{"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":"2026-09-11T09:08:09.651412Z","iopub.execute_input":"2026-09-11T09:08:09.652052Z","iopub.status.idle":"2026-09-11T09:08:09.948963Z","shell.execute_reply.started":"2026-09-11T09:08:09.652022Z","shell.execute_reply":"2026-09-11T09:08:09.948163Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"!python --version","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-11T09:08:09.950140Z","iopub.execute_input":"2026-09-11T09:08:09.950528Z","iopub.status.idle":"2026-09-11T09:08:10.933235Z","shell.execute_reply.started":"2026-09-11T09:08:09.950505Z","shell.execute_reply":"2026-09-11T09:08:10.932379Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"!uname --all","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-11T09:08:10.934600Z","iopub.execute_input":"2026-09-11T09:08:10.934901Z","iopub.status.idle":"2026-09-11T09:08:11.899152Z","shell.execute_reply.started":"2026-09-11T09:08:10.934873Z","shell.execute_reply":"2026-09-11T09:08:11.898285Z"}},"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":"2026-09-11T09:08:11.901317Z","iopub.execute_input":"2026-09-11T09:08:11.901687Z","iopub.status.idle":"2026-09-11T09:08:24.638299Z","shell.execute_reply.started":"2026-09-11T09:08:11.901659Z","shell.execute_reply":"2026-09-11T09:08:24.637568Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-11T09:08:24.639416Z","iopub.execute_input":"2026-09-11T09:08:24.639682Z","iopub.status.idle":"2026-09-11T09:08:25.632052Z","shell.execute_reply.started":"2026-09-11T09:08:24.639660Z","shell.execute_reply":"2026-09-11T09:08:25.630893Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -l","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-11T09:08:25.634470Z","iopub.execute_input":"2026-09-11T09:08:25.634746Z","iopub.status.idle":"2026-09-11T09:08:26.595174Z","shell.execute_reply.started":"2026-09-11T09:08:25.634720Z","shell.execute_reply":"2026-09-11T09:08:26.594014Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls test1","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-11T09:08:26.596918Z","iopub.execute_input":"2026-09-11T09:08:26.597795Z","iopub.status.idle":"2026-09-11T09:08:27.620951Z","shell.execute_reply.started":"2026-09-11T09:08:26.597755Z","shell.execute_reply":"2026-09-11T09:08:27.619796Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls test1/ | wc -l","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-11T09:08:27.622576Z","iopub.execute_input":"2026-09-11T09:08:27.622911Z","iopub.status.idle":"2026-09-11T09:08:28.694541Z","shell.execute_reply.started":"2026-09-11T09:08:27.622880Z","shell.execute_reply":"2026-09-11T09:08:28.693338Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls train/ | wc -l","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-11T09:08:28.696027Z","iopub.execute_input":"2026-09-11T09:08:28.696304Z","iopub.status.idle":"2026-09-11T09:08:29.735465Z","shell.execute_reply.started":"2026-09-11T09:08:28.696279Z","shell.execute_reply":"2026-09-11T09:08:29.734617Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"#ls train/","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-11T09:08:29.738689Z","iopub.execute_input":"2026-09-11T09:08:29.738936Z","iopub.status.idle":"2026-09-11T09:08:29.743321Z","shell.execute_reply.started":"2026-09-11T09:08:29.738912Z","shell.execute_reply":"2026-09-11T09:08:29.742241Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"pwd","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-11T09:08:29.744710Z","iopub.execute_input":"2026-09-11T09:08:29.744975Z","iopub.status.idle":"2026-09-11T09:08:29.756551Z","shell.execute_reply.started":"2026-09-11T09:08:29.744954Z","shell.execute_reply":"2026-09-11T09:08:29.755772Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-11T09:08:29.757898Z","iopub.execute_input":"2026-09-11T09:08:29.758202Z","iopub.status.idle":"2026-09-11T09:08:30.728301Z","shell.execute_reply.started":"2026-09-11T09:08:29.758175Z","shell.execute_reply":"2026-09-11T09:08:30.727387Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -U train | head -n 10","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-11T09:08:30.729975Z","iopub.execute_input":"2026-09-11T09:08:30.730295Z","iopub.status.idle":"2026-09-11T09:08:31.786581Z","shell.execute_reply.started":"2026-09-11T09:08:30.730268Z","shell.execute_reply":"2026-09-11T09:08:31.785707Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -U test1 | head -n 10","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-11T09:08:31.788305Z","iopub.execute_input":"2026-09-11T09:08:31.788646Z","iopub.status.idle":"2026-09-11T09:08:32.793677Z","shell.execute_reply.started":"2026-09-11T09:08:31.788617Z","shell.execute_reply":"2026-09-11T09:08:32.792642Z"}},"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":"2026-09-11T09:08:32.795149Z","iopub.execute_input":"2026-09-11T09:08:32.795568Z","iopub.status.idle":"2026-09-11T09:08:33.870460Z","shell.execute_reply.started":"2026-09-11T09:08:32.795540Z","shell.execute_reply":"2026-09-11T09:08:33.869429Z"},"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":"2026-09-11T09:08:33.871738Z","iopub.execute_input":"2026-09-11T09:08:33.872027Z","iopub.status.idle":"2026-09-11T09:08:34.842023Z","shell.execute_reply.started":"2026-09-11T09:08:33.872004Z","shell.execute_reply":"2026-09-11T09:08:34.841008Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"!python --version","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-11T09:08:34.843170Z","iopub.execute_input":"2026-09-11T09:08:34.843463Z","iopub.status.idle":"2026-09-11T09:08:35.865991Z","shell.execute_reply.started":"2026-09-11T09:08:34.843439Z","shell.execute_reply":"2026-09-11T09:08:35.865085Z"}},"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":"2026-09-11T09:08:35.867407Z","iopub.execute_input":"2026-09-11T09:08:35.867696Z","iopub.status.idle":"2026-09-11T09:08:48.641713Z","shell.execute_reply.started":"2026-09-11T09:08:35.867670Z","shell.execute_reply":"2026-09-11T09:08:48.640731Z"}},"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":"2026-09-11T09:08:48.642782Z","iopub.execute_input":"2026-09-11T09:08:48.643291Z","iopub.status.idle":"2026-09-11T09:08:48.648244Z","shell.execute_reply.started":"2026-09-11T09:08:48.643268Z","shell.execute_reply":"2026-09-11T09:08:48.647088Z"},"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":"2026-09-11T09:08:48.649233Z","iopub.execute_input":"2026-09-11T09:08:48.649491Z","iopub.status.idle":"2026-09-11T09:08:48.683443Z","shell.execute_reply.started":"2026-09-11T09:08:48.649471Z","shell.execute_reply":"2026-09-11T09:08:48.682580Z"},"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":"2026-09-11T09:08:48.684484Z","iopub.execute_input":"2026-09-11T09:08:48.684816Z","iopub.status.idle":"2026-09-11T09:08:48.692248Z","shell.execute_reply.started":"2026-09-11T09:08:48.684781Z","shell.execute_reply":"2026-09-11T09:08:48.691577Z"},"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":"2026-09-11T09:08:48.693655Z","iopub.execute_input":"2026-09-11T09:08:48.694191Z","iopub.status.idle":"2026-09-11T09:08:49.670415Z","shell.execute_reply.started":"2026-09-11T09:08:48.694158Z","shell.execute_reply":"2026-09-11T09:08:49.669498Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -l","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-11T09:08:49.671740Z","iopub.execute_input":"2026-09-11T09:08:49.671993Z","iopub.status.idle":"2026-09-11T09:08:50.639772Z","shell.execute_reply.started":"2026-09-11T09:08:49.671969Z","shell.execute_reply":"2026-09-11T09:08:50.638880Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -l dataset_dogs_vs_cats/train","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-11T09:08:50.641160Z","iopub.execute_input":"2026-09-11T09:08:50.641482Z","iopub.status.idle":"2026-09-11T09:08:51.614701Z","shell.execute_reply.started":"2026-09-11T09:08:50.641455Z","shell.execute_reply":"2026-09-11T09:08:51.613770Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -l dataset_dogs_vs_cats/test #validation","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-11T09:08:51.616101Z","iopub.execute_input":"2026-09-11T09:08:51.616448Z","iopub.status.idle":"2026-09-11T09:08:52.596646Z","shell.execute_reply.started":"2026-09-11T09:08:51.616421Z","shell.execute_reply":"2026-09-11T09:08:52.595721Z"}},"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":"2026-09-11T09:08:52.598073Z","iopub.execute_input":"2026-09-11T09:08:52.598964Z","iopub.status.idle":"2026-09-11T09:08:54.600530Z","shell.execute_reply.started":"2026-09-11T09:08:52.598933Z","shell.execute_reply":"2026-09-11T09:08:54.599458Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"print(src)\nprint(dst)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-11T09:08:54.601730Z","iopub.execute_input":"2026-09-11T09:08:54.602028Z","iopub.status.idle":"2026-09-11T09:08:54.606952Z","shell.execute_reply.started":"2026-09-11T09:08:54.602004Z","shell.execute_reply":"2026-09-11T09:08:54.605878Z"}},"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":"2026-09-11T09:08:54.614574Z","iopub.execute_input":"2026-09-11T09:08:54.614833Z","iopub.status.idle":"2026-09-11T09:08:56.724264Z","shell.execute_reply.started":"2026-09-11T09:08:54.614812Z","shell.execute_reply":"2026-09-11T09:08:56.723175Z"},"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":"2026-09-11T09:08:56.725680Z","iopub.execute_input":"2026-09-11T09:08:56.725990Z","iopub.status.idle":"2026-09-11T09:08:58.735824Z","shell.execute_reply.started":"2026-09-11T09:08:56.725963Z","shell.execute_reply":"2026-09-11T09:08:58.734525Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"!pip -q install livelossplot==0.5.5","metadata":{"execution":{"iopub.status.busy":"2026-09-11T09:08:58.737691Z","iopub.execute_input":"2026-09-11T09:08:58.738677Z","iopub.status.idle":"2026-09-11T09:09:09.112285Z","shell.execute_reply.started":"2026-09-11T09:08:58.738645Z","shell.execute_reply":"2026-09-11T09:09:09.111260Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"from livelossplot import PlotLossesKeras","metadata":{"execution":{"iopub.status.busy":"2026-09-11T09:09:09.113705Z","iopub.execute_input":"2026-09-11T09:09:09.114019Z","iopub.status.idle":"2026-09-11T09:09:09.129771Z","shell.execute_reply.started":"2026-09-11T09:09:09.113992Z","shell.execute_reply":"2026-09-11T09:09:09.129095Z"},"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":"2026-09-11T09:09:09.130777Z","iopub.execute_input":"2026-09-11T09:09:09.131034Z","iopub.status.idle":"2026-09-11T09:09:09.134931Z","shell.execute_reply.started":"2026-09-11T09:09:09.131014Z","shell.execute_reply":"2026-09-11T09:09:09.134242Z"}},"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":"2026-09-11T09:09:09.135949Z","iopub.execute_input":"2026-09-11T09:09:09.136153Z","iopub.status.idle":"2026-09-11T09:09:09.145185Z","shell.execute_reply.started":"2026-09-11T09:09:09.136135Z","shell.execute_reply":"2026-09-11T09:09:09.144455Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"model = Sequential()\ntype(model)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-11T09:09:09.146305Z","iopub.execute_input":"2026-09-11T09:09:09.146632Z","iopub.status.idle":"2026-09-11T09:09:10.645207Z","shell.execute_reply.started":"2026-09-11T09:09:09.146604Z","shell.execute_reply":"2026-09-11T09:09:10.644400Z"}},"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":"2026-09-11T09:09:10.646463Z","iopub.execute_input":"2026-09-11T09:09:10.646818Z","iopub.status.idle":"2026-09-11T09:09:10.773832Z","shell.execute_reply.started":"2026-09-11T09:09:10.646786Z","shell.execute_reply":"2026-09-11T09:09:10.772489Z"}},"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":"2026-09-11T09:09:10.776401Z","iopub.execute_input":"2026-09-11T09:09:10.776623Z","iopub.status.idle":"2026-09-11T09:09:10.838787Z","shell.execute_reply.started":"2026-09-11T09:09:10.776603Z","shell.execute_reply":"2026-09-11T09:09:10.837901Z"}},"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":"2026-09-11T09:09:10.839856Z","iopub.execute_input":"2026-09-11T09:09:10.840210Z","iopub.status.idle":"2026-09-11T09:09:10.846161Z","shell.execute_reply.started":"2026-09-11T09:09:10.840186Z","shell.execute_reply":"2026-09-11T09:09:10.845209Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"model_1 = define_model_1()\nprint(model_1.summary())","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-11T09:09:10.847454Z","iopub.execute_input":"2026-09-11T09:09:10.847788Z","iopub.status.idle":"2026-09-11T09:09:10.915835Z","shell.execute_reply.started":"2026-09-11T09:09:10.847760Z","shell.execute_reply":"2026-09-11T09:09:10.915057Z"}},"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":"2026-09-11T09:09:10.916955Z","iopub.execute_input":"2026-09-11T09:09:10.917247Z","iopub.status.idle":"2026-09-11T09:09:10.925065Z","shell.execute_reply.started":"2026-09-11T09:09:10.917219Z","shell.execute_reply":"2026-09-11T09:09:10.924102Z"}},"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":"2026-09-11T09:09:10.926345Z","iopub.execute_input":"2026-09-11T09:09:10.926581Z","iopub.status.idle":"2026-09-11T09:09:10.935494Z","shell.execute_reply.started":"2026-09-11T09:09:10.926562Z","shell.execute_reply":"2026-09-11T09:09:10.934587Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"model_1 = define_model_1()\nprint(model_1.summary())","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-11T09:09:10.936635Z","iopub.execute_input":"2026-09-11T09:09:10.936944Z","iopub.status.idle":"2026-09-11T09:09:11.002693Z","shell.execute_reply.started":"2026-09-11T09:09:10.936916Z","shell.execute_reply":"2026-09-11T09:09:11.000702Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"datagen = ImageDataGenerator(rescale=1.0/255.0)\ntype(datagen)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-11T09:09:11.003537Z","iopub.execute_input":"2026-09-11T09:09:11.003731Z","iopub.status.idle":"2026-09-11T09:09:11.009445Z","shell.execute_reply.started":"2026-09-11T09:09:11.003714Z","shell.execute_reply":"2026-09-11T09:09:11.008304Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls dataset_dogs_vs_cats/train/","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-11T09:09:11.010459Z","iopub.execute_input":"2026-09-11T09:09:11.011050Z","iopub.status.idle":"2026-09-11T09:09:11.996053Z","shell.execute_reply.started":"2026-09-11T09:09:11.011019Z","shell.execute_reply":"2026-09-11T09:09:11.995123Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Hyperparameter => changable\nIMAGE_SIZE = (200, 200)\nBATCH_SIZE = 64\nEPOCHS = 20","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-11T10:24:11.843579Z","iopub.execute_input":"2026-09-11T10:24:11.843888Z","iopub.status.idle":"2026-09-11T10:24:11.848376Z","shell.execute_reply.started":"2026-09-11T10:24:11.843864Z","shell.execute_reply":"2026-09-11T10:24:11.847287Z"}},"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_SIZE, \n        target_size=IMAGE_SIZE\n)\ntype(train_it)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-11T10:24:14.025717Z","iopub.execute_input":"2026-09-11T10:24:14.026618Z","iopub.status.idle":"2026-09-11T10:24:14.516150Z","shell.execute_reply.started":"2026-09-11T10:24:14.026587Z","shell.execute_reply":"2026-09-11T10:24:14.515445Z"}},"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":"2026-09-11T10:24:17.820214Z","iopub.execute_input":"2026-09-11T10:24:17.820987Z","iopub.status.idle":"2026-09-11T10:24:17.826888Z","shell.execute_reply.started":"2026-09-11T10:24:17.820954Z","shell.execute_reply":"2026-09-11T10:24:17.825934Z"}},"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)\n\ntype(val_it)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-11T10:24:25.753764Z","iopub.execute_input":"2026-09-11T10:24:25.754541Z","iopub.status.idle":"2026-09-11T10:24:25.930348Z","shell.execute_reply.started":"2026-09-11T10:24:25.754509Z","shell.execute_reply":"2026-09-11T10:24:25.929240Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"len(val_it), len(val_it.classes), val_it.classes[-10:]\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-11T10:24:31.169234Z","iopub.execute_input":"2026-09-11T10:24:31.170008Z","iopub.status.idle":"2026-09-11T10:24:31.176833Z","shell.execute_reply.started":"2026-09-11T10:24:31.169976Z","shell.execute_reply":"2026-09-11T10:24:31.175823Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"\n# 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    )\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-11T10:57:26.691545Z","iopub.execute_input":"2026-09-11T10:57:26.692489Z","iopub.status.idle":"2026-09-11T11:11:05.538095Z","shell.execute_reply.started":"2026-09-11T10:57:26.692455Z","shell.execute_reply":"2026-09-11T11:11:05.537411Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# learning curves\nsummarize_diagnostics(history_1)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-11T09:25:02.761560Z","iopub.execute_input":"2026-09-11T09:25:02.762504Z","iopub.status.idle":"2026-09-11T09:25:03.061150Z","shell.execute_reply.started":"2026-09-11T09:25:02.762470Z","shell.execute_reply":"2026-09-11T09:25:03.060453Z"}},"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":"2026-09-11T09:24:03.032812Z","iopub.execute_input":"2026-09-11T09:24:03.033379Z","iopub.status.idle":"2026-09-11T09:24:13.163673Z","shell.execute_reply.started":"2026-09-11T09:24:03.033353Z","shell.execute_reply":"2026-09-11T09:24:13.162793Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls ","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-11T09:24:13.164731Z","iopub.execute_input":"2026-09-11T09:24:13.165099Z","iopub.status.idle":"2026-09-11T09:24:14.160577Z","shell.execute_reply.started":"2026-09-11T09:24:13.165076Z","shell.execute_reply":"2026-09-11T09:24:14.159342Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"pwd","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-11T09:24:14.162473Z","iopub.execute_input":"2026-09-11T09:24:14.163260Z","iopub.status.idle":"2026-09-11T09:24:14.170187Z","shell.execute_reply.started":"2026-09-11T09:24:14.163219Z","shell.execute_reply":"2026-09-11T09:24:14.169393Z"}},"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":"2026-09-11T09:24:14.171522Z","iopub.execute_input":"2026-09-11T09:24:14.171802Z","iopub.status.idle":"2026-09-11T09:24:14.215443Z","shell.execute_reply.started":"2026-09-11T09:24:14.171781Z","shell.execute_reply":"2026-09-11T09:24:14.214525Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"df.columns","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-11T09:24:14.216645Z","iopub.execute_input":"2026-09-11T09:24:14.216897Z","iopub.status.idle":"2026-09-11T09:24:14.223110Z","shell.execute_reply.started":"2026-09-11T09:24:14.216877Z","shell.execute_reply":"2026-09-11T09:24:14.222344Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"image_files[:5], type(image_files), len(image_files)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-11T09:24:14.224166Z","iopub.execute_input":"2026-09-11T09:24:14.224528Z","iopub.status.idle":"2026-09-11T09:24:14.235480Z","shell.execute_reply.started":"2026-09-11T09:24:14.224502Z","shell.execute_reply":"2026-09-11T09:24:14.234676Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"df.describe()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-11T09:24:14.236608Z","iopub.execute_input":"2026-09-11T09:24:14.236968Z","iopub.status.idle":"2026-09-11T09:24:14.278488Z","shell.execute_reply.started":"2026-09-11T09:24:14.236946Z","shell.execute_reply":"2026-09-11T09:24:14.277756Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"df.loc[1]","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-11T09:24:14.279543Z","iopub.execute_input":"2026-09-11T09:24:14.279857Z","iopub.status.idle":"2026-09-11T09:24:14.285818Z","shell.execute_reply.started":"2026-09-11T09:24:14.279837Z","shell.execute_reply":"2026-09-11T09:24:14.284992Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"df.sample(5)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-11T09:24:14.286935Z","iopub.execute_input":"2026-09-11T09:24:14.287251Z","iopub.status.idle":"2026-09-11T09:24:14.300674Z","shell.execute_reply.started":"2026-09-11T09:24:14.287229Z","shell.execute_reply":"2026-09-11T09:24:14.299847Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"df['filename']","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-11T09:24:14.301693Z","iopub.execute_input":"2026-09-11T09:24:14.301952Z","iopub.status.idle":"2026-09-11T09:24:14.312176Z","shell.execute_reply.started":"2026-09-11T09:24:14.301929Z","shell.execute_reply":"2026-09-11T09:24:14.311366Z"}},"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":"2026-09-11T09:24:14.313467Z","iopub.execute_input":"2026-09-11T09:24:14.313758Z","iopub.status.idle":"2026-09-11T09:24:14.396110Z","shell.execute_reply.started":"2026-09-11T09:24:14.313731Z","shell.execute_reply":"2026-09-11T09:24:14.395454Z"}},"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":"2026-09-11T09:24:14.397060Z","iopub.execute_input":"2026-09-11T09:24:14.397430Z","iopub.status.idle":"2026-09-11T09:24:14.402780Z","shell.execute_reply.started":"2026-09-11T09:24:14.397408Z","shell.execute_reply":"2026-09-11T09:24:14.401830Z"}},"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":"2026-09-11T09:24:14.403926Z","iopub.execute_input":"2026-09-11T09:24:14.404446Z","iopub.status.idle":"2026-09-11T09:24:19.259137Z","shell.execute_reply.started":"2026-09-11T09:24:14.404424Z","shell.execute_reply":"2026-