{"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":"2026-09-09T07:13:08.482100Z","iopub.execute_input":"2026-09-09T07:13:08.482347Z","iopub.status.idle":"2026-09-09T07:13:08.799888Z","shell.execute_reply.started":"2026-09-09T07:13:08.482324Z","shell.execute_reply":"2026-09-09T07:13:08.798837Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"!python --version","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-09T07:13:08.801557Z","iopub.execute_input":"2026-09-09T07:13:08.801963Z","iopub.status.idle":"2026-09-09T07:13:09.884915Z","shell.execute_reply.started":"2026-09-09T07:13:08.801938Z","shell.execute_reply":"2026-09-09T07:13:09.883764Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"!uname --all","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-09T07:13:09.889682Z","iopub.execute_input":"2026-09-09T07:13:09.890045Z","iopub.status.idle":"2026-09-09T07:13:10.888816Z","shell.execute_reply.started":"2026-09-09T07:13:09.890009Z","shell.execute_reply":"2026-09-09T07:13:10.887463Z"}},"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":"2026-09-09T07:13:10.890625Z","iopub.execute_input":"2026-09-09T07:13:10.891040Z","iopub.status.idle":"2026-09-09T07:13:21.177236Z","shell.execute_reply.started":"2026-09-09T07:13:10.890994Z","shell.execute_reply":"2026-09-09T07:13:21.176015Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-09T07:13:21.179366Z","iopub.execute_input":"2026-09-09T07:13:21.179688Z","iopub.status.idle":"2026-09-09T07:13:22.200944Z","shell.execute_reply.started":"2026-09-09T07:13:21.179662Z","shell.execute_reply":"2026-09-09T07:13:22.199922Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -l","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-09T07:13:22.204247Z","iopub.execute_input":"2026-09-09T07:13:22.204648Z","iopub.status.idle":"2026-09-09T07:13:23.212212Z","shell.execute_reply.started":"2026-09-09T07:13:22.204618Z","shell.execute_reply":"2026-09-09T07:13:23.211181Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls test1","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-09T07:13:23.213885Z","iopub.execute_input":"2026-09-09T07:13:23.214661Z","iopub.status.idle":"2026-09-09T07:13:24.285989Z","shell.execute_reply.started":"2026-09-09T07:13:23.214630Z","shell.execute_reply":"2026-09-09T07:13:24.284712Z"},"collapsed":true,"jupyter":{"outputs_hidden":true}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls test1/ | wc -l","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-09T07:13:24.287651Z","iopub.execute_input":"2026-09-09T07:13:24.288009Z","iopub.status.idle":"2026-09-09T07:13:25.336779Z","shell.execute_reply.started":"2026-09-09T07:13:24.287973Z","shell.execute_reply":"2026-09-09T07:13:25.335775Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls train/ | wc -l","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-09T07:13:25.338144Z","iopub.execute_input":"2026-09-09T07:13:25.338505Z","iopub.status.idle":"2026-09-09T07:13:26.462690Z","shell.execute_reply.started":"2026-09-09T07:13:25.338465Z","shell.execute_reply":"2026-09-09T07:13:26.461284Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"#ls train/","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-09T07:13:26.466140Z","iopub.execute_input":"2026-09-09T07:13:26.466630Z","iopub.status.idle":"2026-09-09T07:13:26.473228Z","shell.execute_reply.started":"2026-09-09T07:13:26.466597Z","shell.execute_reply":"2026-09-09T07:13:26.472268Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"pwd","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-09T07:13:26.474508Z","iopub.execute_input":"2026-09-09T07:13:26.474937Z","iopub.status.idle":"2026-09-09T07:13:26.485018Z","shell.execute_reply.started":"2026-09-09T07:13:26.474910Z","shell.execute_reply":"2026-09-09T07:13:26.483859Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-09T07:13:26.486347Z","iopub.execute_input":"2026-09-09T07:13:26.486691Z","iopub.status.idle":"2026-09-09T07:13:27.518916Z","shell.execute_reply.started":"2026-09-09T07:13:26.486664Z","shell.execute_reply":"2026-09-09T07:13:27.517555Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -U train | head -n 10","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-09T07:13:27.520536Z","iopub.execute_input":"2026-09-09T07:13:27.521192Z","iopub.status.idle":"2026-09-09T07:13:28.626943Z","shell.execute_reply.started":"2026-09-09T07:13:27.521160Z","shell.execute_reply":"2026-09-09T07:13:28.625722Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -U test1 | head -n 10","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-09T07:13:28.629467Z","iopub.execute_input":"2026-09-09T07:13:28.630250Z","iopub.status.idle":"2026-09-09T07:13:29.687852Z","shell.execute_reply.started":"2026-09-09T07:13:28.630219Z","shell.execute_reply":"2026-09-09T07:13:29.686213Z"}},"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":"2026-09-09T07:13:29.689825Z","iopub.execute_input":"2026-09-09T07:13:29.690564Z","iopub.status.idle":"2026-09-09T07:13:30.776577Z","shell.execute_reply.started":"2026-09-09T07:13:29.690523Z","shell.execute_reply":"2026-09-09T07:13:30.775418Z"},"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":"2026-09-09T07:13:30.777915Z","iopub.execute_input":"2026-09-09T07:13:30.778259Z","iopub.status.idle":"2026-09-09T07:13:31.842181Z","shell.execute_reply.started":"2026-09-09T07:13:30.778227Z","shell.execute_reply":"2026-09-09T07:13:31.841269Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"!python --version","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-09T07:13:31.843778Z","iopub.execute_input":"2026-09-09T07:13:31.844156Z","iopub.status.idle":"2026-09-09T07:13:32.845199Z","shell.execute_reply.started":"2026-09-09T07:13:31.844118Z","shell.execute_reply":"2026-09-09T07:13:32.844232Z"}},"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":"2026-09-09T07:13:32.846686Z","iopub.execute_input":"2026-09-09T07:13:32.847008Z","iopub.status.idle":"2026-09-09T07:13:49.445115Z","shell.execute_reply.started":"2026-09-09T07:13:32.846980Z","shell.execute_reply":"2026-09-09T07:13:49.444091Z"}},"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":"2026-09-09T07:13:49.446455Z","iopub.execute_input":"2026-09-09T07:13:49.448608Z","iopub.status.idle":"2026-09-09T07:13:49.452711Z","shell.execute_reply.started":"2026-09-09T07:13:49.448576Z","shell.execute_reply":"2026-09-09T07:13:49.451977Z"},"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":"2026-09-09T07:13:49.453855Z","iopub.execute_input":"2026-09-09T07:13:49.454299Z","iopub.status.idle":"2026-09-09T07:13:49.469294Z","shell.execute_reply.started":"2026-09-09T07:13:49.454265Z","shell.execute_reply":"2026-09-09T07:13:49.468499Z"},"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":"2026-09-09T07:13:49.475342Z","iopub.execute_input":"2026-09-09T07:13:49.476393Z","iopub.status.idle":"2026-09-09T07:13:49.482361Z","shell.execute_reply.started":"2026-09-09T07:13:49.476352Z","shell.execute_reply":"2026-09-09T07:13:49.481366Z"},"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":"2026-09-09T07:13:49.483520Z","iopub.execute_input":"2026-09-09T07:13:49.483814Z","iopub.status.idle":"2026-09-09T07:13:50.506797Z","shell.execute_reply.started":"2026-09-09T07:13:49.483792Z","shell.execute_reply":"2026-09-09T07:13:50.505720Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -l","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-09T07:13:50.508429Z","iopub.execute_input":"2026-09-09T07:13:50.508813Z","iopub.status.idle":"2026-09-09T07:13:51.563552Z","shell.execute_reply.started":"2026-09-09T07:13:50.508783Z","shell.execute_reply":"2026-09-09T07:13:51.562515Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -l dataset_dogs_vs_cats/train","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-09T07:13:51.565001Z","iopub.execute_input":"2026-09-09T07:13:51.565768Z","iopub.status.idle":"2026-09-09T07:13:52.567178Z","shell.execute_reply.started":"2026-09-09T07:13:51.565736Z","shell.execute_reply":"2026-09-09T07:13:52.565885Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -l dataset_dogs_vs_cats/test #validation","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-09T07:13:52.568737Z","iopub.execute_input":"2026-09-09T07:13:52.569049Z","iopub.status.idle":"2026-09-09T07:13:53.592660Z","shell.execute_reply.started":"2026-09-09T07:13:52.569023Z","shell.execute_reply":"2026-09-09T07:13:53.591672Z"}},"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":"2026-09-09T07:13:53.594522Z","iopub.execute_input":"2026-09-09T07:13:53.594924Z","iopub.status.idle":"2026-09-09T07:13:55.631933Z","shell.execute_reply.started":"2026-09-09T07:13:53.594876Z","shell.execute_reply":"2026-09-09T07:13:55.631133Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"print(src)\nprint(dst)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-09T07:13:55.633019Z","iopub.execute_input":"2026-09-09T07:13:55.633638Z","iopub.status.idle":"2026-09-09T07:13:55.638048Z","shell.execute_reply.started":"2026-09-09T07:13:55.633611Z","shell.execute_reply":"2026-09-09T07:13:55.637067Z"}},"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":"2026-09-09T07:13:55.639300Z","iopub.execute_input":"2026-09-09T07:13:55.639638Z","iopub.status.idle":"2026-09-09T07:13:57.938178Z","shell.execute_reply.started":"2026-09-09T07:13:55.639615Z","shell.execute_reply":"2026-09-09T07:13:57.937065Z"},"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":"2026-09-09T07:13:57.939562Z","iopub.execute_input":"2026-09-09T07:13:57.940272Z","iopub.status.idle":"2026-09-09T07:14:00.085426Z","shell.execute_reply.started":"2026-09-09T07:13:57.940243Z","shell.execute_reply":"2026-09-09T07:14:00.084496Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"!pip -q install livelossplot==0.5.5","metadata":{"execution":{"iopub.status.busy":"2026-09-09T07:14:00.087275Z","iopub.execute_input":"2026-09-09T07:14:00.088165Z","iopub.status.idle":"2026-09-09T07:14:11.033899Z","shell.execute_reply.started":"2026-09-09T07:14:00.088121Z","shell.execute_reply":"2026-09-09T07:14:11.032771Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"from livelossplot import PlotLossesKeras","metadata":{"execution":{"iopub.status.busy":"2026-09-09T07:14:11.035283Z","iopub.execute_input":"2026-09-09T07:14:11.036067Z","iopub.status.idle":"2026-09-09T07:14:11.054195Z","shell.execute_reply.started":"2026-09-09T07:14:11.036036Z","shell.execute_reply":"2026-09-09T07:14:11.053517Z"},"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":"2026-09-09T07:14:11.055210Z","iopub.execute_input":"2026-09-09T07:14:11.055545Z","iopub.status.idle":"2026-09-09T07:14:11.059299Z","shell.execute_reply.started":"2026-09-09T07:14:11.055521Z","shell.execute_reply":"2026-09-09T07:14:11.058443Z"}},"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":"2026-09-09T07:14:11.060535Z","iopub.execute_input":"2026-09-09T07:14:11.061334Z","iopub.status.idle":"2026-09-09T07:14:11.071449Z","shell.execute_reply.started":"2026-09-09T07:14:11.061301Z","shell.execute_reply":"2026-09-09T07:14:11.070804Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"model = Sequential()\ntype(model)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-09T07:14:11.072401Z","iopub.execute_input":"2026-09-09T07:14:11.072976Z","iopub.status.idle":"2026-09-09T07:14:12.456949Z","shell.execute_reply.started":"2026-09-09T07:14:11.072953Z","shell.execute_reply":"2026-09-09T07:14:12.456134Z"}},"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":"2026-09-09T07:14:12.457956Z","iopub.execute_input":"2026-09-09T07:14:12.458557Z","iopub.status.idle":"2026-09-09T07:14:12.839108Z","shell.execute_reply.started":"2026-09-09T07:14:12.458531Z","shell.execute_reply":"2026-09-09T07:14:12.837751Z"}},"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":"2026-09-09T07:14:12.840252Z","iopub.execute_input":"2026-09-09T07:14:12.840638Z","iopub.status.idle":"2026-09-09T07:14:12.914765Z","shell.execute_reply.started":"2026-09-09T07:14:12.840611Z","shell.execute_reply":"2026-09-09T07:14:12.913742Z"}},"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":"2026-09-09T07:14:12.916057Z","iopub.execute_input":"2026-09-09T07:14:12.916330Z","iopub.status.idle":"2026-09-09T07:14:14.534291Z","shell.execute_reply.started":"2026-09-09T07:14:12.916306Z","shell.execute_reply":"2026-09-09T07:14:14.533422Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"model_1 = define_model_1()\nprint(model_1.summary())","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-09T07:14:14.535568Z","iopub.execute_input":"2026-09-09T07:14:14.536003Z","iopub.status.idle":"2026-09-09T07:14:14.616031Z","shell.execute_reply.started":"2026-09-09T07:14:14.535976Z","shell.execute_reply":"2026-09-09T07:14:14.615006Z"}},"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":"2026-09-09T07:14:14.617536Z","iopub.execute_input":"2026-09-09T07:14:14.617833Z","iopub.status.idle":"2026-09-09T07:14:14.625097Z","shell.execute_reply.started":"2026-09-09T07:14:14.617808Z","shell.execute_reply":"2026-09-09T07:14:14.624010Z"}},"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":"2026-09-09T07:14:14.626424Z","iopub.execute_input":"2026-09-09T07:14:14.627278Z","iopub.status.idle":"2026-09-09T07:14:14.636244Z","shell.execute_reply.started":"2026-09-09T07:14:14.627250Z","shell.execute_reply":"2026-09-09T07:14:14.635581Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"model_1 = define_model_1()\nprint(model_1.summary())","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-09T07:14:14.637283Z","iopub.execute_input":"2026-09-09T07:14:14.637587Z","iopub.status.idle":"2026-09-09T07:14:14.710029Z","shell.execute_reply.started":"2026-09-09T07:14:14.637565Z","shell.execute_reply":"2026-09-09T07:14:14.707571Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"datagen = ImageDataGenerator(rescale=1.0/255.0)\ntype(datagen)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-09T07:14:14.711204Z","iopub.execute_input":"2026-09-09T07:14:14.711922Z","iopub.status.idle":"2026-09-09T07:14:14.717387Z","shell.execute_reply.started":"2026-09-09T07:14:14.711893Z","shell.execute_reply":"2026-09-09T07:14:14.716397Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls dataset_dogs_vs_cats/train/","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-09T07:14:14.718603Z","iopub.execute_input":"2026-09-09T07:14:14.718923Z","iopub.status.idle":"2026-09-09T07:14:15.751688Z","shell.execute_reply.started":"2026-09-09T07:14:14.718886Z","shell.execute_reply":"2026-09-09T07:14:15.750421Z"}},"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":"2026-09-09T07:14:48.159652Z","iopub.execute_input":"2026-09-09T07:14:48.161001Z","iopub.status.idle":"2026-09-09T07:14:48.165495Z","shell.execute_reply.started":"2026-09-09T07:14:48.160955Z","shell.execute_reply":"2026-09-09T07:14:48.164624Z"}},"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":"2026-09-09T07:14:52.704869Z","iopub.execute_input":"2026-09-09T07:14:52.705613Z","iopub.status.idle":"2026-09-09T07:14:53.190698Z","shell.execute_reply.started":"2026-09-09T07:14:52.705578Z","shell.execute_reply":"2026-09-09T07:14:53.189828Z"}},"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":"2026-09-09T07:14:54.231271Z","iopub.execute_input":"2026-09-09T07:14:54.231608Z","iopub.status