{"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":"2026-09-12T09:46:52.989663Z","iopub.execute_input":"2026-09-12T09:46:52.990166Z","iopub.status.idle":"2026-09-12T09:46:52.998541Z","shell.execute_reply.started":"2026-09-12T09:46:52.990136Z","shell.execute_reply":"2026-09-12T09:46:52.997459Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"!python --version","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T09:46:53.00024Z","iopub.execute_input":"2026-09-12T09:46:53.001004Z","iopub.status.idle":"2026-09-12T09:46:54.018624Z","shell.execute_reply.started":"2026-09-12T09:46:53.00098Z","shell.execute_reply":"2026-09-12T09:46:54.017371Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"!uname --all","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T09:46:54.020127Z","iopub.execute_input":"2026-09-12T09:46:54.020401Z","iopub.status.idle":"2026-09-12T09:46:55.021655Z","shell.execute_reply.started":"2026-09-12T09:46:54.020379Z","shell.execute_reply":"2026-09-12T09:46:55.020719Z"}},"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":"2026-09-12T09:46:55.02414Z","iopub.execute_input":"2026-09-12T09:46:55.024453Z","iopub.status.idle":"2026-09-12T09:47:04.719565Z","shell.execute_reply.started":"2026-09-12T09:46:55.024429Z","shell.execute_reply":"2026-09-12T09:47:04.718817Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T09:47:04.720563Z","iopub.execute_input":"2026-09-12T09:47:04.721138Z","iopub.status.idle":"2026-09-12T09:47:05.72258Z","shell.execute_reply.started":"2026-09-12T09:47:04.721114Z","shell.execute_reply":"2026-09-12T09:47:05.72121Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -l","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T09:47:05.72425Z","iopub.execute_input":"2026-09-12T09:47:05.724618Z","iopub.status.idle":"2026-09-12T09:47:06.810025Z","shell.execute_reply.started":"2026-09-12T09:47:05.72459Z","shell.execute_reply":"2026-09-12T09:47:06.809121Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls test1","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T09:47:06.811314Z","iopub.execute_input":"2026-09-12T09:47:06.811955Z","iopub.status.idle":"2026-09-12T09:47:07.88126Z","shell.execute_reply.started":"2026-09-12T09:47:06.811927Z","shell.execute_reply":"2026-09-12T09:47:07.880091Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls test1/ | wc -l","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T09:47:07.88281Z","iopub.execute_input":"2026-09-12T09:47:07.883197Z","iopub.status.idle":"2026-09-12T09:47:08.92293Z","shell.execute_reply.started":"2026-09-12T09:47:07.88317Z","shell.execute_reply":"2026-09-12T09:47:08.922062Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls train/ | wc -l","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T09:47:08.924377Z","iopub.execute_input":"2026-09-12T09:47:08.924735Z","iopub.status.idle":"2026-09-12T09:47:10.001154Z","shell.execute_reply.started":"2026-09-12T09:47:08.924709Z","shell.execute_reply":"2026-09-12T09:47:10.000231Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"#ls train/","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T09:47:10.004603Z","iopub.execute_input":"2026-09-12T09:47:10.004897Z","iopub.status.idle":"2026-09-12T09:47:10.009498Z","shell.execute_reply.started":"2026-09-12T09:47:10.004874Z","shell.execute_reply":"2026-09-12T09:47:10.008464Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"pwd","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T09:47:10.010807Z","iopub.execute_input":"2026-09-12T09:47:10.011113Z","iopub.status.idle":"2026-09-12T09:47:10.021343Z","shell.execute_reply.started":"2026-09-12T09:47:10.011086Z","shell.execute_reply":"2026-09-12T09:47:10.020564Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T09:47:10.022422Z","iopub.execute_input":"2026-09-12T09:47:10.022724Z","iopub.status.idle":"2026-09-12T09:47:11.018687Z","shell.execute_reply.started":"2026-09-12T09:47:10.022696Z","shell.execute_reply":"2026-09-12T09:47:11.01778Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -U train | head -n 10","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T09:47:11.020069Z","iopub.execute_input":"2026-09-12T09:47:11.020818Z","iopub.status.idle":"2026-09-12T09:47:12.106368Z","shell.execute_reply.started":"2026-09-12T09:47:11.020791Z","shell.execute_reply":"2026-09-12T09:47:12.105137Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -U test1 | head -n 10","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T09:47:12.108062Z","iopub.execute_input":"2026-09-12T09:47:12.108393Z","iopub.status.idle":"2026-09-12T09:47:13.135499Z","shell.execute_reply.started":"2026-09-12T09:47:12.108368Z","shell.execute_reply":"2026-09-12T09:47:13.134602Z"}},"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":"2026-09-12T09:47:13.137207Z","iopub.execute_input":"2026-09-12T09:47:13.137618Z","iopub.status.idle":"2026-09-12T09:47:14.091333Z","shell.execute_reply.started":"2026-09-12T09:47:13.13758Z","shell.execute_reply":"2026-09-12T09:47:14.090395Z"},"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":"2026-09-12T09:47:14.0925Z","iopub.execute_input":"2026-09-12T09:47:14.092889Z","iopub.status.idle":"2026-09-12T09:47:15.035045Z","shell.execute_reply.started":"2026-09-12T09:47:14.092865Z","shell.execute_reply":"2026-09-12T09:47:15.034208Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"!python --version","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T09:47:15.036447Z","iopub.execute_input":"2026-09-12T09:47:15.036851Z","iopub.status.idle":"2026-09-12T09:47:16.033007Z","shell.execute_reply.started":"2026-09-12T09:47:15.036813Z","shell.execute_reply":"2026-09-12T09:47:16.032036Z"}},"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":"2026-09-12T09:47:16.034396Z","iopub.execute_input":"2026-09-12T09:47:16.034872Z","iopub.status.idle":"2026-09-12T09:47:16.040379Z","shell.execute_reply.started":"2026-09-12T09:47:16.034841Z","shell.execute_reply":"2026-09-12T09:47:16.039596Z"}},"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":"2026-09-12T09:47:16.041611Z","iopub.execute_input":"2026-09-12T09:47:16.042316Z","iopub.status.idle":"2026-09-12T09:47:16.052576Z","shell.execute_reply.started":"2026-09-12T09:47:16.042265Z","shell.execute_reply":"2026-09-12T09:47:16.051834Z"},"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":"2026-09-12T09:47:16.053659Z","iopub.execute_input":"2026-09-12T09:47:16.05386Z","iopub.status.idle":"2026-09-12T09:47:16.062061Z","shell.execute_reply.started":"2026-09-12T09:47:16.053842Z","shell.execute_reply":"2026-09-12T09:47:16.061367Z"},"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":"2026-09-12T09:47:16.06311Z","iopub.execute_input":"2026-09-12T09:47:16.063947Z","iopub.status.idle":"2026-09-12T09:47:16.070952Z","shell.execute_reply.started":"2026-09-12T09:47:16.063923Z","shell.execute_reply":"2026-09-12T09:47:16.070096Z"},"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":"2026-09-12T09:47:16.072031Z","iopub.execute_input":"2026-09-12T09:47:16.072882Z","iopub.status.idle":"2026-09-12T09:47:17.140671Z","shell.execute_reply.started":"2026-09-12T09:47:16.072852Z","shell.execute_reply":"2026-09-12T09:47:17.139364Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -l","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T09:47:17.142286Z","iopub.execute_input":"2026-09-12T09:47:17.142641Z","iopub.status.idle":"2026-09-12T09:47:18.141383Z","shell.execute_reply.started":"2026-09-12T09:47:17.142616Z","shell.execute_reply":"2026-09-12T09:47:18.140457Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -l dataset_dogs_vs_cats/train","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T09:47:18.142809Z","iopub.execute_input":"2026-09-12T09:47:18.143161Z","iopub.status.idle":"2026-09-12T09:47:19.133231Z","shell.execute_reply.started":"2026-09-12T09:47:18.143124Z","shell.execute_reply":"2026-09-12T09:47:19.132305Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -l dataset_dogs_vs_cats/test #validation","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T09:47:19.134886Z","iopub.execute_input":"2026-09-12T09:47:19.13561Z","iopub.status.idle":"2026-09-12T09:47:20.130872Z","shell.execute_reply.started":"2026-09-12T09:47:19.135573Z","shell.execute_reply":"2026-09-12T09:47:20.129915Z"}},"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":"2026-09-12T09:47:20.132323Z","iopub.execute_input":"2026-09-12T09:47:20.13345Z","iopub.status.idle":"2026-09-12T09:47:23.212625Z","shell.execute_reply.started":"2026-09-12T09:47:20.133414Z","shell.execute_reply":"2026-09-12T09:47:23.211812Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"print(src)\nprint(dst)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T09:47:23.213917Z","iopub.execute_input":"2026-09-12T09:47:23.214838Z","iopub.status.idle":"2026-09-12T09:47:23.219795Z","shell.execute_reply.started":"2026-09-12T09:47:23.214802Z","shell.execute_reply":"2026-09-12T09:47:23.218996Z"}},"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":"2026-09-12T09:47:23.225818Z","iopub.execute_input":"2026-09-12T09:47:23.226125Z","iopub.status.idle":"2026-09-12T09:47:25.377261Z","shell.execute_reply.started":"2026-09-12T09:47:23.226103Z","shell.execute_reply":"2026-09-12T09:47:25.375968Z"},"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":"2026-09-12T09:47:25.379023Z","iopub.execute_input":"2026-09-12T09:47:25.379429Z","iopub.status.idle":"2026-09-12T09:47:27.510702Z","shell.execute_reply.started":"2026-09-12T09:47:25.379394Z","shell.execute_reply":"2026-09-12T09:47:27.509622Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"!pip -q install livelossplot==0.5.5","metadata":{"execution":{"iopub.status.busy":"2026-09-12T09:47:27.512715Z","iopub.execute_input":"2026-09-12T09:47:27.513126Z","iopub.status.idle":"2026-09-12T09:47:35.801Z","shell.execute_reply.started":"2026-09-12T09:47:27.513091Z","shell.execute_reply":"2026-09-12T09:47:35.799566Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"from livelossplot import PlotLossesKeras","metadata":{"execution":{"iopub.status.busy":"2026-09-12T09:47:35.802855Z","iopub.execute_input":"2026-09-12T09:47:35.803253Z","iopub.status.idle":"2026-09-12T09:47:35.808628Z","shell.execute_reply.started":"2026-09-12T09:47:35.803219Z","shell.execute_reply":"2026-09-12T09:47:35.807597Z"},"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":"2026-09-12T09:47:35.810036Z","iopub.execute_input":"2026-09-12T09:47:35.810306Z","iopub.status.idle":"2026-09-12T09:47:35.81956Z","shell.execute_reply.started":"2026-09-12T09:47:35.810284Z","shell.execute_reply":"2026-09-12T09:47:35.818679Z"}},"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":"2026-09-12T09:47:35.820886Z","iopub.execute_input":"2026-09-12T09:47:35.821204Z","iopub.status.idle":"2026-09-12T09:47:35.830568Z","shell.execute_reply.started":"2026-09-12T09:47:35.821166Z","shell.execute_reply":"2026-09-12T09:47:35.82959Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"model = Sequential()\ntype(model)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T09:47:35.831711Z","iopub.execute_input":"2026-09-12T09:47:35.832045Z","iopub.status.idle":"2026-09-12T09:47:35.846402Z","shell.execute_reply.started":"2026-09-12T09:47:35.832015Z","shell.execute_reply":"2026-09-12T09:47:35.845364Z"}},"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":"2026-09-12T09:47:35.84743Z","iopub.execute_input":"2026-09-12T09:47:35.847723Z","iopub.status.idle":"2026-09-12T09:47:35.909702Z","shell.execute_reply.started":"2026-09-12T09:47:35.8477Z","shell.execute_reply":"2026-09-12T09:47:35.907438Z"}},"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":"2026-09-12T09:47:35.910802Z","iopub.execute_input":"2026-09-12T09:47:35.911054Z","iopub.status.idle":"2026-09-12T09:47:35.970874Z","shell.execute_reply.started":"2026-09-12T09:47:35.911034Z","shell.execute_reply":"2026-09-12T09:47:35.967322Z"}},"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":"2026-09-12T09:47:35.971892Z","iopub.execute_input":"2026-09-12T09:47:35.972168Z","iopub.status.idle":"2026-09-12T09:47:35.978064Z","shell.execute_reply.started":"2026-09-12T09:47:35.972146Z","shell.execute_reply":"2026-09-12T09:47:35.977014Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"model_1 = define_model_1()\nprint(model_1.summary())","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T09:47:35.979191Z","iopub.execute_input":"2026-09-12T09:47:35.979408Z","iopub.status.idle":"2026-09-12T09:47:36.044935Z","shell.execute_reply.started":"2026-09-12T09:47:35.979389Z","shell.execute_reply":"2026-09-12T09:47:36.044188Z"}},"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":"2026-09-12T09:47:36.046476Z","iopub.execute_input":"2026-09-12T09:47:36.046827Z","iopub.status.idle":"2026-09-12T09:47:36.052551Z","shell.execute_reply.started":"2026-09-12T09:47:36.046789Z","shell.execute_reply":"2026-09-12T09:47:36.051596Z"}},"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":"2026-09-12T09:47:36.053722Z","iopub.execute_input":"2026-09-12T09:47:36.054027Z","iopub.status.idle":"2026-09-12T09:47:36.061198Z","shell.execute_reply.started":"2026-09-12T09:47:36.053998Z","shell.execute_reply":"2026-09-12T09:47:36.060394Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"model_1 = define_model_1()\nprint(model_1.summary())","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T09:47:36.062204Z","iopub.execute_input":"2026-09-12T09:47:36.062415Z","iopub.status.idle":"2026-09-12T09:47:36.1269Z","shell.execute_reply.started":"2026-09-12T09:47:36.062397Z","shell.execute_reply":"2026-09-12T09:47:36.126105Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"datagen = ImageDataGenerator(rescale=1.0/255.0)\ntype(datagen)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T09:47:36.128066Z","iopub.execute_input":"2026-09-12T09:47:36.128396Z","iopub.status.idle":"2026-09-12T09:47:36.135064Z","shell.execute_reply.started":"2026-09-12T09:47:36.128365Z","shell.execute_reply":"2026-09-12T09:47:36.133882Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls dataset_dogs_vs_cats/train/","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T09:47:36.136251Z","iopub.execute_input":"2026-09-12T09:47:36.136583Z","iopub.status.idle":"2026-09-12T09:47:37.131343Z","shell.execute_reply.started":"2026-09-12T09:47:36.136546Z","shell.execute_reply":"2026-09-12T09:47:37.130438Z"}},"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":"2026-09-12T09:47:37.132906Z","iopub.execute_input":"2026-09-12T09:47:37.13322Z","iopub.status.idle":"2026-09-12T09:47:37.139596Z","shell.execute_reply.started":"2026-09-12T09:47:37.133196Z","shell.execute_reply":"2026-09-12T09:47:37.138597Z"}},"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":"2026-09-12T09:47:37.140784Z","iopub.execute_input":"2026-09-12T09:47:37.141004Z","iopub.status.idle":"2026-09-12T09:47:37.716071Z","shell.execute_reply.started":"2026-09-12T09:47:37.140986Z","shell.execute_reply":"2026-09-12T09:47:37.715376Z"}},"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":"2026-09-12T09:47:37.717171Z","iopub.execute_input":"2026-09-12T09:47:37.717499Z","iopub.status.idle":"2026-09-12T09:47:37.724414Z","shell.execute_reply.started":"2026-09-12T09:47:37.717467Z","shell.execute_reply":"2026-09-12T09:47:37.723494Z"}},"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":"2026-09-12T09:47:37.725659Z","iopub.execute_input":"2026-09-12T09:47:37.72594Z","iopub.status.idle":"2026-09-12T09:47:37.951186Z","shell.execute_reply.started":"2026-09-12T09:47:37.72591Z","shell.execute_reply":"2026-09-12T09:47:37.950457Z"}},"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":"2026-09-12T09:47:37.952224Z","iopub.execute_input":"2026-09-12T09:47:37.952598Z","iopub.status.idle":"2026-09-12T09:47:37.958917Z","shell.execute_reply.started":"2026-09-12T09:47:37.952566Z","shell.execute_reply":"2026-09-12T09:47:37.957861Z"}},"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":"2026-09-12T09:47:37.960088Z","iopub.execute_input":"2026-09-12T09:47:37.960367Z","iopub.status.idle":"2026-09-12T10:01:15.849623Z","shell.execute_reply.started":"2026-09-12T09:47:37.960346Z","shell.execute_reply":"2026-09-12T10:01:15.848858Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# learning