{"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":"2026-09-12T09:09:03.780590Z","iopub.execute_input":"2026-09-12T09:09:03.781327Z","iopub.status.idle":"2026-09-12T09:09:03.789537Z","shell.execute_reply.started":"2026-09-12T09:09:03.781296Z","shell.execute_reply":"2026-09-12T09:09:03.788480Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"!python --version","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T09:09:03.791365Z","iopub.execute_input":"2026-09-12T09:09:03.791929Z","iopub.status.idle":"2026-09-12T09:09:04.776675Z","shell.execute_reply.started":"2026-09-12T09:09:03.791905Z","shell.execute_reply":"2026-09-12T09:09:04.775685Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"!uname --all","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T09:09:04.778332Z","iopub.execute_input":"2026-09-12T09:09:04.778738Z","iopub.status.idle":"2026-09-12T09:09:05.759302Z","shell.execute_reply.started":"2026-09-12T09:09:04.778700Z","shell.execute_reply":"2026-09-12T09:09:05.758194Z"}},"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":"2026-09-12T09:09:05.762378Z","iopub.execute_input":"2026-09-12T09:09:05.762661Z","iopub.status.idle":"2026-09-12T09:09:15.035573Z","shell.execute_reply.started":"2026-09-12T09:09:05.762637Z","shell.execute_reply":"2026-09-12T09:09:15.034428Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T09:09:15.038379Z","iopub.execute_input":"2026-09-12T09:09:15.038635Z","iopub.status.idle":"2026-09-12T09:09:16.036762Z","shell.execute_reply.started":"2026-09-12T09:09:15.038613Z","shell.execute_reply":"2026-09-12T09:09:16.035782Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -l","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T09:09:16.038846Z","iopub.execute_input":"2026-09-12T09:09:16.039184Z","iopub.status.idle":"2026-09-12T09:09:17.098204Z","shell.execute_reply.started":"2026-09-12T09:09:16.039157Z","shell.execute_reply":"2026-09-12T09:09:17.096742Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls test1","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T09:09:17.099939Z","iopub.execute_input":"2026-09-12T09:09:17.100772Z","iopub.status.idle":"2026-09-12T09:09:18.173229Z","shell.execute_reply.started":"2026-09-12T09:09:17.100728Z","shell.execute_reply":"2026-09-12T09:09:18.172317Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls test1/ | wc -l","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T09:09:18.174828Z","iopub.execute_input":"2026-09-12T09:09:18.175155Z","iopub.status.idle":"2026-09-12T09:09:19.194881Z","shell.execute_reply.started":"2026-09-12T09:09:18.175128Z","shell.execute_reply":"2026-09-12T09:09:19.193948Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls train/ | wc -l","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T09:09:19.196434Z","iopub.execute_input":"2026-09-12T09:09:19.196751Z","iopub.status.idle":"2026-09-12T09:09:20.268477Z","shell.execute_reply.started":"2026-09-12T09:09:19.196719Z","shell.execute_reply":"2026-09-12T09:09:20.267537Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"#ls train/","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T09:09:20.271905Z","iopub.execute_input":"2026-09-12T09:09:20.272281Z","iopub.status.idle":"2026-09-12T09:09:20.276515Z","shell.execute_reply.started":"2026-09-12T09:09:20.272254Z","shell.execute_reply":"2026-09-12T09:09:20.275522Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"pwd","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T09:09:20.277604Z","iopub.execute_input":"2026-09-12T09:09:20.278149Z","iopub.status.idle":"2026-09-12T09:09:20.287799Z","shell.execute_reply.started":"2026-09-12T09:09:20.278114Z","shell.execute_reply":"2026-09-12T09:09:20.287051Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T09:09:20.289032Z","iopub.execute_input":"2026-09-12T09:09:20.289625Z","iopub.status.idle":"2026-09-12T09:09:21.306459Z","shell.execute_reply.started":"2026-09-12T09:09:20.289588Z","shell.execute_reply":"2026-09-12T09:09:21.305526Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -U train | head -n 10","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T09:09:21.308226Z","iopub.execute_input":"2026-09-12T09:09:21.308604Z","iopub.status.idle":"2026-09-12T09:09:22.378318Z","shell.execute_reply.started":"2026-09-12T09:09:21.308567Z","shell.execute_reply":"2026-09-12T09:09:22.377383Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -U test1 | head -n 10","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T09:09:22.379592Z","iopub.execute_input":"2026-09-12T09:09:22.380162Z","iopub.status.idle":"2026-09-12T09:09:23.401413Z","shell.execute_reply.started":"2026-09-12T09:09:22.380132Z","shell.execute_reply":"2026-09-12T09:09:23.400161Z"}},"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":"2026-09-12T09:09:23.403040Z","iopub.execute_input":"2026-09-12T09:09:23.403351Z","iopub.status.idle":"2026-09-12T09:09:24.398887Z","shell.execute_reply.started":"2026-09-12T09:09:23.403325Z","shell.execute_reply":"2026-09-12T09:09:24.397994Z"},"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":"2026-09-12T09:09:24.400346Z","iopub.execute_input":"2026-09-12T09:09:24.400711Z","iopub.status.idle":"2026-09-12T09:09:25.380907Z","shell.execute_reply.started":"2026-09-12T09:09:24.400673Z","shell.execute_reply":"2026-09-12T09:09:25.379904Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"!python --version","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T09:09:25.382343Z","iopub.execute_input":"2026-09-12T09:09:25.383223Z","iopub.status.idle":"2026-09-12T09:09:26.371641Z","shell.execute_reply.started":"2026-09-12T09:09:25.383179Z","shell.execute_reply":"2026-09-12T09:09:26.370382Z"}},"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":"2026-09-12T09:09:26.373541Z","iopub.execute_input":"2026-09-12T09:09:26.373942Z","iopub.status.idle":"2026-09-12T09:09:26.380289Z","shell.execute_reply.started":"2026-09-12T09:09:26.373905Z","shell.execute_reply":"2026-09-12T09:09:26.379242Z"}},"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":"2026-09-12T09:09:26.381482Z","iopub.execute_input":"2026-09-12T09:09:26.381822Z","iopub.status.idle":"2026-09-12T09:09:26.390555Z","shell.execute_reply.started":"2026-09-12T09:09:26.381799Z","shell.execute_reply":"2026-09-12T09:09:26.389568Z"},"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":"2026-09-12T09:09:26.391671Z","iopub.execute_input":"2026-09-12T09:09:26.392575Z","iopub.status.idle":"2026-09-12T09:09:26.399557Z","shell.execute_reply.started":"2026-09-12T09:09:26.392550Z","shell.execute_reply":"2026-09-12T09:09:26.398752Z"},"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":"2026-09-12T09:09:26.400575Z","iopub.execute_input":"2026-09-12T09:09:26.400846Z","iopub.status.idle":"2026-09-12T09:09:26.410360Z","shell.execute_reply.started":"2026-09-12T09:09:26.400823Z","shell.execute_reply":"2026-09-12T09:09:26.409523Z"},"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":"2026-09-12T09:09:26.411321Z","iopub.execute_input":"2026-09-12T09:09:26.411680Z","iopub.status.idle":"2026-09-12T09:09:27.472681Z","shell.execute_reply.started":"2026-09-12T09:09:26.411656Z","shell.execute_reply":"2026-09-12T09:09:27.471727Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -l","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T09:09:27.474157Z","iopub.execute_input":"2026-09-12T09:09:27.474471Z","iopub.status.idle":"2026-09-12T09:09:28.476333Z","shell.execute_reply.started":"2026-09-12T09:09:27.474446Z","shell.execute_reply":"2026-09-12T09:09:28.475069Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -l dataset_dogs_vs_cats/train","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T09:09:28.478122Z","iopub.execute_input":"2026-09-12T09:09:28.478398Z","iopub.status.idle":"2026-09-12T09:09:29.473913Z","shell.execute_reply.started":"2026-09-12T09:09:28.478375Z","shell.execute_reply":"2026-09-12T09:09:29.473047Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -l dataset_dogs_vs_cats/test #validation","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T09:09:29.475414Z","iopub.execute_input":"2026-09-12T09:09:29.475828Z","iopub.status.idle":"2026-09-12T09:09:30.468787Z","shell.execute_reply.started":"2026-09-12T09:09:29.475801Z","shell.execute_reply":"2026-09-12T09:09:30.467849Z"}},"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":"2026-09-12T09:09:30.470195Z","iopub.execute_input":"2026-09-12T09:09:30.470502Z","iopub.status.idle":"2026-09-12T09:09:33.673628Z","shell.execute_reply.started":"2026-09-12T09:09:30.470475Z","shell.execute_reply":"2026-09-12T09:09:33.672500Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"print(src)\nprint