{"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":"2026-09-06T03:16:47.378946Z","iopub.execute_input":"2026-09-06T03:16:47.37984Z","iopub.status.idle":"2026-09-06T03:16:47.38884Z","shell.execute_reply.started":"2026-09-06T03:16:47.379792Z","shell.execute_reply":"2026-09-06T03:16:47.387714Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"!python --version","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-06T03:16:47.390565Z","iopub.execute_input":"2026-09-06T03:16:47.390888Z","iopub.status.idle":"2026-09-06T03:16:48.406099Z","shell.execute_reply.started":"2026-09-06T03:16:47.390865Z","shell.execute_reply":"2026-09-06T03:16:48.405081Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"!uname --all","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-06T03:16:48.407672Z","iopub.execute_input":"2026-09-06T03:16:48.408117Z","iopub.status.idle":"2026-09-06T03:16:49.411094Z","shell.execute_reply.started":"2026-09-06T03:16:48.408073Z","shell.execute_reply":"2026-09-06T03:16:49.410187Z"}},"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":"2026-09-06T03:16:49.414115Z","iopub.execute_input":"2026-09-06T03:16:49.415299Z","iopub.status.idle":"2026-09-06T03:16:58.981038Z","shell.execute_reply.started":"2026-09-06T03:16:49.415254Z","shell.execute_reply":"2026-09-06T03:16:58.980212Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-06T03:16:58.98217Z","iopub.execute_input":"2026-09-06T03:16:58.982551Z","iopub.status.idle":"2026-09-06T03:16:59.985912Z","shell.execute_reply.started":"2026-09-06T03:16:58.982523Z","shell.execute_reply":"2026-09-06T03:16:59.984646Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -l","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-06T03:16:59.987628Z","iopub.execute_input":"2026-09-06T03:16:59.98808Z","iopub.status.idle":"2026-09-06T03:17:01.025414Z","shell.execute_reply.started":"2026-09-06T03:16:59.988054Z","shell.execute_reply":"2026-09-06T03:17:01.023916Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls test1","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-06T03:17:01.02722Z","iopub.execute_input":"2026-09-06T03:17:01.027561Z","iopub.status.idle":"2026-09-06T03:17:02.116086Z","shell.execute_reply.started":"2026-09-06T03:17:01.027528Z","shell.execute_reply":"2026-09-06T03:17:02.115131Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls test1/ | wc -l","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-06T03:17:02.117676Z","iopub.execute_input":"2026-09-06T03:17:02.118597Z","iopub.status.idle":"2026-09-06T03:17:03.189628Z","shell.execute_reply.started":"2026-09-06T03:17:02.118558Z","shell.execute_reply":"2026-09-06T03:17:03.188748Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls train/ | wc -l","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-06T03:17:03.190956Z","iopub.execute_input":"2026-09-06T03:17:03.191242Z","iopub.status.idle":"2026-09-06T03:17:04.278312Z","shell.execute_reply.started":"2026-09-06T03:17:03.191216Z","shell.execute_reply":"2026-09-06T03:17:04.277415Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"#ls train/","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-02-16T07:02:11.654647Z","iopub.execute_input":"2026-02-16T07:02:11.654977Z","iopub.status.idle":"2026-02-16T07:02:11.65921Z","shell.execute_reply.started":"2026-02-16T07:02:11.654951Z","shell.execute_reply":"2026-02-16T07:02:11.658471Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"pwd","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-06T03:17:36.124598Z","iopub.execute_input":"2026-09-06T03:17:36.125606Z","iopub.status.idle":"2026-09-06T03:17:36.131877Z","shell.execute_reply.started":"2026-09-06T03:17:36.125568Z","shell.execute_reply":"2026-09-06T03:17:36.130922Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-06T03:17:33.201996Z","iopub.execute_input":"2026-09-06T03:17:33.202801Z","iopub.status.idle":"2026-09-06T03:17:34.220991Z","shell.execute_reply.started":"2026-09-06T03:17:33.202767Z","shell.execute_reply":"2026-09-06T03:17:34.220139Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -U train | head -n 