{"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\n# import os\n# for 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":"2026-09-17T21:33:17.949479Z","iopub.execute_input":"2026-09-17T21:33:17.950323Z","iopub.status.idle":"2026-09-17T21:33:17.954559Z","shell.execute_reply.started":"2026-09-17T21:33:17.950297Z","shell.execute_reply":"2026-09-17T21:33:17.953580Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"!python --version","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T21:33:18.798463Z","iopub.execute_input":"2026-09-17T21:33:18.799426Z","iopub.status.idle":"2026-09-17T21:33:19.819334Z","shell.execute_reply.started":"2026-09-17T21:33:18.799390Z","shell.execute_reply":"2026-09-17T21:33:19.818243Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"!uname --all","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T21:33:19.821077Z","iopub.execute_input":"2026-09-17T21:33:19.821661Z","iopub.status.idle":"2026-09-17T21:33:20.820997Z","shell.execute_reply.started":"2026-09-17T21:33:19.821632Z","shell.execute_reply":"2026-09-17T21:33:20.819993Z"}},"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":"2026-09-17T21:33:20.822355Z","iopub.execute_input":"2026-09-17T21:33:20.823123Z","iopub.status.idle":"2026-09-17T21:33:30.788018Z","shell.execute_reply.started":"2026-09-17T21:33:20.823094Z","shell.execute_reply":"2026-09-17T21:33:30.786907Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T21:33:30.790574Z","iopub.execute_input":"2026-09-17T21:33:30.791737Z","iopub.status.idle":"2026-09-17T21:33:31.792101Z","shell.execute_reply.started":"2026-09-17T21:33:30.791710Z","shell.execute_reply":"2026-09-17T21:33:31.791143Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -l","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T21:33:31.793606Z","iopub.execute_input":"2026-09-17T21:33:31.793917Z","iopub.status.idle":"2026-09-17T21:33:32.790104Z","shell.execute_reply.started":"2026-09-17T21:33:31.793892Z","shell.execute_reply":"2026-09-17T21:33:32.789103Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls test1/ | wc -l","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T21:33:32.791796Z","iopub.execute_input":"2026-09-17T21:33:32.792169Z","iopub.status.idle":"2026-09-17T21:33:33.824701Z","shell.execute_reply.started":"2026-09-17T21:33:32.792134Z","shell.execute_reply":"2026-09-17T21:33:33.823744Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls train/ | wc -l","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T21:33:33.826063Z","iopub.execute_input":"2026-09-17T21:33:33.826385Z","iopub.status.idle":"2026-09-17T21:33:35.020832Z","shell.execute_reply.started":"2026-09-17T21:33:33.826359Z","shell.execute_reply":"2026-09-17T21:33:35.019807Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"#ls train/","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T21:33:35.022230Z","iopub.execute_input":"2026-09-17T21:33:35.022861Z","iopub.status.idle":"2026-09-17T21:33:35.027569Z","shell.execute_reply.started":"2026-09-17T21:33:35.022831Z","shell.execute_reply":"2026-09-17T21:33:35.026603Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -U train | head -n 10","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T21:33:35.028988Z","iopub.execute_input":"2026-09-17T21:33:35.029961Z","iopub.status.idle":"2026-09-17T21:33:36.141885Z","shell.execute_reply.started":"2026-09-17T21:33:35.029934Z","shell.execute_reply":"2026-09-17T21:33:36.140939Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -U test1 | head -n 10","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T21:33:36.145071Z","iopub.execute_input":"2026-09-17T21:33:36.145438Z","iopub.status.idle":"2026-09-17T21:33:37.212941Z","shell.execute_reply.started":"2026-09-17T21:33:36.145412Z","shell.execute_reply":"2026-09-17T21:33:37.211841Z"}},"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":"2026-09-17T21:33:37.214329Z","iopub.execute_input":"2026-09-17T21:33:37.215015Z","iopub.status.idle":"2026-09-17T21:33:38.281272Z","shell.execute_reply.started":"2026-09-17T21:33:37.214985Z","shell.execute_reply":"2026-09-17T21:33:38.280317Z"},"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":"2026-09-17T21:33:38.282486Z","iopub.execute_input":"2026-09-17T21:33:38.282796Z","iopub.status.idle":"2026-09-17T21:33:39.336479Z","shell.execute_reply.started":"2026-09-17T21:33:38.282771Z","shell.execute_reply":"2026-09-17T21:33:39.335617Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"!python --version","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T21:33:39.337703Z","iopub.execute_input":"2026-09-17T21:33:39.337945Z","iopub.status.idle":"2026-09-17T21:33:40.376020Z","shell.execute_reply.started":"2026-09-17T21:33:39.337924Z","shell.execute_reply":"2026-09-17T21:33:40.374613Z"}},"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":"2026-09-17T21:33:40.378724Z","iopub.execute_input":"2026-09-17T21:33:40.379138Z","iopub.status.idle":"2026-09-17T21:33:43.371433Z","shell.execute_reply.started":"2026-09-17T21:33:40.379110Z","shell.execute_reply":"2026-09-17T21:33:43.370517Z"}},"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":"2026-09-17T21:33:43.372819Z","iopub.execute_input":"2026-09-17T21:33:43.373775Z","iopub.status.idle":"2026-09-17T21:33:43.381828Z","shell.execute_reply.started":"2026-09-17T21