09-11T09:24:19.257971Z"}},"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":"2026-09-11T09:24:19.260808Z","iopub.execute_input":"2026-09-11T09:24:19.261253Z","iopub.status.idle":"2026-09-11T09:24:24.091638Z","shell.execute_reply.started":"2026-09-11T09:24:19.261213Z","shell.execute_reply":"2026-09-11T09:24:24.090508Z"}},"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":"2026-09-11T09:24:24.092870Z","iopub.execute_input":"2026-09-11T09:24:24.093250Z","iopub.status.idle":"2026-09-11T09:24:24.099176Z","shell.execute_reply.started":"2026-09-11T09:24:24.093225Z","shell.execute_reply":"2026-09-11T09:24:24.098248Z"}},"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":"2026-09-11T09:24:24.100429Z","iopub.execute_input":"2026-09-11T09:24:24.100766Z","iopub.status.idle":"2026-09-11T09:24:28.956413Z","shell.execute_reply.started":"2026-09-11T09:24:24.100739Z","shell.execute_reply":"2026-09-11T09:24:28.955287Z"}},"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":"2026-09-11T09:24:28.957741Z","iopub.execute_input":"2026-09-11T09:24:28.958520Z","iopub.status.idle":"2026-09-11T09:24:52.730224Z","shell.execute_reply.started":"2026-09-11T09:24:28.958474Z","shell.execute_reply":"2026-09-11T09:24:52.729397Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"preds[:10]","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-11T09:24:52.731422Z","iopub.execute_input":"2026-09-11T09:24:52.731756Z","iopub.status.idle":"2026-09-11T09:24:52.738037Z","shell.execute_reply.started":"2026-09-11T09:24:52.731725Z","shell.execute_reply":"2026-09-11T09:24:52.737175Z"}},"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":"2026-09-11T09:24:52.739179Z","iopub.execute_input":"2026-09-11T09:24:52.739500Z","iopub.status.idle":"2026-09-11T09:24:53.935450Z","shell.execute_reply.started":"2026-09-11T09:24:52.739472Z","shell.execute_reply":"2026-09-11T09:24:53.934396Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# end of 2026-09-06\nstop here","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-11T09:24:53.936539Z","iopub.execute_input":"2026-09-11T09:24:53.936836Z","iopub.status.idle":"2026-09-11T09:24:53.943605Z","shell.execute_reply.started":"2026-09-11T09:24:53.936812Z","shell.execute_reply":"2026-09-11T09:24:53.941439Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Transfer Learning","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-11T09:24:53.944522Z","iopub.status.idle":"2026-09-11T09:24:53.945110Z","shell.execute_reply.started":"2026-09-11T09:24:53.944879Z","shell.execute_reply":"2026-09-11T09:24:53.944901Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# Transfer Learning","metadata":{}},{"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":"2026-09-11T09:57:10.472217Z","iopub.execute_input":"2026-09-11T09:57:10.473086Z","iopub.status.idle":"2026-09-11T09:57:10.479654Z","shell.execute_reply.started":"2026-09-11T09:57:10.473053Z","shell.execute_reply":"2026-09-11T09:57:10.478663Z"}},"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":"2026-09-11T09:24:53.948714Z","iopub.status.idle":"2026-09-11T09:24:53.949046Z","shell.execute_reply.started":"2026-09-11T09:24:53.948901Z","shell.execute_reply":"2026-09-11T09:24:53.948916Z"}},"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":"2026-09-11T09:24:53.951003Z","iopub.status.idle":"2026-09-11T09:24:53.951446Z","shell.execute_reply.started":"2026-09-11T09:24:53.951243Z","shell.execute_reply":"2026-09-11T09:24:53.951258Z"}},"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":"2026-09-11T09:24:53.953004Z","iopub.status.idle":"2026-09-11T09:24:53.953464Z","shell.execute_reply.started":"2026-09-11T09:24:53.953254Z","shell.execute_reply":"2026-09-11T09:24:53.953269Z"}},"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":"2026-09-11T09:24:53.954865Z","iopub.status.idle":"2026-09-11T09:24:53.955185Z","shell.execute_reply.started":"2026-09-11T09:24:53.955041Z","shell.execute_reply":"2026-09-11T09:24:53.955055Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"define_model_vgg16()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-11T09:57:24.383570Z","iopub.execute_input":"2026-09-11T09:57:24.384248Z","iopub.status.idle":"2026-09-11T09:57:24.711420Z","shell.execute_reply.started":"2026-09-11T09:57:24.384217Z","shell.execute_reply":"2026-09-11T09:57:24.710181Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"\nIMAGE_SIZE = (224, 224)\nBATCH_SIZE = 64\n\ntrain_it = datagen.flow_from_directory(\n    'dataset_dogs_vs_cats/train/',\n    class_mode='binary',\n    batch_size=BATCH_SIZE,\n    target_size=IMAGE_SIZE\n)\n\nval_it = datagen.flow_from_directory(\n    'dataset_dogs_vs_cats/test/',\n    class_mode='binary',\n    batch_size=BATCH_SIZE,\n    target_size=IMAGE_SIZE\n)\n\n\nvgg16_model = define_model_vgg16()\nvgg16_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=5,\n    verbose=1,\n    callbacks=[PlotLossesKeras()]\n)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-11T10:00:20.799163Z","iopub.execute_input":"2026-09-11T10:00:20.799957Z","iopub.status.idle":"2026-09-11T10:09:51.496404Z","shell.execute_reply.started":"2026-09-11T10:00:20.799924Z","shell.execute_reply":"2026-09-11T10:09:51.495154Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"summarize_diagnostics(vgg16_history)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-11T10:12:54.320519Z","iopub.execute_input":"2026-09-11T10:12:54.320872Z","iopub.status.idle":"2026-09-11T10:12:54.680784Z","shell.execute_reply.started":"2026-09-11T10:12:54.320845Z","shell.execute_reply":"2026-09-11T10:12:54.680031Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"vgg16_model.save('vgg16_dog_cat_model.h5')","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-11T10:14:46.751390Z","iopub.execute_input":"2026-09-11T10:14:46.752305Z","iopub.status.idle":"2026-09-11T10:14:46.938556Z","shell.execute_reply.started":"2026-09-11T10:14:46.752273Z","shell.execute_reply":"2026-09-11T10:14:46.937275Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"vgg16_model.summary()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-11T10:11:05.018541Z","iopub.execute_input":"2026-09-11T10:11:05.019295Z","iopub.status.idle":"2026-09-11T10:11:05.085366Z","shell.execute_reply.started":"2026-09-11T10:11:05.019264Z","shell.execute_reply":"2026-09-11T10:11:05.078887Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import numpy as np\nimport matplotlib.pyplot as plt\n\n\nx_test, y_test = val_it.next()\n\nplt.figure(figsize=(15, 6))\nfor i in range(10):\n    img = x_test[i]\n    actual_label = \"Dog\" if y_test[i] == 1 else \"Cat\"\n    \n\n    pred = vgg16_model.predict(np.expand_dims(img, axis=0), verbose=0)[0][0]\n    pred_label = \"Dog\" if pred > 0.5 else \"Cat\"\n    \n  \n    plt.subplot(2, 5, i + 1)\n    plt.imshow(img)\n    color = 'green' if pred_label == actual_label else 'red'\n    plt.title(f\"Pred: {pred_label}\\n(Actual: {actual_label})\", color=color)\n    plt.axis('off')\n\nplt.tight_layout()\nplt.show()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-11T10:18:28.431574Z","iopub.execute_input":"2026-09-11T10:18:28.432392Z","iopub.status.idle":"2026-09-11T10:18:30.949131Z","shell.execute_reply.started":"2026-09-11T10:18:28.432358Z","shell.execute_reply":"2026-09-11T10:18:30.947847Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"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":"2026-09-11T09:24:53.960685Z","iopub.status.idle":"2026-09-11T09:24:53.961116Z","shell.execute_reply.started":"2026-09-11T09:24:53.960883Z","shell.execute_reply":"2026-09-11T09:24:53.960903Z"}},"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":"2026-09-11T09:24:53.962501Z","iopub.status.idle":"2026-09-11T09:24:53.962911Z","shell.execute_reply.started":"2026-09-11T09:24:53.962699Z","shell.execute_reply":"2026-09-11T09:24:53.962720Z"}},"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":"2026-09-11T09:24:53.964158Z","iopub.status.idle":"2026-09-11T09:24:53.964588Z","shell.execute_reply.started":"2026-09-11T09:24:53.964376Z","shell.execute_reply":"2026-09-11T09:24:53.964398Z"}},"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":"2026-09-11T09:24:53.966494Z","iopub.status.idle":"2026-09-11T09:24:53.966905Z","shell.execute_reply.started":"2026-09-11T09:24:53.966690Z","shell.execute_reply":"2026-09-11T09:24:53.966710Z"}},"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":"2026-09-11T09:25:48.064423Z","iopub.execute_input":"2026-09-11T09:25:48.065210Z","iopub.status.idle":"2026-09-11T09:25:48.070487Z","shell.execute_reply.started":"2026-09-11T09:25:48.065177Z","