{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.10.12","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"nvidiaTeslaT4","dataSources":[{"sourceId":3362,"databundleVersionId":31148,"sourceType":"competition"}],"dockerImageVersionId":30627,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":true}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"# This Python 3 environment comes with many helpful analytics libraries installed\n# It is defined by the kaggle/python Docker image: https://github.com/kaggle/docker-python\n# For example, here's several helpful packages to load\n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n\n# Input data files are available in the read-only \"../input/\" directory\n# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\n\nimport os\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))\n\n# You can write up to 20GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using \"Save & Run All\" \n# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","execution":{"iopub.status.busy":"2026-09-10T04:28:13.492258Z","iopub.execute_input":"2026-09-10T04:28:13.492597Z","iopub.status.idle":"2026-09-10T04:28:13.501276Z","shell.execute_reply.started":"2026-09-10T04:28:13.492572Z","shell.execute_reply":"2026-09-10T04:28:13.500340Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"!python --version","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-10T04:28:13.502675Z","iopub.execute_input":"2026-09-10T04:28:13.503050Z","iopub.status.idle":"2026-09-10T04:28:14.557280Z","shell.execute_reply.started":"2026-09-10T04:28:13.503014Z","shell.execute_reply":"2026-09-10T04:28:14.556129Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"!uname --all","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-10T04:28:14.558560Z","iopub.execute_input":"2026-09-10T04:28:14.559243Z","iopub.status.idle":"2026-09-10T04:28:15.584211Z","shell.execute_reply.started":"2026-09-10T04:28:14.559215Z","shell.execute_reply":"2026-09-10T04:28:15.583096Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import os\nprint(os.listdir(\"../input\"))\n\nimport zipfile\n\nwith zipfile.ZipFile(\"/kaggle/input/dogs-vs-cats/test1.zip\",\"r\") as z:\n    z.extractall(\".\")\n    \nwith zipfile.ZipFile(\"/kaggle/input/dogs-vs-cats/train.zip\",\"r\") as z:\n    z.extractall(\".\")","metadata":{"execution":{"iopub.status.busy":"2026-09-10T04:28:15.585777Z","iopub.execute_input":"2026-09-10T04:28:15.586148Z","iopub.status.idle":"2026-09-10T04:28:26.907443Z","shell.execute_reply.started":"2026-09-10T04:28:15.586119Z","shell.execute_reply":"2026-09-10T04:28:26.906591Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-10T04:28:26.908807Z","iopub.execute_input":"2026-09-10T04:28:26.909140Z","iopub.status.idle":"2026-09-10T04:28:27.983708Z","shell.execute_reply.started":"2026-09-10T04:28:26.909108Z","shell.execute_reply":"2026-09-10T04:28:27.982322Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -l","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-10T04:28:27.988314Z","iopub.execute_input":"2026-09-10T04:28:27.988842Z","iopub.status.idle":"2026-09-10T04:28:29.028286Z","shell.execute_reply.started":"2026-09-10T04:28:27.988812Z","shell.execute_reply":"2026-09-10T04:28:29.026931Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls test1","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-10T04:28:29.030029Z","iopub.execute_input":"2026-09-10T04:28:29.030296Z","iopub.status.idle":"2026-09-10T04:28:30.107829Z","shell.execute_reply.started":"2026-09-10T04:28:29.030273Z","shell.execute_reply":"2026-09-10T04:28:30.106541Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls test1/ | wc -l","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-10T04:28:30.109400Z","iopub.execute_input":"2026-09-10T04:28:30.109689Z","iopub.status.idle":"2026-09-10T04:28:31.184598Z","shell.execute_reply.started":"2026-09-10T04:28:30.109666Z","shell.execute_reply":"2026-09-10T04:28:31.183562Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls train/ | wc -l","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-10T04:28:31.186017Z","iopub.execute_input":"2026-09-10T04:28:31.186330Z","iopub.status.idle":"2026-09-10T04:28:32.295674Z","shell.execute_reply.started":"2026-09-10T04:28:31.186305Z","shell.execute_reply":"2026-09-10T04:28:32.294586Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"#ls train/","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-10T04:28:32.297168Z","iopub.execute_input":"2026-09-10T04:28:32.297465Z","iopub.status.idle":"2026-09-10T04:28:32.302440Z","shell.execute_reply.started":"2026-09-10T04:28:32.297441Z","shell.execute_reply":"2026-09-10T04:28:32.301447Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"pwd","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-10T04:28:32.304059Z","iopub.execute_input":"2026-09-10T04:28:32.304453Z","iopub.status.idle":"2026-09-10T04:28:32.315342Z","shell.execute_reply.started":"2026-09-10T04:28:32.304421Z","shell.execute_reply":"2026-09-10T04:28:32.314407Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-10T04:28:32.316835Z","iopub.execute_input":"2026-09-10T04:28:32.317622Z","iopub.status.idle":"2026-09-10T04:28:33.338780Z","shell.execute_reply.started":"2026-09-10T04:28:32.317579Z","shell.execute_reply":"2026-09-10T04:28:33.337642Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -U train | head -n 10","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-10T04:28:33.340109Z","iopub.execute_input":"2026-09-10T04:28:33.340387Z","iopub.status.idle":"2026-09-10T04:28:34.448153Z","shell.execute_reply.started":"2026-09-10T04:28:33.340364Z","shell.execute_reply":"2026-09-10T04:28:34.446837Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -U test1 | head -n 10","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-10T04:28:34.450425Z","iopub.execute_input":"2026-09-10T04:28:34.450846Z","iopub.status.idle":"2026-09-10T04:28:35.513569Z","shell.execute_reply.started":"2026-09-10T04:28:34.450808Z","shell.execute_reply":"2026-09-10T04:28:35.512145Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# plot dog photos from the dogs vs cats dataset\nfrom matplotlib import pyplot\n# from matplotlib import pyplot as plt\nfrom matplotlib.image import imread\n# define location of dataset\nfolder = 'train/'\n# plot first few images\nfor i in range(9):\n\t# define subplot\n\tpyplot.subplot(330 + 1 + i)\n\t# define filename\n\tfilename = folder + 'dog.' + str(i) + '.jpg'\n\t# load image pixels\n\timage = imread(filename)\n\t# plot raw pixel