(dst)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T09:09:33.674887Z","iopub.execute_input":"2026-09-12T09:09:33.675222Z","iopub.status.idle":"2026-09-12T09:09:33.680621Z","shell.execute_reply.started":"2026-09-12T09:09:33.675197Z","shell.execute_reply":"2026-09-12T09:09:33.679521Z"}},"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":"2026-09-12T09:09:33.687415Z","iopub.execute_input":"2026-09-12T09:09:33.687775Z","iopub.status.idle":"2026-09-12T09:09:35.829897Z","shell.execute_reply.started":"2026-09-12T09:09:33.687752Z","shell.execute_reply":"2026-09-12T09:09:35.828472Z"},"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":"2026-09-12T09:09:35.831688Z","iopub.execute_input":"2026-09-12T09:09:35.832057Z","iopub.status.idle":"2026-09-12T09:09:38.021208Z","shell.execute_reply.started":"2026-09-12T09:09:35.832014Z","shell.execute_reply":"2026-09-12T09:09:38.020247Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"!pip -q install livelossplot==0.5.5","metadata":{"execution":{"iopub.status.busy":"2026-09-12T09:09:38.022843Z","iopub.execute_input":"2026-09-12T09:09:38.023296Z","iopub.status.idle":"2026-09-12T09:09:46.420454Z","shell.execute_reply.started":"2026-09-12T09:09:38.023269Z","shell.execute_reply":"2026-09-12T09:09:46.419375Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"from livelossplot import PlotLossesKeras","metadata":{"execution":{"iopub.status.busy":"2026-09-12T09:09:46.422179Z","iopub.execute_input":"2026-09-12T09:09:46.422559Z","iopub.status.idle":"2026-09-12T09:09:46.428057Z","shell.execute_reply.started":"2026-09-12T09:09:46.422522Z","shell.execute_reply":"2026-09-12T09:09:46.426992Z"},"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":"2026-09-12T09:09:46.429291Z","iopub.execute_input":"2026-09-12T09:09:46.429594Z","iopub.status.idle":"2026-09-12T09:09:46.438275Z","shell.execute_reply.started":"2026-09-12T09:09:46.429564Z","shell.execute_reply":"2026-09-12T09:09:46.437537Z"}},"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":"2026-09-12T09:59:28.973522Z","iopub.execute_input":"2026-09-12T09:59:28.974382Z","iopub.status.idle":"2026-09-12T09:59:28.979397Z","shell.execute_reply.started":"2026-09-12T09:59:28.974346Z","shell.execute_reply":"2026-09-12T09:59:28.978393Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"model = Sequential()\ntype(model)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T09:59:28.981091Z","iopub.execute_input":"2026-09-12T09:59:28.981420Z","iopub.status.idle":"2026-09-12T09:59:28.997440Z","shell.execute_reply.started":"2026-09-12T09:59:28.981389Z","shell.execute_reply":"2026-09-12T09:59:28.996493Z"}},"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":"2026-09-12T09:59:28.999146Z","iopub.execute_input":"2026-09-12T09:59:28.999814Z","iopub.status.idle":"2026-09-12T09:59:29.060375Z","shell.execute_reply.started":"2026-09-12T09:59:28.999787Z","shell.execute_reply":"2026-09-12T09:59:29.058310Z"}},"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":"2026-09-12T09:59:29.061487Z","iopub.execute_input":"2026-09-12T09:59:29.061700Z","iopub.status.idle":"2026-09-12T09:59:29.118849Z","shell.execute_reply.started":"2026-09-12T09:59:29.061681Z","shell.execute_reply":"2026-09-12T09:59:29.117792Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# define cnn model\n'''def 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    model.add(Dropout(0.25))\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'''\n\nfrom tensorflow.keras.models import Sequential\nfrom tensorflow.keras.layers import Conv2D, MaxPooling2D, Flatten, Dense, Dropout\nfrom tensorflow.keras.optimizers import SGD\n\ndef define_model_1():\n    model = Sequential()\n    \n    # Block 1\n    model.add(Conv2D(32, (3, 3), activation='relu', kernel_initializer='he_uniform', padding='same', input_shape=(200, 200, 3)))\n    model.add(MaxPooling2D((2, 2)))\n    \n    # Block 2 (เพิ่มความลึก)\n    model.add(Conv2D(64, (3, 3), activation='relu', kernel_initializer='he_uniform', padding='same'))\n    model.add(MaxPooling2D((2, 2)))\n    \n    # Block 3 (เพิ่มความลึก)\n    model.add(Conv2D(128, (3, 3), activation='relu', kernel_initializer='he_uniform', padding='same'))\n    model.add(MaxPooling2D((2, 2)))\n    model.add(Dropout(0.2)) # แทรก Dropout เล็กน้อยป้องกันการจำ\n    \n    # Classifier\n    