curves\nsummarize_diagnostics(history_1)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T10:01:15.850947Z","iopub.execute_input":"2026-09-12T10:01:15.851773Z","iopub.status.idle":"2026-09-12T10:01:16.213857Z","shell.execute_reply.started":"2026-09-12T10:01:15.851734Z","shell.execute_reply":"2026-09-12T10:01:16.212885Z"}},"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":"2026-09-12T10:01:16.215049Z","iopub.execute_input":"2026-09-12T10:01:16.215665Z","iopub.status.idle":"2026-09-12T10:01:26.301183Z","shell.execute_reply.started":"2026-09-12T10:01:16.215626Z","shell.execute_reply":"2026-09-12T10:01:26.300179Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls ","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T10:01:26.302389Z","iopub.execute_input":"2026-09-12T10:01:26.302752Z","iopub.status.idle":"2026-09-12T10:01:27.294228Z","shell.execute_reply.started":"2026-09-12T10:01:26.30272Z","shell.execute_reply":"2026-09-12T10:01:27.292972Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"pwd","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T10:01:27.295937Z","iopub.execute_input":"2026-09-12T10:01:27.296257Z","iopub.status.idle":"2026-09-12T10:01:27.303406Z","shell.execute_reply.started":"2026-09-12T10:01:27.296232Z","shell.execute_reply":"2026-09-12T10:01:27.302588Z"}},"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":"2026-09-12T10:01:27.304739Z","iopub.execute_input":"2026-09-12T10:01:27.305013Z","iopub.status.idle":"2026-09-12T10:01:27.348186Z","shell.execute_reply.started":"2026-09-12T10:01:27.304981Z","shell.execute_reply":"2026-09-12T10:01:27.347287Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"df.columns","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T10:01:27.349328Z","iopub.execute_input":"2026-09-12T10:01:27.349652Z","iopub.status.idle":"2026-09-12T10:01:27.356646Z","shell.execute_reply.started":"2026-09-12T10:01:27.349623Z","shell.execute_reply":"2026-09-12T10:01:27.355772Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"image_files[:5], type(image_files), len(image_files)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T10:01:27.357815Z","iopub.execute_input":"2026-09-12T10:01:27.358269Z","iopub.status.idle":"2026-09-12T10:01:27.367458Z","shell.execute_reply.started":"2026-09-12T10:01:27.358247Z","shell.execute_reply":"2026-09-12T10:01:27.366569Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"df.describe()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T10:01:27.368476Z","iopub.execute_input":"2026-09-12T10:01:27.368839Z","iopub.status.idle":"2026-09-12T10:01:27.408573Z","shell.execute_reply.started":"2026-09-12T10:01:27.368818Z","shell.execute_reply":"2026-09-12T10:01:27.407584Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"df.loc[1]","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T10:01:27.409684Z","iopub.execute_input":"2026-09-12T10:01:27.409991Z","iopub.status.idle":"2026-09-12T10:01:27.416198Z","shell.execute_reply.started":"2026-09-12T10:01:27.409963Z","shell.execute_reply":"2026-09-12T10:01:27.415335Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"df.sample(5)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T10:01:27.417412Z","iopub.execute_input":"2026-09-12T10:01:27.417732Z","iopub.status.idle":"2026-09-12T10:01:27.434318Z","shell.execute_reply.started":"2026-09-12T10:01:27.417704Z","shell.execute_reply":"2026-09-12T10:01:27.433385Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"df['filename']","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T10:01:27.435328Z","iopub.execute_input":"2026-09-12T10:01:27.435711Z","iopub.status.idle":"2026-09-12T10:01:27.443433Z","shell.execute_reply.started":"2026-09-12T10:01:27.435679Z","shell.execute_reply":"2026-09-12T10:01:27.442803Z"}},"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":"2026-09-12T10:01:27.444604Z","iopub.execute_input":"2026-09-12T10:01:27.444886Z","iopub.status.idle":"2026-09-12T10:01:27.526666Z","shell.execute_reply.started":"2026-09-12T10:01:27.444858Z","shell.execute_reply":"2026-09-12T10:01:27.525947Z"}},"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":"2026-09-12T10:01:27.527606Z","iopub.execute_input":"2026-09-12T10:01:27.528421Z","iopub.status.idle":"2026-09-12T10:01:27.533841Z","shell.execute_reply.started":"2026-09-12T10:01:27.528391Z","shell.execute_reply":"2026-09-12T10:01:27.533033Z"}},"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":"2026-09-12T10:01:27.53483Z","iopub.execute_input":"2026-09-12T10:01:27.535578Z","iopub.status.idle":"2026-09-12T10:01:32.486945Z","shell.execute_reply.started":"2026-09-12T10:01:27.535549Z","shell.execute_reply":"2026-09-12T10:01:32.485846Z"}},"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":"2026-09-12T10:01:32.488695Z","iopub.execute_input":"2026-09-12T10:01:32.48967Z","iopub.status.idle":"2026-09-12T10:01:37.381958Z","shell.execute_reply.started":"2026-09-12T10:01:32.489624Z","shell.execute_reply":"2026-09-12T10:01:37.380515Z"}},"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":"2026-09-12T10:01:37.383863Z","iopub.execute_input":"2026-09-12T10:01:37.384708Z","iopub.status.idle":"2026-09-12T10:01:37.391019Z","shell.execute_reply.started":"2026-09-12T10:01:37.384671Z","shell.execute_reply":"2026-09-12T10:01:37.39022Z"}},"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":"2026-09-12T10:01:37.392173Z","iopub.execute_input":"2026-09-12T10:01:37.39249Z","iopub.status.idle":"2026-09-12T10:01:41.870186Z","shell.execute_reply.started":"2026-09-12T10:01:37.392467Z","shell.execute_reply":"2026-09-12T10:01:41.867607Z"}},"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":"2026-09-12T10:01:41.871341Z","iopub.execute_input":"2026-09-12T10:01:41.871664Z","iopub.status.idle":"2026-09-12T10:02:02.615818Z","shell.execute_reply.started":"2026-09-12T10:01:41.871638Z","shell.execute_reply":"2026-09-12T10:02:02.614953Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"preds[:10]","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T10:02:02.616944Z","iopub.execute_input":"2026-09-12T10:02:02.617241Z","iopub.status.idle":"2026-09-12T10:02:02.623587Z","shell.execute_reply.started":"2026-09-12T10:02:02.617217Z","shell.execute_reply":"2026-09-12T10:02:02.622571Z"}},"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":"2026-09-12T10:02:02.624757Z","iopub.execute_input":"2026-09-12T10:02:02.625066Z","iopub.status.idle":"2026-09-12T10:02:03.908127Z","shell.execute_reply.started":"2026-09-12T10:02:02.625038Z","shell.execute_reply":"2026-09-12T10:02:03.907159Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# end of 2026-09-06\nstop here","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T10:02:03.90917Z","iopub.execute_input":"2026-09-12T10:02:03.909708Z","iopub.status.idle":"2026-09-12T10:02:03.916331Z","shell.execute_reply.started":"2026-09-12T10:02:03.909681Z","shell.execute_reply":"2026-09-12T10:02:03.913906Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Transfer Learning","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T10:02:03.917352Z","iopub.status.idle":"2026-09-12T10:02:03.9178Z","shell.execute_reply.started":"2026-09-12T10:02:03.917611Z","shell.execute_reply":"2026-09-12T10:02:03.917634Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"from keras.applications.vgg16 import VGG16\nfrom keras.models import Model\nfrom keras.layers import Dense, GlobalAveragePooling2D, Dropout\nfrom keras.optimizers import Adam\nfrom keras.callbacks import EarlyStopping, ReduceLROnPlateau\n\ndef define_model_vgg16():\n\n    base_model = VGG16(\n        include_top=False,\n        weights='imagenet',\n        input_shape=(224, 224, 3)\n    )\n\n    # Freeze VGG16\n    for layer in base_model.layers:\n        layer.trainable = False\n\n    # Classifier\n    