.idle":"2026-09-09T07:14:54.238680Z","shell.execute_reply.started":"2026-09-09T07:14:54.231582Z","shell.execute_reply":"2026-09-09T07:14:54.237662Z"}},"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":"2026-09-09T07:14:54.980574Z","iopub.execute_input":"2026-09-09T07:14:54.980920Z","iopub.status.idle":"2026-09-09T07:14:55.165126Z","shell.execute_reply.started":"2026-09-09T07:14:54.980888Z","shell.execute_reply":"2026-09-09T07:14:55.164313Z"}},"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":"2026-09-09T07:14:58.001942Z","iopub.execute_input":"2026-09-09T07:14:58.002709Z","iopub.status.idle":"2026-09-09T07:14:58.009620Z","shell.execute_reply.started":"2026-09-09T07:14:58.002678Z","shell.execute_reply":"2026-09-09T07:14:58.008365Z"}},"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":"2026-09-09T07:15:00.016451Z","iopub.execute_input":"2026-09-09T07:15:00.017340Z","iopub.status.idle":"2026-09-09T07:29:36.989406Z","shell.execute_reply.started":"2026-09-09T07:15:00.017305Z","shell.execute_reply":"2026-09-09T07:29:36.988624Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# learning curves\nsummarize_diagnostics(history_1)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-09T07:29:36.991053Z","iopub.execute_input":"2026-09-09T07:29:36.991429Z","iopub.status.idle":"2026-09-09T07:29:37.316810Z","shell.execute_reply.started":"2026-09-09T07:29:36.991402Z","shell.execute_reply":"2026-09-09T07:29:37.316004Z"}},"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":"2026-09-09T07:29:37.318065Z","iopub.execute_input":"2026-09-09T07:29:37.318334Z","iopub.status.idle":"2026-09-09T07:29:57.986376Z","shell.execute_reply.started":"2026-09-09T07:29:37.318309Z","shell.execute_reply":"2026-09-09T07:29:57.985200Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls ","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-09T07:29:57.988350Z","iopub.execute_input":"2026-09-09T07:29:57.988778Z","iopub.status.idle":"2026-09-09T07:29:59.027695Z","shell.execute_reply.started":"2026-09-09T07:29:57.988748Z","shell.execute_reply":"2026-09-09T07:29:59.026293Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"pwd","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-09T07:29:59.029395Z","iopub.execute_input":"2026-09-09T07:29:59.029731Z","iopub.status.idle":"2026-09-09T07:29:59.037599Z","shell.execute_reply.started":"2026-09-09T07:29:59.029704Z","shell.execute_reply":"2026-09-09T07:29:59.036348Z"}},"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":"2026-09-09T07:29:59.039162Z","iopub.execute_input":"2026-09-09T07:29:59.039550Z","iopub.status.idle":"2026-09-09T07:29:59.093852Z","shell.execute_reply.started":"2026-09-09T07:29:59.039516Z","shell.execute_reply":"2026-09-09T07:29:59.093029Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"df.columns","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-09T07:29:59.095156Z","iopub.execute_input":"2026-09-09T07:29:59.096150Z","iopub.status.idle":"2026-09-09T07:29:59.103621Z","shell.execute_reply.started":"2026-09-09T07:29:59.096114Z","shell.execute_reply":"2026-09-09T07:29:59.102637Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"image_files[:5], type(image_files), len(image_files)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-09T07:29:59.104995Z","iopub.execute_input":"2026-09-09T07:29:59.105365Z","iopub.status.idle":"2026-09-09T07:29:59.116018Z","shell.execute_reply.started":"2026-09-09T07:29:59.105322Z","shell.execute_reply":"2026-09-09T07:29:59.115056Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"df.describe()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-09T07:29:59.117231Z","iopub.execute_input":"2026-09-09T07:29:59.118189Z","iopub.status.idle":"2026-09-09T07:29:59.173706Z","shell.execute_reply.started":"2026-09-09T07:29:59.118141Z","shell.execute_reply":"2026-09-09T07:29:59.172725Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"df.loc[1]","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-09T07:29:59.176431Z","iopub.execute_input":"2026-09-09T07:29:59.176741Z","iopub.status.idle":"2026-09-09T07:29:59.183158Z","shell.execute_reply.started":"2026-09-09T07:29:59.176719Z","shell.execute_reply":"2026-09-09T07:29:59.182207Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"df.sample(5)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-09T07:29:59.184412Z","iopub.execute_input":"2026-09-09T07:29:59.185081Z","iopub.status.idle":"2026-09-09T07:29:59.204625Z","shell.execute_reply.started":"2026-09-09T07:29:59.185053Z","shell.execute_reply":"2026-09-09T07:29:59.203474Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"df['filename']","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-09T07:29:59.205927Z","iopub.execute_input":"2026-09-09T07:29:59.207089Z","iopub.status.idle":"2026-09-09T07:29:59.217141Z","shell.execute_reply.started":"2026-09-09T07:29:59.207058Z","shell.execute_reply":"2026-09-09T07:29:59.216117Z"}},"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":"2026-09-09T07:29:59.218236Z","iopub.execute_input":"2026-09-09T07:29:59.219308Z","iopub.status.idle":"2026-09-09T07:29:59.319501Z","shell.execute_reply.started":"2026-09-09T07:29:59.219277Z","shell.execute_reply":"2026-09-09T07:29:59.318378Z"}},"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":"2026-09-09T07:29:59.321244Z","iopub.execute_input":"2026-09-09T07:29:59.322233Z","iopub.status.idle":"2026-09-09T07:29:59.328617Z","shell.execute_reply.started":"2026-09-09T07:29:59.322182Z","shell.execute_reply":"2026-09-09T07:29:59.327512Z"}},"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":"2026-09-09T07:29:59.329724Z","iopub.execute_input":"2026-09-09T07:29:59.329993Z","iopub.status.idle":"2026-09-09T07:30:04.580477Z","shell.execute_reply.started":"2026-09-09T07:29:59.329970Z","shell.execute_reply":"2026-09-09T07:30:04.579165Z"}},"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":"2026-09-09T07:30:04.582299Z","iopub.execute_input":"2026-09-09T07:30:04.583139Z","iopub.status.idle":"2026-09-09T07:30:09.727394Z","shell.execute_reply.started":"2026-09-09T07:30:04.583090Z","shell.execute_reply":"2026-09-09T07:30:09.726211Z"}},"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":"2026-09-09T07:30:09.728755Z","iopub.execute_input":"2026-09-09T07:30:09.729138Z","iopub.status.idle":"2026-09-09T07:30:09.735597Z","shell.execute_reply.started":"2026-09-09T07:30:09.729111Z","shell.execute_reply":"2026-09-09T07:30:09.734346Z"}},"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":"2026-09-09T07:30:09.736820Z","iopub.execute_input":"2026-09-09T07:30:09.737128Z","iopub.status.idle":"2026-09-09T07:30:14.873673Z","shell.execute_reply.started":"2026-09-09T07:30:09.737105Z","shell.execute_reply":"2026-09-09T07:30:14.871283Z"}},"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":"2026-09-09T07:30:14.875330Z","iopub.execute_input":"2026-09-09T07:30:14.875720Z","iopub.status.idle":"2026-09-09T07:30:37.222871Z","shell.execute_reply.started":"2026-09-09T07:30:14.875684Z","shell.execute_reply":"2026-09-09T07:30:37.221912Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"preds[:10]","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-09T07:30:37.224061Z","iopub.execute_input":"2026-09-09T07:30:37.224814Z","iopub.status.idle":"2026-09-09T07:30:37.231156Z","shell.execute_reply.started":"2026-09-09T07:30:37.224779Z","shell.execute_reply":"2026-09-09T07:30:37.230131Z"}},"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":"2026-09-09T07:30:37.232511Z","iopub.execute_input":"2026-09-09T07:30:37.232864Z","iopub.status.idle":"2026-09-09T07:30:38.886743Z","shell.execute_reply.started":"2026-09-09T07:30:37.232831Z","shell.execute_reply":"2026-09-09T07:30:38.885540Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# end