downloading to {}'.format(fname))\n",
" f_ = drive.CreateFile({'id': f['id']})\n",
" f_.GetContentFile(fname)"
],
"execution_count": 97,
"outputs": [
{
"output_type": "stream",
"text": [
"title: IM-0033-0001-0001.jpeg, id: 1Nvz1PdVCbyGJGSoevz3KgG70A6r1QiJU\n",
"downloading to dataset/normal/IM-0033-0001-0001.jpeg\n",
"title: person939_bacteria_2864.jpeg, id: 1JjNK19qX1-es6edXZPTxeLTTlgJ1AJz3\n",
"downloading to dataset/normal/person939_bacteria_2864.jpeg\n",
"title: person1830_bacteria_4693.jpeg, id: 1MTjAxmvNSofIbpcH4KqTam6jIXucPTuO\n",
"downloading to dataset/normal/person1830_bacteria_4693.jpeg\n",
"title: person934_virus_1595.jpeg, id: 13aQLU7CjsTIGH2-6bhVg8emsL-_rA5CA\n",
"downloading to dataset/normal/person934_virus_1595.jpeg\n",
"title: person339_bacteria_1574.jpeg, id: 1VrOn7yDpD0v2aUqBIaNxs9klIKvaWebM\n",
"downloading to dataset/normal/person339_bacteria_1574.jpeg\n",
"title: person1599_virus_2776.jpeg, id: 1wpKZffayED2fF_gZy3pDS-A98ZToyiYV\n",
"downloading to dataset/normal/person1599_virus_2776.jpeg\n",
"title: person378_virus_761.jpeg, id: 1vrqmrCajESr1w2CwohvbzAFKVBuxnuiV\n",
"downloading to dataset/normal/person378_virus_761.jpeg\n",
"title: NORMAL2-IM-1179-0001.jpeg, id: 193NGjKrRrHwyU6D9okF14GjfK79shiU8\n",
"downloading to dataset/normal/NORMAL2-IM-1179-0001.jpeg\n",
"title: person612_bacteria_2478.jpeg, id: 1teU-F0VX2eQEECXTEo5UJDO4amk-ZFeH\n",
"downloading to dataset/normal/person612_bacteria_2478.jpeg\n",
"title: NORMAL2-IM-0696-0001.jpeg, id: 1rkwB3Q8HpBGkN8cWhJnA1H7Vr9nrIzRw\n",
"downloading to dataset/normal/NORMAL2-IM-0696-0001.jpeg\n",
"title: person1102_bacteria_3043.jpeg, id: 1hfKIOwAv3wvGN7XWGOeT2dmc7sOhMwc3\n",
"downloading to dataset/normal/person1102_bacteria_3043.jpeg\n",
"title: person525_bacteria_2216.jpeg, id: 1G2VbQcUX9zNYOrtXiCBbmWlI1j0pbJLa\n",
"downloading to dataset/normal/person525_bacteria_2216.jpeg\n",
"title: person989_virus_1667.jpeg, id: 13FxbHLC0fiOCU_P8HGafj25X7cFbd1e-\n",
"downloading to dataset/normal/person989_virus_1667.jpeg\n",
"title: person925_virus_1582.jpeg, id: 16l8SD964RWcdqDbEe8ceimeOc7NMEgp8\n",
"downloading to dataset/normal/person925_virus_1582.jpeg\n",
"title: person1935_bacteria_4849.jpeg, id: 1pjZ6zguQorf0b6Na1HZaetNyzKvfEFdG\n",
"downloading to dataset/normal/person1935_bacteria_4849.jpeg\n",
"title: person651_bacteria_2543.jpeg, id: 1hApcfKhbhmb3Q2rxzbb_wWOS23dGkJzX\n",
"downloading to dataset/normal/person651_bacteria_2543.jpeg\n",
"title: NORMAL2-IM-0315-0001.jpeg, id: 1iqeXhyI3orZBQ9DwWlCO4cHXx-wryqlp\n",
"downloading to dataset/normal/NORMAL2-IM-0315-0001.jpeg\n",
"title: person438_bacteria_1893.jpeg, id: 1xSyXO2LMx8qLpBcuvvti4n8hgJRCf1Jz\n",
"downloading to dataset/normal/person438_bacteria_1893.jpeg\n",
"title: person1290_virus_2215.jpeg, id: 1vR9MyxKGIbaFl9PCRx6TrkfClgB2qLDR\n",
"downloading to dataset/normal/person1290_virus_2215.jpeg\n",
"title: IM-0466-0001.jpeg, id: 1JrdtfOYZ7J8y0GdRrDE51TTAFtUh_-R8\n",
"downloading to dataset/normal/IM-0466-0001.jpeg\n",
"title: IM-0240-0001.jpeg, id: 1DhhUYSHCbZllVSXPTF7HL4UEUn-mWVUp\n",
"downloading to dataset/normal/IM-0240-0001.jpeg\n",
"title: person259_bacteria_1220.jpeg, id: 1Soej30qM69IjulzJktnp1GGjN5zPk2wr\n",
"downloading to dataset/normal/person259_bacteria_1220.jpeg\n",
"title: person1558_bacteria_4066.jpeg, id: 18AteswBHmSn-UbJ2nk83AXpLzWxMJl7D\n",
"downloading to dataset/normal/person1558_bacteria_4066.jpeg\n",
"title: NORMAL2-IM-0869-0001.jpeg, id: 1uQMN_PJHwQaDhkpv5yXrHGPYMHKlWzJl\n",
"downloading to dataset/normal/NORMAL2-IM-0869-0001.jpeg\n",
