{"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":"2026-09-09T16:13:09.769011Z","iopub.execute_input":"2026-09-09T16:13:09.769856Z","iopub.status.idle":"2026-09-09T16:13:10.109745Z","shell.execute_reply.started":"2026-09-09T16:13:09.769819Z","shell.execute_reply":"2026-09-09T16:13:10.108695Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"!python --version","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-09T16:13:10.111896Z","iopub.execute_input":"2026-09-09T16:13:10.112433Z","iopub.status.idle":"2026-09-09T16:13:11.163951Z","shell.execute_reply.started":"2026-09-09T16:13:10.1124Z","shell.execute_reply":"2026-09-09T16:13:11.162583Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"!uname --all","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-09T16:13:11.165559Z","iopub.execute_input":"2026-09-09T16:13:11.165851Z","iopub.status.idle":"2026-09-09T16:13:12.162716Z","shell.execute_reply.started":"2026-09-09T16:13:11.165828Z","shell.execute_reply":"2026-09-09T16:13:12.161811Z"}},"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":"2026-09-09T16:13:12.165083Z","iopub.execute_input":"2026-09-09T16:13:12.165407Z","iopub.status.idle":"2026-09-09T16:13:21.96115Z","shell.execute_reply.started":"2026-09-09T16:13:12.16538Z","shell.execute_reply":"2026-09-09T16:13:21.960077Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-09T16:13:21.962443Z","iopub.execute_input":"2026-09-09T16:13:21.962763Z","iopub.status.idle":"2026-09-09T16:13:22.948038Z","shell.execute_reply.started":"2026-09-09T16:13:21.96272Z","shell.execute_reply":"2026-09-09T16:13:22.947148Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -l","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-09T16:13:22.949595Z","iopub.execute_input":"2026-09-09T16:13:22.949944Z","iopub.status.idle":"2026-09-09T16:13:24.009955Z","shell.execute_reply.started":"2026-09-09T16:13:22.949919Z","shell.execute_reply":"2026-09-09T16:13:24.008688Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls test1","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-09T16:13:24.011694Z","iopub.execute_input":"2026-09-09T16:13:24.012005Z","iopub.status.idle":"2026-09-09T16:13:25.116672Z","shell.execute_reply.started":"2026-09-09T16:13:24.011981Z","shell.execute_reply":"2026-09-09T16:13:25.115762Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls test1/ | wc -l","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-09T16:13:25.118Z","iopub.execute_input":"2026-09-09T16:13:25.11877Z","iopub.status.idle":"2026-09-09T16:13:26.213948Z","shell.execute_reply.started":"2026-09-09T16:13:25.11874Z","shell.execute_reply":"2026-09-09T16:13:26.212898Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls train/ | wc -l","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-09T16:13:26.215466Z","iopub.execute_input":"2026-09-09T16:13:26.2159Z","iopub.status.idle":"2026-09-09T16:13:27.329167Z","shell.execute_reply.started":"2026-09-09T16:13:26.215869Z","shell.execute_reply":"2026-09-09T16:13:27.328268Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"#ls train/","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-09T16:13:27.332041Z","iopub.execute_input":"2026-09-09T16:13:27.332295Z","iopub.status.idle":"2026-09-09T16:13:27.336796Z","shell.execute_reply.started":"2026-09-09T16:13:27.332272Z","shell.execute_reply":"2026-09-09T16:13:27.335865Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"pwd","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-09T16:13:27.337909Z","iopub.execute_input":"2026-09-09T16:13:27.33884Z","iopub.status.idle":"2026-09-09T16:13:27.417475Z","shell.execute_reply.started":"2026-09-09T16:13:27.338804Z","shell.execute_reply":"2026-09-09T16:13:27.416643Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-09T16:13:27.41851Z","iopub.execute_input":"2026-09-09T16:13:27.418866Z","iopub.status.idle":"2026-09-09T16:13:28.441817Z","shell.execute_reply.started":"2026-09-09T16:13:27.418843Z","shell.execute_reply":"2026-09-09T16:13:28.440937Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -U train | head -n 10","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-09T16:13:28.443085Z","iopub.execute_input":"2026-09-09T16:13:28.44339Z","iopub.status.idle":"2026-09-09T16:13:29.514457Z","shell.execute_reply.started":"2026-09-09T16:13:28.443363Z","shell.execute_reply":"2026-09-09T16:13:29.513443Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -U test1 | head -n 10","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-09T16:13:29.516111Z","iopub.execute_input":"2026-09-09T16:13:29.51637Z","iopub.status.idle":"2026-09-09T16:13:30.560315Z","shell.execute_reply.started":"2026-09-09T16:13:29.516347Z","shell.execute_reply":"2026-09-09T16:13:30.559417Z"}},"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":"2026-09-09T16:13:30.561703Z","iopub.execute_input":"2026-09-09T16:13:30.562009Z","iopub.status.idle":"2026-09-09T16:13:31.573279Z","shell.execute_reply.started":"2026-09-09T16:13:30.561984Z","shell.execute_reply":"2026-09-09T16:13:31.572338Z"},"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":"2026-09-09T16:13:31.575308Z","iopub.execute_input":"2026-09-09T16:13:31.575681Z","iopub.status.idle":"2026-09-09T16:13:32.548817Z","shell.execute_reply.started":"2026-09-09T16:13:31.57564Z","shell.execute_reply":"2026-09-09T16:13:32.547651Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"!python --version","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-09T16:13:32.550227Z","iopub.execute_input":"2026-09-09T16:13:32.550563Z","iopub.status.idle":"2026-09-09T16:13:33.709421Z","shell.execute_reply.started":"2026-09-09T16:13:32.550535Z","shell.execute_reply":"2026-09-09T16:13:33.70839Z"}},"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":"2026-09-09T16:13:33.711016Z","iopub.execute_input":"2026-09-09T16:13:33.711351Z","iopub.status.idle":"2026-09-09T16:13:36.65566Z","shell.execute_reply.started":"2026-09-09T16:13:33.711324Z","shell.execute_reply":"2026-09-09T16:13:36.654695Z"}},"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":"2026-09-09T16:13:36.657034Z","iopub.execute_input":"2026-09-09T16:13:36.65802Z","iopub.status.idle":"2026-09-09T16:13:36.664811Z","shell.execute_reply.started":"2026-09-09T16:13:36.657965Z","shell.execute_reply":"2026-09-09T16:13:36.66381Z"},"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":"2026-09-09T16:13:36.666183Z","iopub.execute_input":"2026-09-09T16:13:36.666795Z","iopub.status.idle":"2026-09-09T16:13:36.682986Z","shell.execute_reply.started":"2026-09-09T16:13:36.666756Z","shell.execute_reply":"2026-09-09T16:13:36.681909Z"},"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":"2026-09-09T16:13:36.684426Z","iopub.execute_input":"2026-09-09T16:13:36.685221Z","iopub.status.idle":"2026-09-09T16:13:36.69615Z","shell.execute_reply.started":"2026-09-09T16:13:36.685194Z","shell.execute_reply":"2026-09-09T16:13:36.695262Z"},"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":"2026-09-09T16:13:36.697483Z","iopub.execute_input":"2026-09-09T16:13:36.697875Z","iopub.status.idle":"2026-09-09T16:13:37.830511Z","shell.execute_reply.started":"2026-09-09T16:13:36.697827Z","shell.execute_reply":"2026-09-09T16:13:37.829484Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -l","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-09T16:13:37.831944Z","iopub.execute_input":"2026-09-09T16:13:37.832274Z","iopub.status.idle":"2026-09-09T16:13:38.85089Z","shell.execute_reply.started":"2026-09-09T16:13:37.832249Z","shell.execute_reply":"2026-09-09T16:13:38.849562Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -l dataset_dogs_vs_cats/train","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-09T16:13:38.852689Z","iopub.execute_input":"2026-09-09T16:13:38.853085Z","iopub.status.idle":"2026-09-09T16:13:39.864587Z","shell.execute_reply.started":"2026-09-09T16:13:38.853048Z","shell.execute_reply":"2026-09-09T16:13:39.863402Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -l dataset_dogs_vs_cats/test #validation","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-09T16:13:39.866194Z","iopub.execute_input":"2026-09-09T16:13:39.866544Z","iopub.status.idle":"2026-09-09T16:13:40.921192Z","shell.execute_reply.started":"2026-09-09T16:13:39.866514Z","shell.execute_reply":"2026-09-09T16:13:40.919723Z"}},"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":"2026-09-09T16:13:40.922953Z","iopub.execute_input":"2026-09-09T16:13:40.923253Z","iopub.status.idle":"2026-09-09T16:13:44.246536Z","shell.execute_reply.started":"2026-09-09T16:13:40.923228Z","shell.execute_reply":"2026-09-09T16:13:44.245653Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"print(src)\nprint(dst)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-09T16:13:44.247723Z","iopub.execute_input":"2026-09-09T16:13:44.247969Z","iopub.status.idle":"2026-09-09T16:13:44.253564Z","shell.execute_reply.started":"2026-09-09T16:13:44.247946Z","shell.execute_reply":"2026-09-09T16:13:44.252538Z"}},"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":"2026-09-09T16:13:44.262705Z","iopub.execute_input":"2026-09-09T16:13:44.263035Z","iopub.status.idle":"2026-09-09T16:13:46.471881Z","shell.execute_reply.started":"2026-09-09T16:13:44.263011Z","shell.execute_reply":"2026-09-09T16:13:46.47067Z"},"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":"2026-09-09T16:13:46.473301Z","iopub.execute_input":"2026-09-09T16:13:46.473647Z","iopub.status.idle":"2026-09-09T16:13:48.701099Z","shell.execute_reply.started":"2026-09-09T16:13:46.473617Z","shell.execute_reply":"2026-09-09T16:13:48.700126Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"!pip -q install livelossplot==0.5.5","metadata":{"execution":{"iopub.status.busy":"2026-09-09T16:13:48.702593Z","iopub.execute_input":"2026-09-09T16:13:48.702932Z","iopub.status.idle":"2026-09-09T16:13:57.375567Z","shell.execute_reply.started":"2026-09-09T16:13:48.702904Z","shell.execute_reply":"2026-09-09T16:13:57.374087Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"from livelossplot import PlotLossesKeras","metadata":{"execution":{"iopub.status.busy":"2026-09-09T16:13:57.377223Z","iopub.execute_input":"2026-09-09T16:13:57.377581Z","iopub.status.idle":"2026-09-09T16:13:57.388636Z","shell.execute_reply.started":"2026-09-09T16:13:57.377552Z","shell.execute_reply":"2026-09-09T16:13:57.387711Z"},"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":"2026-09-09T16:13:57.389909Z","iopub.execute_input":"2026-09-09T16:13:57.391063Z","iopub.status.idle":"2026-09-09T16:13:57.395618Z","shell.execute_reply.started":"2026-09-09T16:13:57.391037Z","shell.execute_reply":"2026-09-09T16:13:57.394731Z"}},"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":"2026-09-09T16:13:57.396533Z","iopub.execute_input":"2026-09-09T16:13:57.397557Z","iopub.status.idle":"2026-09-09T16:13:57.405397Z","shell.execute_reply.started":"2026-09-09T16:13:57.397531Z","shell.execute_reply":"2026-09-09T16:13:57.404697Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"model = Sequential()\ntype(model)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-09T16:13:57.406348Z","iopub.execute_input":"2026-09-09T16:13:57.407212Z","iopub.status.idle":"2026-09-09T16:13:58.478198Z","shell.execute_reply.started":"2026-09-09T16:13:57.407184Z","shell.execute_reply":"2026-09-09T16:13:58.477206Z"}},"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":"2026-09-09T16:13:58.479177Z","iopub.execute_input":"2026-09-09T16:13:58.479478Z","iopub.status.idle":"2026-09-09T16:13:58.580514Z","shell.execute_reply.started":"2026-09-09T16:13:58.479453Z","shell.execute_reply":"2026-09-09T16:13:58.579618Z"}},"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":"2026-09-09T16:13:58.581623Z","iopub.execute_input":"2026-09-09T16:13:58.581866Z","iopub.status.idle":"2026-09-09T16:13:58.649524Z","shell.execute_reply.started":"2026-09-09T16:13:58.581844Z","shell.execute_reply":"2026-09-09T16:13:58.648633Z"}},"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":"2026-09-09T16:13:58.650713Z","iopub.execute_input":"2026-09-09T16:13:58.650999Z","iopub.status.idle":"2026-09-09T16:13:58.656897Z","shell.execute_reply.started":"2026-09-09T16:13:58.650975Z","shell.execute_reply":"2026-09-09T16:13:58.655985Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"model_1 = define_model_1()\nprint(model_1.summary())","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-09T16:13:58.658238Z","iopub.execute_input":"2026-09-09T16:13:58.658485Z","iopub.status.idle":"2026-09-09T16:13:58.729685Z","shell.execute_reply.started":"2026-09-09T16:13:58.658464Z","shell.execute_reply":"2026-09-09T16:13:58.7288Z"}},"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":"2026-09-09T16:13:58.730794Z","iopub.execute_input":"2026-09-09T16:13:58.731129Z","iopub.status.idle":"2026-09-09T16:13:58.737168Z","shell.execute_reply.started":"2026-09-09T16:13:58.731106Z","shell.execute_reply":"2026-09-09T16:13:58.736214Z"}},"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":"2026-09-09T16:13:58.738468Z","iopub.execute_input":"2026-09-09T16:13:58.738895Z","iopub.status.idle":"2026-09-09T16:13:58.751623Z","shell.execute_reply.started":"2026-09-09T16:13:58.738863Z","shell.execute_reply":"2026-09-09T16:13:58.750543Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"model_1 = define_model_1()\nprint(model_1.summary())","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-09T16:13:58.752706Z","iopub.execute_input":"2026-09-09T16:13:58.752908Z","iopub.status.idle":"2026-09-09T16:13:58.821557Z","shell.execute_reply.started":"2026-09-09T16:13:58.75289Z","shell.execute_reply":"2026-09-09T16:13:58.820798Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"datagen = ImageDataGenerator(rescale=1.0/255.0)\ntype(datagen)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-09T16:13:58.822562Z","iopub.execute_input":"2026-09-09T16:13:58.82324Z","iopub.status.idle":"2026-09-09T16:13:58.828533Z","shell.execute_reply.started":"2026-09-09T16:13:58.823217Z","shell.execute_reply":"2026-09-09T16:13:58.827677Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls dataset_dogs_vs_cats/train/","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-09T16:13:58.829635Z","iopub.execute_input":"2026-09-09T16:13:58.829947Z","iopub.status.idle":"2026-09-09T16:13:59.868877Z","shell.execute_reply.started":"2026-09-09T16:13:58.829926Z","shell.execute_reply":"2026-09-09T16:13:59.867751Z"}},"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":"2026-09-09T16:38:16.970707Z","iopub.execute_input":"2026-09-09T16:38:16.971486Z","iopub.status.idle":"2026-09-09T16:38:16.975805Z","shell.execute_reply.started":"2026-09-09T16:38:16.971452Z","shell.execute_reply":"2026-09-09T16:38:16.974791Z"}},"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":"2026-09-09T16:21:53.048069Z","iopub.execute_input":"2026-09-09T16:21:53.049041Z","iopub.status.idle":"2026-09-09T16:21:53.659515Z","shell.execute_reply.started":"2026-09-09T16:21:53.049005Z","shell.execute_reply":"2026-09-09T16:21:53.658413Z"}},"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":"2026-09-09T16:19:21.321006Z","iopub.execute_input":"2026-09-09T16:19:21.321969Z","iopub.status.idle":"2026-09-09T16:19:21.32814Z","shell.execute_reply.started":"2026-09-09T16:19:21.321933Z","shell.execute_reply":"2026-09-09T16:19:21.327107Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"BATCH_SIZE = 32\nIMAGE_SIZE = (150, 150)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-09T16:19:22.598396Z","iopub.execute_input":"2026-09-09T16:19:22.598749Z","iopub.status.idle":"2026-09-09T16:19:22.603688Z","shell.execute_reply.started":"2026-09-09T16:19:22.59872Z","shell.execute_reply":"2026-09-09T16:19:22.60265Z"}},"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":"2026-09-09T16:21:56.119891Z","iopub.execute_input":"2026-09-09T16:21:56.121017Z","iopub.status.idle":"2026-09-09T16:21:56.411319Z","shell.execute_reply.started":"2026-09-09T16:21:56.120971Z","shell.execute_reply":"2026-09-09T16:21:56.410586Z"}},"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":"2026-09-09T16:14:00.615152Z","iopub.execute_input":"2026-09-09T16:14:00.615425Z","iopub.status.idle":"2026-09-09T16:14:00.622416Z","shell.execute_reply.started":"2026-09-09T16:14:00.615402Z","shell.execute_reply":"2026-09-09T16:14:00.621653Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"x_batch, y_batch = next(iter(train_it))\nprint(x_batch.shape) \nprint(y_batch.shape)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-09T16:21:58.847692Z","iopub.execute_input":"2026-09-09T16:21:58.848431Z","iopub.status.idle":"2026-09-09T16:21:58.953154Z","shell.execute_reply.started":"2026-09-09T16:21:58.848396Z","shell.execute_reply":"2026-09-09T16:21:58.952319Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"from tensorflow.keras.models import Sequential\nfrom tensorflow.keras.layers import Conv2D, MaxPooling2D, Flatten, Dense\n\nmodel_1 = Sequential([\n    Conv2D(32, (3, 3), activation='relu', input_shape=(200, 200, 3)),\n    MaxPooling2D(2, 2),\n    Conv2D(64, (3, 3), activation='relu'),\n    MaxPooling2D(2, 2),\n    Flatten(),\n    Dense(128, activation='relu'),\n    