x = base_model.output\n    x = GlobalAveragePooling2D()(x)\n    x = Dense(256, activation='relu')(x)\n    x = Dropout(0.5)(x)\n    output = Dense(1, activation='sigmoid')(x)\n\n    model = Model(\n        inputs=base_model.input,\n        outputs=output\n    )\n\n    model.compile(\n        optimizer=Adam(learning_rate=0.0001),\n        loss='binary_crossentropy',\n        metrics=['accuracy']\n    )\n\n    return model\n\n\nvgg16_model = define_model_vgg16()\nvgg16_model.summary()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T11:20:43.184784Z","iopub.execute_input":"2026-09-12T11:20:43.185084Z","iopub.status.idle":"2026-09-12T11:21:03.07289Z","shell.execute_reply.started":"2026-09-12T11:20:43.185061Z","shell.execute_reply":"2026-09-12T11:21:03.071918Z"}},"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":"2026-09-12T10:09:06.596905Z","iopub.execute_input":"2026-09-12T10:09:06.597215Z","iopub.status.idle":"2026-09-12T10:09:06.601341Z","shell.execute_reply.started":"2026-09-12T10:09:06.597193Z","shell.execute_reply":"2026-09-12T10:09:06.600402Z"}},"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":"2026-09-12T10:09:07.04532Z","iopub.execute_input":"2026-09-12T10:09:07.045675Z","iopub.status.idle":"2026-09-12T10:09:07.049748Z","shell.execute_reply.started":"2026-09-12T10:09:07.045646Z","shell.execute_reply":"2026-09-12T10:09:07.048721Z"}},"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":"2026-09-12T10:09:07.637007Z","iopub.execute_input":"2026-09-12T10:09:07.637634Z","iopub.status.idle":"2026-09-12T10:09:07.641178Z","shell.execute_reply.started":"2026-09-12T10:09:07.637598Z","shell.execute_reply":"2026-09-12T10:09:07.640354Z"}},"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":"2026-09-12T10:09:09.814114Z","iopub.execute_input":"2026-09-12T10:09:09.81445Z","iopub.status.idle":"2026-09-12T10:09:09.819126Z","shell.execute_reply.started":"2026-09-12T10:09:09.814425Z","shell.execute_reply":"2026-09-12T10:09:09.818044Z"}},"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":"2026-09-12T11:22:00.976834Z","iopub.execute_input":"2026-09-12T11:22:00.977163Z","iopub.status.idle":"2026-09-12T11:22:01.370694Z","shell.execute_reply.started":"2026-09-12T11:22:00.977137Z","shell.execute_reply":"2026-09-12T11:22:01.369771Z"}},"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":"2026-09-12T10:09:13.637837Z","iopub.execute_input":"2026-09-12T10:09:13.638429Z","iopub.status.idle":"2026-09-12T10:09:13.642175Z","shell.execute_reply.started":"2026-09-12T10:09:13.638399Z","shell.execute_reply":"2026-09-12T10:09:13.641239Z"}},"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":"2026-09-12T10:09:14.035657Z","iopub.execute_input":"2026-09-12T10:09:14.036449Z","iopub.status.idle":"2026-09-12T10:09:14.040243Z","shell.execute_reply.started":"2026-09-12T10:09:14.036413Z","shell.execute_reply":"2026-09-12T10:09:14.039281Z"}},"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":"2026-09-12T10:09:14.469425Z","iopub.execute_input":"2026-09-12T10:09:14.470005Z","iopub.status.idle":"2026-09-12T10:09:14.473425Z","shell.execute_reply.started":"2026-09-12T10:09:14.469981Z","shell.execute_reply":"2026-09-12T10:09:14.47257Z"}},"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":"2026-09-12T10:09:14.869101Z","iopub.execute_input":"2026-09-12T10:09:14.869717Z","iopub.status.idle":"2026-09-12T10:09:14.872891Z","shell.execute_reply.started":"2026-09-12T10:09:14.869692Z","shell.execute_reply":"2026-09-12T10:09:14.8721Z"}},"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":"2026-09-12T11:22:12.656777Z","iopub.execute_input":"2026-09-12T11:22:12.657512Z","iopub.status.idle":"2026-09-12T11:22:12.663589Z","shell.execute_reply.started":"2026-09-12T11:22:12.657477Z","shell.execute_reply":"2026-09-12T11:22:12.662821Z"}},"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":"2026-09-12T10:09:18.424077Z","iopub.execute_input":"2026-09-12T10:09:18.424903Z","iopub.status.idle":"2026-09-12T10:14:27.974006Z","shell.execute_reply.started":"2026-09-12T10:09:18.424873Z","shell.execute_reply":"2026-09-12T10:14:27.973203Z"}},"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":"2026-09-12T11:22:17.472432Z","iopub.execute_input":"2026-09-12T11:22:17.473063Z","iopub.status.idle":"2026-09-12T11:22:17.739896Z","shell.execute_reply.started":"2026-09-12T11:22:17.47303Z","shell.execute_reply":"2026-09-12T11:22:17.738708Z"}},"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":"2026-09-12T10:02:03.941861Z","iopub.status.idle":"2026-09-12T10:02:03.942197Z","shell.execute_reply.started":"2026-09-12T10:02:03.942045Z","shell.execute_reply":"2026-09-12T10:02:03.94206Z"}},"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":"2026-09-12T10:02:03.943661Z","iopub.status.idle":"2026-09-12T10:02:03.944043Z","shell.execute_reply.started":"2026-09-12T10:02:03.943846Z","shell.execute_reply":"2026-09-12T10:02:03.94386Z"},"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":"2026-09-12T10:02:03.945284Z","iopub.status.idle":"2026-09-12T10:02:03.945662Z","shell.execute_reply.started":"2026-09-12T10:02:03.945464Z","shell.execute_reply":"2026-09-12T10:02:03.945479Z"}},"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":"2026-09-12T10:02:03.947501Z","iopub.status.idle":"2026-09-12T10:02:03.947874Z","shell.execute_reply.started":"2026-09-12T10:02:03.947731Z","shell.execute_reply":"2026-09-12T10:02:03.947746Z"}},"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":"2026-09-12T10:02:03.948796Z","iopub.status.idle":"2026-09-12T10:02:03.949123Z","shell.execute_reply.started":"2026-09-12T10:02:03.948945Z","shell.execute_reply":"2026-09-12T10:02:03.948958Z"}},"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":"2026-09-12T10:02:03.950434Z","iopub.status.idle":"2026-09-12T10:02:03.950768Z","shell.execute_reply.started":"2026-09-12T10:02:03.950622Z","shell.execute_reply":"2026-09-12T10:02:03.950637Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# plot_images_with_labels(images, labels, \"Dog-Cat\", \"Training\")","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T10:02:03.952672Z","iopub.status.idle":"2026-09-12T10:02:03.953078Z","shell.execute_reply.started":"2026-09-12T10:02:03.952868Z","shell.execute_reply":"2026-09-12T10:02:03.952888Z"}},"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":"2026-09-12T10:02:03.954661Z","iopub.status.idle":"2026-09-12T10:02:03.955068Z","shell.execute_reply.started":"2026-09-12T10:02:03.954855Z","shell.execute_reply":"2026-09-12T10:02:03.954875Z"}},"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":"2026-09-12T10:02:03.956Z","iopub.status.idle":"2026-09-12T10:02:03.956412Z","shell.execute_reply.started":"2026-09-12T10:02:03.956201Z","shell.execute_reply":"2026-09-12T10:02:03.956221Z"}},"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":"2026-09-12T10:02:03.958102Z","iopub.status.idle":"2026-09-12T10:02:03.958552Z","shell.execute_reply.started":"2026-09-12T10:02:03.958313Z","shell.execute_reply":"2026-09-12T10:02:03.958333Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"images = test_it.__next__()\nimages.shape","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T10:02:03.959582Z","iopub.status.idle":"2026-09-12T10:02:03.960227Z","shell.execute_reply.started":"2026-09-12T10:02:03.959824Z","shell.execute_reply":"2026-09-12T10:02:03.959848Z"}},"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":"2026-09-12T10:02:03.962077Z","iopub.status.idle":"2026-09-12T10:02:03.962497Z","shell.execute_reply.started":"2026-09-12T10:02:03.96228Z","shell.execute_reply":"2026-09-12T10:02:03.9623Z"}},"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":"2026-09-12T10:02:03.963566Z","iopub.status.idle":"2026-09-12T10:02:03.963842Z","shell.execute_reply.started":"2026-09-12T10:02:03.963711Z","shell.execute_reply":"2026-09-12T10:02:03.963724Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"Make Prediction","metadata":{}},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null}]}