{"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":"2026-09-12T15:55:01.798407Z","iopub.execute_input":"2026-09-12T15:55:01.799296Z","iopub.status.idle":"2026-09-12T15:55:02.097387Z","shell.execute_reply.started":"2026-09-12T15:55:01.799262Z","shell.execute_reply":"2026-09-12T15:55:02.09664Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"!python --version","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T15:55:02.099361Z","iopub.execute_input":"2026-09-12T15:55:02.099828Z","iopub.status.idle":"2026-09-12T15:55:03.064929Z","shell.execute_reply.started":"2026-09-12T15:55:02.099794Z","shell.execute_reply":"2026-09-12T15:55:03.064103Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"!uname --all","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T15:55:03.066362Z","iopub.execute_input":"2026-09-12T15:55:03.066735Z","iopub.status.idle":"2026-09-12T15:55:04.023235Z","shell.execute_reply.started":"2026-09-12T15:55:03.0667Z","shell.execute_reply":"2026-09-12T15:55:04.022332Z"}},"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":"2026-09-12T15:55:04.024701Z","iopub.execute_input":"2026-09-12T15:55:04.025052Z","iopub.status.idle":"2026-09-12T15:55:15.480894Z","shell.execute_reply.started":"2026-09-12T15:55:04.025018Z","shell.execute_reply":"2026-09-12T15:55:15.480164Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T15:55:15.483691Z","iopub.execute_input":"2026-09-12T15:55:15.48403Z","iopub.status.idle":"2026-09-12T15:55:16.461923Z","shell.execute_reply.started":"2026-09-12T15:55:15.483993Z","shell.execute_reply":"2026-09-12T15:55:16.4611Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -l","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T15:55:16.463265Z","iopub.execute_input":"2026-09-12T15:55:16.463673Z","iopub.status.idle":"2026-09-12T15:55:17.427424Z","shell.execute_reply.started":"2026-09-12T15:55:16.463635Z","shell.execute_reply":"2026-09-12T15:55:17.426533Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls test1","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T15:55:17.429046Z","iopub.execute_input":"2026-09-12T15:55:17.42941Z","iopub.status.idle":"2026-09-12T15:55:18.451663Z","shell.execute_reply.started":"2026-09-12T15:55:17.429374Z","shell.execute_reply":"2026-09-12T15:55:18.450515Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls test1/ | wc -l","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T15:55:18.453123Z","iopub.execute_input":"2026-09-12T15:55:18.453414Z","iopub.status.idle":"2026-09-12T15:55:19.458166Z","shell.execute_reply.started":"2026-09-12T15:55:18.453386Z","shell.execute_reply":"2026-09-12T15:55:19.457331Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls train/ | wc -l","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T15:55:19.459338Z","iopub.execute_input":"2026-09-12T15:55:19.459672Z","iopub.status.idle":"2026-09-12T15:55:20.546154Z","shell.execute_reply.started":"2026-09-12T15:55:19.459637Z","shell.execute_reply":"2026-09-12T15:55:20.544976Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"#ls train/","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T15:55:20.547744Z","iopub.execute_input":"2026-09-12T15:55:20.548035Z","iopub.status.idle":"2026-09-12T15:55:20.553221Z","shell.execute_reply.started":"2026-09-12T15:55:20.54801Z","shell.execute_reply":"2026-09-12T15:55:20.55223Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"pwd","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T15:55:20.554409Z","iopub.execute_input":"2026-09-12T15:55:20.554745Z","iopub.status.idle":"2026-09-12T15:55:20.642232Z","shell.execute_reply.started":"2026-09-12T15:55:20.554722Z","shell.execute_reply":"2026-09-12T15:55:20.641352Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T15:55:20.643424Z","iopub.execute_input":"2026-09-12T15:55:20.643772Z","iopub.status.idle":"2026-09-12T15:55:21.620624Z","shell.execute_reply.started":"2026-09-12T15:55:20.643748Z","shell.execute_reply":"2026-09-12T15:55:21.619511Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -U train | head -n 10","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T15:55:21.622873Z","iopub.execute_input":"2026-09-12T15:55:21.623321Z","iopub.status.idle":"2026-09-12T15:55:22.702325Z","shell.execute_reply.started":"2026-09-12T15:55:21.623273Z","shell.execute_reply":"2026-09-12T15:55:22.701477Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -U test1 | head -n 10","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T15:55:22.7062Z","iopub.execute_input":"2026-09-12T15:55:22.706457Z","iopub.status.idle":"2026-09-12T15:55:23.696327Z","shell.execute_reply.started":"2026-09-12T15:55:22.706433Z","shell.execute_reply":"2026-09-12T15:55:23.695469Z"}},"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":"2026-09-12T15:55:23.697847Z","iopub.execute_input":"2026-09-12T15:55:23.698231Z","iopub.status.idle":"2026-09-12T15:55:24.631213Z","shell.execute_reply.started":"2026-09-12T15:55:23.698193Z","shell.execute_reply":"2026-09-12T15:55:24.630274Z"},"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":"2026-09-12T15:55:24.632421Z","iopub.execute_input":"2026-09-12T15:55:24.633012Z","iopub.status.idle":"2026-09-12T15:55:25.574258Z","shell.execute_reply.started":"2026-09-12T15:55:24.632985Z","shell.execute_reply":"2026-09-12T15:55:25.572971Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"!python --version","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T15:55:25.575707Z","iopub.execute_input":"2026-09-12T15:55:25.57602Z","iopub.status.idle":"2026-09-12T15:55:26.559685Z","shell.execute_reply.started":"2026-09-12T15:55:25.575993Z","shell.execute_reply":"2026-09-12T15:55:26.558711Z"}},"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":"2026-09-12T15:55:26.561164Z","iopub.execute_input":"2026-09-12T15:55:26.561504Z","iopub.status.idle":"2026-09-12T15:55:37.253204Z","shell.execute_reply.started":"2026-09-12T15:55:26.561479Z","shell.execute_reply":"2026-09-12T15:55:37.252227Z"}},"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":"2026-09-12T15:55:37.254553Z","iopub.execute_input":"2026-09-12T15:55:37.255197Z","iopub.status.idle":"2026-09-12T15:55:37.259925Z","shell.execute_reply.started":"2026-09-12T15:55:37.255161Z","shell.execute_reply":"2026-09-12T15:55:37.258911Z"},"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":"2026-09-12T15:55:37.261277Z","iopub.execute_input":"2026-09-12T15:55:37.261656Z","iopub.status.idle":"2026-09-12T15:55:37.345431Z","shell.execute_reply.started":"2026-09-12T15:55:37.261619Z","shell.execute_reply":"2026-09-12T15:55:37.344576Z"},"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":"2026-09-12T15:55:37.346471Z","iopub.execute_input":"2026-09-12T15:55:37.346758Z","iopub.status.idle":"2026-09-12T15:55:37.356461Z","shell.execute_reply.started":"2026-09-12T15:55:37.346734Z","shell.execute_reply":"2026-09-12T15:55:37.35544Z"},"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":"2026-09-12T15:55:37.357526Z","iopub.execute_input":"2026-09-12T15:55:37.357822Z","iopub.status.idle":"2026-09-12T15:55:38.326594Z","shell.execute_reply.started":"2026-09-12T15:55:37.357788Z","shell.execute_reply":"2026-09-12T15:55:38.325774Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -l","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T15:55:38.327885Z","iopub.execute_input":"2026-09-12T15:55:38.328267Z","iopub.status.idle":"2026-09-12T15:55:39.30198Z","shell.execute_reply.started":"2026-09-12T15:55:38.328234Z","shell.execute_reply":"2026-09-12T15:55:39.301045Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -l dataset_dogs_vs_cats/train","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T15:55:39.303431Z","iopub.execute_input":"2026-09-12T15:55:39.304049Z","iopub.status.idle":"2026-09-12T15:55:40.273813Z","shell.execute_reply.started":"2026-09-12T15:55:39.304021Z","shell.execute_reply":"2026-09-12T15:55:40.272669Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -l dataset_dogs_vs_cats/test #validation","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T15:55:40.275528Z","iopub.execute_input":"2026-09-12T15:55:40.275923Z","iopub.status.idle":"2026-09-12T15:55:41.260187Z","shell.execute_reply.started":"2026-09-12T15:55:40.275888Z","shell.execute_reply":"2026-09-12T15:55:41.258842Z"}},"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":"2026-09-12T15:55:41.261707Z","iopub.execute_input":"2026-09-12T15:55:41.262027Z","iopub.status.idle":"2026-09-12T15:55:43.217298Z","shell.execute_reply.started":"2026-09-12T15:55:41.261999Z","shell.execute_reply":"2026-09-12T15:55:43.216578Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"print(src)\nprint(dst)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T15:55:43.21832Z","iopub.execute_input":"2026-09-12T15:55:43.218634Z","iopub.status.idle":"2026-09-12T15:55:43.22334Z","shell.execute_reply.started":"2026-09-12T15:55:43.218576Z","shell.execute_reply":"2026-09-12T15:55:43.222431Z"}},"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":"2026-09-12T15:55:43.22439Z","iopub.execute_input":"2026-09-12T15:55:43.224691Z","iopub.status.idle":"2026-09-12T15:55:45.290734Z","shell.execute_reply.started":"2026-09-12T15:55:43.224668Z","shell.execute_reply":"2026-09-12T15:55:45.289553Z"},"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":"2026-09-12T15:55:45.292161Z","iopub.execute_input":"2026-09-12T15:55:45.293267Z","iopub.status.idle":"2026-09-12T15:55:47.253269Z","shell.execute_reply.started":"2026-09-12T15:55:45.293239Z","shell.execute_reply":"2026-09-12T15:55:47.25224Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"!pip -q install livelossplot==0.5.5","metadata":{"execution":{"iopub.status.busy":"2026-09-12T15:55:47.254547Z","iopub.execute_input":"2026-09-12T15:55:47.25627Z","iopub.status.idle":"2026-09-12T15:55:57.313128Z","shell.execute_reply.started":"2026-09-12T15:55:47.256212Z","shell.execute_reply":"2026-09-12T15:55:57.312065Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"from livelossplot import PlotLossesKeras","metadata":{"execution":{"iopub.status.busy":"2026-09-12T15:55:57.31455Z","iopub.execute_input":"2026-09-12T15:55:57.315268Z","iopub.status.idle":"2026-09-12T15:55:57.330643Z","shell.execute_reply.started":"2026-09-12T15:55:57.31524Z","shell.execute_reply":"2026-09-12T15:55:57.329656Z"},"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":"2026-09-12T15:55:57.331756Z","iopub.execute_input":"2026-09-12T15:55:57.332379Z","iopub.status.idle":"2026-09-12T15:55:57.336267Z","shell.execute_reply.started":"2026-09-12T15:55:57.332347Z","shell.execute_reply":"2026-09-12T15:55:57.335294Z"}},"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 Dropout\nfrom keras.layers import Flatten\nfrom keras.optimizers import SGD\nfrom keras.preprocessing.image import ImageDataGenerator","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T15:55:57.33736Z","iopub.execute_input":"2026-09-12T15:55:57.338238Z","iopub.status.idle":"2026-09-12T15:55:57.346089Z","shell.execute_reply.started":"2026-09-12T15:55:57.338214Z","shell.execute_reply":"2026-09-12T15:55:57.345342Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"model = Sequential()\ntype(model)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T16:08:50.490501Z","iopub.execute_input":"2026-09-12T16:08:50.491358Z","iopub.status.idle":"2026-09-12T16:08:50.501421Z","shell.execute_reply.started":"2026-09-12T16:08:50.491325Z","shell.execute_reply":"2026-09-12T16:08:50.500536Z"}},"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(512, activation='relu'))\n\nmodel.add(Dense(1, activation='sigmoid'))\n\nprint(model.summary())","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T16:08:51.27511Z","iopub.execute_input":"2026-09-12T16:08:51.275931Z","iopub.status.idle":"2026-09-12T16:08:51.341047Z","shell.execute_reply.started":"2026-09-12T16:08:51.275899Z","shell.execute_reply":"2026-09-12T16:08:51.339286Z"}},"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(512, activation='relu'))\n\nmodel.add(Dense(2, activation='softmax'))\n\nprint(model.summary())","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T16:08:52.400047Z","iopub.execute_input":"2026-09-12T16:08:52.400476Z","iopub.status.idle":"2026-09-12T16:08:52.465928Z","shell.execute_reply.started":"2026-09-12T16:08:52.400442Z","shell.execute_reply":"2026-09-12T16:08:52.464908Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# define