"title: person1_bacteria_2.jpeg, id: 1Nm3wSOoDsF1ok-hBgnS_uvysSj-MllNY\n",
"downloading to dataset/normal/person1_bacteria_2.jpeg\n"
],
"name": "stdout"
}
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "YEKbbdbJ4n85",
"colab_type": "text"
},
"source": [
"## Parsing Arguments and Initialising Hyperparameters"
]
},
{
"cell_type": "code",
"metadata": {
"id": "SGmR_Xgj6kJc",
"colab_type": "code",
"colab": {}
},
"source": [
"# pass the argument explicitly\n",
"# use python train_model.py --dataset dataset while running in terminal\n",
"args = vars(ap.parse_args(args=['--dataset', 'dataset']))"
],
"execution_count": 0,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "8D-V8DA2vKOP",
"colab_type": "code",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 54
},
"outputId": "b33dc833-d46d-4bee-f1dc-f40bc4f09451"
},
"source": [
"# construct the argument parser and parse the arguments\n",
"ap = argparse.ArgumentParser()\n",
"ap.add_argument(\"-d\", \"--dataset\", required=True,\n",
"\thelp=\"dataset/\")\n",
"ap.add_argument(\"-p\", \"--plot\", type=str, default=\"plot.png\",\n",
"\thelp=\"dataset/accuracy plot\")\n",
"ap.add_argument(\"-m\", \"--model\", type=str, default=\"covid19.model\",\n",
"\thelp=\"dataset/accuracy plot\")"
],
"execution_count": 99,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"_StoreAction(option_strings=['-m', '--model'], dest='model', nargs=None, const=None, default='covid19.model', type=<class 'str'>, choices=None, help='dataset/accuracy plot', metavar=None)"
]
},
"metadata": {
"tags": []
},
"execution_count": 99
}
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "p0BqzxITUYyv",
"colab_type": "text"
},
"source": [
"## Initialise Initial Learning Rate, Number of Training Epochs and Batch Size Hyperparameters"
]
},
{
"cell_type": "code",
"metadata": {
"id": "69kdahh7xacT",
"colab_type": "code",
"colab": {}
},
"source": [
"# initialize the initial learning rate, number of epochs to train for,\n",
"# and batch size\n",
"INIT_LR = 1e-3\n",
"EPOCHS = 25\n",
"BS = 8"
],
"execution_count": 0,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "_mPXNoPCKZF1",
"colab_type": "code",
"colab": {}
},
"source": [
"# initialise empty lists to store images and labels\n",
"data = []\n",
"labels = []"
],
"execution_count": 0,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "2Jgbz0Wkxb06",
"colab_type": "code",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 884
},
"outputId": "2deb90fc-7186-4781-a4f2-0c4c823c0066"
},
"source": [
"# grab the list of images in our dataset directory, then initialize\n",
"# the list of data (i.e., images) and class images\n",
"print(\"[INFO] loading covid images...\")\n",
"imagePaths = list(paths.list_images(args[\"dataset\"]))\n",
"imagePaths"
],
"execution_count": 102,
"outputs": [
{
"output_type": "stream",
"text": [
"[INFO] loading covid images...\n"
],
"name": "stdout"
},
{
"output_type": "execute_result",
"data": {
"text/plain": [
"['dataset/covid/ryct.2020200034.fig2.jpeg',\n",
" 'dataset/covid/nejmoa2001191_f4.jpeg',\n",
" 'dataset/covid/radiopedia-covid-19-pneumonia-2.jpg',\n",
" 'dataset/covid/1-s2.0-S0140673620303706-fx1_lrg.jpg',\n",
" 'dataset/covid/auntminnie-d-2020_01_28_23_51_6665_2020_01_28_Vietnam_coronavirus.jpeg',\n",
" 'dataset/covid/1-s2.0-S0929664620300449-gr2_lrg-a.jpg',\n",
" 'dataset/covid/auntminnie-b-2020_01_28_23_51_6665_2020_01_28_Vietnam_coronavirus.jpeg',\n",
" 'dataset/covid/nCoV-radiol.2020200269.fig1-day7.jpeg',\n",
" 'dataset/covid/lancet-case2a.jpg',\n",
" 'dataset/covid/ryct.2020200034.fig5-day4.jpeg',\n",
