{"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":"2026-09-12T11:24:27.419887Z","iopub.execute_input":"2026-09-12T11:24:27.420200Z","iopub.status.idle":"2026-09-12T11:24:27.760126Z","shell.execute_reply.started":"2026-09-12T11:24:27.420150Z","shell.execute_reply":"2026-09-12T11:24:27.758971Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"!python --version","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T11:24:29.561566Z","iopub.execute_input":"2026-09-12T11:24:29.561879Z","iopub.status.idle":"2026-09-12T11:24:30.679673Z","shell.execute_reply.started":"2026-09-12T11:24:29.561838Z","shell.execute_reply":"2026-09-12T11:24:30.678469Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"!uname --all","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T11:24:31.305785Z","iopub.execute_input":"2026-09-12T11:24:31.306386Z","iopub.status.idle":"2026-09-12T11:24:32.332429Z","shell.execute_reply.started":"2026-09-12T11:24:31.306350Z","shell.execute_reply":"2026-09-12T11:24:32.331241Z"}},"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":"2026-09-12T11:24:33.417395Z","iopub.execute_input":"2026-09-12T11:24:33.417778Z","iopub.status.idle":"2026-09-12T11:24:43.577441Z","shell.execute_reply.started":"2026-09-12T11:24:33.417745Z","shell.execute_reply":"2026-09-12T11:24:43.576656Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T11:24:43.578968Z","iopub.execute_input":"2026-09-12T11:24:43.579353Z","iopub.status.idle":"2026-09-12T11:24:44.576904Z","shell.execute_reply.started":"2026-09-12T11:24:43.579322Z","shell.execute_reply":"2026-09-12T11:24:44.575559Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -l","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T11:24:48.121520Z","iopub.execute_input":"2026-09-12T11:24:48.122047Z","iopub.status.idle":"2026-09-12T11:24:49.141273Z","shell.execute_reply.started":"2026-09-12T11:24:48.122009Z","shell.execute_reply":"2026-09-12T11:24:49.139843Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls test1","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T11:24:49.532091Z","iopub.execute_input":"2026-09-12T11:24:49.533007Z","iopub.status.idle":"2026-09-12T11:24:50.607335Z","shell.execute_reply.started":"2026-09-12T11:24:49.532967Z","shell.execute_reply":"2026-09-12T11:24:50.606068Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls test1/ | wc -l","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T11:25:20.348761Z","iopub.execute_input":"2026-09-12T11:25:20.349736Z","iopub.status.idle":"2026-09-12T11:25:21.411741Z","shell.execute_reply.started":"2026-09-12T11:25:20.349697Z","shell.execute_reply":"2026-09-12T11:25:21.410823Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls train/ | wc -l","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T11:25:21.593580Z","iopub.execute_input":"2026-09-12T11:25:21.594086Z","iopub.status.idle":"2026-09-12T11:25:22.696314Z","shell.execute_reply.started":"2026-09-12T11:25:21.594051Z","shell.execute_reply":"2026-09-12T11:25:22.695247Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"#ls train/","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T11:25:22.698171Z","iopub.execute_input":"2026-09-12T11:25:22.698922Z","iopub.status.idle":"2026-09-12T11:25:22.703046Z","shell.execute_reply.started":"2026-09-12T11:25:22.698891Z","shell.execute_reply":"2026-09-12T11:25:22.702009Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"pwd","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T11:25:23.508922Z","iopub.execute_input":"2026-09-12T11:25:23.509705Z","iopub.status.idle":"2026-09-12T11:25:23.516876Z","shell.execute_reply.started":"2026-09-12T11:25:23.509668Z","shell.execute_reply":"2026-09-12T11:25:23.515901Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T11:25:24.234413Z","iopub.execute_input":"2026-09-12T11:25:24.235421Z","iopub.status.idle":"2026-09-12T11:25:25.261580Z","shell.execute_reply.started":"2026-09-12T11:25:24.235386Z","shell.execute_reply":"2026-09-12T11:25:25.260407Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -U train | head -n 10","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T11:25:25.263833Z","iopub.execute_input":"2026-09-12T11:25:25.264690Z","iopub.status.idle":"2026-09-12T11:25:26.346225Z","shell.execute_reply.started":"2026-09-12T11:25:25.264646Z","shell.execute_reply":"2026-09-12T11:25:26.345344Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -U test1 | head -n 