{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.10.12","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"nvidiaTeslaT4","dataSources":[{"sourceId":3362,"databundleVersionId":31148,"sourceType":"competition"}],"dockerImageVersionId":30627,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":true}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"# This Python 3 environment comes with many helpful analytics libraries installed\n# It is defined by the kaggle/python Docker image: https://github.com/kaggle/docker-python\n# For example, here's several helpful packages to load\n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n\n# Input data files are available in the read-only \"../input/\" directory\n# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\n\nimport os\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))\n\n# You can write up to 20GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using \"Save & Run All\" \n# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","execution":{"iopub.status.busy":"2026-09-12T09:30:20.954148Z","iopub.execute_input":"2026-09-12T09:30:20.954449Z","iopub.status.idle":"2026-09-12T09:30:21.262232Z","shell.execute_reply.started":"2026-09-12T09:30:20.954425Z","shell.execute_reply":"2026-09-12T09:30:21.261158Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"!python --version","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T09:30:21.264360Z","iopub.execute_input":"2026-09-12T09:30:21.264743Z","iopub.status.idle":"2026-09-12T09:30:22.316157Z","shell.execute_reply.started":"2026-09-12T09:30:21.264719Z","shell.execute_reply":"2026-09-12T09:30:22.315107Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"!uname --all","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T09:30:22.317699Z","iopub.execute_input":"2026-09-12T09:30:22.317956Z","iopub.status.idle":"2026-09-12T09:30:23.296428Z","shell.execute_reply.started":"2026-09-12T09:30:22.317933Z","shell.execute_reply":"2026-09-12T09:30:23.293932Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import os\nprint(os.listdir(\"../input\"))\n\nimport zipfile\n\nwith zipfile.ZipFile(\"/kaggle/input/dogs-vs-cats/test1.zip\",\"r\") as z:\n    z.extractall(\".\")\n    \nwith zipfile.ZipFile(\"/kaggle/input/dogs-vs-cats/train.zip\",\"r\") as z:\n    z.extractall(\".\")","metadata":{"execution":{"iopub.status.busy":"2026-09-12T09:30:23.298926Z","iopub.execute_input":"2026-09-12T09:30:23.302975Z","iopub.status.idle":"2026-09-12T09:30:33.957800Z","shell.execute_reply.started":"2026-09-12T09:30:23.302922Z","shell.execute_reply":"2026-09-12T09:30:33.956771Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T09:30:33.959151Z","iopub.execute_input":"2026-09-12T09:30:33.960518Z","iopub.status.idle":"2026-09-12T09:30:34.929520Z","shell.execute_reply.started":"2026-09-12T09:30:33.960487Z","shell.execute_reply":"2026-09-12T09:30:34.928667Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -l","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T09:30:34.931104Z","iopub.execute_input":"2026-09-12T09:30:34.931489Z","iopub.status.idle":"2026-09-12T09:30:35.910737Z","shell.execute_reply.started":"2026-09-12T09:30:34.931455Z","shell.execute_reply":"2026-09-12T09:30:35.909893Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls test1","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T09:30:35.913597Z","iopub.execute_input":"2026-09-12T09:30:35.913891Z","iopub.status.idle":"2026-09-12T09:30:36.932405Z","shell.execute_reply.started":"2026-09-12T09:30:35.913861Z","shell.execute_reply":"2026-09-12T09:30:36.931133Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls test1/ | wc -l","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T09:30:36.934802Z","iopub.execute_input":"2026-09-12T09:30:36.935200Z","iopub.status.idle":"2026-09-12T09:30:37.965862Z","shell.execute_reply.started":"2026-09-12T09:30:36.935147Z","shell.execute_reply":"2026-09-12T09:30:37.964977Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls train/ | wc -l","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T09:30:37.967262Z","iopub.execute_input":"2026-09-12T09:30:37.967566Z","iopub.status.idle":"2026-09-12T09:30:39.017413Z","shell.execute_reply.started":"2026-09-12T09:30:37.967541Z","shell.execute_reply":"2026-09-12T09:30:39.016323Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"#ls train/","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T09:30:39.019466Z","iopub.execute_input":"2026-09-12T09:30:39.019834Z","iopub.status.idle":"2026-09-12T09:30:39.023796Z","shell.execute_reply.started":"2026-09-12T09:30:39.019799Z","shell.execute_reply":"2026-09-12T09:30:39.023026Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"pwd","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T09:30:39.024855Z","iopub.execute_input":"2026-09-12T09:30:39.025163Z","iopub.status.idle":"2026-09-12T09:30:39.040695Z","shell.execute_reply.started":"2026-09-12T09:30:39.025141Z","shell.execute_reply":"2026-09-12T09:30:39.039762Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T09:30:39.041878Z","iopub.execute_input":"2026-09-12T09:30:39.042228Z","iopub.status.idle":"2026-09-12T09:30:40.010374Z","shell.execute_reply.started":"2026-09-12T09:30:39.042168Z","shell.execute_reply":"2026-09-12T09:30:40.009405Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -U train | head -n 10","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T09:30:40.011900Z","iopub.execute_input":"2026-09-12T09:30:40.012330Z","iopub.status.idle":"2026-09-12T09:30:41.043063Z","shell.execute_reply.started":"2026-09-12T09:30:40.012302Z","shell.execute_reply":"2026-09-12T09:30:41.042120Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -U test1 | head -n 10","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T09:30:41.044533Z","iopub.execute_input":"2026-09-12T09:30:41.044823Z","iopub.status.idle":"2026-09-12T09:30:42.045342Z","shell.execute_reply.started":"2026-09-12T09:30:41.044798Z","shell.execute_reply":"2026-09-12T09:30:42.044229Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# plot