cnn model\ndef define_model_1():\n    model = Sequential()\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    model.add(Flatten())\n    model.add(Dense(128, activation='relu', kernel_initializer='he_uniform'))\n    model.add(Dropout(0.2))\n    model.add(Dense(1, activation='sigmoid'))\n    \n    # compile model\n    opt = 'adam'\n    model.compile(optimizer=opt, loss='binary_crossentropy', metrics=['accuracy'])\n    return model","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T16:08:53.235282Z","iopub.execute_input":"2026-09-12T16:08:53.236127Z","iopub.status.idle":"2026-09-12T16:08:53.241571Z","shell.execute_reply.started":"2026-09-12T16:08:53.236092Z","shell.execute_reply":"2026-09-12T16:08:53.240543Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"model_1 = define_model_1()\nprint(model_1.summary())","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T16:08:53.550205Z","iopub.execute_input":"2026-09-12T16:08:53.550764Z","iopub.status.idle":"2026-09-12T16:08:53.615302Z","shell.execute_reply.started":"2026-09-12T16:08:53.550739Z","shell.execute_reply":"2026-09-12T16:08:53.614645Z"}},"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":"2026-09-12T16:08:53.67436Z","iopub.execute_input":"2026-09-12T16:08:53.674579Z","iopub.status.idle":"2026-09-12T16:08:53.680631Z","shell.execute_reply.started":"2026-09-12T16:08:53.674559Z","shell.execute_reply":"2026-09-12T16:08:53.679646Z"}},"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":"2026-09-12T16:08:54.514761Z","iopub.execute_input":"2026-09-12T16:08:54.515314Z","iopub.status.idle":"2026-09-12T16:08:54.521202Z","shell.execute_reply.started":"2026-09-12T16:08:54.515276Z","shell.execute_reply":"2026-09-12T16:08:54.52034Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"model_1 = define_model_1()\nprint(model_1.summary())","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T16:08:54.835107Z","iopub.execute_input":"2026-09-12T16:08:54.835682Z","iopub.status.idle":"2026-09-12T16:08:54.903583Z","shell.execute_reply.started":"2026-09-12T16:08:54.835648Z","shell.execute_reply":"2026-09-12T16:08:54.902681Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"datagen = ImageDataGenerator(rescale=1.0/255.0)\ntype(datagen)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T16:08:55.630017Z","iopub.execute_input":"2026-09-12T16:08:55.630257Z","iopub.status.idle":"2026-09-12T16:08:55.637523Z","shell.execute_reply.started":"2026-09-12T16:08:55.630235Z","shell.execute_reply":"2026-09-12T16:08:55.636779Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls dataset_dogs_vs_cats/train/","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T16:08:55.990166Z","iopub.execute_input":"2026-09-12T16:08:55.990519Z","iopub.status.idle":"2026-09-12T16:08:56.992438Z","shell.execute_reply.started":"2026-09-12T16:08:55.990492Z","shell.execute_reply":"2026-09-12T16:08:56.991533Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Hyperparameter => changable\nIMAGE_SIZE = (200, 200)\nBATCH_SIE = 64\nEPOCHS = 30","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T16:08:56.994484Z","iopub.execute_input":"2026-09-12T16:08:56.995185Z","iopub.status.idle":"2026-09-12T16:08:56.999727Z","shell.execute_reply.started":"2026-09-12T16:08:56.995156Z","shell.execute_reply":"2026-09-12T16:08:56.998739Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"train_it = datagen.flow_from_directory('dataset_dogs_vs_cats/train/',\n\t\tclass_mode='binary',\n        batch_size=BATCH_SIE, \n        