Dense(1, activation='sigmoid') \n])\n\nmodel_1.compile(optimizer='adam', loss='binary_crossentropy', metrics=['accuracy'])\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-09T16:22:01.381207Z","iopub.execute_input":"2026-09-09T16:22:01.382152Z","iopub.status.idle":"2026-09-09T16:22:01.451428Z","shell.execute_reply.started":"2026-09-09T16:22:01.382106Z","shell.execute_reply":"2026-09-09T16:22:01.450654Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# fit model\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":"2026-09-09T16:38:20.501227Z","iopub.execute_input":"2026-09-09T16:38:20.502071Z","iopub.status.idle":"2026-09-09T17:00:53.125002Z","shell.execute_reply.started":"2026-09-09T16:38:20.502033Z","shell.execute_reply":"2026-09-09T17:00:53.123883Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# learning curves\nsummarize_diagnostics(history_1)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-09T17:07:31.472518Z","iopub.execute_input":"2026-09-09T17:07:31.473392Z","iopub.status.idle":"2026-09-09T17:07:31.828101Z","shell.execute_reply.started":"2026-09-09T17:07:31.473349Z","shell.execute_reply":"2026-09-09T17:07:31.826998Z"}},"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":"2026-09-09T17:07:36.120551Z","iopub.execute_input":"2026-09-09T17:07:36.120937Z","iopub.status.idle":"2026-09-09T17:07:47.026873Z","shell.execute_reply.started":"2026-09-09T17:07:36.12091Z","shell.execute_reply":"2026-09-09T17:07:47.025864Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls ","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-09T17:10:05.153933Z","iopub.execute_input":"2026-09-09T17:10:05.154722Z","iopub.status.idle":"2026-09-09T17:10:06.199679Z","shell.execute_reply.started":"2026-09-09T17:10:05.154687Z","shell.execute_reply":"2026-09-09T17:10:06.198491Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"pwd","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-09T17:10:10.304823Z","iopub.execute_input":"2026-09-09T17:10:10.305458Z","iopub.status.idle":"2026-09-09T17:10:10.314175Z","shell.execute_reply.started":"2026-09-09T17:10:10.305402Z","shell.execute_reply":"2026-09-09T17:10:10.312956Z"}},"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":"2026-09-09T17:10:14.480742Z","iopub.execute_input":"2026-09-09T17:10:14.481056Z","iopub.status.idle":"2026-09-09T17:10:14.51904Z","shell.execute_reply.started":"2026-09-09T17:10:14.481033Z","shell.execute_reply":"2026-09-09T17:10:14.51832Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"df.columns","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-09T17:10:22.491097Z","iopub.execute_input":"2026-09-09T17:10:22.491979Z","iopub.status.idle":"2026-09-09T17:10:22.500209Z","shell.execute_reply.started":"2026-09-09T17:10:22.491931Z","shell.execute_reply":"2026-09-09T17:10:22.499043Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"image_files[:5], type(image_files), len(image_files)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-09T17:10:25.249689Z","iopub.execute_input":"2026-09-09T17:10:25.250456Z","iopub.status.idle":"2026-09-09T17:10:25.256875Z","shell.execute_reply.started":"2026-09-09T17:10:25.250421Z","shell.execute_reply":"2026-09-09T17:10:25.255793Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"df.describe()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-09T17:10:27.738273Z","iopub.execute_input":"2026-09-09T17:10:27.738612Z","iopub.status.idle":"2026-09-09T17:10:27.760317Z","shell.execute_reply.started":"2026-09-09T17:10:27.738573Z","shell.execute_reply":"2026-09-09T17:10:27.75956Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"df.loc[1]","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-09T17:10:29.737844Z","iopub.execute_input":"2026-09-09T17:10:29.73875Z","iopub.status.idle":"2026-09-09T17:10:29.745113Z","shell.execute_reply.started":"2026-09-09T17:10:29.738717Z","shell.execute_reply":"2026-09-09T17:10:29.744152Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"df.sample(5)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-09T17:10:31.802257Z","iopub.execute_input":"2026-09-09T17:10:31.802564Z","iopub.status.idle":"2026-09-09T17:10:31.811488Z","shell.execute_reply.started":"2026-09-09T17:10:31.802539Z","shell.execute_reply":"2026-09-09T17:10:31.81067Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"df['filename']","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-09T17:10:34.052963Z","iopub.execute_input":"2026-09-09T17:10:34.053315Z","iopub.status.idle":"2026-09-09T17:10:34.06101Z","shell.execute_reply.started":"2026-09-09T17:10:34.053288Z","shell.execute_reply":"2026-09-09T17:10:34.060263Z"}},"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 