dog photos from the dogs vs cats dataset\nfrom matplotlib import pyplot\n# from matplotlib import pyplot as plt\nfrom matplotlib.image import imread\n# define location of dataset\nfolder = 'train/'\n# plot first few images\nfor i in range(9):\n\t# define subplot\n\tpyplot.subplot(330 + 1 + i)\n\t# define filename\n\tfilename = folder + 'dog.' + str(i) + '.jpg'\n\t# load image pixels\n\timage = imread(filename)\n\t# plot raw pixel data\n\tpyplot.imshow(image)\n# show the figure\npyplot.show()","metadata":{"execution":{"iopub.status.busy":"2026-09-12T09:30:42.046935Z","iopub.execute_input":"2026-09-12T09:30:42.047646Z","iopub.status.idle":"2026-09-12T09:30:43.038765Z","shell.execute_reply.started":"2026-09-12T09:30:42.047607Z","shell.execute_reply":"2026-09-12T09:30:43.038044Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# plot cat photos from the dogs vs cats dataset\nfrom matplotlib import pyplot\nfrom matplotlib.image import imread\n# define location of dataset\nfolder = 'train/'\n# plot first few images\nfor i in range(9):\n\t# define subplot\n\tpyplot.subplot(330 + 1 + i)\n\t# define filename\n\tfilename = folder + 'cat.' + str(i) + '.jpg'\n\t# load image pixels\n\timage = imread(filename)\n\t# plot raw pixel data\n\tpyplot.imshow(image)\n# show the figure\npyplot.show()","metadata":{"execution":{"iopub.status.busy":"2026-09-12T09:30:43.040949Z","iopub.execute_input":"2026-09-12T09:30:43.041480Z","iopub.status.idle":"2026-09-12T09:30:44.010958Z","shell.execute_reply.started":"2026-09-12T09:30:43.041455Z","shell.execute_reply":"2026-09-12T09:30:44.010037Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"!python --version","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T09:30:44.012075Z","iopub.execute_input":"2026-09-12T09:30:44.012369Z","iopub.status.idle":"2026-09-12T09:30:44.984636Z","shell.execute_reply.started":"2026-09-12T09:30:44.012345Z","shell.execute_reply":"2026-09-12T09:30:44.983578Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import tensorflow\nprint(tensorflow.__version__)\n\nimport keras\nprint(keras.__version__)\n\nimport tensorflow.keras\nprint(tensorflow.__version__)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T09:30:44.986373Z","iopub.execute_input":"2026-09-12T09:30:44.987304Z","iopub.status.idle":"2026-09-12T09:30:56.447009Z","shell.execute_reply.started":"2026-09-12T09:30:44.987264Z","shell.execute_reply":"2026-09-12T09:30:56.446128Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# load dogs vs cats dataset, reshape and save to a new file\nfrom os import listdir\nfrom numpy import asarray\nfrom numpy import save\nfrom keras.preprocessing.image import load_img\nfrom keras.preprocessing.image import img_to_array","metadata":{"execution":{"iopub.status.busy":"2026-09-12T09:30:56.448115Z","iopub.execute_input":"2026-09-12T09:30:56.448911Z","iopub.status.idle":"2026-09-12T09:30:56.452956Z","shell.execute_reply.started":"2026-09-12T09:30:56.448883Z","shell.execute_reply":"2026-09-12T09:30:56.451926Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# define location of dataset\nfolder = 'train/'\nphotos, labels = list(), list()\n# enumerate files in the directory\nfor file in listdir(folder):\n\t# determine class\n\toutput = 0.0\n\tif file.startswith('dog'):\n\t\toutput = 1.0\n\t# load image\n\tphoto = load_img(folder + file, target_size=(200, 200))\n\t# convert to numpy array\n\tphoto = img_to_array(photo)\n\t# store\n\tphotos.append(photo)\n\tlabels.append(output)\n# convert to a numpy arrays\nphotos = asarray(photos)\nlabels = asarray(labels)\nprint(photos.shape, labels.shape)\n# save the reshaped photos\nsave('dogs_vs_cats_photos.npy', photos)\nsave('dogs_vs_cats_labels.npy', labels)","metadata":{"execution":{"iopub.status.busy":"2024-01-27T03:36:15.416611Z","iopub.execute_input":"2024-01-27T03:36:15.417128Z","iopub.status.idle":"2024-01-27T03:36:38.886396Z","shell.execute_reply.started":"2024-01-27T03:36:15.417101Z","shell.execute_reply":"2024-01-27T03:36:38.883149Z"}}},{"cell_type":"markdown","source":"# load and confirm the shape\nfrom numpy import load\nphotos = load('dogs_vs_cats_photos.npy')\nlabels = load('dogs_vs_cats_labels.npy')","metadata":{"execution":{"iopub.status.busy":"2024-01-27T03:36:38.88711Z","iopub.status.idle":"2024-01-27T03:36:38.887458Z","shell.execute_reply.started":"2024-01-27T03:36:38.887281Z","shell.execute_reply":"2024-01-27T03:36:38.887296Z"}}},{"cell_type":"code","source":"# organize dataset into a useful structure\nfrom os import makedirs\nfrom os import listdir\nfrom shutil import copyfile\nfrom random import seed\nfrom random import random","metadata":{"execution":{"iopub.status.busy":"2026-09-12T09:30:56.454222Z","iopub.execute_input":"2026-09-12T09:30:56.454810Z","iopub.status.idle":"2026-09-12T09:30:56.468560Z","shell.execute_reply.started":"2026-09-12T09:30:56.454771Z","shell.execute_reply":"2026-09-12T09:30:56.467821Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# create directories\ndataset_home = 'dataset_dogs_vs_cats/'\nsubdirs = ['train/', 'test/'] #test==>validation\nfor subdir in subdirs:\n    # create label subdirectories\n    labeldirs = ['dogs/', 'cats/']\n    for labldir in labeldirs:\n        newdir = dataset_home + subdir + labldir       \n        makedirs(newdir, exist_ok=True)\n        print(newdir)","metadata":{"execution":{"iopub.status.busy":"2026-09-12T09:30:56.469479Z","iopub.execute_input":"2026-09-12T09:30:56.470062Z","iopub.status.idle":"2026-09-12T09:30:56.478680Z","shell.execute_reply.started":"2026-09-12T09:30:56.470011Z","shell.execute_reply":"2026-09-12T09:30:56.477729Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -l dataset_dogs_vs_cats/train/dogs/ | wc -l","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T09:30:56.484334Z","iopub.execute_input":"2026-09-12T09:30:56.484818Z","iopub.status.idle":"2026-09-12T09:30:57.469797Z","shell.execute_reply.started":"2026-09-12T09:30:56.484795Z","shell.execute_reply":"2026-09-12T09:30:57.468617Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -l","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T09:30:57.471351Z","iopub.execute_input":"2026-09-12T09:30:57.471608Z","iopub.status.idle":"2026-09-12T09:30:58.487254Z","shell.execute_reply.started":"2026-09-12T09:30:57.471586Z","shell.execute_reply":"2026-09-12T09:30:58.486027Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -l dataset_dogs_vs_cats/train","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T09:30:58.488846Z","iopub.execute_input":"2026-09-12T09:30:58.489251Z","iopub.status.idle":"2026-09-12T09:30:59.466423Z","shell.execute_reply.started":"2026-09-12T09:30:58.489214Z","shell.execute_reply":"2026-09-12T09:30:59.465481Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -l dataset_dogs_vs_cats/test #validation","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T09:30:59.468054Z","iopub.execute_input":"2026-09-12T09:30:59.468466Z","iopub.status.idle":"2026-09-12T09:31:00.474945Z","shell.execute_reply.started":"2026-09-12T09:30:59.468440Z","shell.execute_reply":"2026-09-12T09:31:00.473682Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# seed random number generator\nseed(1337)\n# define ratio of pictures to use for validation\nval_ratio = 0.25 #changable\n# copy training dataset images into subdirectories\nsrc_directory = 'train/'\n\nfor file in listdir(src_directory):\n\tsrc = src_directory + '/' + file\n\tdst_dir = 'train/'\n\tif random() < val_ratio:\n\t\tdst_dir = 'test/'\n\tif file.startswith('cat'):\n\t\tdst = dataset_home + dst_dir + 'cats/'  + file\n\t\tcopyfile(src, dst)\n\telif file.startswith('dog'):\n\t\tdst = dataset_home + dst_dir + 'dogs/'  + file\n\t\tcopyfile(src, dst)","metadata":{"execution":{"iopub.status.busy":"2026-09-12T09:31:00.476420Z","iopub.execute_input":"2026-09-12T09:31:00.476712Z","iopub.status.idle":"2026-09-12T09:31:02.493845Z","shell.execute_reply.started":"2026-09-12T09:31:00.476688Z","shell.execute_reply":"2026-09-12T09:31:02.492978Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"print(src)\nprint(dst)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T09:31:02.494898Z","iopub.execute_input":"2026-09-12T09:31:02.495452Z","iopub.status.idle":"2026-09-12T09:31:02.500003Z","shell.execute_reply.started":"2026-09-12T09:31:02.495426Z","shell.execute_reply":"2026-09-12T09:31:02.499247Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"!ls -l dataset_dogs_vs_cats/train/dogs | wc -l\n!ls -l dataset_dogs_vs_cats/train/cats | wc -l","metadata":{"execution":{"iopub.status.busy":"2026-09-12T09:31:02.501105Z","iopub.execute_input":"2026-09-12T09:31:02.501665Z","iopub.status.idle":"2026-09-12T09:31:04.676705Z","shell.execute_reply.started":"2026-09-12T09:31:02.501642Z","shell.execute_reply":"2026-09-12T09:31:04.675781Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"#validation set\n!ls -l dataset_dogs_vs_cats/test/dogs | wc -l\n!ls -l dataset_dogs_vs_cats/test/cats | wc -l","metadata":{"execution":{"iopub.status.busy":"2026-09-12T09:31:04.678275Z","iopub.execute_input":"2026-09-12T09:31:04.678668Z","iopub.status.idle":"2026-09-12T09:31:06.750698Z","shell.execute_reply.started":"2026-09-12T09:31:04.678633Z","shell.execute_reply":"2026-09-12T09:31:06.749133Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"!pip -q install livelossplot==0.5.5","metadata":{"execution":{"iopub.status.busy":"2026-09-12T09:31:06.752700Z","iopub.execute_input":"2026-09-12T09:31:06.753130Z","iopub.status.idle":"2026-09-12T09:31:16.637567Z","shell.execute_reply.started":"2026-09-12T09:31:06.753089Z","shell.execute_reply":"2026-09-12T09:31:16.636492Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"from livelossplot import PlotLossesKeras","metadata":{"execution":{"iopub.status.busy":"2026-09-12T09:31:16.639014Z","iopub.execute_input":"2026-09-12T09:31:16.639329Z","iopub.status.idle":"2026-09-12T09:31:16.656943Z","shell.execute_reply.started":"2026-09-12T09:31:16.639303Z","shell.execute_reply":"2026-09-12T09:31:16.656353Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"Prepare Final Dataset","metadata":{}},{"cell_type":"markdown","source":"# Start tutorial\n# Develop a Baseline CNN Model","metadata":{}},{"cell_type":"code","source":"# https://keras.io/api/applications/","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T09:31:16.658220Z","iopub.execute_input":"2026-09-12T09:31:16.658589Z","iopub.status.idle":"2026-09-12T09:31:16.662962Z","shell.execute_reply.started":"2026-09-12T09:31:16.658555Z","shell.execute_reply":"2026-09-12T09:31:16.662107Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# baseline model for the dogs vs cats dataset\nimport sys\nfrom matplotlib import pyplot\nfrom keras.utils import to_categorical\nfrom keras.models import Sequential\nfrom keras.layers import Conv2D\nfrom keras.layers import MaxPooling2D\nfrom keras.layers import Dense\nfrom keras.layers import Flatten\nfrom keras.optimizers import SGD\nfrom keras.preprocessing.image import ImageDataGenerator","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T09:31:16.664013Z","iopub.execute_input":"2026-09-12T09:31:16.664615Z","iopub.status.idle":"2026-09-12T09:31:16.671702Z","shell.execute_reply.started":"2026-09-12T09:31:16.664591Z","shell.execute_reply":"2026-09-12T09:31:16.671043Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"model = Sequential()\ntype(model)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T09:31:16.672734Z","iopub.execute_input":"2026-09-12T09:31:16.673276Z","iopub.status.idle":"2026-09-12T09:31:18.144621Z","shell.execute_reply.started":"2026-09-12T09:31:16.673245Z","shell.execute_reply":"2026-09-12T09:31:18.143843Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"model = Sequential()\n\nmodel.add(Conv2D(32,\n                 (3, 3),\n                 activation='relu',\n                 