" 'dataset/covid/auntminnie-c-2020_01_28_23_51_6665_2020_01_28_Vietnam_coronavirus.jpeg',\n",
" 'dataset/covid/nejmc2001573_f1b.jpeg',\n",
" 'dataset/covid/ryct.2020200028.fig1a.jpeg',\n",
" 'dataset/covid/nejmoa2001191_f3-PA.jpeg',\n",
" 'dataset/covid/auntminnie-a-2020_01_28_23_51_6665_2020_01_28_Vietnam_coronavirus.jpeg',\n",
" 'dataset/covid/1-s2.0-S0929664620300449-gr2_lrg-d.jpg',\n",
" 'dataset/covid/1-s2.0-S0929664620300449-gr2_lrg-b.jpg',\n",
" 'dataset/covid/nejmoa2001191_f1-PA.jpeg',\n",
" 'dataset/covid/lancet-case2b.jpg',\n",
" 'dataset/covid/radiol.2020200490.fig3.jpeg',\n",
" 'dataset/covid/ryct.2020200034.fig5-day7.jpeg',\n",
" 'dataset/covid/1-s2.0-S0929664620300449-gr2_lrg-c.jpg',\n",
" 'dataset/covid/ryct.2020200034.fig5-day0.jpeg',\n",
" 'dataset/covid/nejmoa2001191_f5-PA.jpeg',\n",
" 'dataset/covid/nejmc2001573_f1a.jpeg',\n",
" 'dataset/normal/IM-0033-0001-0001.jpeg',\n",
" 'dataset/normal/person1102_bacteria_3043.jpeg',\n",
" 'dataset/normal/person438_bacteria_1893.jpeg',\n",
" 'dataset/normal/person651_bacteria_2543.jpeg',\n",
" 'dataset/normal/IM-0240-0001.jpeg',\n",
" 'dataset/normal/person525_bacteria_2216.jpeg',\n",
" 'dataset/normal/person612_bacteria_2478.jpeg',\n",
" 'dataset/normal/IM-0466-0001.jpeg',\n",
" 'dataset/normal/person1558_bacteria_4066.jpeg',\n",
" 'dataset/normal/person989_virus_1667.jpeg',\n",
" 'dataset/normal/person934_virus_1595.jpeg',\n",
" 'dataset/normal/NORMAL2-IM-0315-0001.jpeg',\n",
" 'dataset/normal/person1599_virus_2776.jpeg',\n",
" 'dataset/normal/person925_virus_1582.jpeg',\n",
" 'dataset/normal/NORMAL2-IM-0869-0001.jpeg',\n",
" 'dataset/normal/person1290_virus_2215.jpeg',\n",
" 'dataset/normal/person1830_bacteria_4693.jpeg',\n",
" 'dataset/normal/person378_virus_761.jpeg',\n",
" 'dataset/normal/person339_bacteria_1574.jpeg',\n",
" 'dataset/normal/person939_bacteria_2864.jpeg',\n",
" 'dataset/normal/NORMAL2-IM-1179-0001.jpeg',\n",
" 'dataset/normal/NORMAL2-IM-0696-0001.jpeg',\n",
" 'dataset/normal/person1_bacteria_2.jpeg',\n",
" 'dataset/normal/person259_bacteria_1220.jpeg',\n",
" 'dataset/normal/person1935_bacteria_4849.jpeg']"
]
},
"metadata": {
"tags": []
},
"execution_count": 102
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "Bg6iVJN4zXuH",
"colab_type": "code",
"colab": {}
},
"source": [
"# loop over the image paths\n",
"for imagePath in imagePaths:\n",
"\timagePath\n",
"\t# extract the class label from the filename\n",
"\tlabel = imagePath.split(os.path.sep)[-2]\n",
"\n",
"\t# load the image, swap color channels, and resize it to be a fixed\n",
"\t# 224x224 pixels while ignoring aspect ratio\n",
"\timage = cv2.imread(imagePath)\n",
"\timage = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)\n",
"\timage = cv2.resize(image, (224, 224))\n",
"\n",
"\t# update the data and labels lists, respectively\n",
"\tdata.append(image)\n",
"\tlabels.append(label)"
],
"execution_count": 0,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "xngAFjvlzcHU",
"colab_type": "code",
"colab": {}
},
"source": [
"# convert the data and labels to NumPy arrays while scaling the pixel\n",
"# intensities to the range [0, 255]\n",
"data = np.array(data) / 255.0\n",
"labels = np.array(labels)"
],
"execution_count": 0,
"outputs": []
},
{
"cell_type": "markdown",
"metadata": {
"id": "uvXvx669VSFm",
"colab_type": "text"
},
"source": [
"## One-hot Encode Labels and Create Training/Testing Splits"
]
},
{
"cell_type": "code",
"metadata": {
"id": "NtJsUD1_zgM-",
"colab_type": "code",
"colab": {}
},
"source": [
"# perform one-hot encoding on the labels\n",