data\n\tpyplot.imshow(image)\n# show the figure\npyplot.show()","metadata":{"execution":{"iopub.status.busy":"2026-09-10T04:28:35.515220Z","iopub.execute_input":"2026-09-10T04:28:35.515565Z","iopub.status.idle":"2026-09-10T04:28:36.566433Z","shell.execute_reply.started":"2026-09-10T04:28:35.515539Z","shell.execute_reply":"2026-09-10T04:28:36.565468Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# plot cat photos from the dogs vs cats dataset\nfrom matplotlib import pyplot\nfrom matplotlib.image import imread\n# define location of dataset\nfolder = 'train/'\n# plot first few images\nfor i in range(9):\n\t# define subplot\n\tpyplot.subplot(330 + 1 + i)\n\t# define filename\n\tfilename = folder + 'cat.' + str(i) + '.jpg'\n\t# load image pixels\n\timage = imread(filename)\n\t# plot raw pixel data\n\tpyplot.imshow(image)\n# show the figure\npyplot.show()","metadata":{"execution":{"iopub.status.busy":"2026-09-10T04:28:36.567966Z","iopub.execute_input":"2026-09-10T04:28:36.569168Z","iopub.status.idle":"2026-09-10T04:28:37.657321Z","shell.execute_reply.started":"2026-09-10T04:28:36.569115Z","shell.execute_reply":"2026-09-10T04:28:37.656381Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"!python --version","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-10T04:28:37.658450Z","iopub.execute_input":"2026-09-10T04:28:37.658816Z","iopub.status.idle":"2026-09-10T04:28:38.701292Z","shell.execute_reply.started":"2026-09-10T04:28:37.658792Z","shell.execute_reply":"2026-09-10T04:28:38.700222Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import tensorflow\nprint(tensorflow.__version__)\n\nimport keras\nprint(keras.__version__)\n\nimport tensorflow.keras\nprint(tensorflow.__version__)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-10T04:28:38.703023Z","iopub.execute_input":"2026-09-10T04:28:38.703383Z","iopub.status.idle":"2026-09-10T04:28:38.839335Z","shell.execute_reply.started":"2026-09-10T04:28:38.703355Z","shell.execute_reply":"2026-09-10T04:28:38.838376Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# load dogs vs cats dataset, reshape and save to a new file\nfrom os import listdir\nfrom numpy import asarray\nfrom numpy import save\nfrom keras.preprocessing.image import load_img\nfrom keras.preprocessing.image import img_to_array","metadata":{"execution":{"iopub.status.busy":"2026-09-10T04:28:38.840643Z","iopub.execute_input":"2026-09-10T04:28:38.840914Z","iopub.status.idle":"2026-09-10T04:28:38.845869Z","shell.execute_reply.started":"2026-09-10T04:28:38.840892Z","shell.execute_reply":"2026-09-10T04:28:38.844806Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# define location of dataset\nfolder = 'train/'\nphotos, labels = list(), list()\n# enumerate files in the directory\nfor file in listdir(folder):\n\t# determine class\n\toutput = 0.0\n\tif file.startswith('dog'):\n\t\toutput = 1.0\n\t# load image\n\tphoto = load_img(folder + file, target_size=(200, 200))\n\t# convert to numpy array\n\tphoto = img_to_array(photo)\n\t# store\n\tphotos.append(photo)\n\tlabels.append(output)\n# convert to a numpy arrays\nphotos = asarray(photos)\nlabels = asarray(labels)\nprint(photos.shape, labels.shape)\n# save the reshaped photos\nsave('dogs_vs_cats_photos.npy', photos)\nsave('dogs_vs_cats_labels.npy', labels)","metadata":{"execution":{"iopub.status.busy":"2024-01-27T03:36:15.416611Z","iopub.execute_input":"2024-01-27T03:36:15.417128Z","iopub.status.idle":"2024-01-27T03:36:38.886396Z","shell.execute_reply.started":"2024-01-27T03:36:15.417101Z","shell.execute_reply":"2024-01-27T03:36:38.883149Z"}}},{"cell_type":"markdown","source":"# load and confirm the shape\nfrom numpy import load\nphotos = load('dogs_vs_cats_photos.npy')\nlabels = load('dogs_vs_cats_labels.npy')","metadata":{"execution":{"iopub.status.busy":"2024-01-27T03:36:38.88711Z","iopub.status.idle":"2024-01-27T03:36:38.887458Z","shell.execute_reply.started":"2024-01-27T03:36:38.887281Z","shell.execute_reply":"2024-01-27T03:36:38.887296Z"}}},{"cell_type":"code","source":"# organize dataset into a useful structure\nfrom os import makedirs\nfrom os import listdir\nfrom shutil import copyfile\nfrom random import seed\nfrom random import random","metadata":{"execution":{"iopub.status.busy":"2026-09-10T04:28:38.847261Z","iopub.execute_input":"2026-09-10T04:28:38.847688Z","iopub.status.idle":"2026-09-10T04:28:38.859361Z","shell.execute_reply.started":"2026-09-10T04:28:38.847661Z","shell.execute_reply":"2026-09-10T04:28:38.858277Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# create directories\ndataset_home = 'dataset_dogs_vs_cats/'\nsubdirs = ['train/', 'test/'] #test==>validation\nfor subdir in subdirs:\n    # create label subdirectories\n    labeldirs = ['dogs/', 'cats/']\n    for labldir in labeldirs:\n        newdir = dataset_home + subdir + labldir       \n        makedirs(newdir, exist_ok=True)\n        print(newdir)","metadata":{"execution":{"iopub.status.busy":"2026-09-10T04:28:38.860721Z","iopub.execute_input":"2026-09-10T04:28:38.861068Z","iopub.status.idle":"2026-09-10T04:28:38.869445Z","shell.execute_reply.started":"2026-09-10T04:28:38.861042Z","shell.execute_reply":"2026-09-10T04:28:38.868533Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -l dataset_dogs_vs_cats/train/dogs/ | wc -l","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-10T04:28:38.870906Z","iopub.execute_input":"2026-09-10T04:28:38.871371Z","iopub.status.idle":"2026-09-10T04:28:39.919673Z","shell.execute_reply.started":"2026-09-10T04:28:38.871335Z","shell.execute_reply":"2026-09-10T04:28:39.918425Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -l","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-10T04:28:39.921256Z","iopub.execute_input":"2026-09-10T04:28:39.921579Z","iopub.status.idle":"2026-09-10T04:28:40.977226Z","shell.execute_reply.started":"2026-09-10T04:28:39.921552Z","shell.execute_reply":"2026-09-10T04:28:40.976199Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -l dataset_dogs_vs_cats/train","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-10T04:28:40.978855Z","iopub.execute_input":"2026-09-10T04:28:40.979189Z","iopub.status.idle":"2026-09-10T04:28:42.022647Z","shell.execute_reply.started":"2026-09-10T04:28:40.979157Z","shell.execute_reply":"2026-09-10T04:28:42.021280Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -l dataset_dogs_vs_cats/test #validation","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-10T04:28:42.024300Z","iopub.execute_input":"2026-09-10T04:28:42.024658Z","iopub.status.idle":"2026-09-10T04:28:43.062172Z","shell.execute_reply.started":"2026-09-10T04:28:42.024633Z","shell.execute_reply":"2026-09-10T04:28:43.061246Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# seed