input_shape=(200, 200, 3)\n                )\n         )\n\nmodel.add(MaxPooling2D((2, 2)))\n\nmodel.add(Flatten())\n\nmodel.add(Dense(128, activation='relu'))\n\nmodel.add(Dense(1, activation='sigmoid'))\n\nprint(model.summary())","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T09:31:18.145832Z","iopub.execute_input":"2026-09-12T09:31:18.146178Z","iopub.status.idle":"2026-09-12T09:31:18.463008Z","shell.execute_reply.started":"2026-09-12T09:31:18.146147Z","shell.execute_reply":"2026-09-12T09:31:18.462059Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"model = Sequential()\n\nmodel.add(Conv2D(32,\n                 (3, 3),\n                 activation='relu',\n                 input_shape=(200, 200, 3)\n                )\n         )\n\nmodel.add(MaxPooling2D((2, 2)))\n\nmodel.add(Flatten())\n\nmodel.add(Dense(128, activation='relu'))\n\nmodel.add(Dense(2, activation='softmax'))\n\nprint(model.summary())","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T09:31:18.464077Z","iopub.execute_input":"2026-09-12T09:31:18.464995Z","iopub.status.idle":"2026-09-12T09:31:18.528600Z","shell.execute_reply.started":"2026-09-12T09:31:18.464956Z","shell.execute_reply":"2026-09-12T09:31:18.527682Z"}},"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":"2026-09-12T09:31:18.529664Z","iopub.execute_input":"2026-09-12T09:31:18.529999Z","iopub.status.idle":"2026-09-12T09:31:18.535557Z","shell.execute_reply.started":"2026-09-12T09:31:18.529977Z","shell.execute_reply":"2026-09-12T09:31:18.534631Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"model_1 = define_model_1()\nprint(model_1.summary())","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T09:31:18.536770Z","iopub.execute_input":"2026-09-12T09:31:18.537175Z","iopub.status.idle":"2026-09-12T09:31:18.604213Z","shell.execute_reply.started":"2026-09-12T09:31:18.537140Z","shell.execute_reply":"2026-09-12T09:31:18.603469Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# plot diagnostic learning curves\ndef summarize_diagnostics(history):\n    # plot loss\n    pyplot.subplot(211)\n    pyplot.title('Cross Entropy Loss')\n    pyplot.plot(history.history['loss'], color='blue', label='train')\n    pyplot.plot(history.history['val_loss'], color='orange', label='test')\n    # plot accuracy\n    pyplot.subplot(212)\n    pyplot.title('Classification Accuracy')\n    pyplot.plot(history.history['accuracy'], color='blue', label='train')\n    pyplot.plot(history.history['val_accuracy'], color='orange', label='test')\n    pyplot.show()\n    \n    # save plot to file\n    filename = sys.argv[0].split('/')[-1]\n    pyplot.savefig(filename + '_plot.png') \n    pyplot.close()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T09:31:18.605482Z","iopub.execute_input":"2026-09-12T09:31:18.606042Z","iopub.status.idle":"2026-09-12T09:31:18.611247Z","shell.execute_reply.started":"2026-09-12T09:31:18.606018Z","shell.execute_reply":"2026-09-12T09:31:18.610376Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# run the test harness for evaluating a model, not recommend to call this function\ndef run_test_harness():\n\t# define model\n\tmodel = define_model()\n\t# create data generator\n\tdatagen = ImageDataGenerator(rescale=1.0/255.0)\n\t# prepare iterators\n\ttrain_it = datagen.flow_from_directory('dataset_dogs_vs_cats/train/',\n\t\tclass_mode='binary', batch_size=64, target_size=(200, 200))\n\ttest_it = datagen.flow_from_directory('dataset_dogs_vs_cats/test/',\n\t\tclass_mode='binary', batch_size=64, target_size=(200, 200))\n\t# fit model\n\thistory = model.fit_generator(train_it, steps_per_epoch=len(train_it),\n\t\tvalidation_data=test_it, validation_steps=len(test_it), epochs=20, verbose=0)\n\t# evaluate model\n\t_, acc = model.evaluate_generator(test_it, steps=len(test_it), verbose=0)\n\tprint('> %.3f' % (acc * 100.0))","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T09:31:18.612331Z","iopub.execute_input":"2026-09-12T09:31:18.612613Z","iopub.status.idle":"2026-09-12T09:31:18.620163Z","shell.execute_reply.started":"2026-09-12T09:31:18.612580Z","shell.execute_reply":"2026-09-12T09:31:18.619166Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"model_1 = define_model_1()\nprint(model_1.summary())","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T09:31:18.621260Z","iopub.execute_input":"2026-09-12T09:31:18.621472Z","iopub.status.idle":"2026-09-12T09:31:18.688666Z","shell.execute_reply.started":"2026-09-12T09:31:18.621453Z","shell.execute_reply":"2026-09-12T09:31:18.685115Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"datagen = ImageDataGenerator(rescale=1.0/255.0)\ntype(datagen)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T09:31:18.689647Z","iopub.execute_input":"2026-09-12T09:31:18.689951Z","iopub.status.idle":"2026-09-12T09:31:18.695160Z","shell.execute_reply.started":"2026-09-12T09:31:18.689929Z","shell.execute_reply":"2026-09-12T09:31:18.694254Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls dataset_dogs_vs_cats/train/","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T09:31:18.696571Z","iopub.execute_input":"2026-09-12T09:31:18.696979Z","iopub.status.idle":"2026-09-12T09:31:19.682765Z","shell.execute_reply.started":"2026-09-12T09:31:18.696949Z","shell.execute_reply":"2026-09-12T09:31:19.681855Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Hyperparameter => changable\nIMAGE_SIZE = (200, 200)\nBATCH_SIZE = 64\nEPOCHS = 20","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T09:31:19.684015Z","iopub.execute_input":"2026-09-12T09:31:19.684574Z","iopub.status.idle":"2026-09-12T09:31:19.689017Z","shell.execute_reply.started":"2026-09-12T09:31:19.684547Z","shell.execute_reply":"2026-09-12T09:31:19.688252Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"train_it = datagen.flow_from_directory('dataset_dogs_vs_cats/train/',\n\t\tclass_mode='binary',\n        batch_size=BATCH_SIZE, \n        