shell.execute_reply":"2026-09-11T09:25:48.069698Z"}},"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":"2026-09-11T09:24:53.971772Z","iopub.status.idle":"2026-09-11T09:24:53.972184Z","shell.execute_reply.started":"2026-09-11T09:24:53.971967Z","shell.execute_reply":"2026-09-11T09:24:53.971986Z"}},"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":"2026-09-11T09:24:53.973847Z","iopub.status.idle":"2026-09-11T09:24:53.974122Z","shell.execute_reply.started":"2026-09-11T09:24:53.973986Z","shell.execute_reply":"2026-09-11T09:24:53.973999Z"}},"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":"2026-09-11T09:24:53.975505Z","iopub.status.idle":"2026-09-11T09:24:53.975767Z","shell.execute_reply.started":"2026-09-11T09:24:53.975641Z","shell.execute_reply":"2026-09-11T09:24:53.975653Z"},"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":"2026-09-11T09:24:53.976647Z","iopub.status.idle":"2026-09-11T09:24:53.976905Z","shell.execute_reply.started":"2026-09-11T09:24:53.976778Z","shell.execute_reply":"2026-09-11T09:24:53.976790Z"}},"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":"2026-09-11T09:24:53.978424Z","iopub.status.idle":"2026-09-11T09:24:53.978688Z","shell.execute_reply.started":"2026-09-11T09:24:53.978561Z","shell.execute_reply":"2026-09-11T09:24:53.978574Z"}},"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,"execution":{"iopub.status.busy":"2026-09-11T09:24:53.979532Z","iopub.status.idle":"2026-09-11T09:24:53.979792Z","shell.execute_reply.started":"2026-09-11T09:24:53.979666Z","shell.execute_reply":"2026-09-11T09:24:53.979678Z"}},"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,"execution":{"iopub.status.busy":"2026-09-11T09:24:53.980914Z","iopub.status.idle":"2026-09-11T09:24:53.981191Z","shell.execute_reply.started":"2026-09-11T09:24:53.981056Z","shell.execute_reply":"2026-09-11T09:24:53.981068Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# plot_images_with_labels(images, labels, \"Dog-Cat\", \"Training\")","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-11T09:24:53.982633Z","iopub.status.idle":"2026-09-11T09:24:53.982899Z","shell.execute_reply.started":"2026-09-11T09:24:53.982769Z","shell.execute_reply":"2026-09-11T09:24:53.982781Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# for index, layer in enumerate(model.layers):\n#     print(index, layer.output.shape)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-11T09:24:53.983616Z","iopub.status.idle":"2026-09-11T09:24:53.983875Z","shell.execute_reply.started":"2026-09-11T09:24:53.983748Z","shell.execute_reply":"2026-09-11T09:24:53.983760Z"}},"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,"execution":{"iopub.status.busy":"2026-09-11T09:24:53.984951Z","iopub.status.idle":"2026-09-11T09:24:53.985268Z","shell.execute_reply.started":"2026-09-11T09:24:53.985127Z","shell.execute_reply":"2026-09-11T09:24:53.985141Z"}},"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,"execution":{"iopub.status.busy":"2026-09-11T09:24:53.986232Z","iopub.status.idle":"2026-09-11T09:24:53.986551Z","shell.execute_reply.started":"2026-09-11T09:24:53.986412Z","shell.execute_reply":"2026-09-11T09:24:53.986426Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"images = test_it.__next__()\nimages.shape","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-11T09:24:53.987744Z","iopub.status.idle":"2026-09-11T09:24:53.988059Z","shell.execute_reply.started":"2026-09-11T09:24:53.987918Z","shell.execute_reply":"2026-09-11T09:24:53.987932Z"}},"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,"execution":{"iopub.status.busy":"2026-09-11T09:24:53.989497Z","iopub.status.idle":"2026-09-11T09:24:53.989897Z","shell.execute_reply.started":"2026-09-11T09:24:53.989689Z","shell.execute_reply":"2026-09-11T09:24:53.989708Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"probs = model_inceptionv3.predict(images_to_predict, verbose=1)\nprobs","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-11T09:24:53.991329Z","iopub.status.idle":"2026-09-11T09:24:53.991730Z","shell.execute_reply.started":"2026-09-11T09:24:53.991520Z","shell.execute_reply":"2026-09-11T09:24:53.991539Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"Make Prediction","metadata":{}},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null}]}