directory\ntest_it = datagen_test.flow_from_directory(\n    'dataset_dogs_vs_cats/test/',  # ระบุโฟลเดอร์สำหรับทดสอบ\n    target_size=IMAGE_SIZE,        # ใช้ตัวแปร IMAGE_SIZE ที่ประกาศไว้ด้านบน\n    batch_size=64,\n    class_mode='binary',           # เนื่องจากเป็น binary classification\n    color_mode='rgb',              # บังคับให้เป็น 3 ช่องสี (RGB)\n    shuffle=False                  # Usually testing data should not be shuffled\n)\n\ntype(test_it)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-09T17:10:36.545037Z","iopub.execute_input":"2026-09-09T17:10:36.545382Z","iopub.status.idle":"2026-09-09T17:10:36.810972Z","shell.execute_reply.started":"2026-09-09T17:10:36.545354Z","shell.execute_reply":"2026-09-09T17:10:36.810261Z"}},"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":"2026-09-09T17:10:41.602145Z","iopub.execute_input":"2026-09-09T17:10:41.603031Z","iopub.status.idle":"2026-09-09T17:10:41.609258Z","shell.execute_reply.started":"2026-09-09T17:10:41.603Z","shell.execute_reply":"2026-09-09T17:10:41.607896Z"}},"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":"2026-09-09T17:10:47.491495Z","iopub.execute_input":"2026-09-09T17:10:47.491922Z","iopub.status.idle":"2026-09-09T17:10:52.664698Z","shell.execute_reply.started":"2026-09-09T17:10:47.491889Z","shell.execute_reply":"2026-09-09T17:10:52.661656Z"}},"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":"2026-09-09T17:12:33.883151Z","iopub.execute_input":"2026-09-09T17:12:33.883953Z","iopub.status.idle":"2026-09-09T17:12:37.54895Z","shell.execute_reply.started":"2026-09-09T17:12:33.883919Z","shell.execute_reply":"2026-09-09T17:12:37.54799Z"}},"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(2, 5, figsize=(15, 6))\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":"2026-09-09T17:27:04.521036Z","iopub.execute_input":"2026-09-09T17:27:04.521857Z","iopub.status.idle":"2026-09-09T17:27:04.528083Z","shell.execute_reply.started":"2026-09-09T17:27:04.521821Z","shell.execute_reply":"2026-09-09T17:27:04.526932Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"images, labels = next(test_it)\n\nnum_images = 10\nindices = list(range(num_images))\n\nplot_exmaple_test(images, indices)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-09T17:27:07.370219Z","iopub.execute_input":"2026-09-09T17:27:07.371125Z","iopub.status.idle":"2026-09-09T17:27:08.72903Z","shell.execute_reply.started":"2026-09-09T17:27:07.371089Z","shell.execute_reply":"2026-09-09T17:27:08.727861Z"}},"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":"2026-09-09T17:27:15.243159Z","iopub.execute_input":"2026-09-09T17:27:15.243478Z","iopub.status.idle":"2026-09-09T17:27:27.42147Z","shell.execute_reply.started":"2026-09-09T17:27:15.243454Z","shell.execute_reply":"2026-09-09T17:27:27.420623Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"preds[:10]","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-09T17:27:30.762934Z","iopub.execute_input":"2026-09-09T17:27:30.763944Z","iopub.status.idle":"2026-09-09T17:27:30.770383Z","shell.execute_reply.started":"2026-09-09T17:27:30.763911Z","shell.execute_reply":"2026-09-09T17:27:30.769508Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import numpy as np\ntest_images, test_labels = next(test_it)\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":"2026-09-09T17:27:38.508344Z","iopub.execute_input":"2026-09-09T17:27:38.509202Z","iopub.status.idle":"2026-09-09T17:27:40.006267Z","shell.execute_reply.started":"2026-09-09T17:27:38.509165Z","shell.execute_reply":"2026-09-09T17:27:40.005099Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# end of 2026-09-06\nstop here","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-09T16:14:44.587697Z","iopub.status.idle":"2026-09-09T16:14:44.588108Z","shell.execute_reply.started":"2026-09-09T16:14:44.587894Z","shell.execute_reply":"2026-09-09T16:14:44.587915Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Transfer