target_size=IMAGE_SIZE\n)\ntype(train_it)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T16:08:57.310098Z","iopub.execute_input":"2026-09-12T16:08:57.310379Z","iopub.status.idle":"2026-09-12T16:08:57.804241Z","shell.execute_reply.started":"2026-09-12T16:08:57.310355Z","shell.execute_reply":"2026-09-12T16:08:57.803277Z"}},"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":"2026-09-12T16:08:57.805569Z","iopub.execute_input":"2026-09-12T16:08:57.805855Z","iopub.status.idle":"2026-09-12T16:08:57.812197Z","shell.execute_reply.started":"2026-09-12T16:08:57.805832Z","shell.execute_reply":"2026-09-12T16:08:57.811251Z"}},"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_SIE,\n        target_size=IMAGE_SIZE\n)\ntype(val_it)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T16:08:58.505871Z","iopub.execute_input":"2026-09-12T16:08:58.506146Z","iopub.status.idle":"2026-09-12T16:08:58.726166Z","shell.execute_reply.started":"2026-09-12T16:08:58.506123Z","shell.execute_reply":"2026-09-12T16:08:58.725503Z"}},"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":"2026-09-12T16:08:58.875552Z","iopub.execute_input":"2026-09-12T16:08:58.876338Z","iopub.status.idle":"2026-09-12T16:08:58.882326Z","shell.execute_reply.started":"2026-09-12T16:08:58.8763Z","shell.execute_reply":"2026-09-12T16:08:58.88137Z"}},"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":"2026-09-12T16:09:00.161016Z","iopub.execute_input":"2026-09-12T16:09:00.161313Z","iopub.status.idle":"2026-09-12T16:29:46.195512Z","shell.execute_reply.started":"2026-09-12T16:09:00.161289Z","shell.execute_reply":"2026-09-12T16:29:46.194461Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"del model_1","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T16:08:44.710166Z","iopub.execute_input":"2026-09-12T16:08:44.710996Z","iopub.status.idle":"2026-09-12T16:08:44.716422Z","shell.execute_reply.started":"2026-09-12T16:08:44.710961Z","shell.execute_reply":"2026-09-12T16:08:44.715662Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import numpy as np\nimport matplotlib.pyplot as plt\n\n# 1. ดึงข้อมูลตัวอย่างมา 1 Batch จาก val_it\nx_val, y_val = next(iter(val_it))\n\n# 2. ให้โมเดลทำนายผล\npredictions = model_1.predict(x_val)\n\n# 3. แปลงคลาสจากตัวเลขเป็นข้อความ\nclass_labels = {v: k for k, v in val_it.class_indices.items()} # {0: 'cats', 1: 'dogs'}\n\n# 4. วาดกราฟแสดงผล 10 ภาพแรก\nplt.figure(figsize=(15, 6))\n\nfor i in range(10):\n    plt.subplot(2, 5, i + 1)\n    plt.imshow(x_val[i])\n    \n    # ดึงค่า True และ Predicted Label\n    true_label = class_labels[int(y_val[i])]\n    pred_prob = predictions[i][0]\n    pred_label = class_labels[1 if pred_prob > 0.5 else 0]\n    \n    # กำหนดสีข้อความ: ทายถูก = สีเขียว, ทายผิด = สีแดง\n    color = 'green' if true_label == pred_label else 'red'\n    \n    plt.title(f\"Pred: {pred_label}\\nTrue: {true_label}\", color=color)\n    plt.axis('off')\n\nplt.tight_layout()\nplt.show()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T16:31:40.092223Z","iopub.execute_input":"2026-09-12T16:31:40.093306Z","iopub.status.idle":"2026-09-12T16:31:41.767224Z","shell.execute_reply.started":"2026-09-12T16:31:40.093255Z","shell.execute_reply":"2026-09-12T16:31:41.764049Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# learning curves\nsummarize_diagnostics(history_1)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T16:32:23.527237Z","iopub.execute_input":"2026-09-12T16:32:23.528124Z","iopub.status.idle":"2026-09-12T16:32:23.875035Z","shell.execute_reply.started":"2026-09-12T16:32:23.528089Z","shell.execute_reply":"2026-09-12T16:32:23.874356Z"}},"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":"2026-09-12T16:32:26.306693Z","iopub.execute_input":"2026-09-12T16:32:26.307667Z","iopub.status.idle":"2026-09-12T16:32:37.459507Z","shell.execute_reply.started":"2026-09-12T16:32:26.307593Z","shell.execute_reply":"2026-09-12T16:32:37.458736Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls ","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T16:32:48.551728Z","iopub.execute_input":"2026-09-12T16:32:48.552484Z","iopub.status.idle":"2026-09-12T16:32:49.557264Z","shell.execute_reply.started":"2026-09-12T16:32:48.552451Z","shell.execute_reply":"2026-09-12T16:32:49.556323Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"pwd","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T16:32:50.76082Z","iopub.execute_input":"2026-09-12T16:32:50.761308Z","iopub.status.idle":"2026-09-12T16:32:50.768478Z","shell.execute_reply.started":"2026-09-12T16:32:50.761273Z","shell.execute_reply":"2026-09-12T16:32:50.767645Z"}},"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":"2026-09-12T16:32:52.537462Z","iopub.execute_input":"2026-09-12T16:32:52.538184Z","iopub.status.idle":"2026-09-12T16:32:52.575449Z","shell.execute_reply.started":"2026-09-12T16:32:52.538152Z","shell.execute_reply":"2026-09-12T16:32:52.574457Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"df.columns","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T16:32:55.091768Z","iopub.execute_input":"2026-09-12T16:32:55.092423Z","iopub.status.idle":"2026-09-12T16:32:55.099445Z","shell.execute_reply.started":"2026-09-12T16:32:55.092391Z","shell.execute_reply":"2026-09-12T16:32:55.098558Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"image_files[:5], type(image_files), len(image_files)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T16:32:55.712429Z","iopub.execute_input":"2026-09-12T16:32:55.713097Z","iopub.status.idle":"2026-09-12T16:32:55.718783Z","shell.execute_reply.started":"2026-09-12T16:32:55.713069Z","shell.execute_reply":"2026-09-12T16:32:55.717806Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"df.describe()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T16:32:56.702171Z","iopub.execute_input":"2026-09-12T16:32:56.703016Z","iopub.status.idle":"2026-09-12T16:32:56.733547Z","shell.execute_reply.started":"2026-09-12T16:32:56.702982Z","shell.execute_reply":"2026-09-12T16:32:56.732656Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"df.loc[1]","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T16:32:57.827177Z","iopub.execute_input":"2026-09-12T16:32:57.828188Z","iopub.status.idle":"2026-09-12T16:32:57.834372Z","shell.execute_reply.started":"2026-09-12T16:32:57.828159Z","shell.execute_reply":"2026-09-12T16:32:57.833391Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"df.sample(5)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T16:32:58.851872Z","iopub.execute_input":"2026-09-12T16:32:58.852455Z","iopub.status.idle":"2026-09-12T16:32:58.864348Z","shell.execute_reply.started":"2026-09-12T16:32:58.852422Z","shell.execute_reply":"2026-09-12T16:32:58.86337Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"df['filename']","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T16:32:59.876511Z","iopub.execute_input":"2026-09-12T16:32:59.876844Z","iopub.status.idle":"2026-09-12T16:32:59.884197Z","shell.execute_reply.started":"2026-09-12T16:32:59.876817Z","shell.execute_reply":"2026-09-12T16:32:59.883264Z"}},"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":"2026-09-12T16:33:01.101716Z","iopub.execute_input":"2026-09-12T16:33:01.102022Z","iopub.status.idle":"2026-09-12T16:33:01.183003Z","shell.execute_reply.started":"2026-09-12T16:33:01.102Z","shell.execute_reply":"2026-09-12T16:33:01.182259Z"}},"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":"2026-09-12T16:33:02.527364Z","iopub.execute_input":"2026-09-12T16:33:02.528429Z","iopub.status.idle":"2026-09-12T16:33:02.533982Z","shell.execute_reply.started":"2026-09-12T16:33:02.528396Z","shell.execute_reply":"2026-09-12T16:33:02.532906Z"}},"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":"2026-09-12T16:33:03.612051Z","iopub.execute_input":"2026-09-12T16:33:03.612593Z","iopub.status.idle":"2026-09-12T16:33:08.499728Z","shell.execute_reply.started":"2026-09-12T16:33:03.612564Z","shell.execute_reply":"2026-09-12T16:33:08.497537Z"}},"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":"2026-09-12T16:33:08.501728Z","iopub.execute_input":"2026-09-12T16:33:08.502183Z","iopub.status.idle":"2026-09-12