10","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-06T03:19:28.166966Z","iopub.execute_input":"2026-09-06T03:19:28.167549Z","iopub.status.idle":"2026-09-06T03:19:29.237938Z","shell.execute_reply.started":"2026-09-06T03:19:28.167516Z","shell.execute_reply":"2026-09-06T03:19:29.236728Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -U test1 | head -n 10","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-06T03:20:19.088019Z","iopub.execute_input":"2026-09-06T03:20:19.088337Z","iopub.status.idle":"2026-09-06T03:20:20.131762Z","shell.execute_reply.started":"2026-09-06T03:20:19.088312Z","shell.execute_reply":"2026-09-06T03:20:20.130541Z"}},"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":"2026-09-06T03:20:46.752757Z","iopub.execute_input":"2026-09-06T03:20:46.753534Z","iopub.status.idle":"2026-09-06T03:20:47.797564Z","shell.execute_reply.started":"2026-09-06T03:20:46.753499Z","shell.execute_reply":"2026-09-06T03:20:47.796744Z"},"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":"2026-09-06T03:21:19.78165Z","iopub.execute_input":"2026-09-06T03:21:19.782431Z","iopub.status.idle":"2026-09-06T03:21:20.772698Z","shell.execute_reply.started":"2026-09-06T03:21:19.782392Z","shell.execute_reply":"2026-09-06T03:21:20.771647Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"!python --version","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-06T03:22:04.260723Z","iopub.execute_input":"2026-09-06T03:22:04.261613Z","iopub.status.idle":"2026-09-06T03:22:05.268511Z","shell.execute_reply.started":"2026-09-06T03:22:04.26158Z","shell.execute_reply":"2026-09-06T03:22:05.267133Z"}},"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":"2026-09-06T03:21:53.812444Z","iopub.execute_input":"2026-09-06T03:21:53.813215Z","iopub.status.idle":"2026-09-06T03:21:53.818576Z","shell.execute_reply.started":"2026-09-06T03:21:53.813181Z","shell.execute_reply":"2026-09-06T03:21:53.817635Z"}},"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":"2026-09-06T03:22:59.296653Z","iopub.execute_input":"2026-09-06T03:22:59.297064Z","iopub.status.idle":"2026-09-06T03:22:59.302217Z","shell.execute_reply.started":"2026-09-06T03:22:59.297035Z","shell.execute_reply":"2026-09-06T03:22:59.301216Z"},"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":"2026-09-06T03:23:43.094493Z","iopub.execute_input":"2026-09-06T03:23:43.094912Z","iopub.status.idle":"2026-09-06T03:23:43.10014Z","shell.execute_reply.started":"2026-09-06T03:23:43.094877Z","shell.execute_reply":"2026-09-06T03:23:43.098815Z"},"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":"2026-09-06T03:24:39.907735Z","iopub.execute_input":"2026-09-06T03:24:39.908132Z","iopub.status.idle":"2026-09-06T03:24:39.91489Z","shell.execute_reply.started":"2026-09-06T03:24:39.908104Z","shell.execute_reply":"2026-09-06T03:24:39.913929Z"},"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":"2026-09-06T03:24:59.491827Z","iopub.execute_input":"2026-09-06T03:24:59.492766Z","iopub.status.idle":"2026-09-06T03:25:00.493269Z","shell.execute_reply.started":"2026-09-06T03:24:59.492729Z","shell.execute_reply":"2026-09-06T03:25:00.492341Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -l","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-06T03:25:44.342336Z","iopub.execute_input":"2026-09-06T03:25:44.342719Z","iopub.status.idle":"2026-09-06T03:25:45.361416Z","shell.execute_reply.started":"2026-09-06T03:25:44.342687Z","shell.execute_reply":"2026-09-06T03:25:45.360044Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -l dataset_dogs_vs_cats/train","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-06T03:25:58.600972Z","iopub.execute_input":"2026-09-06T03:25:58.601837Z","iopub.status.idle":"2026-09-06T03:25:59.646729Z","shell.execute_reply.started":"2026-09-06T03:25:58.601788Z","shell.execute_reply":"2026-09-06T03:25:59.6457Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -l dataset_dogs_vs_cats/test #validation","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-06T03:26:02.46198Z","iopub.execute_input":"2026-09-06T03:26:02.462897Z","iopub.status.idle":"2026-09-06T03:26:03.509934Z","shell.execute_reply.started":"2026-09-06T03:26:02.462857Z","shell.execute_reply":"2026-09-06T03:26:03.508854Z"}},"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":"2026-09-06T03:27:26.5159Z","iopub.execute_input":"2026-09-06T03:27:26.516334Z","iopub.status.idle":"2026-09-06T03:27:28.547164Z","shell.execute_reply.started":"2026-09-06T03:27:26.516296Z","shell.execute_reply":"2026-09-06T03:27:28.546101Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"print(src)\nprint(dst)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-06T03:27:29.646793Z","iopub.execute_input":"2026-09-06T03:27:29.6473Z","iopub.status.idle":"2026-09-06T03:27:29.652925Z","shell.execute_reply.started":"2026-09-06T03:27:29.647268Z","shell.execute_reply":"2026-09-06T03:27:29.651994Z"}},"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":"2026-09-06T03:27:37.323516Z","iopub.execute_input":"2026-09-06T03:27:37.323852Z","iopub.status.idle":"2026-09-06T03:27:39.475009Z","shell.execute_reply.started":"2026-09-06T03:27:37.323826Z","shell.execute_reply":"2026-09-06T03:27:39.474103Z"},"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":"2026-09-06T03:27:54.249661Z","iopub.execute_input":"2026-09-06T03:27:54.250019Z","iopub.status.idle":"2026-09-06T03:27:56.321694Z","shell.execute_reply.started":"2026-09-06T03:27:54.249989Z","shell.execute_reply":"2026-09-06T03:27:56.320707Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"!pip -q install livelossplot==0.5.5","metadata":{"execution":{"iopub.status.busy":"2026-09-06T03:28:06.643259Z","iopub.execute_input":"2026-09-06T03:28:06.643625Z","iopub.status.idle":"2026-09-06T03:28:16.920333Z","shell.execute_reply.started":"2026-09-06T03:28:06.643594Z","shell.execute_reply":"2026-09-06T03:28:16.919298Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"from livelossplot import PlotLossesKeras","metadata":{"execution":{"iopub.status.busy":"2026-09-06T03:29:30.800242Z","iopub.execute_input":"2026-09-06T03:29:30.801281Z","iopub.status.idle":"2026-09-06T03:29:30.817075Z","shell.execute_reply.started":"2026-09-06T03:29:30.801242Z","shell.execute_reply":"2026-09-06T03:29:30.816102Z"},"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":"2026-02-16T07:02:33.08589Z","iopub.execute_input":"2026-02-16T07:02:33.086131Z","iopub.status.idle":"2026-02-16T07:02:33.094167Z","shell.execute_reply.started":"2026-02-16T07:02:33.086111Z","shell.execute_reply":"2026-02-16T07:02:33.09349Z"}},"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":"2026-09-06T03:30:02.654251Z","iopub.execute_input":"2026-09-06T03:30:02.655153Z","iopub.status.idle":"2026-09-06T03:30:02.661196Z","shell.execute_reply.started":"2026-09-06T03:30:02.655118Z","shell.execute_reply":"2026-09-06T03:30:02.660063Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"model = Sequential()\ntype(model)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-06T03:31:12.68724Z","iopub.execute_input":"2026-09-06T03:31:12.688072Z","iopub.status.idle":"2026-09-06T03:31:12.697803Z","shell.execute_reply.started":"2026-09-06T03:31:12.688037Z","shell.execute_reply":"2026-09-06T03:31:12.696922Z"}},"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":"2026-09-06T03:36:28.640223Z","iopub.execute_input":"2026-09-06T03:36:28.641247Z","iopub.status.idle":"2026-09-06T03:36:28.707969Z","shell.execute_reply.started":"2026-09-06T03:36:28.641214Z","shell.execute_reply":"2026-09-06T03:36:28.706419Z"}},"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":"2026-09-06T03:41:59.16672Z","iopub.execute_input":"2026-09-06T03:41:59.167534Z","iopub.status.idle":"2026-09-06T03:41:59.233235Z","shell.execute_reply.started":"2026-09-06T03:41:59.1675Z","shell.execute_reply":"2026-09-06T03:41:59.232347Z"}},"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":"2026-09-06T03:43:06.207103Z","iopub.execute_input":"2026-09-06T03:43:06.208132Z","iopub.status.idle":"2026-09-06T03:43:06.21368Z","shell.execute_reply.started":"2026-09-06T03:43:06.208092Z","shell.execute_reply":"2026-09-06T03:43:06.212586Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"model_1 = define_model_1()\nprint(model_1.summary())","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-06T03:43:55.398491Z","iopub.execute_input":"2026-09-06T03:43:55.398839Z","iopub.status.idle":"2026-09-06T03:43:55.471707Z","shell.execute_reply.started":"2026-09-06T03:43:55.398812Z","shell.execute_reply":"2026-09-06T03:43:55.470622Z"}},"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":"2026-09-06T03:44:39.693146Z","iopub.execute_input":"2026-09-06T03:44:39.694171Z","iopub.status.idle":"2026-09-06T03:44:39.701013Z","shell.execute_reply.started":"2026-09-06T03:44:39.694138Z","shell.execute_reply":"2026-09-06T03:44:39.70009Z"}},"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":"2026-09-06T03:45:08.58705Z","iopub.execute_input":"2026-09-06T03:45:08.587873Z","iopub.status.idle":"2026-09-06T03:45:08.593601Z","shell.execute_reply.started":"2026-09-06T03:45:08.587835Z","shell.execute_reply":"2026-09-06T03:45:08.592771Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"model_1 = define_model_1()\nprint(model_1.summary())","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-06T03:45:26.970831Z","iopub.execute_input":"2026-09-06T03:45:26.971642Z","iopub.status.idle":"2026-09-06T03:45:27.041299Z","shell.execute_reply.started":"2026-09-06T03:45:26.971605Z","shell.execute_reply":"2026-09-06T03:45:27.040172Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"datagen = ImageDataGenerator(rescale=1.0/255.0)\ntype(datagen)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-06T03:45:46.937362Z","iopub.execute_input":"2026-09-06T03:45:46.937734Z","iopub.status.idle":"2026-09-06T03:45:46.943597Z","shell.execute_reply.started":"2026-09-06T03:45:46.937705Z","shell.execute_reply":"2026-09-06T03:45:46.942728Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls dataset_dogs_vs_cats/train/","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-06T03:46:42.946292Z","iopub.execute_input":"2026-09-06T03:46:42.947157Z","iopub.status.idle":"2026-09-06T03:46:43.982274Z","shell.execute_reply.started":"2026-09-06T03:46:42.947123Z","shell.execute_reply":"2026-09-06T03:46:43.981028Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Hyperparameter => changable\nIMAGE_SIZE = (200, 200)\nBATCH_SIE = 64\nEPOCHS = 20","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-06T04:26:04.489302Z","iopub.execute_input":"2026-09-06T04:26:04.489912Z","iopub.status.idle":"2026-09-06T04:26:04.494025Z","shell.execute_reply.started":"2026-09-06T04:26:04.48988Z","shell.execute_reply":"2026-09-06T04:26:04.492998Z"}},"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":"2026-09-06T03:47:40.093794Z","iopub.execute_input":"2026-09-06T03:47:40.094588Z","iopub.status.idle":"2026-09-06T03:47:40.880483Z","shell.execute_reply.started":"2026-09-06T03:47:40.094549Z","shell.execute_reply":"2026-09-06T03:47:40.879374Z"}},"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":"2026-09-06T03:48:46.869209Z","iopub.execute_input":"2026-09-06T03:48:46.870099Z","iopub.status.idle":"2026-09-06T03:48:46.877028Z","shell.execute_reply.started":"2026-09-06T03:48:46.870066Z","shell.execute_reply":"2026-09-06T03:48:46.875812Z"}},"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":"2026-09-06T03:50:41.532527Z","iopub.execute_input":"2026-09-06T03:50:41.533471Z","iopub.status.idle":"2026-09-06T03:50:41.845259Z","shell.execute_reply.started":"2026-09-06T03:50:41.533414Z","shell.execute_reply":"2026-09-06T03:50:41.844478Z"}},"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":"2026-09-06T03:50:51.334769Z","iopub.execute_input":"2026-09-06T03:50:51.335578Z","iopub.status.idle":"2026-09-06T03:50:51.343722Z","shell.execute_reply.started":"2026-09-06T03:50:51.335541Z","shell.execute_reply":"2026-09-06T03:50:51.342761Z"}},"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":"2026-09-06T04:26:47.774653Z","iopub.execute_input":"2026-09-06T04:26:47.775628Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# learning curves\nsummarize_diagnostics(history_1)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-06T03:53:03.250975Z","iopub.execute_input":"2026-09-06T03:53:03.251838Z","iopub.status.idle":"2026-09-06T03:53:03.61848Z","shell.execute_reply.started":"2026-09-06T03:53:03.251803Z","shell.execute_reply":"2026-09-06T03:53:03.617683Z"}},"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":"2026-09-06T03:53:36.8458Z","iopub.execute_input":"2026-09-06T03:53:36.846265Z","iopub.status.idle":"2026-09-06T03:53:50.030067Z","shell.execute_reply.started":"2026-09-06T03:53:36.846234Z","shell.execute_reply":"2026-09-06T03:53:50.029037Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls ","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-06T03:54:02.428492Z","iopub.execute_input":"2026-09-06T03:54:02.428935Z","iopub.status.idle":"2026-09-06T03:54:03.504869Z","shell.execute_reply.started":"2026-09-06T03:54:02.428904Z","shell.execute_reply":"2026-09-06T03:54:03.503455Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"pwd","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-06T03:54:13.597443Z","iopub.execute_input":"2026-09-06T03:54:13.598442Z","iopub.status.idle":"2026-09-06T03:54:13.605616Z","shell.execute_reply.started":"2026-09-06T03:54:13.598404Z","shell.execute_reply":"2026-09-06T03:54:13.604526Z"}},"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":"2026-09-06T03:54:32.120108Z","iopub.execute_input":"2026-09-06T03:54:32.121119Z","iopub.status.idle":"2026-09-06T03:54:32.160173Z","shell.execute_reply.started":"2026-09-06T03:54:32.121085Z","shell.execute_reply":"2026-09-06T03:54:32.159171Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"df.columns","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-06T03:54:44.637266Z","iopub.execute_input":"2026-09-06T03:54:44.637768Z","iopub.status.idle":"2026-09-06T03:54:44.645355Z","shell.execute_reply.started":"2026-09-06T03:54:44.637722Z","shell.execute_reply":"2026-09-06T03:54:44.644371Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"image_files[:5], type(image_files), len(image_files)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-06T03:55:25.516986Z","iopub.execute_input":"2026-09-06T03:55:25.517325Z","iopub.status.idle":"2026-09-06T03:55:25.524106Z","shell.execute_reply.started":"2026-09-06T03:55:25.517298Z","shell.execute_reply":"2026-09-06T03:55:25.523073Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"df.describe()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-06T03:55:32.970134Z","iopub.execute_input":"2026-09-06T03:55:32.970472Z","iopub.status.idle":"2026-09-06T03:55:33.005827Z","shell.execute_reply.started":"2026-09-06T03:55:32.970446Z","shell.execute_reply":"2026-09-06T03:55:33.005007Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"df.loc[1]","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-06T03:55:47.45124Z","iopub.execute_input":"2026-09-06T03:55:47.451791Z","iopub.status.idle":"2026-09-06T03:55:47.462178Z","shell.execute_reply.started":"2026-09-06T03:55:47.451747Z","shell.execute_reply":"2026-09-06T03:55:47.459703Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"df.sample(5)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-06T03:56:15.963605Z","iopub.execute_input":"2026-09-06T03:56:15.964414Z","iopub.status.idle":"2026-09-06T03:56:15.9732Z","shell.execute_reply.started":"2026-09-06T03:56:15.964378Z","shell.execute_reply":"2026-09-06T03:56:15.971951Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"df['filename']","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-06T03:56:45.894449Z","iopub.execute_input":"2026-09-06T03:56:45.894818Z","iopub.status.idle":"2026-09-06T03:56:45.903612Z","shell.execute_reply.started":"2026-09-06T03:56:45.89479Z","shell.execute_reply":"2026-09-06T03:56:45.902547Z"}},"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":"2026-09-06T04:00:06.503791Z","iopub.execute_input":"2026-09-06T04:00:06.504757Z","iopub.status.idle":"2026-09-06T04:00:06.593987Z","shell.execute_reply.started":"2026-09-06T04:00:06.504723Z","shell.execute_reply":"2026-09-06T04:00:06.592895Z"}},"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":"2026-09-06T04:07:33.199236Z","iopub.execute_input":"2026-09-06T04:07:33.199945Z","iopub.status.idle":"2026-09-06T04:07:33.208934Z","shell.execute_reply.started":"2026-09-06T04:07:33.199907Z","shell.execute_reply":"2026-09-06T04:07:33.207731Z"}},"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":"2026-09-06T04:07:33.361011Z","iopub.execute_input":"2026-09-06T04:07:33.361394Z","iopub.status.idle":"2026-09-06T04:07:38.542652Z","shell.execute_reply.started":"2026-09-06T04:07:33.361365Z","shell.execute_reply":"2026-09-06T04:07:38.540927Z"}},"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