"lb = LabelBinarizer()\n",
"labels = lb.fit_transform(labels)\n",
"labels = to_categorical(labels)"
],
"execution_count": 0,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "iZZGOF2vzlwF",
"colab_type": "code",
"colab": {}
},
"source": [
"# partition the data into training and testing splits using 80% of\n",
"# the data for training and the remaining 20% for testing\n",
"(trainX, testX, trainY, testY) = train_test_split(data, labels,\n",
"\ttest_size=0.20, stratify=labels, random_state=42)"
],
"execution_count": 0,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "abckXTtZzsi_",
"colab_type": "code",
"colab": {}
},
"source": [
"# initialize the training data augmentation object\n",
"trainAug = ImageDataGenerator(\n",
"\trotation_range=15,\n",
"\tfill_mode=\"nearest\")"
],
"execution_count": 0,
"outputs": []
},
{
"cell_type": "markdown",
"metadata": {
"id": "d3atYyrAWG3y",
"colab_type": "text"
},
"source": [
"## Initialise VGGNet Model and set it up for Fine Tuning"
]
},
{
"cell_type": "code",
"metadata": {
"id": "E-K0TlFjzwIH",
"colab_type": "code",
"colab": {}
},
"source": [
"# load the VGG16 network, ensuring the head FC layer sets are left\n",
"# off\n",
"baseModel = VGG16(weights=\"imagenet\", include_top=False,\n",
"\tinput_tensor=Input(shape=(224, 224, 3)))"
],
"execution_count": 0,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "f539NfIQzzD_",
"colab_type": "code",
"colab": {}
},
"source": [
"# construct the head of the model that will be placed on top of the\n",
"# the base model\n",
"headModel = baseModel.output\n",
"headModel = AveragePooling2D(pool_size=(4, 4))(headModel)\n",
"headModel = Flatten(name=\"flatten\")(headModel)\n",
"headModel = Dense(64, activation=\"relu\")(headModel)\n",
"headModel = Dropout(0.5)(headModel)\n",
"headModel = Dense(2, activation=\"softmax\")(headModel)"
],
"execution_count": 0,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "1bPTJ-1zz4Rr",
"colab_type": "code",
"colab": {}
},
"source": [
"# place the head FC model on top of the base model (this will become\n",
"# the actual model we will train)\n",
"model = Model(inputs=baseModel.input, outputs=headModel)"
],
"execution_count": 0,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "0F1S774K0-IL",
"colab_type": "code",
"colab": {}
},
"source": [
"# loop over all layers in the base model and freeze them so they will\n",
"# *not* be updated during the first training process\n",
"for layer in baseModel.layers:\n",
"\tlayer.trainable = False"
],
"execution_count": 0,
"outputs": []
},
{
"cell_type": "markdown",
"metadata": {
"id": "-57TIjytWdhW",
"colab_type": "text"
},
"source": [
"## Compile and Train our COVID-19 (Novel Coronavirus) Deep Learning Model"
]
},
{
"cell_type": "code",
"metadata": {
"id": "bZAhBL-r1CQq",
"colab_type": "code",
"outputId": "d1b227e8-a87c-46ce-d7e1-85a65eddfa6b",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 34
}
},
"source": [
"# compile our model\n",
"print(\"[INFO] compiling model...\")\n",
"opt = Adam(lr=INIT_LR, decay=INIT_LR / EPOCHS)\n",
"# given that this is a 2-class problem, we use \"binary_crossentropy\" loss\n",
"# rather than categorical crossentropy\n",
"model.compile(loss=\"binary_crossentropy\", optimizer=opt,\n",
"\tmetrics=[\"accuracy\"])"
],
"execution_count": 112,
"outputs": [
{
"output_type": "stream",
"text": [
"[INFO] compiling model...\n"
],
"name": "stdout"
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "DcsiBdEiWuCl",
"colab_type": "code",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 1000
},