of 2026-09-06\nstop here","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-09T07:31:05.625262Z","iopub.execute_input":"2026-09-09T07:31:05.626160Z","iopub.status.idle":"2026-09-09T07:31:05.629803Z","shell.execute_reply.started":"2026-09-09T07:31:05.626126Z","shell.execute_reply":"2026-09-09T07:31:05.628884Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Transfer Learning","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-09T07:14:16.870423Z","iopub.status.idle":"2026-09-09T07:14:16.870859Z","shell.execute_reply.started":"2026-09-09T07:14:16.870645Z","shell.execute_reply":"2026-09-09T07:14:16.870665Z"}},"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":"2026-09-09T07:14:16.872402Z","iopub.status.idle":"2026-09-09T07:14:16.872771Z","shell.execute_reply.started":"2026-09-09T07:14:16.872627Z","shell.execute_reply":"2026-09-09T07:14:16.872642Z"}},"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":"2026-09-09T07:14:16.874068Z","iopub.status.idle":"2026-09-09T07:14:16.874633Z","shell.execute_reply.started":"2026-09-09T07:14:16.874425Z","shell.execute_reply":"2026-09-09T07:14:16.874473Z"}},"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":"2026-09-09T07:14:16.877357Z","iopub.status.idle":"2026-09-09T07:14:16.877716Z","shell.execute_reply.started":"2026-09-09T07:14:16.877571Z","shell.execute_reply":"2026-09-09T07:14:16.877587Z"}},"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":"2026-09-09T07:14:16.879173Z","iopub.status.idle":"2026-09-09T07:14:16.879636Z","shell.execute_reply.started":"2026-09-09T07:14:16.879373Z","shell.execute_reply":"2026-09-09T07:14:16.879394Z"}},"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":"2026-09-09T07:14:16.881550Z","iopub.status.idle":"2026-09-09T07:14:16.881985Z","shell.execute_reply.started":"2026-09-09T07:14:16.881761Z","shell.execute_reply":"2026-09-09T07:14:16.881781Z"}},"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":"2026-09-09T07:14:16.883042Z","iopub.status.idle":"2026-09-09T07:14:16.883494Z","shell.execute_reply.started":"2026-09-09T07:14:16.883246Z","shell.execute_reply":"2026-09-09T07:14:16.883267Z"}},"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":"2026-09-09T07:14:16.885088Z","iopub.status.idle":"2026-09-09T07:14:16.885535Z","shell.execute_reply.started":"2026-09-09T07:14:16.885297Z","shell.execute_reply":"2026-09-09T07:14:16.885318Z"}},"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":"2026-09-09T07:14:16.887041Z","iopub.status.idle":"2026-09-09T07:14:16.887599Z","shell.execute_reply.started":"2026-09-09T07:14:16.887395Z","shell.execute_reply":"2026-09-09T07:14:16.887412Z"}},"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":"2026-09-09T07:14:16.889054Z","iopub.status.idle":"2026-09-09T07:14:16.889513Z","shell.execute_reply.started":"2026-09-09T07:14:16.889266Z","shell.execute_reply":"2026-09-09T07:14:16.889289Z"}},"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":"2026-09-09T07:14:16.890506Z","iopub.status.idle":"2026-09-09T07:14:16.890966Z","shell.execute_reply.started":"2026-09-09T07:14:16.890705Z","shell.execute_reply":"2026-09-09T07:14:16.890726Z"}},"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":"2026-09-09T07:14:16.892453Z","iopub.status.idle":"2026-09-09T07:14:16.892878Z","shell.execute_reply.started":"2026-09-09T07:14:16.892656Z","shell.execute_reply":"2026-09-09T07:14:16.892677Z"}},"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":"2026-09-09T07:14:16.893763Z","iopub.status.idle":"2026-09-09T07:14:16.894212Z","shell.execute_reply.started":"2026-09-09T07:14:16.893967Z","shell.execute_reply":"2026-09-09T07:14:16.893990Z"}},"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