model.add(Flatten())\n    model.add(Dense(128, activation='relu', kernel_initializer='he_uniform'))\n    model.add(Dropout(0.5)) # เพิ่ม Dropout ก่อนออกผลลัพธ์\n    model.add(Dense(1, activation='sigmoid'))\n    \n    # compile model (หมายเหตุ: ใน Keras เวอร์ชั่นใหม่ๆ ใช้ learning_rate แทน lr)\n    opt = SGD(learning_rate=0.001, momentum=0.9)\n    model.compile(optimizer=opt, loss='binary_crossentropy', metrics=['accuracy'])\n    \n    return model","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T09:59:29.120859Z","iopub.execute_input":"2026-09-12T09:59:29.121351Z","iopub.status.idle":"2026-09-12T09:59:29.128750Z","shell.execute_reply.started":"2026-09-12T09:59:29.121327Z","shell.execute_reply":"2026-09-12T09:59:29.128059Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"model_1 = define_model_1()\nprint(model_1.summary())","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T09:59:29.129723Z","iopub.execute_input":"2026-09-12T09:59:29.130043Z","iopub.status.idle":"2026-09-12T09:59:29.240686Z","shell.execute_reply.started":"2026-09-12T09:59:29.130009Z","shell.execute_reply":"2026-09-12T09:59:29.239809Z"}},"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":"2026-09-12T09:59:29.242020Z","iopub.execute_input":"2026-09-12T09:59:29.242363Z","iopub.status.idle":"2026-09-12T09:59:29.250052Z","shell.execute_reply.started":"2026-09-12T09:59:29.242329Z","shell.execute_reply":"2026-09-12T09:59:29.248967Z"}},"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":"2026-09-12T09:59:29.252743Z","iopub.execute_input":"2026-09-12T09:59:29.253183Z","iopub.status.idle":"2026-09-12T09:59:29.260294Z","shell.execute_reply.started":"2026-09-12T09:59:29.253156Z","shell.execute_reply":"2026-09-12T09:59:29.259521Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"model_1 = define_model_1()\nprint(model_1.summary())","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T09:59:29.261275Z","iopub.execute_input":"2026-09-12T09:59:29.261483Z","iopub.status.idle":"2026-09-12T09:59:29.370608Z","shell.execute_reply.started":"2026-09-12T09:59:29.261463Z","shell.execute_reply":"2026-09-12T09:59:29.369773Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"datagen = ImageDataGenerator(rescale=1.0/255.0)\ntype(datagen)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T09:59:29.372387Z","iopub.execute_input":"2026-09-12T09:59:29.372796Z","iopub.status.idle":"2026-09-12T09:59:29.380190Z","shell.execute_reply.started":"2026-09-12T09:59:29.372748Z","shell.execute_reply":"2026-09-12T09:59:29.379214Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls dataset_dogs_vs_cats/train/","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T09:59:29.381443Z","iopub.execute_input":"2026-09-12T09:59:29.381757Z","iopub.status.idle":"2026-09-12T09:59:30.402714Z","shell.execute_reply.started":"2026-09-12T09:59:29.381713Z","shell.execute_reply":"2026-09-12T09:59:30.401750Z"}},"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":"2026-09-12T09:59:30.404320Z","iopub.execute_input":"2026-09-12T09:59:30.405117Z","iopub.status.idle":"2026-09-12T09:59:30.409810Z","shell.execute_reply.started":"2026-09-12T09:59:30.405086Z","shell.execute_reply":"2026-09-12T09:59:30.408809Z"}},"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":"2026-09-12T09:59:30.411146Z","iopub.execute_input":"2026-09-12T09:59:30.411473Z","iopub.status.idle":"2026-09-12T09:59:30.930967Z","shell.execute_reply.started":"2026-09-12T09:59:30.411439Z","shell.execute_reply":"2026-09-12T09:59:30.930206Z"}},"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":"2026-09-12T09:59:30.932176Z","iopub.execute_input":"2026-09-12T09:59:30.932528Z","iopub.status.idle":"2026-09-12T09:59:30.941134Z","shell.execute_reply.started":"2026-09-12T09:59:30.932502Z","shell.execute_reply":"2026-09-12T09:59:30.940314Z"}},"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=64,\n        target_size=IMAGE_SIZE\n)\ntype(val_it)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T09:59:30.944878Z","iopub.execute_input":"2026-09-12T09:59:30.945714Z","iopub.status.idle":"2026-09-12T09:59:31.285039Z","shell.execute_reply.started":"2026-09-12T09:59:30.945676Z","shell.execute_reply":"2026-09-12T09:59:31.284041Z"}},"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":"2026-09-12T09:59:31.286293Z","iopub.execute_input":"2026-09-12T09:59:31.286628Z","iopub.status.idle":"2026-09-12T09:59:31.293595Z","shell.execute_reply.started":"2026-09-12T09:59:31.286595Z","shell.execute_reply":"2026-09-12T09:59:31.292484Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"from