10","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T11:25:27.386811Z","iopub.execute_input":"2026-09-12T11:25:27.387133Z","iopub.status.idle":"2026-09-12T11:25:28.432479Z","shell.execute_reply.started":"2026-09-12T11:25:27.387107Z","shell.execute_reply":"2026-09-12T11:25:28.431142Z"}},"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":"2026-09-12T11:25:28.434339Z","iopub.execute_input":"2026-09-12T11:25:28.434701Z","iopub.status.idle":"2026-09-12T11:25:29.494393Z","shell.execute_reply.started":"2026-09-12T11:25:28.434666Z","shell.execute_reply":"2026-09-12T11:25:29.493361Z"},"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":"2026-09-12T11:25:29.993748Z","iopub.execute_input":"2026-09-12T11:25:29.994474Z","iopub.status.idle":"2026-09-12T11:25:31.009668Z","shell.execute_reply.started":"2026-09-12T11:25:29.994441Z","shell.execute_reply":"2026-09-12T11:25:31.008765Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"!python --version","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T11:25:31.597689Z","iopub.execute_input":"2026-09-12T11:25:31.598483Z","iopub.status.idle":"2026-09-12T11:25:32.611578Z","shell.execute_reply.started":"2026-09-12T11:25:31.598447Z","shell.execute_reply":"2026-09-12T11:25:32.610379Z"}},"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":"2026-09-12T11:25:43.783737Z","iopub.execute_input":"2026-09-12T11:25:43.784095Z","iopub.status.idle":"2026-09-12T11:25:43.798350Z","shell.execute_reply.started":"2026-09-12T11:25:43.784061Z","shell.execute_reply":"2026-09-12T11:25:43.797452Z"}},"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":"2026-09-12T11:25:46.150983Z","iopub.execute_input":"2026-09-12T11:25:46.151800Z","iopub.status.idle":"2026-09-12T11:25:46.157448Z","shell.execute_reply.started":"2026-09-12T11:25:46.151764Z","shell.execute_reply":"2026-09-12T11:25:46.156412Z"},"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":"2026-09-12T11:25:49.954054Z","iopub.execute_input":"2026-09-12T11:25:49.954565Z","iopub.status.idle":"2026-09-12T11:25:49.959389Z","shell.execute_reply.started":"2026-09-12T11:25:49.954515Z","shell.execute_reply":"2026-09-12T11:25:49.958345Z"},"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":"2026-09-12T11:25:52.065273Z","iopub.execute_input":"2026-09-12T11:25:52.065993Z","iopub.status.idle":"2026-09-12T11:25:52.072130Z","shell.execute_reply.started":"2026-09-12T11:25:52.065950Z","shell.execute_reply":"2026-09-12T11:25:52.071151Z"},"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":"2026-09-12T11:25:53.026726Z","iopub.execute_input":"2026-09-12T11:25:53.027666Z","iopub.status.idle":"2026-09-12T11:25:54.059884Z","shell.execute_reply.started":"2026-09-12T11:25:53.027623Z","shell.execute_reply":"2026-09-12T11:25:54.058921Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -l","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T11:25:54.491339Z","iopub.execute_input":"2026-09-12T11:25:54.491687Z","iopub.status.idle":"2026-09-12T11:25:55.565053Z","shell.execute_reply.started":"2026-09-12T11:25:54.491659Z","shell.execute_reply":"2026-09-12T11:25:55.563750Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -l dataset_dogs_vs_cats/train","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T11:25:55.567436Z","iopub.execute_input":"2026-09-12T11:25:55.567746Z","iopub.status.idle":"2026-09-12T11:25:56.601272Z","shell.execute_reply.started":"2026-09-12T11:25:55.567720Z","shell.execute_reply":"2026-09-12T11:25:56.600203Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -l dataset_dogs_vs_cats/test #validation","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T11:25:56.875406Z","iopub.execute_input":"2026-09-12T11:25:56.875748Z","iopub.status.idle":"2026-09-12T11:25:57.915418Z","shell.execute_reply.started":"2026-09-12T11:25:56.875723Z","shell.execute_reply":"2026-09-12T11:25:57.914343Z"}},"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":"2026-09-12T11:25:57.917544Z","iopub.execute_input":"2026-09-12T11:25:57.918330Z","iopub.status.idle":"2026-09-12T11:26:00.004068Z","shell.execute_reply.started":"2026-09-12T11:25:57.918248Z","shell.execute_reply":"2026-09-12T11:26:00.003294Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"print(src)\nprint(dst)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T11:26:00.005683Z","iopub.execute_input":"2026-09-12T11:26:00.006047Z","iopub.status.idle":"2026-09-12T11:26:00.010966Z","shell.execute