":"2026-09-06T04:09:56.744542Z","iopub.execute_input":"2026-09-06T04:09:56.745475Z","iopub.status.idle":"2026-09-06T04:10:02.215182Z","shell.execute_reply.started":"2026-09-06T04:09:56.74544Z","shell.execute_reply":"2026-09-06T04:10:02.213851Z"}},"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":"2026-09-06T04:19:01.683414Z","iopub.execute_input":"2026-09-06T04:19:01.684203Z","iopub.status.idle":"2026-09-06T04:19:01.689807Z","shell.execute_reply.started":"2026-09-06T04:19:01.684168Z","shell.execute_reply":"2026-09-06T04:19:01.688759Z"}},"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":"2026-09-06T04:19:01.990554Z","iopub.execute_input":"2026-09-06T04:19:01.991349Z","iopub.status.idle":"2026-09-06T04:19:07.46172Z","shell.execute_reply.started":"2026-09-06T04:19:01.991315Z","shell.execute_reply":"2026-09-06T04:19:07.460193Z"}},"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":"2026-09-06T04:14:15.236434Z","iopub.execute_input":"2026-09-06T04:14:15.237218Z","iopub.status.idle":"2026-09-06T04:14:37.81748Z","shell.execute_reply.started":"2026-09-06T04:14:15.237173Z","shell.execute_reply":"2026-09-06T04:14:37.816737Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"preds[:10]","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-06T04:15:12.455004Z","iopub.execute_input":"2026-09-06T04:15:12.455329Z","iopub.status.idle":"2026-09-06T04:15:12.462568Z","shell.execute_reply.started":"2026-09-06T04:15:12.455303Z","shell.execute_reply":"2026-09-06T04:15:12.4611Z"}},"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":"2026-09-06T04:22:12.643043Z","iopub.execute_input":"2026-09-06T04:22:12.643743Z","iopub.status.idle":"2026-09-06T04:22:14.331142Z","shell.execute_reply.started":"2026-09-06T04:22:12.643707Z","shell.execute_reply":"2026-09-06T04:22:14.329836Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# end of 2026-09-06\nstop here","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-06T04:24:00.691974Z","iopub.execute_input":"2026-09-06T04:24:00.693219Z","iopub.status.idle":"2026-09-06T04:24:00.699103Z","shell.execute_reply.started":"2026-09-06T04:24:00.693183Z","shell.execute_reply":"2026-09-06T04:24:00.697694Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Transfer Learning","metadata":{"trusted":true},"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":"2026-02-16T07:08:34.328001Z","iopub.execute_input":"2026-02-16T07:08:34.328334Z","iopub.status.idle":"2026-02-16T07:08:34.33556Z","shell.execute_reply.started":"2026-02-16T07:08:34.328308Z","shell.execute_reply":"2026-02-16T07:08:34.334631Z"}},"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":"2026-02-16T07:06:10.528649Z","iopub.execute_input":"2026-02-16T07:06:10.529339Z","iopub.status.idle":"2026-02-16T07:06:10.532994Z","shell.execute_reply.started":"2026-02-16T07:06:10.529306Z","shell.execute_reply":"2026-02-16T07:06:10.532148Z"}},"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":"2026-02-16T07:06:18.061672Z","iopub.execute_input":"2026-02-16T07:06:18.062335Z","iopub.status.idle":"2026-02-16T07:06:18.065876Z","shell.execute_reply.started":"2026-02-16T07:06:18.062302Z","shell.execute_reply":"2026-02-16T07:06:18.064909Z"}},"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":"2026-02-16T07:03:43.521957Z","iopub.execute_input":"2026-02-16T07:03:43.522229Z","iopub.status.idle":"2026-02-16T07:03:43.525953Z","shell.execute_reply.started":"2026-02-16T07:03:43.522206Z","shell.execute_reply":"2026-02-16T07:03:43.525102Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# load model\n# model_16_top = VGG16(include_top=True, input_shape=(224, 224, 3))\n# model_16_top.summary()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-02-16T07:03:43.527034Z","iopub.execute_input":"2026-02-16T07:03:43.527566Z","iopub.status.idle":"2026-02-16T07:03:43.533544Z","shell.execute_reply.started":"2026-02-16T07:03:43.527544Z","shell.execute_reply":"2026-02-16T07:03:43.532816Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"vgg16_model = define_model_vgg16()\nvgg16_model.summary()\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-02-16T07:08:38.694916Z","iopub.execute_input":"2026-02-16T07:08:38.695524Z","iopub.status.idle":"2026-02-16T07:08:39.071031Z","shell.execute_reply.started":"2026-02-16T07:08:38.695491Z","shell.execute_reply":"2026-02-16T07:08:39.069481Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# for index, layer in enumerate(vgg16_model.layers):\n#     print(index, layer.name, layer.trainable)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-02-16T07:03:43.910675Z","iopub.execute_input":"2026-02-16T07:03:43.910954Z","iopub.status.idle":"2026-02-16T07:03:43.914695Z","shell.execute_reply.started":"2026-02-16T07:03:43.91093Z","shell.execute_reply":"2026-02-16T07:03:43.913724Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# for index, layer in enumerate(vgg16_model.layers[-7:]):\n#     print(index, layer.name, layer.trainable)\n    ","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-02-16T07:03:43.915763Z","iopub.execute_input":"2026-02-16T07:03:43.916044Z","iopub.status.idle":"2026-02-16T07:03:43.92276Z","shell.execute_reply.started":"2026-02-16T07:03:43.916014Z","shell.execute_reply":"2026-02-16T07:03:43.921957Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# for index, layer in enumerate(vgg16_model.layers[-7:]):\n#     layer.trainable = True\n#     print(index, layer.name, layer.trainable)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-02-16T07:03:43.923787Z","iopub.execute_input":"2026-02-16T07:03:43.924063Z","iopub.status.idle":"2026-02-16T07:03:43.930359Z","shell.execute_reply.started":"2026-02-16T07:03:43.924041Z","shell.execute_reply":"2026-02-16T07:03:43.9295Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# for index, layer in enumerate(vgg16_model.layers):\n#     if index >= 15:\n#         layer.trainable = True\n\n# for index, layer in enumerate(vgg16_model.layers):\n#     print(index, layer.name, layer.trainable)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-02-16T07:05:42.844519Z","iopub.execute_input":"2026-02-16T07:05:42.845298Z","iopub.status.idle":"2026-02-16T07:05:42.849027Z","shell.execute_reply.started":"2026-02-16T07:05:42.845261Z","shell.execute_reply":"2026-02-16T07:05:42.848238Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"id(vgg16_model)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-02-16T07:08:49.353611Z","iopub.execute_input":"2026-02-16T07:08:49.35397Z","iopub.status.idle":"2026-02-16T07:08:49.35955Z","shell.execute_reply.started":"2026-02-16T07:08:49.353942Z","shell.execute_reply":"2026-02-16T07:08:49.358663Z"}},"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":"2026-02-16T07:08:52.691725Z","iopub.execute_input":"2026-02-16T07:08:52.692533Z","iopub.status.idle":"2026-02-16T07:15:06.05523Z","shell.execute_reply.started":"2026-02-16T07:08:52.692496Z","shell.execute_reply":"2026-02-16T07:15:06.054255Z"}},"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":"2026-02-16T07:16:16.626158Z","iopub.execute_input":"2026-02-16T07:16:16.6271Z","iopub.status.idle":"2026-02-16T07:17:18.360983Z","shell.execute_reply.started":"2026-02-16T07:16:16.627065Z","shell.execute_reply":"2026-02-16T07:17:18.360184Z"}},"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":"2026-02-16T07:39:22.0384Z","iopub.execute_input":"2026-02-16T07:39:22.03875Z","iopub.status.idle":"2026-02-16T07:39:22.045262Z","shell.execute_reply.started":"2026-02-16T07:39:22.038719Z","shell.execute_reply":"2026-02-16T07:39:22.044409Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"model_inceptionv3 = define_model_inceptionv3()\nprint(id(model_inceptionv3))\n# model_inceptionv3.summary()","metadata":{"execution":{"iopub.status.busy":"2026-02-16T07:39:22.35245Z","iopub.execute_input":"2026-02-16T07:39:22.352743Z","iopub.status.idle":"2026-02-16T07:39:24.449375Z","shell.execute_reply.started":"2026-02-16T07:39:22.352718Z","shell.execute_reply":"2026-02-16T07:39:24.448546Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import numpy as np\nfrom tensorflow.keras import backend as K\n\ntrainable_params = int(np.sum([K.count_params(w) for w in