tensorflow.keras.preprocessing.image import ImageDataGenerator\n\n# สำหรับ Training Data: ใส่ Augmentation เข้าไปจัดเต็ม\ntrain_datagen = ImageDataGenerator(\n    rescale=1.0/255.0,\n    rotation_range=20,      # สุ่มหมุนภาพไม่เกิน 20 องศา\n    width_shift_range=0.1,  # สุ่มเลื่อนภาพซ้ายขวา 10%\n    height_shift_range=0.1, # สุ่มเลื่อนภาพขึ้นลง 10%\n    horizontal_flip=True,   # สุ่มพลิกภาพซ้ายขวา\n    zoom_range=0.2          # สุ่มซูมภาพเข้าออก\n)\n\n# สำหรับ Validation Data: ห้ามใส่ Augmentation (ทำแค่ Rescale)\nval_datagen = ImageDataGenerator(rescale=1.0/255.0)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T09:59:31.294896Z","iopub.execute_input":"2026-09-12T09:59:31.295295Z","iopub.status.idle":"2026-09-12T09:59:31.303415Z","shell.execute_reply.started":"2026-09-12T09:59:31.295259Z","shell.execute_reply":"2026-09-12T09:59:31.302276Z"}},"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":"2026-09-12T09:59:31.304690Z","iopub.execute_input":"2026-09-12T09:59:31.305061Z","iopub.status.idle":"2026-09-12T10:13:36.148212Z","shell.execute_reply.started":"2026-09-12T09:59:31.305019Z","shell.execute_reply":"2026-09-12T10:13:36.147316Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# learning curves\nsummarize_diagnostics(history_1)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T10:13:36.149305Z","iopub.execute_input":"2026-09-12T10:13:36.149592Z","iopub.status.idle":"2026-09-12T10:13:36.524529Z","shell.execute_reply.started":"2026-09-12T10:13:36.149567Z","shell.execute_reply":"2026-09-12T10:13:36.523813Z"}},"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":"2026-09-12T10:13:36.527127Z","iopub.execute_input":"2026-09-12T10:13:36.527425Z","iopub.status.idle":"2026-09-12T10:13:46.993709Z","shell.execute_reply.started":"2026-09-12T10:13:36.527388Z","shell.execute_reply":"2026-09-12T10:13:46.992890Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls ","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T10:13:46.998821Z","iopub.execute_input":"2026-09-12T10:13:46.999080Z","iopub.status.idle":"2026-09-12T10:13:48.037483Z","shell.execute_reply.started":"2026-09-12T10:13:46.999057Z","shell.execute_reply":"2026-09-12T10:13:48.036196Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"pwd","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T10:13:48.039468Z","iopub.execute_input":"2026-09-12T10:13:48.039858Z","iopub.status.idle":"2026-09-12T10:13:48.047404Z","shell.execute_reply.started":"2026-09-12T10:13:48.039818Z","shell.execute_reply":"2026-09-12T10:13:48.046543Z"}},"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":"2026-09-12T10:13:48.048754Z","iopub.execute_input":"2026-09-12T10:13:48.049084Z","iopub.status.idle":"2026-09-12T10:13:48.086731Z","shell.execute_reply.started":"2026-09-12T10:13:48.049038Z","shell.execute_reply":"2026-09-12T10:13:48.086052Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"df.columns","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T10:13:48.087856Z","iopub.execute_input":"2026-09-12T10:13:48.088199Z","iopub.status.idle":"2026-09-12T10:13:48.094510Z","shell.execute_reply.started":"2026-09-12T10:13:48.088168Z","shell.execute_reply":"2026-09-12T10:13:48.093465Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"image_files[:5], type(image_files), len(image_files)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T10:13:48.095739Z","iopub.execute_input":"2026-09-12T10:13:48.096083Z","iopub.status.idle":"2026-09-12T10:13:48.103870Z","shell.execute_reply.started":"2026-09-12T10:13:48.096050Z","shell.execute_reply":"2026-09-12T10:13:48.103144Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"df.describe()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T10:13:48.104966Z","iopub.execute_input":"2026-09-12T10:13:48.105688Z","iopub.status.idle":"2026-09-12T10:13:48.125383Z","shell.execute_reply.started":"2026-09-12T10:13:48.105653Z","shell.execute_reply":"2026-09-12T10:13:48.124453Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"df.loc[1]","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T10:13:48.126332Z","