_reply.started":"2026-09-12T11:26:00.006024Z","shell.execute_reply":"2026-09-12T11:26:00.010019Z"}},"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":"2026-09-12T11:26:00.012118Z","iopub.execute_input":"2026-09-12T11:26:00.012978Z","iopub.status.idle":"2026-09-12T11:26:02.226812Z","shell.execute_reply.started":"2026-09-12T11:26:00.012953Z","shell.execute_reply":"2026-09-12T11:26:02.225524Z"},"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":"2026-09-12T11:26:02.229105Z","iopub.execute_input":"2026-09-12T11:26:02.229451Z","iopub.status.idle":"2026-09-12T11:26:04.324191Z","shell.execute_reply.started":"2026-09-12T11:26:02.229420Z","shell.execute_reply":"2026-09-12T11:26:04.323192Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"!pip -q install livelossplot==0.5.5","metadata":{"execution":{"iopub.status.busy":"2026-09-12T11:26:04.325733Z","iopub.execute_input":"2026-09-12T11:26:04.326018Z","iopub.status.idle":"2026-09-12T11:26:15.443825Z","shell.execute_reply.started":"2026-09-12T11:26:04.325960Z","shell.execute_reply":"2026-09-12T11:26:15.442420Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"from livelossplot import PlotLossesKeras","metadata":{"execution":{"iopub.status.busy":"2026-09-12T11:26:15.445581Z","iopub.execute_input":"2026-09-12T11:26:15.445901Z","iopub.status.idle":"2026-09-12T11:26:15.462086Z","shell.execute_reply.started":"2026-09-12T11:26:15.445872Z","shell.execute_reply":"2026-09-12T11:26:15.461327Z"},"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":"2026-09-12T11:26:22.220212Z","iopub.execute_input":"2026-09-12T11:26:22.220922Z","iopub.status.idle":"2026-09-12T11:26:22.224829Z","shell.execute_reply.started":"2026-09-12T11:26:22.220889Z","shell.execute_reply":"2026-09-12T11:26:22.223841Z"}},"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":"2026-09-12T11:26:24.204197Z","iopub.execute_input":"2026-09-12T11:26:24.204987Z","iopub.status.idle":"2026-09-12T11:26:24.209844Z","shell.execute_reply.started":"2026-09-12T11:26:24.204952Z","shell.execute_reply":"2026-09-12T11:26:24.208872Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"model = Sequential()\ntype(model)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T11:26:26.317721Z","iopub.execute_input":"2026-09-12T11:26:26.318051Z","iopub.status.idle":"2026-09-12T11:26:27.734393Z","shell.execute_reply.started":"2026-09-12T11:26:26.318024Z","shell.execute_reply":"2026-09-12T11:26:27.733438Z"}},"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":"2026-09-12T11:26:28.138957Z","iopub.execute_input":"2026-09-12T11:26:28.139763Z","iopub.status.idle":"2026-09-12T11:26:28.267195Z","shell.execute_reply.started":"2026-09-12T11:26:28.139730Z","shell.execute_reply":"2026-09-12T11:26:28.266210Z"}},"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":"2026-09-12T11:26:33.133726Z","iopub.execute_input":"2026-09-12T11:26:33.134031Z","iopub.status.idle":"2026-09-12T11:26:33.198908Z","shell.execute_reply.started":"2026-09-12T11:26:33.134006Z","shell.execute_reply":"2026-09-12T11:26:33.198126Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# define cnn model\ndef define_model_1():\n\tmodel = Sequential()\n\tmodel.add(Conv2D(32, (3, 3), activation='relu', kernel_initializer='he_uniform', padding='same', input_shape=(200, 200, 3)))\n\tmodel.add(MaxPooling2D((2, 2)))\n\tmodel.add(Flatten())\n\tmodel.add(Dense(128, activation='relu', kernel_initializer='he_uniform'))\n\tmodel.add(Dense(1, activation='sigmoid'))\n\t# compile model\n\topt = SGD(lr=0.001, momentum=0.9)\n\tmodel.compile(optimizer=opt, loss='binary_crossentropy', metrics=['accuracy'])\n\treturn model","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T11:26:35.467936Z","iopub.execute_input":"2026-09-12T11:26:35.468413Z","iopub.status.idle":"2026-09-12T11:26:35.476248Z","shell.execute_reply.started":"2026-09-12T11:26:35.468372Z","shell.execute_reply":"2026-09-12T11:26:35.475313Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"model_1 = define_model_1()\nprint(model_1.summary())","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T11:26:39.372693Z","iopub.execute_input":"2026-09-12T11:26:39.373403Z","iopub.status.idle":"2026-09-12T11:26:39.449326Z","shell.execute_reply.started":"2026-09-12T11:26:39.373361Z","shell.execute_reply":"2026-09-12T11:26:39.448261Z"}},"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":"2026-09-12T11:26:39.612227Z","iopub.execute_input":"2026-09-12T11:26:39.612586Z","iopub.status.idle":"2026-09-12T11:26:39.619202Z","shell.execute_reply.started":"2026-09-12T11:26:39.612560Z","shell.execute_reply":"2026-09-12T11:26:39.618167Z"}},"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":"2026-09-12T11:26:39.818386Z","iopub.execute_input":"2026-09-12T11:26:39.818726Z","iopub.status.idle":"2026-09-12T11:26:39.825337Z","shell.execute_reply.started":"2026-09-12T11:26:39.818702Z","shell.execute_reply":"2026-09-12T11:26:39.824381Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"model_1 = define_model_1()\nprint(model_1.summary())","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T11:26:40.015557Z","iopub.execute_input":"2026-09-12T11:26:40.016258Z","iopub.status.idle":"2026-09-12T11:26:40.088562Z","shell.execute_reply.started":"2026-09-12T11:26:40.016222Z","shell.execute_reply":"2026-09-12T11:26:40.087566Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"datagen = ImageDataGenerator(rescale=1.0/255.0)\ntype(datagen)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T11:26:43.259997Z","iopub.execute_input":"2026-09-12T11:26:43.260802Z","iopub.status.idle":"2026-09-12T11:26:43.266540Z","shell.execute_reply.started":"2026-09-12T11:26:43.260768Z","shell.execute_reply":"2026-09-12T11:26:43.265554Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls dataset_dogs_vs_cats/train/","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T11:26:43.466930Z","iopub.execute_input":"2026-09-12T11:26:43.467742Z","iopub.status.idle":"2026-09-12T11:26:44.494653Z","shell.execute_reply.started":"2026-09-12T11:26:43.467709Z","shell.execute_reply":"2026-09-12T11:26:44.493704Z"}},"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":"2026-09-12T11:27:40.605923Z","iopub.execute_input":"2026-09-12T11:27:40.606743Z","iopub.status.idle":"2026-09-12T11:27:40.610942Z","shell.execute_reply.started":"2026-09-12T11:27:40.606708Z","shell.execute_reply":"2026-09-12T11:27:40.609947Z"}},"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":"2026-09-12T11:27:42.340194Z","iopub.execute_input":"2026-09-12T11:27:42.340574Z","iopub.status.idle":"2026-09-12T11:27:42.833392Z","shell.execute_reply.started":"2026-09-12T11:27:42.340546Z","shell.execute_reply":"2026-09-12T11:27:42.832542Z"}},"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":"2026-09-12T11:27:44.560145Z","iopub.execute_input":"2026-09-12T11:27:44.560513Z","iopub.status.idle":"2026-09-12T11:27:44.567813Z","shell.execute_reply.started":"2026-09-12T11:27:44.560484Z","shell.execute_reply":"2026-09-12T11:27:44.566751Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"val_it = datagen.flow_from_directory('dataset_dogs_vs_cats/test/',\n\t\tclass_mode='binary',\n        batch_size=BATCH_SIZE,\n        target_size=IMAGE_SIZE\n)\ntype(val_it)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T11:27:44.815191Z","iopub.execute_input":"2026-09-12T11:27:44.815562Z","iopub.status.idle":"2026-09-12T11:27:45.043474Z","shell.execute_reply.started":"2026-09-12T11:27:44.815534Z","shell.execute_reply":"2026-09-12T11:27:45.042645Z"}},"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":"2026-09-12T11:27:45.044818Z","iopub.execute_input":"2026-09-12T11:27:45.045091Z","iopub.status.idle":"2026-09-12T11:27:45.052232Z","shell.execute_reply.started":"2026-09-12T11:27:45.045068Z","shell.execute_reply":"2026-09-12T11:27:45.051091Z"}},"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":"2026-09-12T11:27:47.599560Z","iopub.execute_input":"2026-09-12T11:27:47.599857Z","iopub.status.idle":"2026-09-12T11:43:03.603181Z","shell.execute_reply.started":"2026-09-12T11:27:47.599834Z","shell.execute_reply":"2026-09-12T11:43:03.602442Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# learning curves\nsummarize_diagnostics(history_1)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T11:43:03.605085Z","iopub.execute_input":"2026-09-12T11:43:03.606142Z","iopub.status.idle":"2026-09-12T11:43:03.909329Z","shell.execute_reply.started":"2026-09-12T11:43:03.606097Z","shell.execute_reply":"2026-09-12T11:43:03.908141Z"}},"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":"2026-09-12T11:43:03.910635Z","iopub.execute_input":"2026-09-12T11:43:03.911047Z","iopub.status.idle":"2026-09-12T11:43:15.751658Z","shell.execute_reply.started":"2026-09-12T11:43:03.911019Z","shell.execute_reply":"2026-09-12T11:43:15.750761Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls ","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T11:43:35.080559Z","iopub.execute_input":"2026-09-12T11:43:35.081632Z","iopub.status.idle":"2026-09-12T11:43:36.135681Z","shell.execute_reply.started":"2026-09-12T11:43:35.081598Z","shell.execute_reply":"2026-09-12T11:43:36.134691Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"pwd","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T11:43:36.138456Z","iopub.execute_input":"2026-09-12T11:43:36.138865Z","iopub.status.idle":"2026-09-12T11:43:36.146406Z","shell.execute_reply.started":"2026-09-12T11:43:36.138834Z","shell.execute_reply":"2026-09-12T11:43:36.145215Z"}},"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":"2026-09-12T11:43:36.147670Z","iopub.execute_input":"2026-09-12T11:43:36.147943Z","iopub.status.idle":"2026-09-12T11:43:36.186979Z","shell.execute_reply.started":"2026-09-12T11:43:36.147924Z","shell.execute_reply":"2026-09-12T11:43:36.186106Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"df.columns","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T11:43:36.189174Z","iopub.execute_input":"2026-09-12T11:43:36.189567Z","iopub.status.idle":"2026-09-12T11:43:36.195768Z","shell.execute_reply.started":"2026-09-12T11:43:36.189536Z","shell.execute_reply":"2026-09-12T11:43:36.194776Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"image_files[:5], type(image_files), len(image_files)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T11:43:36.196940Z","iopub.execute_input":"2026-09-12T11:43:36.197664Z","iopub.status.idle":"2026-09-12T11:43:36.207890Z","shell.execute_reply.started":"2026-09-12T11:43:36.197631Z","shell.execute_reply":"2026-09-12T11:43:36.207061Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"df.describe()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T11:43:38.774019Z","iopub.execute_input":"2026-09-12T11:43:38.774368Z","iopub.status.idle":"2026-09-12T11:43:38.816491Z","shell.execute_reply.started":"2026-09-12T11:43:38.774340Z","shell.execute_reply":"2026-09-12T11:43:38.815418Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"df.loc[1]","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T11:43:38.916863Z","iopub.execute_input":"2026-09-12T11:43:38.917821Z","iopub.status.idle":"2026-09-12T11:43:38.925154Z","shell.execute_reply.started":"2026-09-12T11:43:38.917787Z","shell.execute_reply":"2026-09-12T11:43:38.924132Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"df.sample(5)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T11:43:39.077376Z","iopub.execute_input":"2026-09-12T11:43:39.078133Z","iopub.status.idle":"2026-09-12T11:43:39.091966Z","shell.execute_reply.started":"2026-09-12T11:43:39.078099Z","shell.execute_reply":"2026-09-12T11:43:39.090848Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"df['filename']","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T11:43:39.207275Z","iopub.execute_input":"2026-09-12T11:43:39.207598Z","iopub.status.idle":"2026-09-12T11:43:39.215586Z","shell.execute_reply.started":"2026-09-12T11:43:39.207575Z","shell.execute_reply":"2026-09-12T11:43:39.214360Z"}},"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":"2026-09-12T11:43:39.344720Z","iopub.execute_input":"2026-09-12T11:43:39.345625Z","iopub.status.idle":"2026-09-12T11:43:39.434952Z","shell.execute_reply.started":"2026-09-12T11:43:39.345590Z","shell.execute_reply":"2026-09-12T11:43:39.434073Z"}},"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":"2026-09-12T11:43:39.447814Z","iopub.execute_input":"2026-09-12T11:43:39.448079Z","iopub.status.idle":"2026-09-12T11:43:39.454002Z","shell.execute_reply.started":"2026-09-12T11:43:39.448056Z","shell.execute_reply":"2026-09-12T11:43:39.453152Z"}},"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":"2026-09-12T11:43:39.573567Z","iopub.execute_input":"2026-09-12T11:43:39.573881Z","iopub.status.idle":"2026-09-12T11:43:44.836366Z","shell.execute_reply.started":"2026-09-12T11:43:39.573858Z","shell.execute_reply":"2026-09-12T11:43:44.834785Z"}},"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":"2026-09-12T11:43:44.839086Z","iopub.execute_input":"2026-09-12T11:43:44.839850Z","iopub.status.idle":"2026-09-12T11:43:50.049591Z","shell.execute_reply.started":"2026-09-12T11:43:44.839798Z","shell.execute_reply":"2026-09-12T11:43:50.048572Z"}},"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":"2026-09-12T11:43:50.050881Z","iopub.execute_input