random number generator\nseed(1337)\n# define ratio of pictures to use for validation\nval_ratio = 0.25 #changable\n# copy training dataset images into subdirectories\nsrc_directory = 'train/'\n\nfor file in listdir(src_directory):\n\tsrc = src_directory + '/' + file\n\tdst_dir = 'train/'\n\tif random() < val_ratio:\n\t\tdst_dir = 'test/'\n\tif file.startswith('cat'):\n\t\tdst = dataset_home + dst_dir + 'cats/'  + file\n\t\tcopyfile(src, dst)\n\telif file.startswith('dog'):\n\t\tdst = dataset_home + dst_dir + 'dogs/'  + file\n\t\tcopyfile(src, dst)","metadata":{"execution":{"iopub.status.busy":"2026-09-10T04:28:43.063614Z","iopub.execute_input":"2026-09-10T04:28:43.063910Z","iopub.status.idle":"2026-09-10T04:28:45.142380Z","shell.execute_reply.started":"2026-09-10T04:28:43.063886Z","shell.execute_reply":"2026-09-10T04:28:45.141134Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"print(src)\nprint(dst)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-10T04:28:45.143899Z","iopub.execute_input":"2026-09-10T04:28:45.144181Z","iopub.status.idle":"2026-09-10T04:28:45.149458Z","shell.execute_reply.started":"2026-09-10T04:28:45.144158Z","shell.execute_reply":"2026-09-10T04:28:45.148519Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"!ls -l dataset_dogs_vs_cats/train/dogs | wc -l\n!ls -l dataset_dogs_vs_cats/train/cats | wc -l","metadata":{"execution":{"iopub.status.busy":"2026-09-10T04:28:45.150868Z","iopub.execute_input":"2026-09-10T04:28:45.151232Z","iopub.status.idle":"2026-09-10T04:28:47.367455Z","shell.execute_reply.started":"2026-09-10T04:28:45.151200Z","shell.execute_reply":"2026-09-10T04:28:47.366366Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"#validation set\n!ls -l dataset_dogs_vs_cats/test/dogs | wc -l\n!ls -l dataset_dogs_vs_cats/test/cats | wc -l","metadata":{"execution":{"iopub.status.busy":"2026-09-10T04:28:47.374331Z","iopub.execute_input":"2026-09-10T04:28:47.374728Z","iopub.status.idle":"2026-09-10T04:28:49.449843Z","shell.execute_reply.started":"2026-09-10T04:28:47.374703Z","shell.execute_reply":"2026-09-10T04:28:49.448377Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"!pip -q install livelossplot==0.5.5","metadata":{"execution":{"iopub.status.busy":"2026-09-10T04:28:49.451658Z","iopub.execute_input":"2026-09-10T04:28:49.452084Z","iopub.status.idle":"2026-09-10T04:29:01.818343Z","shell.execute_reply.started":"2026-09-10T04:28:49.452043Z","shell.execute_reply":"2026-09-10T04:29:01.816906Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"from livelossplot import PlotLossesKeras","metadata":{"execution":{"iopub.status.busy":"2026-09-10T04:29:01.820047Z","iopub.execute_input":"2026-09-10T04:29:01.820791Z","iopub.status.idle":"2026-09-10T04:29:01.837573Z","shell.execute_reply.started":"2026-09-10T04:29:01.820763Z","shell.execute_reply":"2026-09-10T04:29:01.836562Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"Prepare Final Dataset","metadata":{}},{"cell_type":"markdown","source":"# Start tutorial\n# Develop a Baseline CNN Model","metadata":{}},{"cell_type":"code","source":"# https://keras.io/api/applications/","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-10T04:29:01.838670Z","iopub.execute_input":"2026-09-10T04:29:01.838902Z","iopub.status.idle":"2026-09-10T04:29:01.843960Z","shell.execute_reply.started":"2026-09-10T04:29:01.838883Z","shell.execute_reply":"2026-09-10T04:29:01.842470Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# baseline model for the dogs vs cats dataset\nimport sys\nfrom matplotlib import pyplot\nfrom keras.utils import to_categorical\nfrom keras.models import Sequential\nfrom keras.layers import Conv2D\nfrom keras.layers import MaxPooling2D\nfrom keras.layers import Dense\nfrom keras.layers import Flatten\nfrom keras.optimizers import SGD\nfrom keras.preprocessing.image import ImageDataGenerator","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-10T04:29:01.845425Z","iopub.execute_input":"2026-09-10T04:29:01.845770Z","iopub.status.idle":"2026-09-10T04:29:01.852781Z","shell.execute_reply.started":"2026-09-10T04:29:01.845740Z","shell.execute_reply":"2026-09-10T04:29:01.851984Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"model = Sequential()\ntype(model)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-10T04:29:01.853844Z","iopub.execute_input":"2026-09-10T04:29:01.854065Z","iopub.status.idle":"2026-09-10T04:29:01.869102Z","shell.execute_reply.started":"2026-09-10T04:29:01.854046Z","shell.execute_reply":"2026-09-10T04:29:01.868122Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"model = Sequential()\n\nmodel.add(Conv2D(32,\n                 (3, 3),\n                 activation='relu',\n                 input_shape=(200, 200, 3)\n                )\n         )\n\nmodel.add(MaxPooling2D((2, 2)))\n\nmodel.add(Flatten())\n\nmodel.add(Dense(128, activation='relu'))\n\nmodel.add(Dense(1, activation='sigmoid'))\n\nprint(model.summary())","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-10T04:29:01.870258Z","iopub.execute_input":"2026-09-10T04:29:01.870643Z","iopub.status.idle":"2026-09-10T04:29:01.937969Z","shell.execute_reply.started":"2026-09-10T04:29:01.870618Z","shell.execute_reply":"2026-09-10T04:29:01.937040Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"model = Sequential()\n\nmodel.add(Conv2D(32,\n                 (3, 3),\n                 activation='relu',\n                 input_shape=(200, 200, 3)\n                )\n         )\n\nmodel.add(MaxPooling2D((2, 2)))\n\nmodel.add(Flatten())\n\nmodel.add(Dense(128, activation='relu'))\n\nmodel.add(Dense(2, activation='softmax'))\n\nprint(model.summary())","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-10T04:29:01.939015Z","iopub.execute_input":"2026-09-10T04:29:01.939368Z","iopub.status.idle":"2026-09-10T04:29:02.008295Z","shell.execute_reply.started":"2026-09-10T04:29:01.939345Z","shell.execute_reply":"2026-09-10T04:29:02.007147Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# define cnn model\ndef define_model_1():\n\tmodel = Sequential()\n\tmodel.add(Conv2D(32, (3, 3), activation='relu', kernel_initializer='he_uniform', padding='same', input_shape=(200, 200, 3)))\n\tmodel.add(MaxPooling2D((2, 2)))\n\tmodel.add(Flatten())\n\tmodel.add(Dense(128, activation='relu', kernel_initializer='he_uniform'))\n\tmodel.add(Dense(1, activation='sigmoid'))\n\t# compile model\n\topt = SGD(lr=0.001, momentum=0.9)\n\tmodel.compile(optimizer=opt, loss='binary_crossentropy', metrics=['accuracy'])\n\treturn model","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-10T04:29:02.009643Z","iopub.execute_input":"2026-09-10T04:29:02.010393Z","iopub.status.idle":"2026-09-10T04:29:02.015950Z","shell.execute_reply.started":"2026-09-10T04:29:02.010354Z","shell.execute_reply":"2026-09-10T04:29:02.015165Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"model_1 = define_model_1()\nprint(model_1.summary())","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-10T04:29:02.017392Z","iopub.execute_input":"2026-09-10T04:29:02.017754Z","iopub.status.idle":"2026-09-10T04:29:02.091972Z","shell.execute_reply.started":"2026-09-10T04:29:02.017722Z","shell.execute_reply":"2026-09-10T04:29:02.091165Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# plot diagnostic learning curves\ndef summarize_diagnostics(history):\n    # plot loss\n    pyplot.subplot(211)\n    pyplot.title('Cross Entropy Loss')\n    pyplot.plot(history.history['loss'], color='blue', label='train')\n    pyplot.plot(history.history['val_loss'], color='orange', label='test')\n    # plot accuracy\n    pyplot.subplot(212)\n    pyplot.title('Classification Accuracy')\n    pyplot.plot(history.history['accuracy'], color='blue', label='train')\n    pyplot.plot(history.history['val_accuracy'], color='orange', label='test')\n    pyplot.show()\n    \n    # save plot to file\n    filename = sys.argv[0].split('/')[-1]\n    pyplot.savefig(filename + '_plot.png') \n    pyplot.close()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-10T04:29:02.096075Z","iopub.execute_input":"2026-09-10T04:29:02.096369Z","iopub.status.idle":"2026-09-10T04:29:02.103867Z","shell.execute_reply.started":"2026-09-10T04:29:02.096339Z","shell.execute_reply":"2026-09-10T04:29:02.102991Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# run the test harness for evaluating a model, not recommend to call this function\ndef run_test_harness():\n\t# define model\n\tmodel = define_model()\n\t# create data generator\n\tdatagen = ImageDataGenerator(rescale=1.0/255.0)\n\t# prepare iterators\n\ttrain_it = datagen.flow_from_directory('dataset_dogs_vs_cats/train/',\n\t\tclass_mode='binary', batch_size=64, target_size=(200, 200))\n\ttest_it = datagen.flow_from_directory('dataset_dogs_vs_cats/test/',\n\t\tclass_mode='binary', batch_size=64, target_size=(200, 200))\n\t# fit model\n\thistory = model.fit_generator(train_it, steps_per_epoch=len(train_it),\n\t\tvalidation_data=test_it, validation_steps=len(test_it), epochs=20, verbose=0)\n\t# evaluate model\n\t_, acc = model.evaluate_generator(test_it, steps=len(test_it), verbose=0)\n\tprint('> %.3f' % (acc * 100.0))","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-10T04:29:02.105173Z","iopub.execute_input":"2026-09-10T04:29:02.105532Z","iopub.status.idle":"2026-09-10T04:29:02.114067Z","shell.execute_reply.started":"2026-09-10T04:29:02.105485Z","shell.execute_reply":"2026-09-10T04:29:02.113215Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"model_1 = define_model_1()\nprint(model_1.summary())","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-10T04:29:02.115127Z","iopub.execute_input":"2026-09-10T04:29:02.115466Z","iopub.status.idle":"2026-09-10T04:29:02.190014Z","shell.execute_reply.started":"2026-09-10T04:29:02.115444Z","shell.execute_reply":"2026-09-10T04:29:02.188999Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"datagen = ImageDataGenerator(rescale=1.0/255.0)\ntype(datagen)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-10T04:29:02.191130Z","iopub.execute_input":"2026-09-10T04:29:02.191393Z","iopub.status.idle":"2026-09-10T04:29:02.199253Z","shell.execute_reply.started":"2026-09-10T04:29:02.191372Z","shell.execute_reply":"2026-09-10T04:29:02.198235Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls dataset_dogs_vs_cats/train/","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-10T04:29:02.200445Z","iopub.execute_input":"2026-09-10T04:29:02.200765Z","iopub.status.idle":"2026-09-10T04:29:03.251012Z","shell.execute_reply.started":"2026-09-10T04:29:02.200724Z","shell.execute_reply":"2026-09-10T04:29:03.249812Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Hyperparameter => changable\nIMAGE_SIZE = (200, 200)\nBATCH_SIE = 64\nEPOCHS = 20","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-10T04:29:03.253027Z","iopub.execute_input":"2026-09-10T04:29:03.253383Z","iopub.status.idle":"2026-09-10T04:29:03.258290Z","shell.execute_reply.started":"2026-09-10T04:29:03.253356Z","shell.execute_reply":"2026-09-10T04:29:03.257338Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"train_it = datagen.flow_from_directory('dataset_dogs_vs_cats/train/',\n\t\tclass_mode='binary',\n        batch_size=BATCH_SIE, \n        target_size=IMAGE_SIZE\n)\ntype(train_it)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-10T04:29:03.259807Z","iopub.execute_input":"2026-09-10T04:29:03.260163Z","iopub.status.idle":"2026-09-10T04:29:03.966607Z","shell.execute_reply.started":"2026-09-10T04:29:03.260131Z","shell.execute_reply":"2026-09-10T04:29:03.965433Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"len(train_it), len(train_it.classes), train_it.classes[:10]","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-10T04:29:03.968002Z","iopub.execute_input":"2026-09-10T04:29:03.968663Z","iopub.status.idle":"2026-09-10T04:29:03.975570Z","shell.execute_reply.started":"2026-09-10T04:29:03.968628Z","shell.execute_reply":"2026-09-10T04:29:03.974431Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"val_it = datagen.flow_from_directory('dataset_dogs_vs_cats/test/',\n\t\tclass_mode='binary',\n        batch_size=BATCH_SIZE,\n        target_size=IMAGE_SIZE\n)\ntype(val_it)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-10T04:29:03.976788Z","iopub.execute_input":"2026-09-10T04:29:03.977046Z","iopub.status.idle":"2026-09-10T04:29:04.515792Z","shell.execute_reply.started":"2026-09-10T04:29:03.977025Z","shell.execute_reply":"2026-09-10T04:29:04.514361Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"len(val_it), len(val_it.classes), val_it.classes[-10:]","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-10T04:30:43.516781Z","iopub.execute_input":"2026-09-10T04:30:43.517784Z","iopub.status.idle":"2026-09-10T04:30:43.551256Z","shell.execute_reply.started":"2026-09-10T04:30:43.517750Z","shell.execute_reply":"2026-09-10T04:30:43.550010Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# fit model\nmodel_1.reset_states()\nhistory_1 = model_1.fit(\n    train_it,\n    steps_per_epoch=len(train_it),\n    validation_data=val_it,\n    validation_steps=len(val_it),\n    epochs=EPOCHS,\n    verbose=2,\n    callbacks = [PlotLossesKeras()]\n    )","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-10T04:30:44.187232Z","iopub.execute_input":"2026-09-10T04:30:44.188243Z","iopub.status.idle":"2026-09-10T04:30:44.220995Z","shell.execute_reply.started":"2026-09-10T04:30:44.188208Z","shell.execute_reply":"2026-09-10T04:30:44.219351Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# learning curves\nsummarize_diagnostics(history_1)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-10T04:30:44.267690Z","iopub.execute_input":"2026-09-10T04:30:44.268550Z","iopub.status.idle":"2026-09-10T04:30:44.297726Z","shell.execute_reply.started":"2026-09-10T04:30:44.268515Z","shell.execute_reply":"2026-09-10T04:30:44.296284Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# evaluate model\n_, acc = model_1.evaluate(val_it, steps=len(val_it), verbose=1)\nprint('> %.3f' % (acc * 100.0))","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-10T04:30:49.074403Z","iopub.execute_input":"2026-09-10T04:30:49.075078Z","iopub.status.idle":"2026-09-10T04:30:49.105318Z","shell.execute_reply.started":"2026-09-10T04:30:49.075044Z","shell.execute_reply":"2026-09-10T04:30:49.103797Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls ","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-10T04:30:56.403620Z","iopub.execute_input":"2026-09-10T04:30:56.404368Z","iopub.status.idle":"2026-09-10T04:30:57.498796Z","shell.execute_reply.started":"2026-09-10T04:30:56.404337Z","shell.execute_reply":"2026-09-10T04:30:57.497453Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"pwd","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-10T04:30:57.500723Z","iopub.execute_input":"2026-09-10T04:30:57.501603Z","iopub.status.idle":"2026-09-10T04:30:57.508955Z","shell.execute_reply.started":"2026-09-10T04:30:57.501568Z","shell.execute_reply":"2026-09-10T04:30:57.507851Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import os\nimport pandas as pd\nfrom glob import glob\n\n# Define the image folder path\nimage_folder = '/kaggle/working/test1'\n\n# List all .jpg files in the directory (adjust the pattern if needed)\nimage_files = glob(os.path.join(image_folder, '*.jpg'))\n\n# Check if images were found\nif not image_files:\n    print(\"No images found. Please verify the directory and file extensions.\")\n    \n# Create a DataFrame with the file paths\ndf = pd.DataFrame({'filename': image_files})\n\n# If your use-case doesn't require labels (for example, during testing), you can leave out the label column.\n# Otherwise, if you need a dummy label, you can add one:\n# df['class'] = 'dummy_label'\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-10T04:30:58.234915Z","iopub.execute_input":"2026-09-10T04:30:58.235257Z","iopub.status.idle":"2026-09-10T04:30:58.277464Z","shell.execute_reply.started":"2026-09-10T04:30:58.235235Z","shell.execute_reply":"2026-09-10T04:30:58.276690Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"df.columns","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-10T04:31:01.147031Z","iopub.execute_input":"2026-09-10T04:31:01.147438Z","iopub.status.idle":"2026-09-10T04:31:01.156535Z","shell.execute_reply.started":"2026-09-10T04:31:01.147409Z","shell.execute_reply":"2026-09-10T04:31:01.155091Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"image_files[:5], type(image_files), len(image_files)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-10T04:31:01.379272Z","iopub.execute_input":"2026-09-10T04:31:01.380204Z","iopub.status.idle":"2026-09-10T04:31:01.386651Z","shell.execute_reply.started":"2026-09-10T04:31:01.380158Z","shell.execute_reply":"2026-09-10T04:31:01.385444Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"df.describe()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-10T04:31:01.803966Z","iopub.execute_input":"2026-09-10T04:31:01.804716Z","iopub.status.idle":"2026-09-10T04:31:01.838440Z","shell.execute_reply.started":"2026-09-10T04:31:01.804682Z","shell.execute_reply":"2026-09-10T04:31:01.837278Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"df.loc[1]","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-10T04:31:01.995251Z","iopub.execute_input":"2026-09-10T04:31:01.996009Z","iopub.status.idle":"2026-09-10T04:31:02.003193Z","shell.execute_reply.started":"2026-09-10T04:31:01.995974Z","shell.execute_reply":"2026-09-10T04:31:02.002088Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"df.sample(5)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-10T04:31:08.034587Z","iopub.execute_input":"2026-09-10T04:31:08.035363Z","iopub.status.idle":"2026-09-10T04:31:08.048135Z","shell.execute_reply.started":"2026-09-10T04:31:08.035329Z","shell.execute_reply":"2026-09-10T04:31:08.047035Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"df['filename']","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-10T04:31:08.228784Z","iopub.execute_input":"2026-09-10T04:31:08.229569Z","iopub.status.idle":"2026-09-10T04:31:08.236871Z","shell.execute_reply.started":"2026-09-10T04:31:08.229531Z","shell.execute_reply":"2026-09-10T04:31:08.235783Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"IMAGE_SIZE = (200, 200)\n\n# datagen = ImageDataGenerator(rescale=1.0/255.0,\n#                             horizontal_flip=True,)\n# print(IMAGE_SIZE)\n# # prepare iterators\n# train_it = datagen.flow_from_directory('dataset_dogs_vs_cats/train/',\n#     class_mode='binary', batch_size=64, target_size=IMAGE_SIZE )\n\n# val_it = datagen.flow_from_directory('dataset_dogs_vs_cats/test/',\n#     class_mode='binary', batch_size=64, target_size=IMAGE_SIZE )\n\n# Prediction\nfrom tensorflow.keras.preprocessing.image import ImageDataGenerator\n\n# Initialize your ImageDataGenerator (modify parameters as needed)\ndatagen_test = ImageDataGenerator(rescale=1./255,\n                                 vertical_flip=True)\n\n# Create the data generator using the DataFrame\ntest_it = datagen_test.flow_from_dataframe(\n    dataframe=df,\n    x_col='filename',\n    y_col=None,            # No labels for testing, so set to None\n    target_size=IMAGE_SIZE,\n    batch_size=64,\n    class_mode=None,       # Since there are no labels\n    # shuffle=True,         # Usually testing data should not be shuffled\n    