:33:43.373709Z","shell.execute_reply":"2026-09-17T21:33:43.380578Z"},"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":"2026-09-17T21:33:43.383725Z","iopub.execute_input":"2026-09-17T21:33:43.385006Z","iopub.status.idle":"2026-09-17T21:33:43.401297Z","shell.execute_reply.started":"2026-09-17T21:33:43.384945Z","shell.execute_reply":"2026-09-17T21:33:43.400754Z"},"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":"2026-09-17T21:33:43.402485Z","iopub.execute_input":"2026-09-17T21:33:43.402892Z","iopub.status.idle":"2026-09-17T21:33:43.413347Z","shell.execute_reply.started":"2026-09-17T21:33:43.402856Z","shell.execute_reply":"2026-09-17T21:33:43.412461Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -l","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T21:33:43.414720Z","iopub.execute_input":"2026-09-17T21:33:43.415033Z","iopub.status.idle":"2026-09-17T21:33:44.512809Z","shell.execute_reply.started":"2026-09-17T21:33:43.415009Z","shell.execute_reply":"2026-09-17T21:33:44.511704Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -l dataset_dogs_vs_cats/train","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T21:33:44.514340Z","iopub.execute_input":"2026-09-17T21:33:44.515144Z","iopub.status.idle":"2026-09-17T21:33:45.560435Z","shell.execute_reply.started":"2026-09-17T21:33:44.515114Z","shell.execute_reply":"2026-09-17T21:33:45.559315Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -l dataset_dogs_vs_cats/test #validation","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T21:33:45.562178Z","iopub.execute_input":"2026-09-17T21:33:45.562622Z","iopub.status.idle":"2026-09-17T21:33:46.714611Z","shell.execute_reply.started":"2026-09-17T21:33:45.562582Z","shell.execute_reply":"2026-09-17T21:33:46.713498Z"}},"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":"2026-09-17T21:33:46.716163Z","iopub.execute_input":"2026-09-17T21:33:46.716498Z","iopub.status.idle":"2026-09-17T21:33:50.147014Z","shell.execute_reply.started":"2026-09-17T21:33:46.716470Z","shell.execute_reply":"2026-09-17T21:33:50.145758Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"print(src)\nprint(dst)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T21:33:50.148409Z","iopub.execute_input":"2026-09-17T21:33:50.148744Z","iopub.status.idle":"2026-09-17T21:33:50.154264Z","shell.execute_reply.started":"2026-09-17T21:33:50.148718Z","shell.execute_reply":"2026-09-17T21:33:50.153099Z"}},"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":"2026-09-17T21:33:50.155571Z","iopub.execute_input":"2026-09-17T21:33:50.155916Z","iopub.status.idle":"2026-09-17T21:33:53.283327Z","shell.execute_reply.started":"2026-09-17T21:33:50.155880Z","shell.execute_reply":"2026-09-17T21:33:53.282322Z"},"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":"2026-09-17T21:33:53.284764Z","iopub.execute_input":"2026-09-17T21:33:53.285397Z","iopub.status.idle":"2026-09-17T21:33:55.383897Z","shell.execute_reply.started":"2026-09-17T21:33:53.285369Z","shell.execute_reply":"2026-09-17T21:33:55.382616Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"!pip -q install livelossplot==0.5.5","metadata":{"execution":{"iopub.status.busy":"2026-09-17T21:33:55.385420Z","iopub.execute_input":"2026-09-17T21:33:55.385882Z","iopub.status.idle":"2026-09-17T21:34:03.910214Z","shell.execute_reply.started":"2026-09-17T21:33:55.385852Z","shell.execute_reply":"2026-09-17T21:34:03.909079Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"from livelossplot import PlotLossesKeras","metadata":{"execution":{"iopub.status.busy":"2026-09-17T21:34:03.912452Z","iopub.execute_input":"2026-09-17T21:34:03.912924Z","iopub.status.idle":"2026-09-17T21:34:03.926802Z","shell.execute_reply.started":"2026-09-17T21:34:03.912894Z","shell.execute_reply":"2026-09-17T21:34:03.925837Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"Prepare Final Dataset","metadata":{}},{"cell_type":"code","source":"# https://keras.io/api/applications/","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T21:34:03.927981Z","iopub.execute_input":"2026-09-17T21:34:03.928334Z","iopub.status.idle":"2026-09-17T21:34:03.933216Z","shell.execute_reply.started":"2026-09-17T21:34:03.928303Z","shell.execute_reply":"2026-09-17T21:34:03.932243Z"}},"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":"2026-09-17T21:34:03.940154Z","iopub.execute_input":"2026-09-17T21:34:03.940439Z","iopub.status.idle":"2026-09-17T21:34:03.945752Z","shell.execute_reply.started":"2026-09-17T21:34:03.940415Z","shell.execute_reply":"2026-09-17T21:34:03.944774Z"}},"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',\n                     kernel_initializer='he_uniform',\n                     padding='same',\n                     input_shape=(200, 200, 3))\n             )\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":"2026-09-17T21:34:03.946914Z","iopub.execute_input":"2026-09-17T21:34:03.947262Z","iopub.status.idle":"2026-09-17T21:34:03.956264Z","shell.execute_reply.started":"2026-09-17T21:34:03.947239Z","shell.execute_reply":"2026-09-17T21:34:03.955298Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"model_1 = define_model_1()\nprint(model_1.summary())","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T21:34:03.957357Z","iopub.execute_input":"2026-09-17T21:34:03.958127Z","iopub.status.idle":"2026-09-17T21:34:05.125303Z","shell.execute_reply.started":"2026-09-17T21:34:03.958104Z","shell.execute_reply":"2026-09-17T21:34:05.124236Z"}},"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":"2026-09-17T21:34:05.126640Z","iopub.execute_input":"2026-09-17T21:34:05.127008Z","iopub.status.idle":"2026-09-17T21:34:05.133639Z","shell.execute_reply.started":"2026-09-17T21:34:05.126973Z","shell.execute_reply":"2026-09-17T21:34:05.132744Z"}},"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":"2026-09-17T21:34:05.134678Z","iopub.execute_input":"2026-09-17T21:34:05.134897Z","iopub.status.idle":"2026-09-17T21:34:05.206836Z","shell.execute_reply.started":"2026-09-17T21:34:05.134877Z","shell.execute_reply":"2026-09-17T21:34:05.205968Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# The Functional API\nfrom tensorflow.keras.models import Model\nfrom tensorflow.keras.layers import Input, Conv2D, MaxPooling2D, Flatten, Dense\n\n# explicitly define the input tensor topology\nmy_inputs = Input(shape=(200, 200, 3))\n\n# Construct the forward pass of the computational graph\nx1 = Conv2D(32, (3, 3), activation='relu')(my_inputs)\n\nx2 = MaxPooling2D((2, 2))(x1)\n\nx3 = Flatten()(x2)\n\nx5 = Dense(256, activation='relu')(x3)\n\nx4 = Dense(128, activation='relu')(x5)\n\n# Define the output tensor with the target objective function representation\nmy_outputs = Dense(2, activation='softmax')(x4)\n\n# Instantiate the formal model architecture\nmodel = Model(inputs=my_inputs, outputs=my_outputs)\n\nprint(model.summary())","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T21:34:05.207978Z","iopub.execute_input":"2026-09-17T21:34:05.208218Z","iopub.status.idle":"2026-09-17T21:34:05.294516Z","shell.execute_reply.started":"2026-09-17T21:34:05.208196Z","shell.execute_reply":"2026-09-17T21:34:05.292640Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# The Functional API - new cell\nfrom tensorflow.keras.models import Model\nfrom tensorflow.keras.layers import Input, Conv2D, MaxPooling2D, Flatten, Dense\n\n# explicitly define the input tensor topology\nmy_inputs = Input(shape=(200, 200, 3))\n\n# Construct the forward pass of the computational graph\nx1 = Conv2D(32, (3, 3), activation='relu')(my_inputs)\n\nx1 = Conv2D(64, (3, 3), activation='relu')(x1)\n\nx2 = MaxPooling2D((2, 2))(x1)\n\nx3 = Flatten()(x2)\n\nx5 = Dense(256, activation='relu')(x3)\n\nx4 = Dense(128, activation='relu')(x5)\n\n# Define the output tensor with the target objective function representation\nmy_outputs = Dense(2, activation='softmax')(x4)\n\n# Instantiate the formal model architecture\nmodel = Model(inputs=my_inputs, outputs=my_outputs)\n\nprint(model.summary())","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T21:34:05.295704Z","iopub.execute_input":"2026-09-17T21:34:05.295986Z","iopub.status.idle":"2026-09-17T21:34:05.394314Z","shell.execute_reply.started":"2026-09-17T21:34:05.295963Z","shell.execute_reply":"2026-09-17T21:34:05.393422Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"datagen = ImageDataGenerator(rescale=1.0/255.0)\ntype(datagen)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T21:34:05.395798Z","iopub.execute_input":"2026-09-17T21:34:05.396152Z","iopub.status.idle":"2026-09-17T21:34:05.403035Z","shell.execute_reply.started":"2026-09-17T21:34:05.396118Z","shell.execute_reply":"2026-09-17T21:34:05.402202Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls dataset_dogs_vs_cats/train/","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T21:34:05.404282Z","iopub.execute_input":"2026-09-17T21:34:05.404629Z","iopub.status.idle":"2026-09-17T21:34:06.445206Z","shell.execute_reply.started":"2026-09-17T21:34:05.404598Z","shell.execute_reply":"2026-09-17T21:34:06.443928Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"IMAGE_SIZE = 224 #for vgg16\nBATCH_SIZE = 64\nEPOCHS = 30","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T21:34:06.447061Z","iopub.execute_input":"2026-09-17T21:34:06.447484Z","iopub.status.idle":"2026-09-17T21:34:06.452924Z","shell.execute_reply.started":"2026-09-17T21:34:06.447444Z","shell.execute_reply":"2026-09-17T21:34:06.451953Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Use another dataset\n\nfrom tensorflow.keras.preprocessing.image import ImageDataGenerator\n\n# 1. Instantiate the generator with the validation_split ratio\ndatagen = ImageDataGenerator(\n    rescale=1.0/255.0,\n    horizontal_flip=True,\n    validation_split=0.2  # Defined here at initialization\n)\n\ntrain_path = '/kaggle/input/datasets/kasikrit/308-456-dogs-vs-cats-dataset/dataset_dogs_vs_cats/train'\n\n# 2. Extract the training subset (80% of data)\ntrain_it = datagen.flow_from_directory(\n    train_path,\n    class_mode='binary',\n    batch_size=BATCH_SIZE,\n    target_size=(IMAGE_SIZE, IMAGE_SIZE),\n    subset='training',     # Explicitly request the training partition\n    shuffle=True           # Stochastic sampling is standard for training\n)\n\n# 3. Extract the validation subset (20% of data)\nval_it = datagen.flow_from_directory(\n    train_path,\n    class_mode='binary',\n    batch_size=BATCH_SIZE,\n    target_size=(IMAGE_SIZE, IMAGE_SIZE),\n    subset='validation',   # Explicitly request the validation partition\n    shuffle=False          # Disable shuffle to maintain