":"2026-09-12T11:43:50.051279Z","iopub.status.idle":"2026-09-12T11:43:50.057135Z","shell.execute_reply.started":"2026-09-12T11:43:50.051244Z","shell.execute_reply":"2026-09-12T11:43:50.056163Z"}},"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":"2026-09-12T11:43:50.059401Z","iopub.execute_input":"2026-09-12T11:43:50.060096Z","iopub.status.idle":"2026-09-12T11:43:55.303697Z","shell.execute_reply.started":"2026-09-12T11:43:50.060055Z","shell.execute_reply":"2026-09-12T11:43:55.302558Z"}},"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":"2026-09-12T11:43:55.304854Z","iopub.execute_input":"2026-09-12T11:43:55.305550Z","iopub.status.idle":"2026-09-12T11:44:18.231513Z","shell.execute_reply.started":"2026-09-12T11:43:55.305521Z","shell.execute_reply":"2026-09-12T11:44:18.230603Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"preds[:10]","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T11:44:18.232766Z","iopub.execute_input":"2026-09-12T11:44:18.233115Z","iopub.status.idle":"2026-09-12T11:44:18.239701Z","shell.execute_reply.started":"2026-09-12T11:44:18.233082Z","shell.execute_reply":"2026-09-12T11:44:18.238757Z"}},"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":"2026-09-12T11:44:18.240816Z","iopub.execute_input":"2026-09-12T11:44:18.241032Z","iopub.status.idle":"2026-09-12T11:44:19.891687Z","shell.execute_reply.started":"2026-09-12T11:44:18.241012Z","shell.execute_reply":"2026-09-12T11:44:19.889277Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# end of 2026-09-06\n stop here","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T11:57:53.502114Z","iopub.execute_input":"2026-09-12T11:57:53.502877Z","iopub.status.idle":"2026-09-12T11:57:53.508691Z","shell.execute_reply.started":"2026-09-12T11:57:53.502839Z","shell.execute_reply":"2026-09-12T11:57:53.507426Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Transfer Learning","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T11:45:12.115707Z","iopub.execute_input":"2026-09-12T11:45:12.116019Z","iopub.status.idle":"2026-09-12T11:45:12.120705Z","shell.execute_reply.started":"2026-09-12T11:45:12.115995Z","shell.execute_reply":"2026-09-12T11:45:12.119812Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"datagen = ImageDataGenerator(rescale=1.0/255.0)\n\ntrain_it = datagen.flow_from_directory(\n    'dataset_dogs_vs_cats/train',  # << เปลี่ยนให้เป็น Path เดิมของคุณ\n    class_mode='binary',\n    batch_size=64,\n    target_size=(224, 224)\n)\n\nval_it = datagen.flow_from_directory(\n    'dataset_dogs_vs_cats/test',   # << เปลี่ยนให้เป็น Path เดิมของคุณ\n    class_mode='binary',\n    batch_size=64,\n    target_size=(224, 224)\n)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T12:03:38.587560Z","iopub.execute_input":"2026-09-12T12:03:38.588465Z","iopub.status.idle":"2026-09-12T12:03:39.308928Z","shell.execute_reply.started":"2026-09-12T12:03:38.588429Z","shell.execute_reply":"2026-09-12T12:03:39.307808Z"}},"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":"2026-09-12T11:45:15.024861Z","iopub.execute_input":"2026-09-12T11:45:15.025696Z","iopub.status.idle":"2026-09-12T11:45:15.029440Z","shell.execute_reply.started":"2026-09-12T11:45:15.025664Z","shell.execute_reply":"2026-09-12T11:45:15.028536Z"}},"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":"2026-09-12T11:45:16.608872Z","iopub.execute_input":"2026-09-12T11:45:16.609480Z","iopub.status.idle":"2026-09-12T11:45:16.613359Z","shell.execute_reply.started":"2026-09-12T11:45:16.609448Z","shell.execute_reply":"2026-09-12T11:45:16.612349Z"}},"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":"2026-09-12T11:45:17.922441Z","iopub.execute_input":"2026-09-12T11:45:17.922776Z","iopub.status.idle":"2026-09-12T11:45:17.927126Z","shell.execute_reply.started":"2026-09-12T11:45:17.922741Z","shell.execute_reply":"2026-09-12T11:45:17.925967Z"}},"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":"2026-09-12T11:45:18.096008Z","iopub.execute_input":"2026-09-12T11:45:18.096834Z","iopub.status.idle":"2026-09-12T11:45:18.100752Z","shell.execute_reply.started":"2026-09-12T11:45:18.096801Z","shell.execute_reply":"2026-09-12T11:45:18.099715Z"}},"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":"2026-09-12T12:02:16.857926Z","iopub.execute_input":"2026-09-12T12:02:16.858796Z","iopub.status.idle":"2026-09-12T12:02:17.264538Z","shell.execute_reply.started":"2026-09-12T12:02:16.858761Z","