"outputId": "720ec732-5309-45cf-b941-53808da744f5"
},
"source": [
"# train the head of the network\n",
"print(\"[INFO] training head...\")\n",
"H = model.fit_generator(\n",
"\ttrainAug.flow(trainX, trainY, batch_size=BS),\n",
"\tsteps_per_epoch=len(trainX) // BS,\n",
"\tvalidation_data=(testX, testY),\n",
"\tvalidation_steps=len(testX) // BS,\n",
"\tepochs=EPOCHS)"
],
"execution_count": 113,
"outputs": [
{
"output_type": "stream",
"text": [
"[INFO] training head...\n",
"Epoch 1/25\n",
"4/5 [=======================>......] - ETA: 4s - loss: 0.8074 - acc: 0.5000Epoch 1/25\n",
"10/5 [============================================================] - 5s 541ms/sample - loss: 0.6900 - acc: 0.4000\n",
"5/5 [==============================] - 28s 6s/step - loss: 0.7906 - acc: 0.4750 - val_loss: 0.7002 - val_acc: 0.4000\n",
"Epoch 2/25\n",
"4/5 [=======================>......] - ETA: 4s - loss: 0.8129 - acc: 0.5000Epoch 1/25\n",
"10/5 [============================================================] - 5s 520ms/sample - loss: 0.6944 - acc: 0.5000\n",
"5/5 [==============================] - 26s 5s/step - loss: 0.8463 - acc: 0.4750 - val_loss: 0.7116 - val_acc: 0.5000\n",
"Epoch 3/25\n",
"4/5 [=======================>......] - ETA: 4s - loss: 0.9334 - acc: 0.3750Epoch 1/25\n",
"10/5 [============================================================] - 5s 523ms/sample - loss: 0.6626 - acc: 0.5000\n",
"5/5 [==============================] - 26s 5s/step - loss: 0.9154 - acc: 0.4000 - val_loss: 0.6693 - val_acc: 0.5000\n",
"Epoch 4/25\n",
"4/5 [=======================>......] - ETA: 4s - loss: 0.6753 - acc: 0.5312Epoch 1/25\n",
"10/5 [============================================================] - 5s 519ms/sample - loss: 0.6599 - acc: 0.5000\n",
"5/5 [==============================] - 26s 5s/step - loss: 0.6819 - acc: 0.5250 - val_loss: 0.6634 - val_acc: 0.5000\n",
"Epoch 5/25\n",
"4/5 [=======================>......] - ETA: 4s - loss: 0.6272 - acc: 0.5938Epoch 1/25\n",
"10/5 [============================================================] - 5s 523ms/sample - loss: 0.6402 - acc: 0.6000\n",
"5/5 [==============================] - 26s 5s/step - loss: 0.6574 - acc: 0.6000 - val_loss: 0.6426 - val_acc: 0.6000\n",
"Epoch 6/25\n",
"4/5 [=======================>......] - ETA: 4s - loss: 0.5795 - acc: 0.7500Epoch 1/25\n",
"10/5 [============================================================] - 5s 521ms/sample - loss: 0.6225 - acc: 0.6000\n",
"5/5 [==============================] - 26s 5s/step - loss: 0.6094 - acc: 0.6750 - val_loss: 0.6242 - val_acc: 0.6000\n",
"Epoch 7/25\n",
"4/5 [=======================>......] - ETA: 4s - loss: 0.6771 - acc: 0.5938Epoch 1/25\n",
"10/5 [============================================================] - 5s 524ms/sample - loss: 0.6057 - acc: 0.9000\n",
"5/5 [==============================] - 26s 5s/step - loss: 0.6696 - acc: 0.5750 - val_loss: 0.6072 - val_acc: 0.9000\n",
"Epoch 8/25\n",
"4/5 [=======================>......] - ETA: 4s - loss: 0.6181 - acc: 0.6562Epoch 1/25\n",
"10/5 [============================================================] - 5s 524ms/sample - loss: 0.5877 - acc: 0.9000\n",
"5/5 [==============================] - 26s 5s/step - loss: 0.5990 - acc: 0.6750 - val_loss: 0.5885 - val_acc: 0.9000\n",
"Epoch 9/25\n",
"4/5 [=======================>......] - ETA: 4s - loss: 0.5830 - acc: 0.5625Epoch 1/25\n",
"10/5 [============================================================] - 5s 522ms/sample - loss: 0.5722 - acc: 0.9000\n",
"5/5 [==============================] - 26s 5s/step - loss: 0.5946 - acc: 0.6000 - val_loss: 0.5727 - val_acc: 0.9000\n",