shuffle=False,\n)\n\ntype(test_it)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-10T04:31:08.396377Z","iopub.execute_input":"2026-09-10T04:31:08.396759Z","iopub.status.idle":"2026-09-10T04:31:08.492401Z","shell.execute_reply.started":"2026-09-10T04:31:08.396731Z","shell.execute_reply":"2026-09-10T04:31:08.491555Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import matplotlib.pyplot as plt\n\n\ndef plot_exmaple(images, labels):\n    # Assuming images shape is (64, height, width, channels)\n    fig, axes = plt.subplots(8, 8, figsize=(16, 16))\n    axes = axes.flatten()  # Flatten the 8x8 grid into a 1D array for easy iteration\n\n    for i, ax in enumerate(axes):\n        if i < len(images):\n            ax.imshow(images[i])\n            ax.set_title(str(labels[i]))  # Fixed: set_title instead of title\n            ax.axis(\"off\")  # Turn off axis ticks/labels for clarity\n        else:\n            ax.axis(\"off\")  # Hide unused subplots if images < 64\n\n    plt.tight_layout()\n    plt.show()\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-10T04:31:08.771188Z","iopub.execute_input":"2026-09-10T04:31:08.772201Z","iopub.status.idle":"2026-09-10T04:31:08.778383Z","shell.execute_reply.started":"2026-09-10T04:31:08.772157Z","shell.execute_reply":"2026-09-10T04:31:08.777539Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"train_images, train_labels = train_it.__next__()\nprint(train_images.shape, len(train_labels))\nplot_exmaple(train_images, train_labels)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-10T04:31:09.115435Z","iopub.execute_input":"2026-09-10T04:31:09.115789Z","iopub.status.idle":"2026-09-10T04:31:14.516853Z","shell.execute_reply.started":"2026-09-10T04:31:09.115764Z","shell.execute_reply":"2026-09-10T04:31:14.515303Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"val_images, val_labels = val_it.__next__()\nval_images.shape\nplot_exmaple(val_images, val_labels)\nval_labels[:8]","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-10T04:31:14.519285Z","iopub.execute_input":"2026-09-10T04:31:14.519796Z","iopub.status.idle":"2026-09-10T04:31:14.567516Z","shell.execute_reply.started":"2026-09-10T04:31:14.519749Z","shell.execute_reply":"2026-09-10T04:31:14.565888Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"def plot_exmaple_test(images, indices):\n    # Assuming images shape is (64, height, width, channels)\n    fig, axes = plt.subplots(8, 8, figsize=(16, 16))\n    axes = axes.flatten()  # Flatten the 8x8 grid into a 1D array for easy iteration\n\n    for i, ax in enumerate(axes):\n        if i < len(images):\n            ax.imshow(images[i])\n            ax.set_title(str(indices[i]))  # ตั้งค่า title ด้วย index จาก list/array indices\n            ax.axis(\"off\")  # Turn off axis ticks/labels for clarity\n        else:\n            ax.axis(\"off\")  # Hide unused subplots if images < 64\n\n    plt.tight_layout()\n    plt.show()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-10T04:31:23.981826Z","iopub.execute_input":"2026-09-10T04:31:23.982804Z","iopub.status.idle":"2026-09-10T04:31:23.988995Z","shell.execute_reply.started":"2026-09-10T04:31:23.982770Z","shell.execute_reply":"2026-09-10T04:31:23.987809Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"test_images = test_it.__next__()  # หรือ next(test_it)\n\n# สร้าง list เลขดัชนีตามจำนวนภาพที่มี\nindices = list(range(len(test_images)))\n\nplot_exmaple_test(test_images, indices)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-10T04:31:26.332064Z","iopub.execute_input":"2026-09-10T04:31:26.332892Z","iopub.status.idle":"2026-09-10T04:31:31.774713Z","shell.execute_reply.started":"2026-09-10T04:31:26.332858Z","shell.execute_reply":"2026-09-10T04:31:31.773195Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Predict\npreds = model_1.predict(test_it, verbose=1)\ntype(preds), preds.shape","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-10T04:31:31.777230Z","iopub.execute_input":"2026-09-10T04:31:31.777735Z","iopub.status.idle":"2026-09-10T04:31:59.436329Z","shell.execute_reply.started":"2026-09-10T04:31:31.777687Z","shell.execute_reply":"2026-09-10T04:31:59.435186Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"preds[:10]","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-10T04:31:59.437644Z","iopub.execute_input":"2026-09-10T04:31:59.437965Z","iopub.status.idle":"2026-09-10T04:31:59.445078Z","shell.execute_reply.started":"2026-09-10T04:31:59.437943Z","shell.execute_reply":"2026-09-10T04:31:59.444141Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import numpy as np\n\n\n# 1. สุ่ม index มา 10 ตัวจากชุดข้อมูล\nsample_indices = np.random.choice(len(test_images), size=10, replace=False)\nsample_images = test_images[sample_indices]\n\n# 2. Predict \npredictions = model_1.predict(sample_images)\npredicted_classes = np.argmax(predictions, axis=1)  # ดึง class ที่ได้คะแนนสูงสุด\n\n# 3. แสดงผล 10 ภาพ (ปรับเป็น grid 2x5)\nfig, axes = plt.subplots(2, 5, figsize=(15, 6))\naxes = axes.flatten()\n\nfor i, ax in enumerate(axes):\n    ax.imshow(sample_images[i])\n    # แสดง Index เดิม และ Class ที่ทายได้\n    ax.set_title(f\"Idx: {sample_indices[i]}\\nPred: {predicted_classes[i]}\")\n    ax.axis(\"off\")\n\nplt.tight_layout()\nplt.show()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-10T04:31:59.447180Z","iopub.execute_input":"2026-09-10T04:31:59.447616Z","iopub.status.idle":"2026-09-10T04:32:00.862888Z","shell.execute_reply.started":"2026-09-10T04:31:59.447580Z","shell.execute_reply":"2026-09-10T04:32:00.860004Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# end of 2026-09-06\nstop here","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-10T04:32:00.864312Z","iopub.execute_input":"2026-09-10T04:32:00.864732Z","iopub.status.idle":"2026-09-10T04:32:00.870679Z","shell.execute_reply.started":"2026-09-10T04:32:00.864700Z","shell.execute_reply":"2026-09-10T04:32:00.869400Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Transfer Learning","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"#Create transfer learning model for VGG16\nimport sys\nfrom matplotlib import pyplot\nfrom keras.utils import to_categorical\nfrom keras.applications.vgg16 import VGG16\nfrom keras.models import Model\nfrom keras.layers import Dense\nfrom keras.layers import Flatten\nfrom keras.optimizers import SGD\nfrom keras.preprocessing.image import ImageDataGenerator\n\n# define cnn model\ndef define_model_vgg16():\n\t# load model\n\tmodel = VGG16(include_top=False, input_shape=(224, 224, 3))\n\t# mark loaded layers as not trainable\n\tfor layer in model.layers:\n\t\tlayer.trainable = False\n\t# add new classifier layers\n\tflat1 = Flatten()(model.layers[-1].output)\n\tclass1 = Dense(128, activation='relu', kernel_initializer='he_uniform')(flat1)\n\toutput = Dense(1, activation='sigmoid')(class1)\n\t# define new model\n\tmodel = Model(inputs=model.inputs, outputs=output)\n\t# compile model\n\topt = SGD(lr=0.001, momentum=0.9)\n\tmodel.compile(optimizer=opt, loss='binary_crossentropy', metrics=['accuracy'])\n\treturn model","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-02-16T07:08:34.328001Z","iopub.execute_input":"2026-02-16T07:08:34.328334Z","iopub.status.idle":"2026-02-16T07:08:34.33556Z","shell.execute_reply.started":"2026-02-16T07:08:34.328308Z","shell.execute_reply":"2026-02-16T07:08:34.334631Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# load model\n# model = VGG16(include_top=False, input_shape=(224, 224, 3))\n# mark loaded layers as not trainable\n# for layer in model.layers:\n#     layer.trainable = False\n\n# print(model.layers[-1].output)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-02-16T07:06:10.528649Z","iopub.execute_input":"2026-02-16T07:06:10.529339Z","iopub.status.idle":"2026-02-16T07:06:10.532994Z","shell.execute_reply.started":"2026-02-16T07:06:10.529306Z","shell.execute_reply":"2026-02-16T07:06:10.532148Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# load model\n# model_16_feature_extractor = VGG16(include_top=False, input_shape=(224, 224, 3))\n# model_16_feature_extractor.summary()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-02-16T07:06:18.061672Z","iopub.execute_input":"2026-02-16T07:06:18.062335Z","iopub.status.idle":"2026-02-16T07:06:18.065876Z","shell.execute_reply.started":"2026-02-16T07:06:18.062302Z","shell.execute_reply":"2026-02-16T07:06:18.064909Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# for index, layer in enumerate(model_16_feature_extractor.layers):\n# \t\tprint(index, layer.trainable)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-02-16T07:03:43.521957Z","iopub.execute_input":"2026-02-16T07:03:43.522229Z","iopub.status.idle":"2026-02-16T07:03:43.525953Z","shell.execute_reply.started":"2026-02-16T07:03:43.522206Z","shell.execute_reply":"2026-02-16T07:03:43.525102Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# load model\n# model_16_top = VGG16(include_top=True, input_shape=(224, 224, 3))\n# model_16_top.summary()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-02-16T07:03:43.527034Z","iopub.execute_input":"2026-02-16T07:03:43.527566Z","iopub.status.idle":"2026-02-16T07:03:43.533544Z","shell.execute_reply.started":"2026-02-16T07:03:43.527544Z","shell.execute_reply":"2026-02-16T07:03:43.532816Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"vgg16_model = define_model_vgg16()\nvgg16_model.summary()\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-02-16T07:08:38.694916Z","iopub.execute_input":"2026-02-16T07:08:38.695524Z","iopub.status.idle":"2026-02-16T07:08:39.071031Z","shell.execute_reply.started":"2026-02-16T07:08:38.695491Z","shell.execute_reply":"2026-02-16T07:08:39.069481Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# for index, layer in enumerate(vgg16_model.layers):\n#     print(index, layer.name, layer.trainable)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-02-16T07:03:43.910675Z","iopub.execute_input":"2026-02-16T07:03:43.910954Z","iopub.status.idle":"2026-02-16T07:03:43.914695Z","shell.execute_reply.started":"2026-02-16T07:03:43.91093Z","shell.execute_reply":"2026-02-16T07:03:43.913724Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# for index, layer in enumerate(vgg16_model.layers[-7:]):\n#     print(index, layer.name, layer.trainable)\n    ","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-02-16T07:03:43.915763Z","iopub.execute_input":"2026-02-16T07:03:43.916044Z","iopub.status.idle":"2026-02-16T07:03:43.92276Z","shell.execute_reply.started":"2026-02-16T07:03:43.916014Z","shell.execute_reply":"2026-02-16T07:03:43.921957Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# for index, layer in enumerate(vgg16_model.layers[-7:]):\n#     layer.trainable = True\n#     print(index, layer.name, layer.trainable)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-02-16T07:03:43.923787Z","iopub.execute_input":"2026-02-16T07:03:43.924063Z","iopub.status.idle":"2026-02-16T07:03:43.930359Z","shell.execute_reply.started":"2026-02-16T07:03:43.924041Z","shell.execute_reply":"2026-02-16T07:03:43.9295Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# for index, layer in enumerate(vgg16_model.layers):\n#     if index >= 15:\n#         layer.trainable = True\n\n# for index, layer in enumerate(vgg16_model.layers):\n#     print(index, layer.name, layer.trainable)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-02-16T07:05:42.844519Z","iopub.execute_input":"2026-02-16T07:05:42.845298Z","iopub.status.idle":"2026-02-16T07:05:42.849027Z","shell.execute_reply.started":"2026-02-16T07:05:42.845261Z","shell.execute_reply":"2026-02-16T07:05:42.848238Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"id(vgg16_model)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-02-16T07:08:49.353611Z","iopub.execute_input":"2026-02-16T07:08:49.35397Z","iopub.status.idle":"2026-02-16T07:08:49.35955Z","shell.execute_reply.started":"2026-02-16T07:08:49.353942Z","shell.execute_reply":"2026-02-16T07:08:49.358663Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# fit model\nprint(id(vgg16_model))\nvgg16_model.reset_states()\nvgg16_model_history = vgg16_model.fit(\n    train_it, \n    steps_per_epoch=len(train_it),\n    validation_data=val_it,\n    validation_steps=len(val_it),\n    epochs=3, verbose=1,\n    callbacks = [PlotLossesKeras()]\n    )","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-02-16T07:08:52.691725Z","iopub.execute_input":"2026-02-16T07:08:52.692533Z","iopub.status.idle":"2026-02-16T07:15:06.05523Z","shell.execute_reply.started":"2026-02-16T07:08:52.692496Z","shell.execute_reply":"2026-02-16T07:15:06.054255Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# learning curves\nsummarize_diagnostics(vgg16_model_history)\n\n# evaluate model\n_, acc = vgg16_model.evaluate_generator(val_it, steps=len(val_it), verbose=1)\nprint('Val: > %.3f' % (acc * 100.0))\n\n# evaluate model\n_, acc = vgg16_model.evaluate_generator(test_it, steps=len(test_it), verbose=1)\nprint('Test: > %.3f' % (acc * 100.0))","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-02-16T07:16:16.626158Z","iopub.execute_input":"2026-02-16T07:16:16.6271Z","iopub.status.idle":"2026-02-16T07:17:18.360983Z","shell.execute_reply.started":"2026-02-16T07:16:16.627065Z","shell.execute_reply":"2026-02-16T07:17:18.360184Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"from