target_size=IMAGE_SIZE\n)\ntype(train_it)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T09:31:19.690093Z","iopub.execute_input":"2026-09-12T09:31:19.691050Z","iopub.status.idle":"2026-09-12T09:31:20.172056Z","shell.execute_reply.started":"2026-09-12T09:31:19.691024Z","shell.execute_reply":"2026-09-12T09:31:20.171087Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"len(train_it), len(train_it.classes), train_it.classes[:10]","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T09:31:20.173230Z","iopub.execute_input":"2026-09-12T09:31:20.173852Z","iopub.status.idle":"2026-09-12T09:31:20.180530Z","shell.execute_reply.started":"2026-09-12T09:31:20.173825Z","shell.execute_reply":"2026-09-12T09:31:20.179546Z"}},"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":"2026-09-12T09:31:20.181898Z","iopub.execute_input":"2026-09-12T09:31:20.182295Z","iopub.status.idle":"2026-09-12T09:31:20.458671Z","shell.execute_reply.started":"2026-09-12T09:31:20.182258Z","shell.execute_reply":"2026-09-12T09:31:20.457978Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"len(val_it), len(val_it.classes), val_it.classes[-10:]","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T09:31:20.459644Z","iopub.execute_input":"2026-09-12T09:31:20.459900Z","iopub.status.idle":"2026-09-12T09:31:20.465781Z","shell.execute_reply.started":"2026-09-12T09:31:20.459878Z","shell.execute_reply":"2026-09-12T09:31:20.464946Z"}},"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":"2026-09-12T09:31:20.466863Z","iopub.execute_input":"2026-09-12T09:31:20.467409Z","iopub.status.idle":"2026-09-12T09:46:05.331281Z","shell.execute_reply.started":"2026-09-12T09:31:20.467385Z","shell.execute_reply":"2026-09-12T09:46:05.330163Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# learning curves\nsummarize_diagnostics(history_1)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T09:46:05.332672Z","iopub.execute_input":"2026-09-12T09:46:05.333733Z","iopub.status.idle":"2026-09-12T09:46:05.737891Z","shell.execute_reply.started":"2026-09-12T09:46:05.333704Z","shell.execute_reply":"2026-09-12T09:46:05.736716Z"}},"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":"2026-09-12T09:46:05.739302Z","iopub.execute_input":"2026-09-12T09:46:05.739670Z","iopub.status.idle":"2026-09-12T09:46:17.944715Z","shell.execute_reply.started":"2026-09-12T09:46:05.739643Z","shell.execute_reply":"2026-09-12T09:46:17.943840Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls ","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T09:46:17.946145Z","iopub.execute_input":"2026-09-12T09:46:17.946490Z","iopub.status.idle":"2026-09-12T09:46:19.043016Z","shell.execute_reply.started":"2026-09-12T09:46:17.946464Z","shell.execute_reply":"2026-09-12T09:46:19.041490Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"pwd","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T09:46:19.045137Z","iopub.execute_input":"2026-09-12T09:46:19.045586Z","iopub.status.idle":"2026-09-12T09:46:19.053302Z","shell.execute_reply.started":"2026-09-12T09:46:19.045555Z","shell.execute_reply":"2026-09-12T09:46:19.052315Z"}},"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":"2026-09-12T09:46:19.054646Z","iopub.execute_input":"2026-09-12T09:46:19.055593Z","iopub.status.idle":"2026-09-12T09:46:19.101834Z","shell.execute_reply.started":"2026-09-12T09:46:19.055552Z","shell.execute_reply":"2026-09-12T09:46:19.100871Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"df.columns","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T09:46:19.103257Z","iopub.execute_input":"2026-09-12T09:46:19.103904Z","iopub.status.idle":"2026-09-12T09:46:19.111233Z","shell.execute_reply.started":"2026-09-12T09:46:19.103876Z","shell.execute_reply":"2026-09-12T09:46:19.110272Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"image_files[:5], type(image_files), len(image_files)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T09:46:19.112514Z","iopub.execute_input":"2026-09-12T09:46:19.112900Z","iopub.status.idle":"2026-09-12T09:46:19.121520Z","shell.execute_reply.started":"2026-09-12T09:46:19.112876Z","shell.execute_reply":"2026-09-12T09:46:19.120418Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"df.describe()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T09:46:19.122821Z","iopub.execute_input":"2026-09-12T09:46:19.123177Z","iopub.status.idle":"2026-09-12T09:46:19.165943Z","shell.execute_reply.started":"2026-09-12T09:46:19.123132Z","shell.execute_reply":"2026-09-12T09:46:19.164959Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"df.loc[1]","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T09:46:19.167406Z","iopub.execute_input":"2026-09-12T09:46:19.167819Z","iopub.status.idle":"2026-09-12T09:46:19.175916Z","shell.execute_reply.started":"2026-09-12T09:46:19.167781Z","shell.execute_reply":"2026-09-12T09:46:19.174935Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"df.sample(5)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T09:46:19.177363Z","iopub.execute_input":"2026-09-12T09:46:19.177669Z","iopub.status.idle":"2026-09-12T09:46:19.194622Z","shell.execute_reply.started":"2026-09-12T09:46:19.177646Z","shell.execute_reply":"2026-09-12T09:46:19.193590Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"df['filename']","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T09:46:19.195939Z","iopub.execute_input":"2026-09-12T09:46:19.196610Z","iopub.status.idle":"2026-09-12T09:46:19.207800Z","shell.execute_reply.started":"2026-09-12T09:46:19.196575Z","shell.execute_reply":"2026-09-12T09:46:19.206710Z"}},"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":"2026-09-12T09:46:19.208968Z","iopub.execute_input":"2026-09-12T09:46:19.209281Z","iopub.status.idle":"2026-09-12T09:46:19.306597Z","shell.execute_reply.started":"2026-09-12T09:46:19.209257Z","shell.execute_reply":"2026-09-12T09:46:19.305765Z"}},"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":"2026-09-12T09:46:19.307670Z","iopub.execute_input":"2026-09-12T09:46:19.308318Z","iopub