"Epoch 10/25\n",
"4/5 [=======================>......] - ETA: 4s - loss: 0.6184 - acc: 0.6250Epoch 1/25\n",
"10/5 [============================================================] - 5s 521ms/sample - loss: 0.5552 - acc: 1.0000\n",
"5/5 [==============================] - 26s 5s/step - loss: 0.5971 - acc: 0.6750 - val_loss: 0.5548 - val_acc: 1.0000\n",
"Epoch 11/25\n",
"4/5 [=======================>......] - ETA: 4s - loss: 0.5461 - acc: 0.7188Epoch 1/25\n",
"10/5 [============================================================] - 5s 516ms/sample - loss: 0.5419 - acc: 0.9000\n",
"5/5 [==============================] - 26s 5s/step - loss: 0.5636 - acc: 0.7250 - val_loss: 0.5408 - val_acc: 0.9000\n",
"Epoch 12/25\n",
"4/5 [=======================>......] - ETA: 4s - loss: 0.4810 - acc: 0.8125Epoch 1/25\n",
"10/5 [============================================================] - 5s 521ms/sample - loss: 0.5267 - acc: 1.0000\n",
"5/5 [==============================] - 26s 5s/step - loss: 0.4990 - acc: 0.7750 - val_loss: 0.5238 - val_acc: 1.0000\n",
"Epoch 13/25\n",
"4/5 [=======================>......] - ETA: 4s - loss: 0.5292 - acc: 0.7188Epoch 1/25\n",
"10/5 [============================================================] - 5s 515ms/sample - loss: 0.5120 - acc: 1.0000\n",
"5/5 [==============================] - 26s 5s/step - loss: 0.5119 - acc: 0.7250 - val_loss: 0.5086 - val_acc: 1.0000\n",
"Epoch 14/25\n",
"4/5 [=======================>......] - ETA: 4s - loss: 0.5016 - acc: 0.7812Epoch 1/25\n",
"10/5 [============================================================] - 5s 519ms/sample - loss: 0.4990 - acc: 0.9000\n",
"5/5 [==============================] - 26s 5s/step - loss: 0.4782 - acc: 0.8250 - val_loss: 0.4951 - val_acc: 0.9000\n",
"Epoch 15/25\n",
"4/5 [=======================>......] - ETA: 4s - loss: 0.4332 - acc: 0.8438Epoch 1/25\n",
"10/5 [============================================================] - 5s 519ms/sample - loss: 0.4828 - acc: 1.0000\n",
"5/5 [==============================] - 26s 5s/step - loss: 0.4538 - acc: 0.8250 - val_loss: 0.4791 - val_acc: 1.0000\n",
"Epoch 16/25\n",
"4/5 [=======================>......] - ETA: 4s - loss: 0.4967 - acc: 0.8438Epoch 1/25\n",
"10/5 [============================================================] - 5s 518ms/sample - loss: 0.4623 - acc: 1.0000\n",
"5/5 [==============================] - 26s 5s/step - loss: 0.5060 - acc: 0.8000 - val_loss: 0.4607 - val_acc: 1.0000\n",
"Epoch 17/25\n",
"4/5 [=======================>......] - ETA: 4s - loss: 0.4402 - acc: 0.8750Epoch 1/25\n",
"10/5 [============================================================] - 5s 519ms/sample - loss: 0.4508 - acc: 1.0000\n",
"5/5 [==============================] - 26s 5s/step - loss: 0.4336 - acc: 0.8750 - val_loss: 0.4499 - val_acc: 1.0000\n",
"Epoch 18/25\n",
"4/5 [=======================>......] - ETA: 4s - loss: 0.4267 - acc: 0.8438Epoch 1/25\n",
"10/5 [============================================================] - 5s 512ms/sample - loss: 0.4480 - acc: 1.0000\n",
"5/5 [==============================] - 26s 5s/step - loss: 0.4075 - acc: 0.8750 - val_loss: 0.4441 - val_acc: 1.0000\n",
"Epoch 19/25\n",
"4/5 [=======================>......] - ETA: 4s - loss: 0.3768 - acc: 0.9375Epoch 1/25\n",
"10/5 [============================================================] - 5s 521ms/sample - loss: 0.4411 - acc: 1.0000\n",
"5/5 [==============================] - 26s 5s/step - loss: 0.3933 - acc: 0.9000 - val_loss: 0.4348 - val_acc: 1.0000\n",