index alignment for metrics\n)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T21:34:06.453955Z","iopub.execute_input":"2026-09-17T21:34:06.454226Z","iopub.status.idle":"2026-09-17T21:34:11.420160Z","shell.execute_reply.started":"2026-09-17T21:34:06.454204Z","shell.execute_reply":"2026-09-17T21:34:11.419384Z"}},"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":"2026-09-17T21:34:11.421341Z","iopub.execute_input":"2026-09-17T21:34:11.421684Z","iopub.status.idle":"2026-09-17T21:34:11.429009Z","shell.execute_reply.started":"2026-09-17T21:34:11.421652Z","shell.execute_reply":"2026-09-17T21:34:11.427915Z"}},"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":"2026-09-17T21:34:11.430337Z","iopub.execute_input":"2026-09-17T21:34:11.430668Z","iopub.status.idle":"2026-09-17T21:34:11.443133Z","shell.execute_reply.started":"2026-09-17T21:34:11.430646Z","shell.execute_reply":"2026-09-17T21:34:11.441694Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# fit model\n# model_1.reset_states()\n# history_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":"2026-09-17T21:34:11.444422Z","iopub.execute_input":"2026-09-17T21:34:11.444838Z","iopub.status.idle":"2026-09-17T21:34:11.453143Z","shell.execute_reply.started":"2026-09-17T21:34:11.444804Z","shell.execute_reply":"2026-09-17T21:34:11.452223Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# learning curves\n# summarize_diagnostics(history_1)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T21:34:11.454330Z","iopub.execute_input":"2026-09-17T21:34:11.455161Z","iopub.status.idle":"2026-09-17T21:34:11.461786Z","shell.execute_reply.started":"2026-09-17T21:34:11.455117Z","shell.execute_reply":"2026-09-17T21:34:11.460938Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# evaluate model\n# _, acc = model_1.evaluate(val_it, steps=len(val_it), verbose=1)\n# print('> %.3f' % (acc * 100.0))","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T21:34:11.462840Z","iopub.execute_input":"2026-09-17T21:34:11.463129Z","iopub.status.idle":"2026-09-17T21:34:11.471712Z","shell.execute_reply.started":"2026-09-17T21:34:11.463105Z","shell.execute_reply":"2026-09-17T21:34:11.470830Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"## Create test datagenerator from 308-456 Dogs vs Cats ","metadata":{}},{"cell_type":"code","source":"ls /kaggle/input/datasets/kasikrit/308-456-dogs-vs-cats-dataset/dataset_dogs_vs_cats/test","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T21:34:11.473337Z","iopub.execute_input":"2026-09-17T21:34:11.473648Z","iopub.status.idle":"2026-09-17T21:34:12.520165Z","shell.execute_reply.started":"2026-09-17T21:34:11.473626Z","shell.execute_reply":"2026-09-17T21:34:12.519224Z"}},"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\ntest_path = '/kaggle/input/datasets/kasikrit/308-456-dogs-vs-cats-dataset/dataset_dogs_vs_cats/test'\n\nprint(test_path)\n# # List all .jpg files in the directory (adjust the pattern if needed)\n# image_files = glob(os.path.join(image_folder, '*.jpg'))\n\n# # Check if images were found\n# if not image_files:\n#     print(\"No images found. Please verify the directory and file extensions.\")\n    \n# # Create a DataFrame with the file paths\n# test_df = 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":"2026-09-17T21:34:12.521674Z","iopub.execute_input":"2026-09-17T21:34:12.522089Z","iopub.status.idle":"2026-09-17T21:34:12.528244Z","shell.execute_reply.started":"2026-09-17T21:34:12.522064Z","shell.execute_reply":"2026-09-17T21:34:12.527220Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"\n","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# test_df.columns","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T21:34:12.529678Z","iopub.execute_input":"2026-09-17T21:34:12.530064Z","iopub.status.idle":"2026-09-17T21:34:12.539500Z","shell.execute_reply.started":"2026-09-17T21:34:12.530032Z","shell.execute_reply":"2026-09-17T21:34:12.538579Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# image_files[:5], type(image_files), len(image_files)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T21:34:12.540596Z","iopub.execute_input":"2026-09-17T21:34:12.542002Z","iopub.status.idle":"2026-09-17T21:34:12.548404Z","shell.execute_reply.started":"2026-09-17T21:34:12.541950Z","shell.execute_reply":"2026-09-17T21:34:12.547701Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# test_df.describe()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T21:34:12.549467Z","iopub.execute_input":"2026-09-17T21:34:12.549942Z","iopub.status.idle":"2026-09-17T21:34:12.557071Z","shell.execute_reply.started":"2026-09-17T21:34:12.549918Z","shell.execute_reply":"2026-09-17T21:34:12.556089Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# test_df.loc[1]","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T21:34:12.558274Z","iopub.execute_input":"2026-09-17T21:34:12.558682Z","iopub.status.idle":"2026-09-17T21:34:12.565456Z","shell.execute_reply.started":"2026-09-17T21:34:12.558647Z","shell.execute_reply":"2026-09-17T21:34:12.564569Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# test_df.sample(5)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T21:34:12.566497Z","iopub.execute_input":"2026-09-17T21:34:12.566774Z","iopub.status.idle":"2026-09-17T21:34:12.575185Z","shell.execute_reply.started":"2026-09-17T21:34:12.566755Z","shell.execute_reply":"2026-09-17T21:34:12.574293Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# # Create test data generator\n# from tensorflow.keras.preprocessing.image import ImageDataGenerator\n\n# # Initialize your ImageDataGenerator (modify parameters as needed)\n# datagen_test = ImageDataGenerator(rescale=1./255,\n#                                  vertical_flip=True)\n\n# # Create the data generator using the DataFrame\n# test_it = datagen_test.flow_from_dataframe(\n#     dataframe=test_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=BATCH_SIZE,\n#     class_mode=None,       # Since there are no labels\n#     # shuffle=True,         # Usually testing data should not be shuffled\n#     shuffle=False,\n# )\n\n# type(test_it)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T21:34:12.576327Z","iopub.execute_input":"2026-09-17T21:34:12.576653Z","iopub.status.idle":"2026-09-17T21:34:12.584268Z","shell.execute_reply.started":"2026-09-17T21:34:12.576624Z","shell.execute_reply":"2026-09-17T21:34:12.583368Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"IMAGE_SIZE, BATCH_SIZE","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T21:34:12.585476Z","iopub.execute_input":"2026-09-17T21:34:12.585828Z","iopub.status.idle":"2026-09-17T21:34:12.595238Z","shell.execute_reply.started":"2026-09-17T21:34:12.585797Z","shell.execute_reply":"2026-09-17T21:34:12.594345Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# 1. Instantiate the generator with the validation_split ratio\ntest_datagen = ImageDataGenerator(\n    rescale=1.0/255.0,\n    horizontal_flip=True\n)\n\ntest_it = test_datagen.flow_from_directory(\n    test_path,\n    class_mode='binary',\n    batch_size=BATCH_SIZE,\n    target_size=(IMAGE_SIZE, IMAGE_SIZE)\n)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T21:34:12.596424Z","iopub.execute_input":"2026-09-17T21:34:12.597344Z","iopub.status.idle":"2026-09-17T21:34:18.452693Z","shell.execute_reply.started":"2026-09-17T21:34:12.597317Z","shell.execute_reply":"2026-09-17T21:34:18.451979Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import matplotlib.pyplot as plt\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            ax.axis(\"on\")\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":"2026-09-17T21:34:18.453991Z","iopub.execute_input":"2026-09-17T21:34:18.454344Z","iopub.status.idle":"2026-09-17T21:34:18.461952Z","shell.execute_reply.started":"2026-09-17T21:34:18.454311Z","shell.execute_reply":"2026-09-17T21:34:18.461048Z"}},"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":"2026-09-17T21:34:18.463019Z","iopub.execute_input":"2026-09-17T21:34:18.463248Z","iopub.status.idle":"2026-09-17T21:34:28.043283Z","shell.execute_reply.started":"2026-09-17T21:34:18.463227Z","shell.execute_reply":"2026-09-17T21:34:28.039888Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"val_images, val_labels = val_it.__next__()\nval_images.shape\nplot_exmaple(val_images, val_labels)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T21:34:28.044979Z","iopub.execute_input":"2026-09-17T21:34:28.045389Z","iopub.status.idle":"2026-09-17T21:34:37.618580Z","shell.execute_reply.started":"2026-09-17T21:34:28.045363Z","shell.execute_reply":"2026-09-17T21:34:37.616934Z"}},"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":"2026-09-17T21:34:37.620347Z","iopub.execute_input":"2026-09-17T21:34:37.620817Z","iopub.status.idle":"2026-09-17T21:34:37.629155Z","shell.execute_reply.started":"2026-09-17T21:34:37.620770Z","shell.execute_reply":"2026-09-17T21:34:37.628170Z"},"jupyter":{"source_hidden":true}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"test_images, test_labels = test_it.__next__()  # หรือ next(test_it)\nprint(f\"{test_images.shape=}, {test_labels.shape}\")\n\n# สร้าง list เลขดัชนีตามจำนวนภาพที่มี\nindices = list(range(len(test_images)))\n\nplot_exmaple(test_images, test_labels)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T21:34:37.630720Z","iopub.execute_input":"2026-09-17T21:34:37.631028Z","iopub.status.idle":"2026-09-17T21:34:47.614660Z","shell.execute_reply.started":"2026-09-17T21:34:37.631000Z","shell.execute_reply":"2026-09-17T21:34:47.611869Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# import numpy as np\n\n\n# # 1. สุ่ม index มา 10 ตัวจากชุดข้อมูล\n# sample_indices = np.random.choice(len(test_images), size=10, replace=False)\n# sample_images = test_images[sample_indices]\n\n# # 2. Predict \n# predictions = model_1.predict(sample_images)\n# predicted_classes = np.argmax(predictions, axis=1)  # ดึง class ที่ได้คะแนนสูงสุด\n\n# # 3. แสดงผล 10 ภาพ (ปรับเป็น grid 2x5)\n# fig, axes = plt.subplots(2, 5, figsize=(15, 6))\n# axes = axes.flatten()\n\n# for 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\n# plt.tight_layout()\n# plt.show()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T21:34:47.616747Z","iopub.execute_input":"2026-09-17T21:34:47.617225Z","iopub.status.idle":"2026-09-17T21:34:47.623583Z","shell.execute_reply.started":"2026-09-17T21:34:47.617173Z","shell.execute_reply":"2026-09-17T21:34:47.622482Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# 2026-09-13\n# Transfer