.status.idle":"2026-09-12T09:46:19.314357Z","shell.execute_reply.started":"2026-09-12T09:46:19.308291Z","shell.execute_reply":"2026-09-12T09:46:19.313124Z"}},"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":"2026-09-12T09:46:19.315473Z","iopub.execute_input":"2026-09-12T09:46:19.315933Z","iopub.status.idle":"2026-09-12T09:46:24.766287Z","shell.execute_reply.started":"2026-09-12T09:46:19.315908Z","shell.execute_reply":"2026-09-12T09:46:24.762151Z"}},"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":"2026-09-12T09:46:24.767793Z","iopub.execute_input":"2026-09-12T09:46:24.768555Z","iopub.status.idle":"2026-09-12T09:46:30.250929Z","shell.execute_reply.started":"2026-09-12T09:46:24.768523Z","shell.execute_reply":"2026-09-12T09:46:30.249625Z"}},"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":"2026-09-12T09:46:30.252871Z","iopub.execute_input":"2026-09-12T09:46:30.253398Z","iopub.status.idle":"2026-09-12T09:46:30.262393Z","shell.execute_reply.started":"2026-09-12T09:46:30.253348Z","shell.execute_reply":"2026-09-12T09:46:30.261345Z"}},"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":"2026-09-12T09:46:30.263500Z","iopub.execute_input":"2026-09-12T09:46:30.263731Z","iopub.status.idle":"2026-09-12T09:46:35.631520Z","shell.execute_reply.started":"2026-09-12T09:46:30.263710Z","shell.execute_reply":"2026-09-12T09:46:35.629544Z"}},"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":"2026-09-12T09:46:35.641089Z","iopub.execute_input":"2026-09-12T09:46:35.641862Z","iopub.status.idle":"2026-09-12T09:47:00.491628Z","shell.execute_reply.started":"2026-09-12T09:46:35.641829Z","shell.execute_reply":"2026-09-12T09:47:00.490618Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"preds[:10]","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T09:47:00.492887Z","iopub.execute_input":"2026-09-12T09:47:00.493292Z","iopub.status.idle":"2026-09-12T09:47:00.500328Z","shell.execute_reply.started":"2026-09-12T09:47:00.493250Z","shell.execute_reply":"2026-09-12T09:47:00.499283Z"}},"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":"2026-09-12T09:47:00.501699Z","iopub.execute_input":"2026-09-12T09:47:00.502366Z","iopub.status.idle":"2026-09-12T09:47:01.917708Z","shell.execute_reply.started":"2026-09-12T09:47:00.502329Z","shell.execute_reply":"2026-09-12T09:47:01.916242Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# end of 2026-09-06\nstop here","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T09:47:01.918958Z","iopub.execute_input":"2026-09-12T09:47:01.919327Z","iopub.status.idle":"2026-09-12T09:47:01.925756Z","shell.execute_reply.started":"2026-09-12T09:47:01.919293Z","shell.execute_reply":"2026-09-12T09:47:01.924598Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Transfer Learning","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T09:48:02.091061Z","iopub.execute_input":"2026-09-12T09:48:02.092241Z","iopub.status.idle":"2026-09-12T09:48:02.096684Z","shell.execute_reply.started":"2026-09-12T09:48:02.092136Z","shell.execute_reply":"2026-09-12T09:48:02.095473Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"from keras.applications.vgg16 import VGG16\nfrom keras.models import Model\nfrom keras.layers import Dense, GlobalAveragePooling2D, Dropout\nfrom keras.optimizers import Adam\nfrom keras.callbacks import EarlyStopping, ReduceLROnPlateau\n\ndef define_model_vgg16():\n\n    base_model = VGG16(\n        include_top=False,\n        weights='imagenet',\n        input_shape=(224, 224, 3)\n    )\n\n    # Freeze VGG16\n    for layer in base_model.layers:\n        layer.trainable = False\n\n    # Classifier\n    x = base_model.output\n    x = GlobalAveragePooling2D()(x)\n    x = Dense(256, activation='relu')(x)\n    x = Dropout(0.5)(x)\n    output = Dense(1, activation='sigmoid')(x)\n\n    model = Model(\n        inputs=base_model.input,\n        outputs=output\n    )\n\n    model.compile(\n        optimizer=Adam(learning_rate=0.0001),\n        loss='binary_crossentropy',\n        metrics=['accuracy']\n    )\n\n    return model\n\n\nvgg16_model = define_model_vgg16()\nvgg16_model.summary()\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T10:02:56.523613Z","iopub.execute_input":"2026-09-12T10:02:56.523938Z","iopub.status.idle":"2026-09-12T10:02:56.918919Z","shell.execute_reply.started":"2026-09-12T10:02:56.523913Z","shell.execute_reply":"2026-09-12T10:02:56.915969Z"}},"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":"2026-09-12T09:52:13.632010Z","iopub.execute_input":"2026-09-12T09:52:13.632403Z","iopub.status.idle":"2026-09-12T09:52:13.638121Z","shell.execute_reply.started":"2026-09-12T09:52:13.632373Z","shell.execute_reply":"2026-09-12T09:52:13.636588Z"}},"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":"2026-09-12T09:52:16.768572Z","iopub.execute_input":"2026-09-12T09:52:16.769124Z","iopub.status.idle":"2026-09-12T09:52:16.773320Z","shell.execute_reply.started":"2026-09-12T09:52:16.769082Z","shell.execute_reply":"2026-09-12T09:52:16.772270Z"}},"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":"2026-09-12T09:52:20.496104Z","iopub.execute_input":"2026-09-12T09:52:20.496918Z","iopub.status.idle":"2026-09-12T09:52:20.501142Z","shell.execute_reply.started":"2026-09-12T09:52:20.496884Z","shell.execute_reply":"2026-09-12T09:52:20.500172Z"}},"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":"2026-09-12T09:52:23.392777Z","iopub.execute_input":"2026-09-12T09:52:23.393723Z","iopub.status.idle":"2026-09-12T09:52:23.397848Z","shell.execute_reply.started":"2026-09-12T09:52:23.393691Z","shell.execute_reply":"2026-09-12T09:52:23.396705Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"vgg16_model = define_model_vgg16()\nvgg16_model.summary()\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T10:03:03.190759Z","iopub.execute_input":"2026-09-12T10:03:03.191530Z","iopub.status.idle":"2026-09-12T10:03:03.573762Z","shell.execute_reply.started":"2026-09-12T10:03:03.191496Z","shell.execute_reply":"2026-09-12T10:03:03.572122Z"}},"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":"2026-09-12T09:52:39.103782Z","iopub.execute_input":"2026-09-12T09:52:39.104407Z","iopub.status.idle":"2026-09-12T09:52:39.108425Z","shell.execute_reply.started":"2026-09-12T09:52:39.104373Z","shell.execute_reply":"2026-09-12T09:52:39.107433Z"}},"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":"2026-09-12T09:52:41.799110Z","iopub.execute_input":"2026-09-12T09:52:41.799907Z","iopub.status.idle":"2026-09-12T09:52:41.805511Z","shell.execute_reply.started":"2026-09-12T09:52:41.799871Z","shell.execute_reply":"2026-09-12T09:52:41.804692Z"}},"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":"2026-09-12T09:52:44.520139Z","iopub.execute_input":"2026-09-12T09:52:44.520499Z","iopub.status.idle":"2026-09-12T09:52:44.524730Z","shell.execute_reply.started":"2026-09-12T09:52:44.520473Z","shell.execute_reply":"2026-09-12T09:52:44.523825Z"}},"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":"2026-09-12T09:52:47.366656Z","iopub.execute_input":"2026-09-12T09:52:47.367569Z","iopub.status.idle":"2026-09-12T09:52:47.372352Z","shell.execute_reply.started":"2026-09-12T09:52:47.367536Z","shell.execute_reply":"2026-09-12T09:52:47.371127Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"id(vgg16_model)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T09:52:57.487933Z","iopub.execute_input":"2026-09-12T09:52:57.488811Z","iopub.status.idle":"2026-09-12T09:52:57.494412Z","shell.execute_reply.started":"2026-09-12T09:52:57.488777Z","shell.execute_reply":"2026-09-12T09:52:57.493330Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# fit model\nprint(id(vgg16_model))\nvgg16_model.reset_states()\nvgg16_model_history = vgg16_model.fit(\n    train_it, \n    steps_per_epoch=len(train_it),\n    validation_data=val_it,\n    validation_steps=len(val_it),\n    epochs=3, verbose=1,\n    callbacks = [PlotLossesKeras()]\n    )","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T10:07:51.174656Z","iopub.execute_input":"2026-09-12T10:07:51.175526Z","iopub.status.idle":"2026-09-12T10:12:14.898383Z","shell.execute_reply.started":"2026-09-12T10:07:51.175491Z","shell.execute_reply":"2026-09-12T10:12:14.897602Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# learning curves\nsummarize_diagnostics(vgg16_model_history)\n\n# evaluate model\n_, acc = vgg16_model.evaluate_generator(val_it, steps=len(val_it), verbose=1)\nprint('Val: > %.3f' % (acc * 100.0))\n\n# evaluate model\n_, acc = vgg16_model.evaluate_generator(test_it, steps=len(test_it), verbose=1)\nprint('Test: > %.3f' % (acc * 100.0))","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T10:14:01.822162Z","iopub.execute_input":"2026-09-12T10:14:01.823073Z","iopub.status.idle":"2026-09-12T10:14:44.593405Z","shell.execute_reply.started":"2026-09-12T10:14:01.823036Z","shell.execute_reply":"2026-09-12T10:14:44.592281Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"from keras.applications.inception_v3 import InceptionV3\n\ndef define_model_inceptionv3():\n    # load model\n    model = InceptionV3(include_top=False, input_shape=(299, 299, 3))\n    # mark loaded layers as not trainable\n    for layer in model.layers:\n        layer.trainable = False\n        # layer.trainable = True #try to test\n    \n    # add new classifier layers\n    flat1 = Flatten()(model.layers[-1].output)\n    class1 = Dense(1024, activation='relu', kernel_initializer='he_uniform')(flat1)\n    class2 = Dense(512, activation='relu', kernel_initializer='he_uniform')(class1)\n    class3 = Dense(256, activation='relu', kernel_initializer='he_uniform')(class2)\n    class4 = Dense(128, activation='relu', kernel_initializer='he_uniform')(class3)\n    # output = Dense(1, activation='sigmoid')(flat1)\n    output = Dense(2, activation='softmax')(class4)\n    # define new model\n    model = Model(inputs=model.inputs, outputs=output)\n    # compile model\n    opt = SGD(lr=0.001, momentum=0.9)\n    model.compile(optimizer=opt, loss='binary_crossentropy', metrics=['accuracy'])\n    return model","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T10:32:31.172723Z","iopub.execute_input":"2026-09-12T10:32:31.173084Z","iopub.status.idle":"2026-09-12T10:32:31.180722Z","shell.execute_reply.started":"2026-09-12T10:32:31.173055Z","shell.execute_reply":"2026-09-12T10:32:31.179620Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"model_inceptionv3 = define_model_inceptionv3()\nprint(id(model_inceptionv3))\n# model_inceptionv3.summary()","metadata":{"execution":{"iopub.status.busy":"2026-09-12T10:32:33.671542Z","iopub.execute_input":"2026-09-12T10:32:33.672179Z","iopub.status.idle":"2026-09-12T10:32:36.046358Z","shell.execute_reply.started":"2026-09-12T10:32:33.672144Z","shell.execute_reply":"2026-09-12T10:32:36.045261Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import numpy as np\nfrom tensorflow.keras import backend as K\n\ntrainable_params = int(np.sum([K.count_params(w) for w in model_inceptionv3.trainable_weights]))\nprint(trainable_params)\n","metadata":{"trusted":true,"scrolled":true,"execution":{"iopub.status.busy":"2026-09-12T10:32:36.048047Z","iopub.execute_input":"2026-09-12T10:32:36.048406Z","iopub.status.idle":"2026-09-12T10:32:36.054762Z","shell.execute_reply.started":"2026-09-12T10:32:36.048372Z","shell.execute_reply":"2026-09-12T10:32:36.053744Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"from tensorflow.keras import backend as K\n\nfor w in model_inceptionv3.trainable_weights:\n    print(w.name, K.count_params(w))\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T10:32:36.056212Z","iopub.execute_input":"2026-09-12T10:32:36.056565Z","iopub.status.idle":"2026-09-12T10:32:36.069762Z","shell.execute_reply.started":"2026-09-12T10:32:36.056532Z","shell.execute_reply":"2026-09-12T10:32:36.069004Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# fit model\nmodel_inceptionv3.reset_states()\nhistory_inceptionv3 = model_inceptionv3.fit(\n    train_it, \n    steps_per_epoch=len(train_it),\n    validation_data=val_it,\n    validation_steps=len(val_it),\n    epochs=3, verbose=1,\n    callbacks = [PlotLossesKeras()]\n    )","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T10:32:37.526925Z","iopub.execute_input":"2026-09-12T10:32:37.527333Z","iopub.status.idle":"2026-09-12T10:32:38.616570Z","shell.execute_reply.started":"2026-09-12T10:32:37.527300Z","shell.execute_reply":"2026-09-12T10:32:38.615278Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import matplotlib.pyplot as plt\n\ndef plot_images_with_labels(images, labels, train_log, set_label, save=False):\n    \"\"\"\n    Plots a grid of images with their corresponding labels and saves the figure.