"Epoch 20/25\n",
"4/5 [=======================>......] - ETA: 4s - loss: 0.4058 - acc: 0.9062Epoch 1/25\n",
"10/5 [============================================================] - 5s 510ms/sample - loss: 0.4168 - acc: 1.0000\n",
"5/5 [==============================] - 26s 5s/step - loss: 0.3710 - acc: 0.9250 - val_loss: 0.4126 - val_acc: 1.0000\n",
"Epoch 21/25\n",
"4/5 [=======================>......] - ETA: 4s - loss: 0.3716 - acc: 0.9688Epoch 1/25\n",
"10/5 [============================================================] - 5s 516ms/sample - loss: 0.4035 - acc: 1.0000\n",
"5/5 [==============================] - 26s 5s/step - loss: 0.3809 - acc: 0.9750 - val_loss: 0.3999 - val_acc: 1.0000\n",
"Epoch 22/25\n",
"4/5 [=======================>......] - ETA: 4s - loss: 0.4062 - acc: 0.9062Epoch 1/25\n",
"10/5 [============================================================] - 5s 518ms/sample - loss: 0.3942 - acc: 1.0000\n",
"5/5 [==============================] - 26s 5s/step - loss: 0.4105 - acc: 0.9000 - val_loss: 0.3885 - val_acc: 1.0000\n",
"Epoch 23/25\n",
"4/5 [=======================>......] - ETA: 4s - loss: 0.3891 - acc: 0.9062Epoch 1/25\n",
"10/5 [============================================================] - 5s 510ms/sample - loss: 0.3829 - acc: 1.0000\n",
"5/5 [==============================] - 26s 5s/step - loss: 0.3935 - acc: 0.9000 - val_loss: 0.3763 - val_acc: 1.0000\n",
"Epoch 24/25\n",
"4/5 [=======================>......] - ETA: 4s - loss: 0.3775 - acc: 0.8750Epoch 1/25\n",
"10/5 [============================================================] - 5s 516ms/sample - loss: 0.3823 - acc: 1.0000\n",
"5/5 [==============================] - 26s 5s/step - loss: 0.3753 - acc: 0.9000 - val_loss: 0.3725 - val_acc: 1.0000\n",
"Epoch 25/25\n",
"4/5 [=======================>......] - ETA: 4s - loss: 0.3172 - acc: 0.9375Epoch 1/25\n",
"10/5 [============================================================] - 5s 511ms/sample - loss: 0.3979 - acc: 1.0000\n",
"5/5 [==============================] - 26s 5s/step - loss: 0.3311 - acc: 0.9500 - val_loss: 0.3827 - val_acc: 1.0000\n"
],
"name": "stdout"
}
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "4qi5pRFaYafc",
"colab_type": "text"
},
"source": [
"## Evaluate our Model"
]
},
{
"cell_type": "code",
"metadata": {
"id": "LGEhLOje1lZD",
"colab_type": "code",
"outputId": "d24774c6-2d5d-4597-e4ee-6940f4171a37",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 34
}
},
"source": [
"# make predictions on the testing set\n",
"print(\"[INFO] evaluating network...\")\n",
"predIdxs = model.predict(testX, batch_size=BS)"
],
"execution_count": 114,
"outputs": [
{
"output_type": "stream",
"text": [
"[INFO] evaluating network...\n"
],
"name": "stdout"
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "mgmE_mib_Zu-",
"colab_type": "code",
"colab": {}
},
"source": [
"# for each image in the testing set we need to find the index of the\n",
"# label with corresponding largest predicted probability\n",
"predIdxs = np.argmax(predIdxs, axis=1)"
],
"execution_count": 0,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "vxqO7tst_ffA",
"colab_type": "code",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 170
},
"outputId": "44a5bf7e-bcd0-45b1-9450-5375204cc895"
},
"source": [
"# show a nicely formatted classification report\n",
"# using scikit-learn’s helper utility\n",
"print(classification_report(testY.argmax(axis=1), predIdxs,\n",
"\ttarget_names=lb.classes_))"
],
"execution_count": 116,
"outputs": [
{
"output_type": "stream",
"text": [
" precision recall f1-score support\n",