iopub.execute_input":"2026-09-12T10:13:48.126536Z","iopub.status.idle":"2026-09-12T10:13:48.132886Z","shell.execute_reply.started":"2026-09-12T10:13:48.126517Z","shell.execute_reply":"2026-09-12T10:13:48.131835Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"df.sample(5)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T10:13:48.134041Z","iopub.execute_input":"2026-09-12T10:13:48.134251Z","iopub.status.idle":"2026-09-12T10:13:48.143401Z","shell.execute_reply.started":"2026-09-12T10:13:48.134232Z","shell.execute_reply":"2026-09-12T10:13:48.142501Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"df['filename']","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T10:13:48.144337Z","iopub.execute_input":"2026-09-12T10:13:48.144593Z","iopub.status.idle":"2026-09-12T10:13:48.153868Z","shell.execute_reply.started":"2026-09-12T10:13:48.144571Z","shell.execute_reply":"2026-09-12T10:13:48.153037Z"}},"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":"2026-09-12T10:13:48.155110Z","iopub.execute_input":"2026-09-12T10:13:48.155375Z","iopub.status.idle":"2026-09-12T10:13:48.238806Z","shell.execute_reply.started":"2026-09-12T10:13:48.155352Z","shell.execute_reply":"2026-09-12T10:13:48.238238Z"}},"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":"2026-09-12T10:13:48.240023Z","iopub.execute_input":"2026-09-12T10:13:48.240353Z","iopub.status.idle":"2026-09-12T10:13:48.246236Z","shell.execute_reply.started":"2026-09-12T10:13:48.240320Z","shell.execute_reply":"2026-09-12T10:13:48.245300Z"}},"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":"2026-09-12T10:13:48.247289Z","iopub.execute_input":"2026-09-12T10:13:48.247496Z","iopub.status.idle":"2026-09-12T10:13:53.391366Z","shell.execute_reply.started":"2026-09-12T10:13:48.247476Z","shell.execute_reply":"2026-09-12T10:13:53.389878Z"}},"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":"2026-09-12T10:13:53.393025Z","iopub.execute_input":"2026-09-12T10:13:53.393515Z","iopub.status.idle":"2026-09-12T10:13:58.433960Z","shell.execute_reply.started":"2026-09-12T10:13:53.393469Z","shell.execute_reply":"2026-09-12T10:13:58.432846Z"}},"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":"2026-09-12T10:13:58.435373Z","iopub.execute_input":"2026-09-12T10:13:58.435763Z","iopub.status.idle":"2026-09-12T10:13:58.442306Z","shell.execute_reply.started":"2026-09-12T10:13:58.435738Z","shell.execute_reply":"2026-09-12T10:13:58.441297Z"}},"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":"2026-09-12T10:13:58.443354Z","iopub.execute_input":"2026-09-12T10:13:58.443860Z","iopub.status.idle":"2026-09-12T10:14:03.133609Z","shell.execute_reply.started":"2026-09-12T10:13:58.443834Z","shell.execute_reply":"2026-09-12T10:14:03.131485Z"}},"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":"2026-09-12T10:14:03.141357Z","iopub.execute_input":"2026-09-12T10:14:03.141697Z","iopub.status.idle":"2026-09-12T10:14:23.942072Z","shell.execute_reply.started":"2026-09-12T10:14:03.141666Z","shell.execute_reply":"2026-09-12T10:14:23.941016Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"preds[:10]","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T10:14:23.943390Z","iopub.execute_input":"2026-09-12T10:14:23.944349Z","iopub.status.idle":"2026-09-12T10:14:23.950909Z","shell.execute_reply.started":"2026-09-12T10:14:23.944310Z","shell.execute_reply":"2026-09-12T10:14:23.950051Z"}},"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":"2026-09-12T10:14:23.951969Z","iopub.execute_input":"2026-09-12T10:14:23.952877Z","iopub.status.idle":"2026-09-12T10:14:25.714331Z","shell.execute_reply.started":"2026-09-12T10:14:23.952795Z","shell.execute_reply":"2026-09-12T10:14:25.712412Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# end of 2026-09-06\n#stop here","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T10:14:25.715528Z","iopub.execute_input":"2026-09-12T10:14:25.715846Z","iopub.status.idle":"2026-09-12T10:14:25.719894Z","shell.execute_reply.started":"2026-09-12T10:14:25.715817Z","shell.execute_reply":"2026-09-12T10:14:25.718894Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Transfer Learning","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T10:14:25.721064Z","iopub.execute_input":"2026-09-12T10:14:25.721424Z","iopub.status.idle":"2026-09-12T10:14:25.728553Z","shell.execute_reply.started":"2026-09-12T10:14:25.721370Z","shell.execute_reply":"2026-09-12T10:14:25.727816Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"#Create