Learning","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T21:34:47.624957Z","iopub.execute_input":"2026-09-17T21:34:47.625337Z","iopub.status.idle":"2026-09-17T21:34:47.639208Z","shell.execute_reply.started":"2026-09-17T21:34:47.625302Z","shell.execute_reply":"2026-09-17T21:34:47.637962Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"id(train_it), id(val_it), id(test_it)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T21:34:47.640736Z","iopub.execute_input":"2026-09-17T21:34:47.641097Z","iopub.status.idle":"2026-09-17T21:34:47.652224Z","shell.execute_reply.started":"2026-09-17T21:34:47.641066Z","shell.execute_reply":"2026-09-17T21:34:47.651312Z"}},"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# Hyperparameter => changable\nIMAGE_SIZE = 224\nBATCH_SIE = 64\nEPOCHS = 20\n\n# define cnn model\ndef define_model_vgg16():\n\t# load model\n\tmodel = VGG16(include_top=False, input_shape=(IMAGE_SIZE, IMAGE_SIZE, 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\n\nvgg16 = define_model_vgg16()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T21:34:47.653465Z","iopub.execute_input":"2026-09-17T21:34:47.653847Z","iopub.status.idle":"2026-09-17T21:34:48.078512Z","shell.execute_reply.started":"2026-09-17T21:34:47.653812Z","shell.execute_reply":"2026-09-17T21:34:48.077290Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Load model\nmodel_vgg16_top = VGG16(include_top=True,\n                        input_shape=(IMAGE_SIZE, IMAGE_SIZE, 3)\n                       )\nmodel_vgg16_top.summary()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T21:34:48.079979Z","iopub.execute_input":"2026-09-17T21:34:48.080295Z","iopub.status.idle":"2026-09-17T21:34:50.457824Z","shell.execute_reply.started":"2026-09-17T21:34:48.080269Z","shell.execute_reply":"2026-09-17T21:34:50.456884Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Load model\nmodel_16_feature_extractor = VGG16(include_top=False,\n                                   input_shape=(IMAGE_SIZE, IMAGE_SIZE, 3)\n                                  )\nmodel_16_feature_extractor.summary() #feature extractor as a backbone","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T21:34:50.459397Z","iopub.execute_input":"2026-09-17T21:34:50.459814Z","iopub.status.idle":"2026-09-17T21:34:50.827562Z","shell.execute_reply.started":"2026-09-17T21:34:50.459776Z","shell.execute_reply":"2026-09-17T21:34:50.826680Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"for index, layer in enumerate(model_16_feature_extractor.layers):\n\t\tprint(index, layer.trainable, layer.output.shape)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T21:34:50.829024Z","iopub.execute_input":"2026-09-17T21:34:50.829430Z","iopub.status.idle":"2026-09-17T21:34:50.835480Z","shell.execute_reply.started":"2026-09-17T21:34:50.829391Z","shell.execute_reply":"2026-09-17T21:34:50.834489Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"for index, layer in enumerate(model_16_feature_extractor.layers):\n    if index <= 15:\n        layer.trainable = False\n\nfor index, layer in enumerate(model_16_feature_extractor.layers):\n    print(index, layer.name, layer.trainable)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T21:34:50.836746Z","iopub.execute_input":"2026-09-17T21:34:50.837593Z","iopub.status.idle":"2026-09-17T21:34:50.846597Z","shell.execute_reply.started":"2026-09-17T21:34:50.837551Z","shell.execute_reply":"2026-09-17T21:34:50.845589Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"model_16_feature_extractor.layers[-1].output","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T21:34:50.847985Z","iopub.execute_input":"2026-09-17T21:34:50.848316Z","iopub.status.idle":"2026-09-17T21:34:50.858633Z","shell.execute_reply.started":"2026-09-17T21:34:50.848292Z","shell.execute_reply":"2026-09-17T21:34:50.857499Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Use functional API\nflat1 = Flatten()(model_16_feature_extractor.layers[-1].output)\nprint(flat1.shape)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T21:34:50.859885Z","iopub.execute_input":"2026-09-17T21:34:50.860298Z","iopub.status.idle":"2026-09-17T21:34:50.871282Z","shell.execute_reply.started":"2026-09-17T21:34:50.860267Z","shell.execute_reply":"2026-09-17T21:34:50.870405Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"class1 = Dense(128, activation='relu', kernel_initializer='he_uniform')(flat1)\nprint(class1.shape)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T21:34:50.872360Z","iopub.execute_input":"2026-09-17T21:34:50.872659Z","iopub.status.idle":"2026-09-17T21:34:50.893301Z","shell.execute_reply.started":"2026-09-17T21:34:50.872636Z","shell.execute_reply":"2026-09-17T21:34:50.892245Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"output = Dense(1, activation='sigmoid')(class1)\nprint(output.shape)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T21:34:50.894470Z","iopub.execute_input":"2026-09-17T21:34:50.894784Z","iopub.status.idle":"2026-09-17T21:34:50.910888Z","shell.execute_reply.started":"2026-09-17T21:34:50.894760Z","shell.execute_reply":"2026-09-17T21:34:50.909748Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# define new model to be trained\nmodel_vgg16 = Model(inputs=model_16_feature_extractor.inputs, outputs=output)\n# compile model\nopt = SGD(lr=0.001, momentum=0.9)\n\nmodel_vgg16.compile(optimizer=opt,\n                    loss='binary_crossentropy',\n                    metrics=['accuracy']\n                   )","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T21:34:50.912026Z","iopub.execute_input":"2026-09-17T21:34:50.912329Z","iopub.status.idle":"2026-09-17T21:34:50.929719Z","shell.execute_reply.started":"2026-09-17T21:34:50.912302Z","shell.execute_reply":"2026-09-17T21:34:50.928951Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"print(model_vgg16.summary())","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T21:34:50.930739Z","iopub.execute_input":"2026-09-17T21:34:50.930997Z","iopub.status.idle":"2026-09-17T21:34:50.979358Z","shell.execute_reply.started":"2026-09-17T21:34:50.930975Z","shell.execute_reply":"2026-09-17T21:34:50.977399Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"id(train_it), id(val_it)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T21:34:50.980610Z","iopub.execute_input":"2026-09-17T21:34:50.980951Z","iopub.status.idle":"2026-09-17T21:34:50.988198Z","shell.execute_reply.started":"2026-09-17T21:34:50.980917Z","shell.execute_reply":"2026-09-17T21:34:50.987196Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# model_vgg16 = define_model_vgg16()\n# print(model_vgg16)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T21:34:50.989437Z","iopub.execute_input":"2026-09-17T21:34:50.989794Z","iopub.status.idle":"2026-09-17T21:34:50.997427Z","shell.execute_reply.started":"2026-09-17T21:34:50.989763Z","shell.execute_reply":"2026-09-17T21:34:50.996288Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# fit model\nimport tensorflow as tf\nfrom tensorflow.keras.callbacks import EarlyStopping, ReduceLROnPlateau # ดึงตัวช่วยหยุดและปรับ LR มาใช้\n\n# 1. Verify that TensorFlow can communicate with the GPU hardware\nphysical_devices = tf.config.list_physical_devices('GPU')\nprint(f\"Hardware status: {len(physical_devices)} GPU(s) detected.\")\n\nif len(physical_devices) > 0:\n    # Optional but highly recommended: Prevent TF from pre-allocating 100% of VRAM\n    try:\n        tf.config.experimental.set_memory_growth(physical_devices[0], True)\n    except Exception as e:\n        print(f\"Memory growth configuration failed: {e}\")\n\n    # 2. Explicitly bind the execution to the primary GPU\n    with tf.device('/GPU:0'):\n        \n        print(f\"Model ID: {id(model_vgg16)}\")\n        \n        # เอา reset_states() ออกไปแล้วเพราะไม่มีผลกับ VGG16\n        \n        model_vgg16_history = model_vgg16.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,  \n            verbose=1,\n            callbacks=[\n                PlotLossesKeras(),\n                EarlyStopping(monitor='val_accuracy', patience=10, restore_best_weights=True),\n                ReduceLROnPlateau(monitor='val_loss', factor=0.5, patience=3)\n            ]\n        )\nelse:\n    print(\"WARNING: No GPU detected. Execution will proceed on the CPU, which will be significantly slower.\")\n    # Fallback to standard execution\n    model_vgg16_history = model_vgg16.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,\n        verbose=1,\n        callbacks=[\n            PlotLossesKeras(),\n            EarlyStopping(monitor='val_accuracy', patience=10, restore_best_weights=True),\n            ReduceLROnPlateau(monitor='val_loss', factor=0.5, patience=3)\n        ]\n    )","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T21:47:10.805291Z","iopub.execute_input":"2026-09-17T21:47:10.806022Z","iopub.status.idle":"2026-09-17T21:52:06.125725Z","shell.execute_reply.started":"2026-09-17T21:47:10.805982Z","shell.execute_reply":"2026-09-17T21:52:06.124893Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# learning curves\nsummarize_diagnostics(model_vgg16_history)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T21:52:06.127323Z","iopub.execute_input":"2026-09-17T21:52:06.127918Z","iopub.status.idle":"2026-09-17T21:52:06.428022Z","shell.execute_reply.started":"2026-09-17T21:52:06.127888Z","shell.execute_reply":"2026-09-17T21:52:06.427249Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# evaluate model\n_, acc = model_vgg16.evaluate(val_it, steps=len(val_it), verbose=1)\nprint('Val: > %.3f' % (acc * 100.0))","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T21:52:06.429219Z","iopub.execute_input":"2026-09-17T21:52:06.429639Z","iopub.status.idle":"2026-09-17T21:52:25.057995Z","shell.execute_reply.started":"2026-09-17T21:52:06.429611Z","shell.execute_reply":"2026-09-17T21:52:25.056991Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# evaluate model for the test set\n_, test_acc = model_vgg16.evaluate(test_it, steps=len(test_it), verbose=1)\nprint('Test: > %.3f' % (test_acc * 100.0))","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T21:52:25.060742Z","iopub.execute_input":"2026-09-17T21:52:25.061097Z","iopub.status.idle":"2026-09-17T21:53:30.146720Z","shell.execute_reply.started":"2026-09-17T21:52:25.061065Z","shell.execute_reply":"2026-09-17T21:53:30.145811Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import numpy as np\nfrom sklearn.metrics import classification_report\n\n# 1. Reset the generator state to ensure alignment from index 0\ntest_it.reset()\n\n# 2. Extract the ordered ground truth labels from the generator\ny_true = test_it.classes\nprint(y_true.shape)\n\n# 3. Execute the forward pass