T16:33:13.243653Z","shell.execute_reply.started":"2026-09-12T16:33:08.502154Z","shell.execute_reply":"2026-09-12T16:33:13.242533Z"}},"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":"2026-09-12T16:34:42.773492Z","iopub.execute_input":"2026-09-12T16:34:42.774037Z","iopub.status.idle":"2026-09-12T16:34:42.780421Z","shell.execute_reply.started":"2026-09-12T16:34:42.774003Z","shell.execute_reply":"2026-09-12T16:34:42.779387Z"}},"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":"2026-09-12T16:34:43.861298Z","iopub.execute_input":"2026-09-12T16:34:43.862147Z","iopub.status.idle":"2026-09-12T16:34:48.914544Z","shell.execute_reply.started":"2026-09-12T16:34:43.862114Z","shell.execute_reply":"2026-09-12T16:34:48.913032Z"}},"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":"2026-09-12T16:35:37.982238Z","iopub.execute_input":"2026-09-12T16:35:37.983035Z","iopub.status.idle":"2026-09-12T16:36:00.322542Z","shell.execute_reply.started":"2026-09-12T16:35:37.982999Z","shell.execute_reply":"2026-09-12T16:36:00.321654Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"preds[:10]","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T16:36:00.324146Z","iopub.execute_input":"2026-09-12T16:36:00.324863Z","iopub.status.idle":"2026-09-12T16:36:00.331121Z","shell.execute_reply.started":"2026-09-12T16:36:00.324836Z","shell.execute_reply":"2026-09-12T16:36:00.330256Z"}},"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":"2026-09-12T16:36:00.332272Z","iopub.execute_input":"2026-09-12T16:36:00.333253Z","iopub.status.idle":"2026-09-12T16:36:01.625825Z","shell.execute_reply.started":"2026-09-12T16:36:00.333213Z","shell.execute_reply":"2026-09-12T16:36:01.624784Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# end of 2026-09-06\nstop here","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T16:36:15.828441Z","iopub.execute_input":"2026-09-12T16:36:15.829217Z","iopub.status.idle":"2026-09-12T16:36:15.834487Z","shell.execute_reply.started":"2026-09-12T16:36:15.829181Z","shell.execute_reply":"2026-09-12T16:36:15.833289Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Transfer Learning","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T16:36:16.837104Z","iopub.execute_input":"2026-09-12T16:36:16.83772Z","iopub.status.idle":"2026-09-12T16:36:16.841891Z","shell.execute_reply.started":"2026-09-12T16:36:16.837687Z","shell.execute_reply":"2026-09-12T16:36:16.840951Z"}},"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":"2026-09-12T16:36:17.657349Z","iopub.execute_input":"2026-09-12T16:36:17.658127Z","iopub.status.idle":"2026-09-12T16:36:17.665108Z","shell.execute_reply.started":"2026-09-12T16:36:17.658097Z","shell.execute_reply":"2026-09-12T16:36:17.664056Z"}},"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":"2026-09-06T04:36:59.994101Z","iopub.execute_input":"2026-09-06T04:36:59.995147Z","iopub.status.idle":"2026-09-06T04:36:59.999098Z","shell.execute_reply.started":"2026-09-06T04:36:59.995112Z","shell.execute_reply":"2026-09-06T04:36:59.998107Z"}},"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":"2026-09-06T04:37:00.954384Z","iopub.execute_input":"2026-09-06T04:37:00.954784Z","iopub.status.idle":"2026-09-06T04:37:00.958834Z","shell.execute_reply.started":"2026-09-06T04:37:00.954755Z","shell.execute_reply":"2026-09-06T04:37:00.957924Z"}},"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":"2026-09-06T04:37:01.705857Z","iopub.execute_input":"2026-09-06T04:37:01.706685Z","iopub.status.idle":"2026-09-06T04:37:01.710664Z","shell.execute_reply.started":"2026-09-06T04:37:01.706646Z","shell.execute_reply":"2026-09-06T04:37:01.709585Z"}},"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":"2026-02-16T07:03:43.527034Z","iopub.execute_input":"2026-02-16T07:03:43.527566Z","iopub.status.idle":"2026-02-16T07:03:43.533544Z","shell.execute_reply.started":"2026-02-16T07:03:43.527544Z","shell.execute_reply":"2026-02-16T07:03:43.532816Z"}},"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":"2026-09