model_inceptionv3.trainable_weights]))\nprint(trainable_params)\n","metadata":{"trusted":true,"scrolled":true,"execution":{"iopub.status.busy":"2026-02-16T07:39:24.451116Z","iopub.execute_input":"2026-02-16T07:39:24.451727Z","iopub.status.idle":"2026-02-16T07:39:24.457165Z","shell.execute_reply.started":"2026-02-16T07:39:24.451691Z","shell.execute_reply":"2026-02-16T07:39:24.456303Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"from tensorflow.keras import backend as K\n\nfor w in model_inceptionv3.trainable_weights:\n    print(w.name, K.count_params(w))\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-02-16T07:39:24.458253Z","iopub.execute_input":"2026-02-16T07:39:24.458457Z","iopub.status.idle":"2026-02-16T07:39:24.468376Z","shell.execute_reply.started":"2026-02-16T07:39:24.458437Z","shell.execute_reply":"2026-02-16T07:39:24.467705Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# fit model\nmodel_inceptionv3.reset_states()\nhistory_inceptionv3 = model_inceptionv3.fit(\n    train_it, \n    steps_per_epoch=len(train_it),\n    validation_data=val_it,\n    validation_steps=len(val_it),\n    epochs=3, verbose=1,\n    callbacks = [PlotLossesKeras()]\n    )","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import matplotlib.pyplot as plt\n\ndef plot_images_with_labels(images, labels, train_log, set_label, save=False):\n    \"\"\"\n    Plots a grid of images with their corresponding labels and saves the figure.\n    \n    Args:\n    - images (list or np.array): List of images to be displayed.\n    - labels (np.array): Array of one-hot encoded labels.\n    - train_log (str): The directory or log name to save the plot.\n    - set_label (str): The specific set label (e.g., \"train\", \"validation\", etc.).\n    - config (dict): Configuration dictionary containing image dimensions.\n    \n    Returns:\n    - None: Displays and saves the plot.\n    \"\"\"\n    # Convert one-hot encoded labels to class indices\n    class_indices = labels\n\n    # Create subplots\n    fig, axes = plt.subplots(3, 4, figsize=(14, 10), dpi=120)\n    axes = axes.flatten()\n\n    for img, label_idx, ax in zip(images, class_indices, axes):\n        # Undo any preprocessing (like rescaling for pre-trained models)\n        if np.max(img) == 1:\n            img = img * 255\n\n        # Display the image\n        img_shape = (224, 224, 3)\n        ax.imshow(img.astype(\"uint8\"))\n        # ax.imshow(img)\n\n        # Set the title to the corresponding class label\n        ax.set_title(f\"Label: {label_idx}\", fontsize=18)\n        ax.axis('on')\n\n    # Set the overall title for the figure\n    plot_title = f\"{train_log}-{set_label}\"\n    plt.suptitle(plot_title, fontsize=18)\n\n    # Show the plot\n    plt.show()\n\n    # Save the figure\n    if save:\n        plot_file = os.path.join(train_log, f\"{plot_title}.png\")\n        fig.savefig(plot_file, dpi=120)\n        print(f'Saved {plot_file}')\n","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# plot_images_with_labels(images, labels, \"Dog-Cat\", \"Training\")","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# for index, layer in enumerate(model.layers):\n#     print(index, layer.output.shape)","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# # mark loaded layers as not trainable\n# for index, layer in enumerate(model.layers[:15]):\n#     print(index, layer.name, layer.output_shape)\n#     layer.trainable = False\n    \n# for index, layer in enumerate(model.layers[15:]):\n#     print(index, layer.name, layer.output_shape)\n#     layer.trainable = True","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# evaluate model\n_, acc = model_inceptionv3.evaluate(test_it, steps=len(test_it), verbose=1)\nprint('> %.3f' % (acc * 100.0))\n# learning curves\n# summarize_diagnostics(history)\n\n# best_model = 'vgg16_model.hdf5'\n# my_model.save(best_model)","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"images = test_it.__next__()\nimages.shape","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# 5 first img: 1, 0, 1, 1, 0\nimages_to_predict = images[:5]\nimages_to_predict.shape","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"probs = model_inceptionv3.predict(images_to_predict, verbose=1)\nprobs","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"Make Prediction","metadata":{}},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null}]}