"\n",
" covid 1.00 1.00 1.00 5\n",
" normal 1.00 1.00 1.00 5\n",
"\n",
" accuracy 1.00 10\n",
" macro avg 1.00 1.00 1.00 10\n",
"weighted avg 1.00 1.00 1.00 10\n",
"\n"
],
"name": "stdout"
}
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "6KLseFOJYz8P",
"colab_type": "text"
},
"source": [
"## Compute a Confusion Matrix for Further Statistical Evaluation"
]
},
{
"cell_type": "code",
"metadata": {
"id": "r6u2XiVj_iXx",
"colab_type": "code",
"colab": {}
},
"source": [
"# compute the confusion matrix and and use it to derive the raw\n",
"# accuracy, sensitivity, and specificity\n",
"cm = confusion_matrix(testY.argmax(axis=1), predIdxs)\n",
"total = sum(sum(cm))\n",
"acc = (cm[0, 0] + cm[1, 1]) / total\n",
"sensitivity = cm[0, 0] / (cm[0, 0] + cm[0, 1])\n",
"specificity = cm[1, 1] / (cm[1, 0] + cm[1, 1])\n"
],
"execution_count": 0,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "MYkydJsk_nNE",
"colab_type": "code",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 102
},
"outputId": "e9a04cc5-cb27-4d53-b409-e1c717530fff"
},
"source": [
"# show the confusion matrix, accuracy, sensitivity, and specificity\n",
"print(cm)\n",
"print(\"acc: {:.4f}\".format(acc))\n",
"print(\"sensitivity: {:.4f}\".format(sensitivity))\n",
"print(\"specificity: {:.4f}\".format(specificity))"
],
"execution_count": 118,
"outputs": [
{
"output_type": "stream",
"text": [
"[[5 0]\n",
" [0 5]]\n",
"acc: 1.0000\n",
"sensitivity: 1.0000\n",
"specificity: 1.0000\n"
],
"name": "stdout"
}
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "3e2UzBGYZP3b",
"colab_type": "text"
},
"source": [
"## Plot our Training Accuracy/Loss History for Inspection"
]
},
{
"cell_type": "code",
"metadata": {
"id": "_tnWWhE-_qhR",
"colab_type": "code",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 626
},
"outputId": "753fe8ef-1924-4c89-a6bc-01ef2019c931"
},
"source": [
"# plot the training loss and accuracy\n",
"N = EPOCHS\n",
"plt.style.use(\"ggplot\")\n",
"plt.figure(figsize=(20,10))\n",
"plt.plot(np.arange(0, N), H.history[\"loss\"], label=\"train_loss\")\n",
"plt.plot(np.arange(0, N), H.history[\"val_loss\"], label=\"val_loss\")\n",
"plt.plot(np.arange(0, N), H.history[\"acc\"], label=\"train_acc\")\n",
"plt.plot(np.arange(0, N), H.history[\"val_acc\"], label=\"val_acc\")\n",
"plt.title(\"Training Loss and Accuracy on COVID-19 Dataset\")\n",
"plt.xlabel(\"Epoch #\")\n",
"plt.ylabel(\"Loss/Accuracy\")\n",
"plt.legend(loc=\"lower left\")\n",
"plt.savefig(args[\"plot\"])\n"
],
"execution_count": 119,
"outputs": [
{
"output_type": "display_data",
"data": {
"image/png": "iVBORw0KGgoAAAANSUhEUgAABJIAAAJhCAYAAAAaO5qSAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nERERERERERGpk/8PHy32LQLtTi4AAAAASUVORK5CYII=\n",
"text/plain": [
"<Figure size 1440x720 with 1 Axes>"
]
},
"metadata": {
"tags": []
}
}
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "H3A3s_MRZVkm",
"colab_type": "text"
},
"source": [
"## Serialize our tf.keras COVID-19 Classifier Model to Disk"
]
},
{
"cell_type": "code",
"metadata": {
"id": "bi9Ly3qc_ua-",
"colab_type": "code",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 34
},
"outputId": "e543dcab-162c-41c1-9ab0-6a14fe529887"
},
"source": [
"# serialize the model to disk\n",
"print(\"[INFO] saving COVID-19 detector model...\")\n",
"model.save(args[\"model\"], save_format=\"h5\")"
],
"execution_count": 120,
"outputs": [
{
"output_type": "stream",
"text": [
"[INFO] saving COVID-19 detector model...\n"
],
"name": "stdout"
}
]
}
]
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment