{"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":"2026-09-11T10:46:42.346754Z","iopub.execute_input":"2026-09-11T10:46:42.347051Z","iopub.status.idle":"2026-09-11T10:46:42.676282Z","shell.execute_reply.started":"2026-09-11T10:46:42.347012Z","shell.execute_reply":"2026-09-11T10:46:42.675375Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"!python --version","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-11T10:46:42.678972Z","iopub.execute_input":"2026-09-11T10:46:42.679282Z","iopub.status.idle":"2026-09-11T10:46:43.751495Z","shell.execute_reply.started":"2026-09-11T10:46:42.679260Z","shell.execute_reply":"2026-09-11T10:46:43.750499Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"!uname --all","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-11T10:46:43.752994Z","iopub.execute_input":"2026-09-11T10:46:43.753361Z","iopub.status.idle":"2026-09-11T10:46:44.739874Z","shell.execute_reply.started":"2026-09-11T10:46:43.753324Z","shell.execute_reply":"2026-09-11T10:46:44.738840Z"}},"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":"2026-09-11T10:46:44.741376Z","iopub.execute_input":"2026-09-11T10:46:44.741647Z","iopub.status.idle":"2026-09-11T10:46:55.635097Z","shell.execute_reply.started":"2026-09-11T10:46:44.741621Z","shell.execute_reply":"2026-09-11T10:46:55.633912Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-11T10:46:55.636466Z","iopub.execute_input":"2026-09-11T10:46:55.636742Z","iopub.status.idle":"2026-09-11T10:46:56.613564Z","shell.execute_reply.started":"2026-09-11T10:46:55.636719Z","shell.execute_reply":"2026-09-11T10:46:56.612565Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -l","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-11T10:46:56.614881Z","iopub.execute_input":"2026-09-11T10:46:56.615169Z","iopub.status.idle":"2026-09-11T10:46:57.574986Z","shell.execute_reply.started":"2026-09-11T10:46:56.615144Z","shell.execute_reply":"2026-09-11T10:46:57.573744Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls test1","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-11T10:46:57.579446Z","iopub.execute_input":"2026-09-11T10:46:57.579811Z","iopub.status.idle":"2026-09-11T10:46:58.622065Z","shell.execute_reply.started":"2026-09-11T10:46:57.579784Z","shell.execute_reply":"2026-09-11T10:46:58.621205Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls test1/ | wc -l","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-11T10:46:58.623195Z","iopub.execute_input":"2026-09-11T10:46:58.623565Z","iopub.status.idle":"2026-09-11T10:46:59.631345Z","shell.execute_reply.started":"2026-09-11T10:46:58.623537Z","shell.execute_reply":"2026-09-11T10:46:59.630440Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls train/ | wc -l","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-11T10:46:59.632661Z","iopub.execute_input":"2026-09-11T10:46:59.632919Z","iopub.status.idle":"2026-09-11T10:47:00.701889Z","shell.execute_reply.started":"2026-09-11T10:46:59.632895Z","shell.execute_reply":"2026-09-11T10:47:00.700518Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"#ls train/","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-11T10:47:00.703742Z","iopub.execute_input":"2026-09-11T10:47:00.704117Z","iopub.status.idle":"2026-09-11T10:47:00.709226Z","shell.execute_reply.started":"2026-09-11T10:47:00.704080Z","shell.execute_reply":"2026-09-11T10:47:00.708216Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"pwd","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-11T10:47:00.710432Z","iopub.execute_input":"2026-09-11T10:47:00.710696Z","iopub.status.idle":"2026-09-11T10:47:00.792526Z","shell.execute_reply.started":"2026-09-11T10:47:00.710640Z","shell.execute_reply":"2026-09-11T10:47:00.791741Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-11T10:47:00.793545Z","iopub.execute_input":"2026-09-11T10:47:00.793882Z","iopub.status.idle":"2026-09-11T10:47:01.801628Z","shell.execute_reply.started":"2026-09-11T10:47:00.793858Z","shell.execute_reply":"2026-09-11T10:47:01.800758Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -U train | head -n 10","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-11T10:47:01.803244Z","iopub.execute_input":"2026-09-11T10:47:01.803638Z","iopub.status.idle":"2026-09-11T10:47:02.830136Z","shell.execute_reply.started":"2026-09-11T10:47:01.803601Z","shell.execute_reply":"2026-09-11T10:47:02.829135Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -U test1 | head -n 10","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-11T10:47:02.831821Z","iopub.execute_input":"2026-09-11T10:47:02.832217Z","iopub.status.idle":"2026-09-11T10:47:03.827620Z","shell.execute_reply.started":"2026-09-11T10:47:02.832188Z","shell.execute_reply":"2026-09-11T10:47:03.826692Z"}},"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":"2026-09-11T10:47:03.828911Z","iopub.execute_input":"2026-09-11T10:47:03.829353Z","iopub.status.idle":"2026-09-11T10:47:04.822354Z","shell.execute_reply.started":"2026-09-11T10:47:03.829284Z","shell.execute_reply":"2026-09-11T10:47:04.821369Z"},"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":"2026-09-11T10:47:04.823713Z","iopub.execute_input":"2026-09-11T10:47:04.824042Z","iopub.status.idle":"2026-09-11T10:47:05.758938Z","shell.execute_reply.started":"2026-09-11T10:47:04.824007Z","shell.execute_reply":"2026-09-11T10:47:05.757792Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"!python --version","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-11T10:47:05.760087Z","iopub.execute_input":"2026-09-11T10:47:05.760462Z","iopub.status.idle":"2026-09-11T10:47:06.768460Z","shell.execute_reply.started":"2026-09-11T10:47:05.760435Z","shell.execute_reply":"2026-09-11T10:47:06.766606Z"}},"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":"2026-09-11T10:47:06.770027Z","iopub.execute_input":"2026-09-11T10:47:06.770444Z","iopub.status.idle":"2026-09-11T10:47:23.506430Z","shell.execute_reply.started":"2026-09-11T10:47:06.770409Z","shell.execute_reply":"2026-09-11T10:47:23.505611Z"}},"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":"2026-09-11T10:47:23.507417Z","iopub.execute_input":"2026-09-11T10:47:23.508191Z","iopub.status.idle":"2026-09-11T10:47:23.512343Z","shell.execute_reply.started":"2026-09-11T10:47:23.508165Z","shell.execute_reply":"2026-09-11T10:47:23.511386Z"},"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":"2026-09-11T10:47:23.513415Z","iopub.execute_input":"2026-09-11T10:47:23.513650Z","iopub.status.idle":"2026-09-11T10:47:23.524038Z","shell.execute_reply.started":"2026-09-11T10:47:23.513628Z","shell.execute_reply":"2026-09-11T10:47:23.523348Z"},"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":"2026-09-11T10:47:23.525059Z","iopub.execute_input":"2026-09-11T10:47:23.525389Z","iopub.status.idle":"2026-09-11T10:47:23.535750Z","shell.execute_reply.started":"2026-09-11T10:47:23.525357Z","shell.execute_reply":"2026-09-11T10:47:23.534729Z"},"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":"2026-09-11T10:47:23.541230Z","iopub.execute_input":"2026-09-11T10:47:23.541588Z","iopub.status.idle":"2026-09-11T10:47:24.516872Z","shell.execute_reply.started":"2026-09-11T10:47:23.541566Z","shell.execute_reply":"2026-09-11T10:47:24.515629Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -l","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-11T10:47:24.518414Z","iopub.execute_input":"2026-09-11T10:47:24.518796Z","iopub.status.idle":"2026-09-11T10:47:25.488552Z","shell.execute_reply.started":"2026-09-11T10:47:24.518759Z","shell.execute_reply":"2026-09-11T10:47:25.487382Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -l dataset_dogs_vs_cats/train","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-11T10:47:25.490196Z","iopub.execute_input":"2026-09-11T10:47:25.490595Z","iopub.status.idle":"2026-09-11T10:47:26.461063Z","shell.execute_reply.started":"2026-09-11T10:47:25.490559Z","shell.execute_reply":"2026-09-11T10:47:26.460100Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -l dataset_dogs_vs_cats/test #validation","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-11T10:47:26.462490Z","iopub.execute_input":"2026-09-11T10:47:26.462928Z","iopub.status.idle":"2026-09-11T10:47:27.433226Z","shell.execute_reply.started":"2026-09-11T10:47:26.462899Z","shell.execute_reply":"2026-09-11T10:47:27.432036Z"}},"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":"2026-09-11T10:47:27.434696Z","iopub.execute_input":"2026-09-11T10:47:27.435078Z","iopub.status.idle":"2026-09-11T10:47:29.451079Z","shell.execute_reply.started":"2026-09-11T10:47:27.435050Z","shell.execute_reply":"2026-09-11T10:47:29.449984Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"print(src)\nprint(dst)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-11T10:47:29.452415Z","iopub.execute_input":"2026-09-11T10:47:29.452733Z","iopub.status.idle":"2026-09-11T10:47:29.457617Z","shell.execute_reply.started":"2026-09-11T10:47:29.452707Z","shell.execute_reply":"2026-09-11T10:47:29.456638Z"}},"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":"2026-09-11T10:47:29.458790Z","iopub.execute_input":"2026-09-11T10:47:29.459102Z","iopub.status.idle":"2026-09-11T10:47:31.533539Z","shell.execute_reply.started":"2026-09-11T10:47:29.459071Z","shell.execute_reply":"2026-09-11T10:47:31.532613Z"},"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":"2026-09-11T10:47:31.534936Z","iopub.execute_input":"2026-09-11T10:47:31.535240Z","iopub.status.idle":"2026-09-11T10:47:33.579776Z","shell.execute_reply.started":"2026-09-11T10:47:31.535213Z","shell.execute_reply":"2026-09-11T10:47:33.578737Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"!pip -q install livelossplot==0.5.5","metadata":{"execution":{"iopub.status.busy":"2026-09-11T10:47:33.581531Z","iopub.execute_input":"2026-09-11T10:47:33.581849Z","iopub.status.idle":"2026-09-11T10:47:45.639225Z","shell.execute_reply.started":"2026-09-11T10:47:33.581820Z","shell.execute_reply":"2026-09-11T10:47:45.637918Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"from livelossplot import PlotLossesKeras","metadata":{"execution":{"iopub.status.busy":"2026-09-11T10:47:45.640781Z","iopub.execute_input":"2026-09-11T10:47:45.641093Z","iopub.status.idle":"2026-09-11T10:47:45.657528Z","shell.execute_reply.started":"2026-09-11T10:47:45.641065Z","shell.execute_reply":"2026-09-11T10:47:45.656539Z"},"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":"2026-09-11T10:47:45.658605Z","iopub.execute_input":"2026-09-11T10:47:45.659417Z","iopub.status.idle":"2026-09-11T10:47:45.663087Z","shell.execute_reply.started":"2026-09-11T10:47:45.659393Z","shell.execute_reply":"2026-09-11T10:47:45.662121Z"}},"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":"2026-09-11T10:47:45.664164Z","iopub.execute_input":"2026-09-11T10:47:45.664422Z","iopub.status.idle":"2026-09-11T10:47:45.674034Z","shell.execute_reply.started":"2026-09-11T10:47:45.664401Z","shell.execute_reply":"2026-09-11T10:47:45.673438Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"model = Sequential()\ntype(model)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-11T10:47:45.674839Z","iopub.execute_input":"2026-09-11T10:47:45.675069Z","iopub.status.idle":"2026-09-11T10:47:47.608423Z","shell.execute_reply.started":"2026-09-11T10:47:45.675049Z","shell.execute_reply":"2026-09-11T10:47:47.607586Z"}},"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":"2026-09-11T10:47:47.609466Z","iopub.execute_input":"2026-09-11T10:47:47.609751Z","iopub.status.idle":"2026-09-11T10:47:47.978698Z","shell.execute_reply.started":"2026-09-11T10:47:47.609728Z","shell.execute_reply":"2026-09-11T10:47:47.977845Z"}},"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":"2026-09-11T10:47:47.980002Z","iopub.execute_input":"2026-09-11T10:47:47.980380Z","iopub.status.idle":"2026-09-11T10:47:48.044173Z","shell.execute_reply.started":"2026-09-11T10:47:47.980344Z","shell.execute_reply":"2026-09-11T10:47:48.043378Z"}},"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":"2026-09-11T10:47:48.045669Z","iopub.execute_input":"2026-09-11T10:47:48.046029Z","iopub.status.idle":"2026-09-11T10:47:48.053166Z","shell.execute_reply.started":"2026-09-11T10:47:48.045995Z","shell.execute_reply":"2026-09-11T10:47:48.052374Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"model_1 = define_model_1()\nprint(model_1.summary())","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-11T10:47:48.054216Z","iopub.execute_input":"2026-09-11T10:47:48.054691Z","iopub.status.idle":"2026-09-11T10:47:48.137480Z","shell.execute_reply.started":"2026-09-11T10:47:48.054667Z","shell.execute_reply":"2026-09-11T10:47:48.136578Z"}},"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":"2026-09-11T10:47:48.138692Z","iopub.execute_input":"2026-09-11T10:47:48.138967Z","iopub.status.idle":"2026-09-11T10:47:48.145267Z","shell.execute_reply.started":"2026-09-11T10:47:48.138945Z","shell.execute_reply":"2026-09-11T10:47:48.144231Z"}},"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":"2026-09-11T10:47:48.146546Z","iopub.execute_input":"2026-09-11T10:47:48.146868Z","iopub.status.idle":"2026-09-11T10:47:48.158102Z","shell.execute_reply.started":"2026-09-11T10:47:48.146845Z","shell.execute_reply":"2026-09-11T10:47:48.157224Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"model_1 = define_model_1()\nprint(model_1.summary())","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-11T10:47:48.159173Z","iopub.execute_input":"2026-09-11T10:47:48.159519Z","iopub.status.idle":"2026-09-11T10:47:48.233744Z","shell.execute_reply.started":"2026-09-11T10:47:48.159487Z","shell.execute_reply":"2026-09-11T10:47:48.232963Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"datagen = ImageDataGenerator(rescale=1.0/255.0)\ntype(datagen)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-11T10:47:48.234814Z","iopub.execute_input":"2026-09-11T10:47:48.235332Z","iopub.status.idle":"2026-09-11T10:47:48.241366Z","shell.execute_reply.started":"2026-09-11T10:47:48.235278Z","shell.execute_reply":"2026-09-11T10:47:48.240559Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls dataset_dogs_vs_cats/train/","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-11T10:47:48.242509Z","iopub.execute_input":"2026-09-11T10:47:48.242776Z","iopub.status.idle":"2026-09-11T10:47:49.238828Z","shell.execute_reply.started":"2026-09-11T10:47:48.242754Z","shell.execute_reply":"2026-09-11T10:47:49.237895Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Hyperparameter => changable\nIMAGE_SIZE = (200, 200)\nBATCH_SIZE = 64\nEPOCHS = 20","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-11T10:47:49.240122Z","iopub.execute_input":"2026-09-11T10:47:49.240422Z","iopub.status.idle":"2026-09-11T10:47:49.245251Z","shell.execute_reply.started":"2026-09-11T10:47:49.240395Z","shell.execute_reply":"2026-09-11T10:47:49.244523Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"train_it = datagen.flow_from_directory('dataset_dogs_vs_cats/train/',\n\t\tclass_mode='binary',\n        batch_size=BATCH_SIZE, \n        target_size=IMAGE_SIZE\n)\ntype(train_it)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-11T10:47:49.246246Z","iopub.execute_input":"2026-09-11T10:47:49.246600Z","iopub.status.idle":"2026-09-11T10:47:49.819335Z","shell.execute_reply.started":"2026-09-11T10:47:49.246578Z","shell.execute_reply":"2026-09-11T10:47:49.818498Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"len(train_it), len(train_it.classes), train_it.classes[:10]","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-11T10:47:49.820602Z","iopub.execute_input":"2026-09-11T10:47:49.820891Z","iopub.status.idle":"2026-09-11T10:47:49.826838Z","shell.execute_reply.started":"2026-09-11T10:47:49.820867Z","shell.execute_reply":"2026-09-11T10:47:49.826081Z"}},"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":"2026-09-11T10:47:49.827923Z","iopub.execute_input":"2026-09-11T10:47:49.828443Z","iopub.status.idle":"2026-09-11T10:47:50.015999Z","shell.execute_reply.started":"2026-09-11T10:47:49.828405Z","shell.execute_reply":"2026-09-11T10:47:50.015036Z"}},"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":"2026-09-11T10:47:50.017336Z","iopub.execute_input":"2026-09-11T10:47:50.017687Z","iopub.status.idle":"2026-09-11T10:47:50.024056Z","shell.execute_reply.started":"2026-09-11T10:47:50.017654Z","shell.execute_reply":"2026-09-11T10:47:50.023026Z"}},"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":"2026-09-11T10:47:50.025221Z","iopub.execute_input":"2026-09-11T10:47:50.025569Z","iopub.status.idle":"2026-09-11T11:02:28.475826Z","shell.execute_reply.started":"2026-09-11T10:47:50.025528Z","shell.execute_reply":"2026-09-11T11:02:28.474760Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# learning curves\nsummarize_diagnostics(history_1)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-11T11:02:28.477108Z","iopub.execute_input":"2026-09-11T11:02:28.477488Z","iopub.status.idle":"2026-09-11T11:02:28.762380Z","shell.execute_reply.started":"2026-09-11T11:02:28.477463Z","shell.execute_reply":"2026-09-11T11:02:28.761759Z"}},"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":"2026-09-11T11:02:28.763446Z","iopub.execute_input":"2026-09-11T11:02:28.763771Z","iopub.status.idle":"2026-09-11T11:02:40.105405Z","shell.execute_reply.started":"2026-09-11T11:02:28.763739Z","shell.execute_reply":"2026-09-11T11:02:40.104515Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls ","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-11T11:02:40.106414Z","iopub.execute_input":"2026-09-11T11:02:40.106762Z","iopub.status.idle":"2026-09-11T11:02:41.100337Z","shell.execute_reply.started":"2026-09-11T11:02:40.106738Z","shell.execute_reply":"2026-09-11T11:02:41.099367Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"pwd","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-11T11:02:41.101955Z","iopub.execute_input":"2026-09-11T11:02:41.102744Z","iopub.status.idle":"2026-09-11T11:02:41.109030Z","shell.execute_reply.started":"2026-09-11T11:02:41.102714Z","shell.execute_reply":"2026-09-11T11:02:41.108140Z"}},"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":"2026-09-11T11:02:41.110371Z","iopub.execute_input":"2026-09-11T11:02:41.110682Z","iopub.status.idle":"2026-09-11T11:02:41.164521Z","shell.execute_reply.started":"2026-09-11T11:02:41.110651Z","shell.execute_reply":"2026-09-11T11:02:41.163799Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"df.columns","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-11T11:02:41.165664Z","iopub.execute_input":"2026-09-11T11:02:41.165934Z","iopub.status.idle":"2026-09-11T11:02:41.173569Z","shell.execute_reply.started":"2026-09-11T11:02:41.165911Z","shell.execute_reply":"2026-09-11T11:02:41.172735Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"image_files[:5], type(image_files), len(image_files)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-11T11:02:41.175103Z","iopub.execute_input":"2026-09-11T11:02:41.175428Z","iopub.status.idle":"2026-09-11T11:02:41.183854Z","shell.execute_reply.started":"2026-09-11T11:02:41.175398Z","shell.execute_reply":"2026-09-11T11:02:41.183176Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"df.describe()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-11T11:02:41.185029Z","iopub.execute_input":"2026-09-11T11:02:41.185381Z","iopub.status.idle":"2026-09-11T11:02:41.239073Z","shell.execute_reply.started":"2026-09-11T11:02:41.185347Z","shell.execute_reply":"2026-09-11T11:02:41.238133Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"df.loc[1]","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-11T11:02:41.240292Z","iopub.execute_input":"2026-09-11T11:02:41.240650Z","iopub.status.idle":"2026-09-11T11:02:41.246697Z","shell.execute_reply.started":"2026-09-11T11:02:41.240620Z","shell.execute_reply":"2026-09-11T11:02:41.245808Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"df.sample(5)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-11T11:02:41.247832Z","iopub.execute_input":"2026-09-11T11:02:41.248137Z","iopub.status.idle":"2026-09-11T11:02:41.269088Z","shell.execute_reply.started":"2026-09-11T11:02:41.248107Z","shell.execute_reply":"2026-09-11T11:02:41.268080Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"df['filename']","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-11T11:02:41.270349Z","iopub.execute_input":"2026-09-11T11:02:41.270714Z","iopub.status.idle":"2026-09-11T11:02:41.278912Z","shell.execute_reply.started":"2026-09-11T11:02:41.270678Z","shell.execute_reply":"2026-09-11T11:02:41.278005Z"}},"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":"2026-09-11T11:02:41.279992Z","iopub.execute_input":"2026-09-11T11:02:41.280539Z","iopub.status.idle":"2026-09-11T11:02:41.368147Z","shell.execute_reply.started":"2026-09-11T11:02:41.280509Z","shell.execute_reply":"2026-09-11T11:02:41.367237Z"}},"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":"2026-09-11T11:02:41.370233Z","iopub.execute_input":"2026-09-11T11:02:41.370905Z","iopub.status.idle":"2026-09-11T11:02:41.375942Z","shell.execute_reply.started":"2026-09-11T11:02:41.370883Z","shell.execute_reply":"2026-09-11T11:02:41.375055Z"}},"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":"2026-09-11T11:02:41.377951Z","iopub.execute_input":"2026-09-11T11:02:41.378263Z","iopub.status.idle":"2026-09-11T11:02:46.233089Z","shell.execute_reply.started":"2026-09-11T11:02:41.378228Z","shell.execute_reply":"2026-09-11T11:02:46.231771Z"}},"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":"2026-09-11T11:02:46.234120Z","iopub.execute_input":"2026-09-11T11:02:46.234449Z","iopub.status.idle":"2026-09-11T11:02:51.063132Z","shell.execute_reply.started":"2026-09-11T11:02:46.234423Z","shell.execute_reply":"2026-09-11T11:02:51.062126Z"}},"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":"2026-09-11T11:02:51.064477Z","iopub.execute_input":"2026-09-11T11:02:51.065110Z","iopub.status.idle":"2026-09-11T11:02:51.071049Z","shell.execute_reply.started":"2026-09-11T11:02:51.065082Z","shell.execute_reply":"2026-09-11T11:02:51.070168Z"}},"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":"2026-09-11T11:02:51.072090Z","iopub.execute_input":"2026-09-11T11:02:51.072643Z","iopub.status.idle":"2026-09-11T11:02:55.891400Z","shell.execute_reply.started":"2026-09-11T11:02:51.072617Z","shell.execute_reply":"2026-09-11T11:02:55.890368Z"}},"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":"2026-09-11T11:07:29.612953Z","iopub.execute_input":"2026-09-11T11:07:29.613807Z","iopub.status.idle":"2026-09-11T11:07:52.220952Z","shell.execute_reply.started":"2026-09-11T11:07:29.613772Z","shell.execute_reply":"2026-09-11T11:07:52.220140Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"preds[:10]","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-11T11:12:43.899148Z","iopub.execute_input":"2026-09-11T11:12:43.900100Z","iopub.status.idle":"2026-09-11T11:12:43.906753Z","shell.execute_reply.started":"2026-09-11T11:12:43.900064Z","shell.execute_reply":"2026-09-11T11:12:43.905738Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import numpy as np\n\n\nsample_indices = np.random.choice(len(test_images), size=10, replace=False)\nsample_images = test_images[sample_indices]\n\n \npredictions = model_1.predict(sample_images)\npredicted_classes = np.argmax(predictions, axis=1)  # ดึง class ที่ได้คะแนนสูงสุด\n\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":"2026-09-11T11:12:44.979247Z","iopub.execute_input":"2026-09-11T11:12:44.979647Z","iopub.status.idle":"2026-09-11T11:12:46.504792Z","shell.execute_reply.started":"2026-09-11T11:12:44.979617Z","shell.execute_reply":"2026-09-11T11:12:46.503653Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# end of 2026-09-06\nstop here","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# Transfer Learning","metadata":{}},{"cell_type":"code","source":"#Create transfer learning model for VGG16\nimport sys\nfrom matplotlib import pyplot\nfrom keras.utils import to_categorical\nfrom keras.applications.vgg16 import VGG16\nfrom keras.models import Model\nfrom keras.layers import Dense\nfrom keras.layers import Flatten\nfrom keras.optimizers import SGD\nfrom keras.preprocessing.image import ImageDataGenerator\n\n# define cnn model\ndef define_model_vgg16():\n\t# load model\n\tmodel = VGG16(include_top=False, input_shape=(224, 224, 3))\n\t# mark loaded layers as not trainable\n\tfor layer in model.layers:\n\t\tlayer.trainable = False\n\t# add new classifier layers\n\tflat1 = Flatten()(model.layers[-1].output)\n\tclass1 = Dense(128, activation='relu', kernel_initializer='he_uniform')(flat1)\n\toutput = Dense(1, activation='sigmoid')(class1)\n\t# define new model\n\tmodel = Model(inputs=model.inputs, outputs=output)\n\t# compile model\n\topt = SGD(lr=0.001, momentum=0.9)\n\tmodel.compile(optimizer=opt, loss='binary_crossentropy', metrics=['accuracy'])\n\treturn model","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-11T11:16:34.784924Z","iopub.execute_input":"2026-09-11T11:16:34.785637Z","iopub.status.idle":"2026-09-11T11:16:34.792660Z","shell.execute_reply.started":"2026-09-11T11:16:34.785605Z","shell.execute_reply":"2026-09-11T11:16:34.791635Z"}},"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},"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},"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},"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},"outputs":[],"execution_count":null},{"cell_type":"code","source":"define_model_vgg16()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-11T11:13:51.033808Z","iopub.execute_input":"2026-09-11T11:13:51.034406Z","iopub.status.idle":"2026-09-11T11:13:53.993441Z","shell.execute_reply.started":"2026-09-11T11:13:51.034373Z","shell.execute_reply":"2026-09-11T11:13:53.992573Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"IMAGE_SIZE = (224, 224)\nBATCH_SIZE = 64\n\ntrain_it = datagen.flow_from_directory(\n    'dataset_dogs_vs_cats/train/',\n    class_mode='binary',\n    batch_size=BATCH_SIZE,\n    target_size=IMAGE_SIZE\n)\n\nval_it = datagen.flow_from_directory(\n    'dataset_dogs_vs_cats/test/',\n    class_mode='binary',\n    batch_size=BATCH_SIZE,\n    target_size=IMAGE_SIZE\n)\n\nvgg16_model = define_model_vgg16()\nvgg16_history = vgg16_model.fit(\n    train_it,\n    steps_per_epoch=len(train_it),\n    validation_data=val_it,\n    validation_steps=len(val_it),\n    epochs=5,\n    verbose=1,\n    callbacks=[PlotLossesKeras()]\n)\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-11T11:16:44.089075Z","iopub.execute_input":"2026-09-11T11:16:44.089824Z","iopub.status.idle":"2026-09-11T11:27:14.345385Z","shell.execute_reply.started":"2026-09-11T11:16:44.089789Z","shell.execute_reply":"2026-09-11T11:27:14.344649Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# learning curves\nsummarize_diagnostics(vgg16_history)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-11T11:28:21.481168Z","iopub.execute_input":"2026-09-11T11:28:21.482051Z","iopub.status.idle":"2026-09-11T11:28:21.848957Z","shell.execute_reply.started":"2026-09-11T11:28:21.482019Z","shell.execute_reply":"2026-09-11T11:28:21.847875Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"vgg16_model = define_model_vgg16()\nvgg16_model.summary()\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-11T11:28:26.986631Z","iopub.execute_input":"2026-09-11T11:28:26.986970Z","iopub.status.idle":"2026-09-11T11:28:27.360256Z","shell.execute_reply.started":"2026-09-11T11:28:26.986928Z","shell.execute_reply":"2026-09-11T11:28:27.359350Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import numpy as np\nimport matplotlib.pyplot as plt\n\n\nx_test, y_test = val_it.next()\n\nplt.figure(figsize=(15, 6))\nfor i in range(10):\n    img = x_test[i]\n    actual_label = \"Dog\" if y_test[i] == 1 else \"Cat\"\n    \n\n    pred = vgg16_model.predict(np.expand_dims(img, axis=0), verbose=0)[0][0]\n    pred_label = \"Dog\" if pred > 0.5 else \"Cat\"\n    \n  \n    plt.subplot(2, 5, i + 1)\n    plt.imshow(img)\n    color = 'green' if pred_label == actual_label else 'red'\n    plt.title(f\"Pred: {pred_label}\\n(Actual: {actual_label})\", color=color)\n    plt.axis('off')\n\nplt.tight_layout()\nplt.show()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-11T11:28:31.233127Z","iopub.execute_input":"2026-09-11T11:28:31.233715Z","iopub.status.idle":"2026-09-11T11:28:33.840991Z","shell.execute_reply.started":"2026-09-11T11:28:31.233682Z","shell.execute_reply":"2026-09-11T11:28:33.839990Z"}},"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},"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},"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},"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},"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":"2026-09-11T11:29:04.775991Z","iopub.execute_input":"2026-09-11T11:29:04.776744Z","iopub.status.idle":"2026-09-11T11:29:04.782066Z","shell.execute_reply.started":"2026-09-11T11:29:04.776712Z","shell.execute_reply":"2026-09-11T11:29:04.781166Z"}},"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":"2026-09-11T11:29:08.629485Z","iopub.execute_input":"2026-09-11T11:29:08.630535Z","iopub.status.idle":"2026-09-11T11:35:16.258058Z","shell.execute_reply.started":"2026-09-11T11:29:08.630497Z","shell.execute_reply":"2026-09-11T11:35:16.257058Z"}},"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":"2026-09-11T11:35:24.318997Z","iopub.execute_input":"2026-09-11T11:35:24.319810Z","iopub.status.idle":"2026-09-11T11:36:15.929521Z","shell.execute_reply.started":"2026-09-11T11:35:24.319775Z","shell.execute_reply":"2026-09-11T11:36:15.928635Z"}},"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":"2026-09-11T11:36:32.257782Z","iopub.execute_input":"2026-09-11T11:36:32.258827Z","iopub.status.idle":"2026-09-11T11:36:32.265351Z","shell.execute_reply.started":"2026-09-11T11:36:32.258787Z","shell.execute_reply":"2026-09-11T11:36:32.264291Z"}},"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":"2026-09-11T11:36:35.424896Z","iopub.execute_input":"2026-09-11T11:36:35.425529Z","iopub.status.idle":"2026-09-11T11:36:40.956124Z","shell.execute_reply.started":"2026-09-11T11:36:35.425497Z","shell.execute_reply":"2026-09-11T11:36:40.955405Z"},"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":"2026-09-11T11:36:40.957862Z","iopub.execute_input":"2026-09-11T11:36:40.958719Z","iopub.status.idle":"2026-09-11T11:36:40.964518Z","shell.execute_reply.started":"2026-09-11T11:36:40.958683Z","shell.execute_reply":"2026-09-11T11:36:40.963494Z"}},"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":"2026-09-11T11:36:45.261375Z","iopub.execute_input":"2026-09-11T11:36:45.262097Z","iopub.status.idle":"2026-09-11T11:36:45.267733Z","shell.execute_reply.started":"2026-09-11T11:36:45.262063Z","shell.execute_reply":"2026-09-11T11:36:45.266821Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# fit model\nmodel_inceptionv3.reset_states()\nhistory_inceptionv3 = model_inceptionv3.fit(\n    train_it, \n    steps_per_epoch=len(train_it),\n    validation_data=val_it,\n    validation_steps=len(val_it),\n    epochs=3, verbose=1,\n    callbacks = [PlotLossesKeras()]\n    )","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"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":"2026-09-11T11:37:36.675245Z","iopub.execute_input":"2026-09-11T11:37:36.675869Z","iopub.status.idle":"2026-09-11T11:37:36.682871Z","shell.execute_reply.started":"2026-09-11T11:37:36.675836Z","shell.execute_reply":"2026-09-11T11:37:36.681888Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# plot_images_with_labels(images, labels, \"Dog-Cat\", \"Training\")","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# for index, layer in enumerate(model.layers):\n#     print(index, layer.output.shape)","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# # mark loaded layers as not trainable\n# for index, layer in enumerate(model.layers[:15]):\n#     print(index, layer.name, layer.output_shape)\n#     layer.trainable = False\n    \n# for index, layer in enumerate(model.layers[15:]):\n#     print(index, layer.name, layer.output_shape)\n#     layer.trainable = True","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# evaluate model\n_, acc = model_inceptionv3.evaluate(test_it, steps=len(test_it), verbose=1)\nprint('> %.3f' % (acc * 100.0))\n# learning curves\n# summarize_diagnostics(history)\n\n# best_model = 'vgg16_model.hdf5'\n# my_model.save(best_model)","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"images = test_it.__next__()\nimages.shape","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-11T11:38:08.924144Z","iopub.execute_input":"2026-09-11T11:38:08.924607Z","iopub.status.idle":"2026-09-11T11:38:09.041016Z","shell.execute_reply.started":"2026-09-11T11:38:08.924565Z","shell.execute_reply":"2026-09-11T11:38:09.040076Z"}},"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":"2026-09-11T11:38:10.120921Z","iopub.execute_input":"2026-09-11T11:38:10.121264Z","iopub.status.idle":"2026-09-11T11:38:10.127013Z","shell.execute_reply.started":"2026-09-11T11:38:10.121236Z","shell.execute_reply":"2026-09-11T11:38:10.126064Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"probs = model_inceptionv3.predict(images_to_predict, verbose=1)\nprobs","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"Make Prediction","metadata":{}},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null}]}