":"2026-09-09T07:14:16.895738Z","iopub.status.idle":"2026-09-09T07:14:16.896185Z","shell.execute_reply.started":"2026-09-09T07:14:16.895953Z","shell.execute_reply":"2026-09-09T07:14:16.895975Z"}},"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":"2026-09-09T07:14:16.898096Z","iopub.status.idle":"2026-09-09T07:14:16.898560Z","shell.execute_reply.started":"2026-09-09T07:14:16.898322Z","shell.execute_reply":"2026-09-09T07:14:16.898343Z"}},"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":"2026-09-09T07:14:16.899460Z","iopub.status.idle":"2026-09-09T07:14:16.899864Z","shell.execute_reply.started":"2026-09-09T07:14:16.899653Z","shell.execute_reply":"2026-09-09T07:14:16.899673Z"},"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":"2026-09-09T07:14:16.902047Z","iopub.status.idle":"2026-09-09T07:14:16.902541Z","shell.execute_reply.started":"2026-09-09T07:14:16.902298Z","shell.execute_reply":"2026-09-09T07:14:16.902319Z"}},"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":"2026-09-09T07:14:16.903841Z","iopub.status.idle":"2026-09-09T07:14:16.904322Z","shell.execute_reply.started":"2026-09-09T07:14:16.904068Z","shell.execute_reply":"2026-09-09T07:14:16.904092Z"}},"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":"2026-09-09T07:14:16.905988Z","iopub.status.idle":"2026-09-09T07:14:16.906261Z","shell.execute_reply.started":"2026-09-09T07:14:16.906126Z","shell.execute_reply":"2026-09-09T07:14:16.906138Z"}},"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":"2026-09-09T07:14:16.907343Z","iopub.status.idle":"2026-09-09T07:14:16.907667Z","shell.execute_reply.started":"2026-09-09T07:14:16.907523Z","shell.execute_reply":"2026-09-09T07:14:16.907537Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# plot_images_with_labels(images, labels, \"Dog-Cat\", \"Training\")","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-09T07:14:16.908892Z","iopub.status.idle":"2026-09-09T07:14:16.909152Z","shell.execute_reply.started":"2026-09-09T07:14:16.909024Z","shell.execute_reply":"2026-09-09T07:14:16.909036Z"}},"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":"2026-09-09T07:14:16.910309Z","iopub.status.idle":"2026-09-09T07:14:16.910633Z","shell.execute_reply.started":"2026-09-09T07:14:16.910491Z","shell.execute_reply":"2026-09-09T07:14:16.910506Z"}},"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":"2026-09-09T07:14:16.912025Z","iopub.status.idle":"2026-09-09T07:14:16.912310Z","shell.execute_reply.started":"2026-09-09T07:14:16.912172Z","shell.execute_reply":"2026-09-09T07:14:16.912186Z"}},"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":"2026-09-09T07:14:16.914237Z","iopub.status.idle":"2026-09-09T07:14:16.914574Z","shell.execute_reply.started":"2026-09-09T07:14:16.914377Z","shell.execute_reply":"2026-09-09T07:14:16.914390Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"images = test_it.__next__()\nimages.shape","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-09T07:14:16.915518Z","iopub.status.idle":"2026-09-09T07:14:16.915826Z","shell.execute_reply.started":"2026-09-09T07:14:16.915686Z","shell.execute_reply":"2026-09-09T07:14:16.915700Z"}},"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":"2026-09-09T07:14:16.917330Z","iopub.status.idle":"2026-09-09T07:14:16.917656Z","shell.execute_reply.started":"2026-09-09T07:14:16.917515Z","shell.execute_reply":"2026-09-09T07:14:16.917530Z"}},"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":"2026-09-09T07:14:16.918774Z","iopub.status.idle":"2026-09-09T07:14:16.919043Z","shell.execute_reply.started":"2026-09-09T07:14:16.918907Z","shell.execute_reply":"2026-09-09T07:14:16.918927Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"Make Prediction","metadata":{}},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null}]}