keras.applications.inception_v3 import InceptionV3\n\ndef define_model_inceptionv3():\n    # load model\n    model = InceptionV3(include_top=False, input_shape=(299, 299, 3))\n    # mark loaded layers as not trainable\n    for layer in model.layers:\n        layer.trainable = False\n        # layer.trainable = True #try to test\n    \n    # add new classifier layers\n    flat1 = Flatten()(model.layers[-1].output)\n    class1 = Dense(1024, activation='relu', kernel_initializer='he_uniform')(flat1)\n    class2 = Dense(512, activation='relu', kernel_initializer='he_uniform')(class1)\n    class3 = Dense(256, activation='relu', kernel_initializer='he_uniform')(class2)\n    class4 = Dense(128, activation='relu', kernel_initializer='he_uniform')(class3)\n    # output = Dense(1, activation='sigmoid')(flat1)\n    output = Dense(2, activation='softmax')(class4)\n    # define new model\n    model = Model(inputs=model.inputs, outputs=output)\n    # compile model\n    opt = SGD(lr=0.001, momentum=0.9)\n    model.compile(optimizer=opt, loss='binary_crossentropy', metrics=['accuracy'])\n    return model","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-02-16T07:39:22.0384Z","iopub.execute_input":"2026-02-16T07:39:22.03875Z","iopub.status.idle":"2026-02-16T07:39:22.045262Z","shell.execute_reply.started":"2026-02-16T07:39:22.038719Z","shell.execute_reply":"2026-02-16T07:39:22.044409Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"model_inceptionv3 = define_model_inceptionv3()\nprint(id(model_inceptionv3))\n# model_inceptionv3.summary()","metadata":{"execution":{"iopub.status.busy":"2026-02-16T07:39:22.35245Z","iopub.execute_input":"2026-02-16T07:39:22.352743Z","iopub.status.idle":"2026-02-16T07:39:24.449375Z","shell.execute_reply.started":"2026-02-16T07:39:22.352718Z","shell.execute_reply":"2026-02-16T07:39:24.448546Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import numpy as np\nfrom tensorflow.keras import backend as K\n\ntrainable_params = int(np.sum([K.count_params(w) for w in model_inceptionv3.trainable_weights]))\nprint(trainable_params)\n","metadata":{"trusted":true,"scrolled":true,"execution":{"iopub.status.busy":"2026-02-16T07:39:24.451116Z","iopub.execute_input":"2026-02-16T07:39:24.451727Z","iopub.status.idle":"2026-02-16T07:39:24.457165Z","shell.execute_reply.started":"2026-02-16T07:39:24.451691Z","shell.execute_reply":"2026-02-16T07:39:24.456303Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"from tensorflow.keras import backend as K\n\nfor w in model_inceptionv3.trainable_weights:\n    print(w.name, K.count_params(w))\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-02-16T07:39:24.458253Z","iopub.execute_input":"2026-02-16T07:39:24.458457Z","iopub.status.idle":"2026-02-16T07:39:24.468376Z","shell.execute_reply.started":"2026-02-16T07:39:24.458437Z","shell.execute_reply":"2026-02-16T07:39:24.467705Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# fit model\nmodel_inceptionv3.reset_states()\nhistory_inceptionv3 = model_inceptionv3.fit(\n    train_it, \n    steps_per_epoch=len(train_it),\n    validation_data=val_it,\n    validation_steps=len(val_it),\n    epochs=3, verbose=1,\n    callbacks = [PlotLossesKeras()]\n    )","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import matplotlib.pyplot as plt\n\ndef plot_images_with_labels(images, labels, train_log, set_label, save=False):\n    \"\"\"\n    Plots a grid of images with their corresponding labels and saves the figure.\n    \n    Args:\n    - images (list or np.array): List of images to be displayed.\n    - labels (np.array): Array of one-hot encoded labels.\n    - train_log (str): The directory or log name to save the plot.\n    - set_label (str): The specific set label (e.g., \"train\", \"validation\", etc.).\n    - config (dict): Configuration dictionary containing image dimensions.\n    \n    Returns:\n    - None: Displays and saves the plot.\n    \"\"\"\n    # Convert one-hot encoded labels to class indices\n    class_indices = labels\n\n    # Create subplots\n    fig, axes = plt.subplots(3, 4, figsize=(14, 10), dpi=120)\n    axes = axes.flatten()\n\n    for img, label_idx, ax in zip(images, class_indices, axes):\n        # Undo any preprocessing (like rescaling for pre-trained models)\n        if np.max(img) == 1:\n            img = img * 255\n\n        # Display the image\n        img_shape = (224, 224, 3)\n        ax.imshow(img.astype(\"uint8\"))\n        # ax.imshow(img)\n\n        # Set the title to the corresponding class label\n        ax.set_title(f\"Label: {label_idx}\", fontsize=18)\n        ax.axis('on')\n\n    # Set the overall title for the figure\n    plot_title = f\"{train_log}-{set_label}\"\n    plt.suptitle(plot_title, fontsize=18)\n\n    # Show the plot\n    plt.show()\n\n    # Save the figure\n    if save:\n        plot_file = os.path.join(train_log, f\"{plot_title}.png\")\n        fig.savefig(plot_file, dpi=120)\n        print(f'Saved {plot_file}')\n","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# plot_images_with_labels(images, labels, \"Dog-Cat\", \"Training\")","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# for index, layer in enumerate(model.layers):\n#     print(index, layer.output.shape)","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# # mark loaded layers as not trainable\n# for index, layer in enumerate(model.layers[:15]):\n#     print(index, layer.name, layer.output_shape)\n#     layer.trainable = False\n    \n# for index, layer in enumerate(model.layers[15:]):\n#     print(index, layer.name, layer.output_shape)\n#     layer.trainable = True","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# evaluate model\n_, acc = model_inceptionv3.evaluate(test_it, steps=len(test_it), verbose=1)\nprint('> %.3f' % (acc * 100.0))\n# learning curves\n# summarize_diagnostics(history)\n\n# best_model = 'vgg16_model.hdf5'\n# my_model.save(best_model)","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"images = test_it.__next__()\nimages.shape","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# 5 first img: 1, 0, 1, 1, 0\nimages_to_predict = images[:5]\nimages_to_predict.shape","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"probs = model_inceptionv3.predict(images_to_predict, verbose=1)\nprobs","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"Make Prediction","metadata":{}},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null}]}