transfer learning model for VGG16\nimport sys\nfrom matplotlib import pyplot\nfrom keras.utils import to_categorical\nfrom keras.applications.vgg16 import VGG16\nfrom keras.models import Model\nfrom keras.layers import Dense\nfrom keras.layers import Flatten\nfrom keras.optimizers import SGD\nfrom keras.preprocessing.image import ImageDataGenerator\n\n# define cnn model\ndef define_model_vgg16():\n\t# load model\n\tmodel = VGG16(include_top=False, input_shape=(224, 224, 3))\n\t# mark loaded layers as not trainable\n\tfor layer in model.layers:\n\t\tlayer.trainable = False\n\t# add new classifier layers\n\tflat1 = Flatten()(model.layers[-1].output)\n\tclass1 = Dense(128, activation='relu', kernel_initializer='he_uniform')(flat1)\n\toutput = Dense(1, activation='sigmoid')(class1)\n\t# define new model\n\tmodel = Model(inputs=model.inputs, outputs=output)\n\t# compile model\n\topt = SGD(lr=0.001, momentum=0.9)\n\tmodel.compile(optimizer=opt, loss='binary_crossentropy', metrics=['accuracy'])\n\treturn model","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T10:14:25.729663Z","iopub.execute_input":"2026-09-12T10:14:25.730355Z","iopub.status.idle":"2026-09-12T10:14:25.739538Z","shell.execute_reply.started":"2026-09-12T10:14:25.730330Z","shell.execute_reply":"2026-09-12T10:14:25.738753Z"}},"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":"2026-09-12T10:14:25.740645Z","iopub.execute_input":"2026-09-12T10:14:25.741402Z","iopub.status.idle":"2026-09-12T10:14:25.748006Z","shell.execute_reply.started":"2026-09-12T10:14:25.741365Z","shell.execute_reply":"2026-09-12T10:14:25.746942Z"}},"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":"2026-09-12T10:14:25.749145Z","iopub.execute_input":"2026-09-12T10:14:25.749753Z","iopub.status.idle":"2026-09-12T10:14:25.760299Z","shell.execute_reply.started":"2026-09-12T10:14:25.749718Z","shell.execute_reply":"2026-09-12T10:14:25.759562Z"}},"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":"2026-09-12T10:14:25.761393Z","iopub.execute_input":"2026-09-12T10:14:25.761701Z","iopub.status.idle":"2026-09-12T10:14:25.770406Z","shell.execute_reply.started":"2026-09-12T10:14:25.761671Z","shell.execute_reply":"2026-09-12T10:14:25.769585Z"}},"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":"2026-09-12T10:14:25.771284Z","iopub.execute_input":"2026-09-12T10:14:25.771659Z","iopub.status.idle":"2026-09-12T10:14:25.778259Z","shell.execute_reply.started":"2026-09-12T10:14:25.771627Z","shell.execute_reply":"2026-09-12T10:14:25.777323Z"}},"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":"2026-09-12T10:14:25.779545Z","iopub.execute_input":"2026-09-12T10:14:25.780159Z","iopub.status.idle":"2026-09-12T10:14:26.519848Z","shell.execute_reply.started":"2026-09-12T10:14:25.780106Z","shell.execute_reply":"2026-09-12T10:14:26.517467Z"}},"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":"2026-09-12T10:14:26.520780Z","iopub.execute_input":"2026-09-12T10:14:26.521051Z","iopub.status.idle":"2026-09-12T10:14:26.526315Z","shell.execute_reply.started":"2026-09-12T10:14:26.521025Z","shell.execute_reply":"2026-09-12T10:14:26.525229Z"}},"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":"2026-09-12T10:14:26.527615Z","iopub.execute_input":"2026-09-12T10:14:26.528018Z","iopub.status.idle":"2026-09-12T10:14:26.536348Z","shell.execute_reply.started":"2026-09-12T10:14:26.527947Z","shell.execute_reply":"2026-09-12T10:14:26.535541Z"}},"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":"2026-09-12T10:14:26.537287Z","iopub.execute_input":"2026-09-12T10:14:26.537591Z","iopub.status.idle":"2026-09-12T10:14:26.543882Z","shell.execute_reply.started":"2026-09-12T10:14:26.537558Z","shell.execute_reply":"2026-09-12T10:14:26.543184Z"}},"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":"2026-09-12T10:14:26.544938Z","iopub.execute_input":"2026-09-12T10:14:26.545280Z","iopub.status.idle":"2026-09-12T10:14:26.552834Z","shell.execute_reply.started":"2026-09-12T10:14:26.545252Z","shell.execute_reply":"2026-09-12T10:14:26.552039Z"}},"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":"2026-09-12T10:14:26.553846Z","iopub.execute_input":"2026-09-12T