-12T16:36:24.546399Z","iopub.execute_input":"2026-09-12T16:36:24.54707Z","iopub.status.idle":"2026-09-12T16:36:25.567866Z","shell.execute_reply.started":"2026-09-12T16:36:24.547037Z","shell.execute_reply":"2026-09-12T16:36:25.566892Z"}},"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":"2026-02-16T07:03:43.910675Z","iopub.execute_input":"2026-02-16T07:03:43.910954Z","iopub.status.idle":"2026-02-16T07:03:43.914695Z","shell.execute_reply.started":"2026-02-16T07:03:43.91093Z","shell.execute_reply":"2026-02-16T07:03:43.913724Z"}},"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":"2026-02-16T07:03:43.915763Z","iopub.execute_input":"2026-02-16T07:03:43.916044Z","iopub.status.idle":"2026-02-16T07:03:43.92276Z","shell.execute_reply.started":"2026-02-16T07:03:43.916014Z","shell.execute_reply":"2026-02-16T07:03:43.921957Z"}},"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":"2026-02-16T07:03:43.923787Z","iopub.execute_input":"2026-02-16T07:03:43.924063Z","iopub.status.idle":"2026-02-16T07:03:43.930359Z","shell.execute_reply.started":"2026-02-16T07:03:43.924041Z","shell.execute_reply":"2026-02-16T07:03:43.9295Z"}},"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":"2026-02-16T07:05:42.844519Z","iopub.execute_input":"2026-02-16T07:05:42.845298Z","iopub.status.idle":"2026-02-16T07:05:42.849027Z","shell.execute_reply.started":"2026-02-16T07:05:42.845261Z","shell.execute_reply":"2026-02-16T07:05:42.848238Z"}},"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":"2026-09-12T16:36:30.737339Z","iopub.execute_input":"2026-09-12T16:36:30.73821Z","iopub.status.idle":"2026-09-12T16:36:30.74348Z","shell.execute_reply.started":"2026-09-12T16:36:30.738168Z","shell.execute_reply":"2026-09-12T16:36:30.742518Z"}},"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":"2026-09-12T16:36:31.912409Z","iopub.execute_input":"2026-09-12T16:36:31.912779Z","iopub.status.idle":"2026-09-12T16:36:40.510144Z","shell.execute_reply.started":"2026-09-12T16:36:31.912749Z","shell.execute_reply":"2026-09-12T16:36:40.508666Z"}},"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":"2026-09-12T16:36:45.897445Z","iopub.execute_input":"2026-09-12T16:36:45.897808Z","iopub.status.idle":"2026-09-12T16:36:45.929772Z","shell.execute_reply.started":"2026-09-12T16:36:45.89778Z","shell.execute_reply":"2026-09-12T16:36:45.928664Z"}},"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 = 'adam'\n    model.compile(optimizer=opt, loss='binary_crossentropy', metrics=['accuracy'])\n    return model","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-02-16T07:39:22.0384Z","iopub.execute_input":"2026-02-16T07:39:22.03875Z","iopub.status.idle":"2026-02-16T07:39:22.045262Z","shell.execute_reply.started":"2026-02-16T07:39:22.038719Z","shell.execute_reply":"2026-02-16T07:39:22.044409Z"}},"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":"2026-02-16T07:39:22.35245Z","iopub.execute_input":"2026-02-16T07:39:22.352743Z","iopub.status.idle":"2026-02-16T07:39:24.449375Z","shell.execute_reply.started":"2026-02-16T07:39:22.352718Z","shell.execute_reply":"2026-02-16T07:39:24.448546Z"},"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":"2026-02-16T07:39:24.451116Z","iopub.execute_input":"2026-02-16T07:39:24.451727Z","iopub.status.idle":"2026-02-16T07:39:24.457165Z","shell.execute_reply.started":"2026-02-16T07:39:24.451691Z","shell.execute_reply":"2026-02-16T07:39:24.456303Z"}},"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":"2026-02-16T07:39:24.458253Z","iopub.execute_input":"2026-02-16T07:39:24.458457Z","iopub.status.idle":"2026-02-16T07:39:24.468376Z","shell.execute_reply.started":"2026-02-16T07:39:24.458437Z","shell.execute_reply":"2026-02-16T07:39:24.467705Z"}},"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},"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},"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},"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},"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}]}