shell.execute_reply":"2026-09-12T12:02:17.263682Z"}},"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":"2026-09-12T11:45:22.961196Z","iopub.execute_input":"2026-09-12T11:45:22.961553Z","iopub.status.idle":"2026-09-12T11:45:22.967255Z","shell.execute_reply.started":"2026-09-12T11:45:22.961525Z","shell.execute_reply":"2026-09-12T11:45:22.966280Z"}},"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":"2026-09-12T11:45:23.154219Z","iopub.execute_input":"2026-09-12T11:45:23.154963Z","iopub.status.idle":"2026-09-12T11:45:23.159219Z","shell.execute_reply.started":"2026-09-12T11:45:23.154931Z","shell.execute_reply":"2026-09-12T11:45:23.158046Z"}},"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":"2026-09-12T11:45:23.347112Z","iopub.execute_input":"2026-09-12T11:45:23.347583Z","iopub.status.idle":"2026-09-12T11:45:23.352079Z","shell.execute_reply.started":"2026-09-12T11:45:23.347543Z","shell.execute_reply":"2026-09-12T11:45:23.350854Z"}},"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":"2026-09-12T11:45:25.426198Z","iopub.execute_input":"2026-09-12T11:45:25.426565Z","iopub.status.idle":"2026-09-12T11:45:25.431109Z","shell.execute_reply.started":"2026-09-12T11:45:25.426535Z","shell.execute_reply":"2026-09-12T11:45:25.430029Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"id(vgg16_model)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T11:45:25.776427Z","iopub.execute_input":"2026-09-12T11:45:25.776746Z","iopub.status.idle":"2026-09-12T11:45:25.782746Z","shell.execute_reply.started":"2026-09-12T11:45:25.776721Z","shell.execute_reply":"2026-09-12T11:45:25.781699Z"}},"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":"2026-09-12T11:57:02.063947Z","iopub.execute_input":"2026-09-12T11:57:02.064258Z","iopub.status.idle":"2026-09-12T11:57:19.906575Z","shell.execute_reply.started":"2026-09-12T11:57:02.064233Z","shell.execute_reply":"2026-09-12T11:57:19.904962Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# learning curves\nsummarize_diagnostics(vgg16_model_history)\n\n# evaluate model\n_, acc = vgg16_model.evaluate_generator(val_it, steps=len(val_it), verbose=1)\nprint('Val: > %.3f' % (acc * 100.0))\n\n# evaluate model\n_, acc = vgg16_model.evaluate_generator(test_it, steps=len(test_it), verbose=1)\nprint('Test: > %.3f' % (acc * 100.0))","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T11:45:34.741423Z","iopub.status.idle":"2026-09-12T11:45:34.741779Z","shell.execute_reply.started":"2026-09-12T11:45:34.741620Z","shell.execute_reply":"2026-09-12T11:45:34.741637Z"}},"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\nfrom keras.models import Model\nfrom keras.layers import Flatten, Dense\nfrom keras.optimizers import SGD\n\ndef define_model_inceptionv3():\n    # load model\n    model = InceptionV3(include_top=False, input_shape=(299, 299, 3))\n    \n    # mark loaded layers as not trainable\n    for layer in model.layers:\n        layer.trainable = False\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    \n    # แก้จุดที่ 1: ใช้ 1 node + sigmoid สำหรับ Binary classification\n    output = Dense(1, activation='sigmoid')(class4)\n    \n    # define new model\n    model = Model(inputs=model.inputs, outputs=output)\n    \n    # compile model (binary_crossentropy คู่กับ sigmoid)\n    opt = SGD(learning_rate=0.001, momentum=0.9) # เปลี่ยน lr แทน lr= เพื่อรองรับ Keras เวอร์ชันใหม่\n    model.compile(optimizer=opt, loss='binary_crossentropy', metrics=['accuracy'])\n    \n    return model","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T11:52:04.691241Z","iopub.execute_input":"2026-09-12T11:52:04.691596Z","iopub.status.idle":"2026-09-12T11:52:04.701608Z","shell.execute_reply.started":"2026-09-12T11:52:04.691569Z","shell.execute_reply":"2026-09-12T11:52:04.700584Z"}},"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":"2026-09-12T11:52:06.922052Z","iopub.execute_input":"2026-09-12T11:52:06.922381Z","iopub.status.idle":"2026-09-12T11:52:09.175463Z","shell.execute_reply.started":"2026-09-12T11:52:06.922353Z","shell.execute_reply":"2026-09-12T11:52:09.174487Z"},"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":"2026-09-12T11:52:09.176765Z","iopub.execute_input":"2026-09-12T11:52:09.177634Z","iopub.status.idle":"2026-09-12T11:52:09.183925Z","shell.execute_reply.started":"2026-09-12T11:52:09.177609Z","shell.execute_reply":"2026-09-12T11:52:09.182938Z"}},"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":"2026-09-12T11:52:17.787602Z","iopub.execute_input":"2026-09-12T11:52:17.787958Z","iopub.status.idle":"2026-09-12T11:52:17.793875Z","shell.execute_reply.started":"2026-09-12T11:52:17.787931Z","shell.execute_reply":"2026-09-12T11:52:17.792956Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import tensorflow as tf\n\ntf.debugging.disable_traceback_filtering()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T11:52:21.176852Z","iopub.execute_input":"2026-09-12T11:52:21.177708Z","iopub.status.idle":"2026-09-12T11:52:21.184158Z","shell.execute_reply.started":"2026-09-12T11:52:21.177671Z","shell.execute_reply":"2026-09-12T11:52:21.183027Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"\n# fit model\nhistory_inceptionv3 = model_inceptionv3.fit(\n    train_it,\n    validation_data=val_it,\n    epochs=3,\n    verbose=1,\n    callbacks=[PlotLossesKeras()]\n)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T11:52:23.453156Z","iopub.execute_input":"2026-09-12T11:52:23.453933Z","iopub.status.idle":"2026-09-12T11:52:31.148932Z","shell.execute_reply.started":"2026-09-12T11:52:23.453897Z","shell.execute_reply":"2026-09-12T11:52:31.147217Z"}},"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":"2026-09-12T11:48:56.550846Z","iopub.execute_input":"2026-09-12T11:48:56.551467Z","iopub.status.idle":"2026-09-12T11:48:56.558379Z","shell.execute_reply.started":"2026-09-12T11:48:56.551433Z","shell.execute_reply":"2026-09-12T11:48:56.557357Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# plot_images_with_labels(images, labels, \"Dog-Cat\", \"Training\")","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T11:46:48.036753Z","iopub.execute_input":"2026-09-12T11:46:48.037549Z","iopub.status.idle":"2026-09-12T11:46:48.041539Z","shell.execute_reply.started":"2026-09-12T11:46:48.037516Z","shell.execute_reply":"2026-09-12T11:46:48.040450Z"}},"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":"2026-09-12T11:46:48.240111Z","iopub.execute_input":"2026-09-12T11:46:48.240982Z","iopub.status.idle":"2026-09-12T11:46:48.244588Z","shell.execute_reply.started":"2026-09-12T11:46:48.240940Z","shell.execute_reply":"2026-09-12T11:46:48.243670Z"}},"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":"2026-09-12T11:46:48.356222Z","iopub.execute_input":"2026-09-12T11:46:48.357379Z","iopub.status.idle":"2026-09-12T11:46:48.360990Z","shell.execute_reply.started":"2026-09-12T11:46:48.357339Z","shell.execute_reply":"2026-09-12T11:46:48.360131Z"}},"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":"2026-09-12T11:46:48.514395Z","iopub.execute_input":"2026-09-12T11:46:48.515193Z","iopub.status.idle":"2026-09-12T11:46:49.465278Z","shell.execute_reply.started":"2026-09-12T11:46:48.515161Z","shell.execute_reply":"2026-09-12T11:46:49.463838Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"images = test_it.__next__()\nimages.shape","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T11:46:54.642929Z","iopub.execute_input":"2026-09-12T11:46:54.643787Z","iopub.status.idle":"2026-09-12T11:46:54.747464Z","shell.execute_reply.started":"2026-09-12T11:46:54.643755Z","shell.execute_reply":"2026-09-12T11:46:54.746497Z"}},"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":"2026-09-12T11:46:52.578700Z","iopub.execute_input":"2026-09-12T11:46:52.579495Z","iopub.status.idle":"2026-09-12T11:46:52.605700Z","shell.execute_reply.started":"2026-09-12T11:46:52.579459Z","shell.execute_reply":"2026-09-12T11:46:52.604254Z"}},"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":"2026-09-12T11:46:57.266200Z","iopub.execute_input":"2026-09-12T11:46:57.266881Z","iopub.status.idle":"2026-09-12T11:46:57.292553Z","shell.execute_reply.started":"2026-09-12T11:46:57.266844Z","shell.execute_reply":"2026-09-12T11:46:57.291336Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"Make Prediction","metadata":{}},{"cell_type":"code","source":"# fit model\nvgg16_model_history = vgg16_model.fit(\n    train_it,\n    validation_data=val_it,\n    epochs=5,\n    verbose=1,\n    callbacks=[PlotLossesKeras()]\n)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T12:07:14.257143Z","iopub.execute_input":"2026-09-12T12:07:14.257958Z","iopub.status.idle":"2026-09-12T12:16:14.803893Z","shell.execute_reply.started":"2026-09-12T12:07:14.257921Z","shell.execute_reply":"2026-09-12T12:16:14.802874Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null}]}