10:14:26.554111Z","iopub.status.idle":"2026-09-12T10:14:26.562816Z","shell.execute_reply.started":"2026-09-12T10:14:26.554089Z","shell.execute_reply":"2026-09-12T10:14:26.562030Z"}},"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":"2026-09-12T10:14:26.563674Z","iopub.execute_input":"2026-09-12T10:14:26.563927Z","iopub.status.idle":"2026-09-12T10:14:31.052266Z","shell.execute_reply.started":"2026-09-12T10:14:26.563905Z","shell.execute_reply":"2026-09-12T10:14:31.050941Z"}},"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":"2026-09-12T10:14:31.053034Z","iopub.status.idle":"2026-09-12T10:14:31.053317Z","shell.execute_reply.started":"2026-09-12T10:14:31.053181Z","shell.execute_reply":"2026-09-12T10:14:31.053195Z"}},"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":"2026-09-12T10:14:31.054539Z","iopub.status.idle":"2026-09-12T10:14:31.054944Z","shell.execute_reply.started":"2026-09-12T10:14:31.054733Z","shell.execute_reply":"2026-09-12T10:14:31.054754Z"}},"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":"2026-09-12T10:14:31.056717Z","iopub.status.idle":"2026-09-12T10:14:31.057177Z","shell.execute_reply.started":"2026-09-12T10:14:31.056919Z","shell.execute_reply":"2026-09-12T10:14:31.056941Z"},"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":"2026-09-12T10:14:31.058738Z","iopub.status.idle":"2026-09-12T10:14:31.059191Z","shell.execute_reply.started":"2026-09-12T10:14:31.058938Z","shell.execute_reply":"2026-09-12T10:14:31.058960Z"}},"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":"2026-09-12T10:14:31.060772Z","iopub.status.idle":"2026-09-12T10:14:31.061243Z","shell.execute_reply.started":"2026-09-12T10:14:31.061009Z","shell.execute_reply":"2026-09-12T10:14:31.061033Z"}},"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":"2026-09-12T10:14:31.062642Z","iopub.status.idle":"2026-09-12T10:14:31.063099Z","shell.execute_reply.started":"2026-09-12T10:14:31.062843Z","shell.execute_reply":"2026-09-12T10:14:31.062865Z"}},"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":"2026-09-12T10:14:31.064928Z","iopub.status.idle":"2026-09-12T10:14:31.065360Z","shell.execute_reply.started":"2026-09-12T10:14:31.065157Z","shell.execute_reply":"2026-09-12T10:14:31.065179Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# plot_images_with_labels(images, labels, \"Dog-Cat\", \"Training\")","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T10:14:31.066468Z","iopub.status.idle":"2026-09-12T10:14:31.066912Z","shell.execute_reply.started":"2026-09-12T10:14:31.066681Z","shell.execute_reply":"2026-09-12T10:14:31.066703Z"}},"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":"2026-09-12T10:14:31.068222Z","iopub.status.idle":"2026-09-12T10:14:31.068634Z","shell.execute_reply.started":"2026-09-12T10:14:31.068424Z","shell.execute_reply":"2026-09-12T10:14:31.068445Z"}},"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":"2026-09-12T10:14:31.070039Z","iopub.status.idle":"2026-09-12T10:14:31.070452Z","shell.execute_reply.started":"2026-09-12T10:14:31.070237Z","shell.execute_reply":"2026-09-12T10:14:31.070258Z"}},"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":"2026-09-12T10:14:31.072075Z","iopub.status.idle":"2026-09-12T10:14:31.072390Z","shell.execute_reply.started":"2026-09-12T10:14:31.072247Z","shell.execute_reply":"2026-09-12T10:14:31.072263Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"images = test_it.__next__()\nimages.shape","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T10:14:31.073838Z","iopub.status.idle":"2026-09-12T10:14:31.074165Z","shell.execute_reply.started":"2026-09-12T10:14:31.074014Z","shell.execute_reply":"2026-09-12T10:14:31.074036Z"}},"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":"2026-09-12T10:14:31.075164Z","iopub.status.idle":"2026-09-12T10:14:31.075427Z","shell.execute_reply.started":"2026-09-12T10:14:31.075298Z","shell.execute_reply":"2026-09-12T10:14:31.075312Z"}},"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":"2026-09-12T10:14:31.076394Z","iopub.status.idle":"2026-09-12T10:14:31.076652Z","shell.execute_reply.started":"2026-09-12T10:14:31.076526Z","shell.execute_reply":"2026-09-12T10:14:31.076539Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"Make Prediction","metadata":{}},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null}]}