\n    \n    Args:\n    - images (list or np.array): List of images to be displayed.\n    - labels (np.array): Array of one-hot encoded labels.\n    - train_log (str): The directory or log name to save the plot.\n    - set_label (str): The specific set label (e.g., \"train\", \"validation\", etc.).\n    - config (dict): Configuration dictionary containing image dimensions.\n    \n    Returns:\n    - None: Displays and saves the plot.\n    \"\"\"\n    # Convert one-hot encoded labels to class indices\n    class_indices = labels\n\n    # Create subplots\n    fig, axes = plt.subplots(3, 4, figsize=(14, 10), dpi=120)\n    axes = axes.flatten()\n\n    for img, label_idx, ax in zip(images, class_indices, axes):\n        # Undo any preprocessing (like rescaling for pre-trained models)\n        if np.max(img) == 1:\n            img = img * 255\n\n        # Display the image\n        img_shape = (224, 224, 3)\n        ax.imshow(img.astype(\"uint8\"))\n        # ax.imshow(img)\n\n        # Set the title to the corresponding class label\n        ax.set_title(f\"Label: {label_idx}\", fontsize=18)\n        ax.axis('on')\n\n    # Set the overall title for the figure\n    plot_title = f\"{train_log}-{set_label}\"\n    plt.suptitle(plot_title, fontsize=18)\n\n    # Show the plot\n    plt.show()\n\n    # Save the figure\n    if save:\n        plot_file = os.path.join(train_log, f\"{plot_title}.png\")\n        fig.savefig(plot_file, dpi=120)\n        print(f'Saved {plot_file}')\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T10:32:43.453863Z","iopub.execute_input":"2026-09-12T10:32:43.454650Z","iopub.status.idle":"2026-09-12T10:32:43.461543Z","shell.execute_reply.started":"2026-09-12T10:32:43.454618Z","shell.execute_reply":"2026-09-12T10:32:43.460581Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# plot_images_with_labels(images, labels, \"Dog-Cat\", \"Training\")","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T10:32:44.371108Z","iopub.execute_input":"2026-09-12T10:32:44.371463Z","iopub.status.idle":"2026-09-12T10:32:44.375865Z","shell.execute_reply.started":"2026-09-12T10:32:44.371437Z","shell.execute_reply":"2026-09-12T10:32:44.374902Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# for index, layer in enumerate(model.layers):\n#     print(index, layer.output.shape)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T10:32:44.722649Z","iopub.execute_input":"2026-09-12T10:32:44.723507Z","iopub.status.idle":"2026-09-12T10:32:44.727304Z","shell.execute_reply.started":"2026-09-12T10:32:44.723473Z","shell.execute_reply":"2026-09-12T10:32:44.726388Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# # mark loaded layers as not trainable\n# for index, layer in enumerate(model.layers[:15]):\n#     print(index, layer.name, layer.output_shape)\n#     layer.trainable = False\n    \n# for index, layer in enumerate(model.layers[15:]):\n#     print(index, layer.name, layer.output_shape)\n#     layer.trainable = True","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T10:32:53.972054Z","iopub.execute_input":"2026-09-12T10:32:53.972842Z","iopub.status.idle":"2026-09-12T10:32:53.978889Z","shell.execute_reply.started":"2026-09-12T10:32:53.972806Z","shell.execute_reply":"2026-09-12T10:32:53.977687Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# evaluate model\n_, acc = model_inceptionv3.evaluate(test_it, steps=len(test_it), verbose=1)\nprint('> %.3f' % (acc * 100.0))\n# learning curves\n# summarize_diagnostics(history)\n\n# best_model = 'vgg16_model.hdf5'\n# my_model.save(best_model)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T10:32:51.207172Z","iopub.execute_input":"2026-09-12T10:32:51.207834Z","iopub.status.idle":"2026-09-12T10:32:52.248506Z","shell.execute_reply.started":"2026-09-12T10:32:51.207802Z","shell.execute_reply":"2026-09-12T10:32:52.247230Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"images = test_it.__next__()\nimages.shape","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T10:32:56.422336Z","iopub.execute_input":"2026-09-12T10:32:56.423067Z","iopub.status.idle":"2026-09-12T10:32:56.535270Z","shell.execute_reply.started":"2026-09-12T10:32:56.423024Z","shell.execute_reply":"2026-09-12T10:32:56.534200Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# 5 first img: 1, 0, 1, 1, 0\nimages_to_predict = images[:5]\nimages_to_predict.shape","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T10:32:56.677985Z","iopub.execute_input":"2026-09-12T10:32:56.678805Z","iopub.status.idle":"2026-09-12T10:32:56.685451Z","shell.execute_reply.started":"2026-09-12T10:32:56.678769Z","shell.execute_reply":"2026-09-12T10:32:56.684117Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"probs = model_inceptionv3.predict(images_to_predict, verbose=1)\nprobs","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T10:32:57.205371Z","iopub.execute_input":"2026-09-12T10:32:57.205679Z","iopub.status.idle":"2026-09-12T10:32:57.314097Z","shell.execute_reply.started":"2026-09-12T10:32:57.205656Z","shell.execute_reply":"2026-09-12T10:32:57.312758Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"Make Prediction","metadata":{}},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null}]}