Learning","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-09T16:14:44.589779Z","iopub.status.idle":"2026-09-09T16:14:44.590293Z","shell.execute_reply.started":"2026-09-09T16:14:44.590032Z","shell.execute_reply":"2026-09-09T16:14:44.590057Z"}},"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":"2026-09-09T16:14:44.591571Z","iopub.status.idle":"2026-09-09T16:14:44.59207Z","shell.execute_reply.started":"2026-09-09T16:14:44.591804Z","shell.execute_reply":"2026-09-09T16:14:44.591826Z"}},"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":"2026-09-09T16:14:44.593703Z","iopub.status.idle":"2026-09-09T16:14:44.5942Z","shell.execute_reply.started":"2026-09-09T16:14:44.59394Z","shell.execute_reply":"2026-09-09T16:14:44.593963Z"}},"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":"2026-09-09T16:14:44.595573Z","iopub.status.idle":"2026-09-09T16:14:44.596039Z","shell.execute_reply.started":"2026-09-09T16:14:44.595812Z","shell.execute_reply":"2026-09-09T16:14:44.595835Z"}},"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":"2026-09-09T16:14:44.59706Z","iopub.status.idle":"2026-09-09T16:14:44.597471Z","shell.execute_reply.started":"2026-09-09T16:14:44.597263Z","shell.execute_reply":"2026-09-09T16:14:44.597284Z"}},"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":"2026-09-09T16:14:44.598899Z","iopub.status.idle":"2026-09-09T16:14:44.59935Z","shell.execute_reply.started":"2026-09-09T16:14:44.599095Z","shell.execute_reply":"2026-09-09T16:14:44.599142Z"}},"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":"2026-09-09T16:14:44.601727Z","iopub.status.idle":"2026-09-09T16:14:44.602235Z","shell.execute_reply.started":"2026-09-09T16:14:44.601938Z","shell.execute_reply":"2026-09-09T16:14:44.60196Z"}},"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":"2026-09-09T16:14:44.603336Z","iopub.status.idle":"2026-09-09T16:14:44.603769Z","shell.execute_reply.started":"2026-09-09T16:14:44.603532Z","shell.execute_reply":"2026-09-09T16:14:44.603553Z"}},"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":"2026-09-09T16:14:44.605376Z","iopub.status.idle":"2026-09-09T16:14:44.605813Z","shell.execute_reply.started":"2026-09-09T16:14:44.605575Z","shell.execute_reply":"2026-09-09T16:14:44.605614Z"}},"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":"2026-09-09T16:14:44.607071Z","iopub.status.idle":"2026-09-09T16:14:44.607527Z","shell.execute_reply.started":"2026-09-09T16:14:44.607283Z","shell.execute_reply":"2026-09-09T16:14:44.607323Z"}},"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":"2026-09-09T16:14:44.608922Z","iopub.status.idle":"2026-09-09T16:14:44.609335Z","shell.execute_reply.started":"2026-09-09T16:14:44.609124Z","shell.execute_reply":"2026-09-09T16:14:44.609157Z"}},"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":"2026-09-09T16:14:44.610816Z","iopub.status.idle":"2026-09-09T16:14:44.611179Z","shell.execute_reply.started":"2026-09-09T16:14:44.611009Z","shell.execute_reply":"2026-09-09T16:14:44.611026Z"}},"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":"2026-09-09T16:14:44.612186Z","iopub.status.idle":"2026-09-09T16:14:44.612456Z","shell.execute_reply.started":"2026-09-09T16:14:44.612324Z","shell.execute_reply":"2026-09-09T16:14:44.612337Z"}},"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":"2026-09-09T16:14:44.6138Z","iopub.status.idle":"2026-09-09T16:14:44.614152Z","shell.execute_reply.started":"2026-09-09T16:14:44.613989Z","shell.execute_reply":"2026-09-09T16:14:44.614005Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"from keras.applications.inception_v3 import InceptionV3\n\ndef define_model_inceptionv3():\n    # load model\n    model = InceptionV3(include_top=False, input_shape=(299, 299, 3))\n    # mark loaded layers as not trainable\n    for layer in model.layers:\n        layer.trainable = False\n        # layer.trainable = True #try to test\n    \n    # add new classifier layers\n    flat1 = Flatten()(model.layers[-1].output)\n    class1 = Dense(1024, activation='relu', kernel_initializer='he_uniform')(flat1)\n    class2 = Dense(512, activation='relu', kernel_initializer='he_uniform')(class1)\n    class3 = Dense(256, activation='relu', kernel_initializer='he_uniform')(class2)\n    class4 = Dense(128, activation='relu', kernel_initializer='he_uniform')(class3)\n    # output = Dense(1, activation='sigmoid')(flat1)\n    output = Dense(2, activation='softmax')(class4)\n    # define new model\n    model = Model(inputs=model.inputs, outputs=output)\n    # compile model\n    opt = SGD(lr=0.001, momentum=0.9)\n    model.compile(optimizer=opt, loss='binary_crossentropy', metrics=['accuracy'])\n    return model","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-09T16:14:44.615438Z","iopub.status.idle":"2026-09-09T16:14:44.615761Z","shell.execute_reply.started":"2026-09-09T16:14:44.615571Z","shell.execute_reply":"2026-09-09T16:14:44.615584Z"}},"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":"2026-09-09T16:14:44.617868Z","iopub.status.idle":"2026-09-09T16:14:44.618178Z","shell.execute_reply.started":"2026-09-09T16:14:44.61802Z","shell.execute_reply":"2026-09-09T16:14:44.618032Z"},"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":"2026-09-09T16:14:44.619801Z","iopub.status.idle":"2026-09-09T16:14:44.620201Z","shell.execute_reply.started":"2026-09-09T16:14:44.62003Z","shell.execute_reply":"2026-09-09T16:14:44.620048Z"}},"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":"2026-09-09T16:14:44.621719Z","iopub.status.idle":"2026-09-09T16:14:44.622036Z","shell.execute_reply.started":"2026-09-09T16:14:44.621896Z","shell.execute_reply":"2026-09-09T16:14:44.621911Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# fit model\nmodel_inceptionv3.reset_states()\nhistory_inceptionv3 = model_inceptionv3.fit(\n    train_it, \n    steps_per_epoch=len(train_it),\n    validation_data=val_it,\n    validation_steps=len(val_it),\n    epochs=3, verbose=1,\n    callbacks = [PlotLossesKeras()]\n    )","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-09T16:14:44.623429Z","iopub.status.idle":"2026-09-09T16:14:44.623789Z","shell.execute_reply.started":"2026-09-09T16:14:44.623645Z","shell.execute_reply":"2026-09-09T16:14:44.623661Z"}},"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":"2026-09-09T16:14:44.625114Z","iopub.status.idle":"2026-09-09T16:14:44.625388Z","shell.execute_reply.started":"2026-09-09T16:14:44.625258Z","shell.execute_reply":"2026-09-09T16:14:44.625271Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# plot_images_with_labels(images, labels, \"Dog-Cat\", \"Training\")","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-09T16:14:44.62753Z","iopub.status.idle":"2026-09-09T16:14:44.627946Z","shell.execute_reply.started":"2026-09-09T16:14:44.627782Z","shell.execute_reply":"2026-09-09T16:14:44.6278Z"}},"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":"2026-09-09T16:14:44.629525Z","iopub.status.idle":"2026-09-09T16:14:44.629895Z","shell.execute_reply.started":"2026-09-09T16:14:44.629734Z","shell.execute_reply":"2026-09-09T16:14:44.629751Z"}},"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":"2026-09-09T16:14:44.631349Z","iopub.status.idle":"2026-09-09T16:14:44.63171Z","shell.execute_reply.started":"2026-09-09T16:14:44.631524Z","shell.execute_reply":"2026-09-09T16:14:44.63154Z"}},"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":"2026-09-09T16:14:44.634067Z","iopub.status.idle":"2026-09-09T16:14:44.634445Z","shell.execute_reply.started":"2026-09-09T16:14:44.63427Z","shell.execute_reply":"2026-09-09T16:14:44.634287Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"images = test_it.__next__()\nimages.shape","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-09T16:14:44.635356Z","iopub.status.idle":"2026-09-09T16:14:44.635671Z","shell.execute_reply.started":"2026-09-09T16:14:44.635489Z","shell.execute_reply":"2026-09-09T16:14:44.635501Z"}},"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":"2026-09-09T16:14:44.63689Z","iopub.status.idle":"2026-09-09T16:14:44.637173Z","shell.execute_reply.started":"2026-09-09T16:14:44.63703Z","shell.execute_reply":"2026-09-09T16:14:44.637043Z"}},"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":"2026-09-09T16:14:44.638184Z","iopub.status.idle":"2026-09-09T16:14:44.638485Z","shell.execute_reply.started":"2026-09-09T16:14:44.638348Z","shell.execute_reply":"2026-09-09T16:14:44.638362Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"Make Prediction","metadata":{}},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null}]}