over the entire test dataset\n# Calculate exact steps to prevent infinite looping or partial evaluation\nsteps = np.ceil(test_it.samples / test_it.batch_size)\nprobabilities = model_vgg16.predict(test_it, steps=steps, verbose=1).squeeze()\nprint(probabilities.shape)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T21:53:30.147842Z","iopub.execute_input":"2026-09-17T21:53:30.148135Z","iopub.status.idle":"2026-09-17T21:54:02.268686Z","shell.execute_reply.started":"2026-09-17T21:53:30.148112Z","shell.execute_reply":"2026-09-17T21:54:02.267592Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"probabilities[:20]","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T21:54:02.270357Z","iopub.execute_input":"2026-09-17T21:54:02.270750Z","iopub.status.idle":"2026-09-17T21:54:02.279888Z","shell.execute_reply.started":"2026-09-17T21:54:02.270713Z","shell.execute_reply":"2026-09-17T21:54:02.278853Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"(probabilities[0] > 0.5).astype(int)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T21:54:02.281412Z","iopub.execute_input":"2026-09-17T21:54:02.281846Z","iopub.status.idle":"2026-09-17T21:54:02.289820Z","shell.execute_reply.started":"2026-09-17T21:54:02.281819Z","shell.execute_reply":"2026-09-17T21:54:02.288927Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# 4. Discretize continuous logistic probabilities into binary class predictions\ny_pred = (probabilities > 0.5).astype(int)\nprint(y_pred.shape)\n\n# 5. Extract dynamic class labels mapping (e.g., {'cats': 0, 'dogs': 1})\n# This ensures the report correctly maps index 0 and 1 to your string labels\ntarget_names = list(test_it.class_indices.keys())\n\n# 6. Compute and output the classification report\nreport = classification_report(y_true, y_pred, target_names=target_names)\nprint(report)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T21:54:02.290751Z","iopub.execute_input":"2026-09-17T21:54:02.291009Z","iopub.status.idle":"2026-09-17T21:54:02.316437Z","shell.execute_reply.started":"2026-09-17T21:54:02.290985Z","shell.execute_reply":"2026-09-17T21:54:02.315604Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"y_true[:10], y_pred[:10]","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T21:54:02.317441Z","iopub.execute_input":"2026-09-17T21:54:02.317779Z","iopub.status.idle":"2026-09-17T21:54:02.324258Z","shell.execute_reply.started":"2026-09-17T21:54:02.317740Z","shell.execute_reply":"2026-09-17T21:54:02.323297Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Predict\nimport numpy as np\nimport matplotlib.pyplot as plt\n\n# 1. Aggregate sufficient samples from the iterator\nimages_list = []\nlabels_list = []\n\n# Fetch 2 batches (2 * 64 = 128 samples) to ensure we have pool > 100\nfor _ in range(2):\n    batch_images, batch_labels = next(test_it)\n    images_list.append(batch_images)\n    labels_list.append(batch_labels)\n\n# Concatenate into a single tensor\nall_images = np.concatenate(images_list, axis=0)\nall_labels = np.concatenate(labels_list, axis=0)\n\n# 2. Stochastically sample 100 unique indices\nnp.random.seed(42) # For reproducibility\nrandom_indices = np.random.choice(all_images.shape[0], size=100, replace=False)\n\nsample_images = all_images[random_indices]\nsample_labels = all_labels[random_indices]\n\n# 3. Execute the forward pass\n# Squeeze is used to convert shape (100, 1) to (100,)\nprobabilities = model_vgg16.predict(sample_images).squeeze()\n\n# 4. Thresholding (Assuming standard mapping: 0 = Cat, 1 = Dog)\npredictions = (probabilities > 0.5).astype(int)\nclass_mapping = {0: 'Cat', 1: 'Dog'}\n\nprint(\"Done.\")","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T21:54:02.327285Z","iopub.execute_input":"2026-09-17T21:54:02.327635Z","iopub.status.idle":"2026-09-17T21:54:10.039264Z","shell.execute_reply.started":"2026-09-17T21:54:02.327610Z","shell.execute_reply":"2026-09-17T21:54:10.038288Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Initialize a 10x10 matrix visualization\nfig, axes = plt.subplots(10, 10, figsize=(20, 22))\naxes = axes.flatten()\n\nfor i in range(100):\n    ax = axes[i]\n    \n    # Isolate image tensor. \n    # NOTE: If your VGG16 preprocessor applies mean-centering (caffe style) \n    # instead of standard [0,1] scaling, you must reverse it here for correct plt.imshow() rendering.\n    # We assume standard [0, 1] or [0, 255] spatial tensors below.\n    img = sample_images[i]\n    if img.max() > 1.0 or img.min() < 0:\n        # Simple normalization for display purposes\n        img = (img - img.min()) / (img.max() - img.min())\n        \n    ax.imshow(img)\n    ax.axis('off')\n    \n    # Extract structural labels\n    gt_class = class_mapping[int(sample_labels[i])]\n    pred_class = class_mapping[predictions[i]]\n    prob = probabilities[i]\n    \n    # Apply conditional color coding (Green for True Positives/Negatives, Red for False Positives/Negatives)\n    text_color = 'darkgreen' if gt_class == pred_class else 'darkred'\n    \n    title_str = f\"GT: {gt_class}\\nPred: {pred_class}\\nProb: {prob:.3f}\"\n    ax.set_title(title_str, color=text_color, fontsize=9, pad=4)\n\nplt.tight_layout()\nplt.show()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T21:54:10.042099Z","iopub.execute_input":"2026-09-17T21:54:10.042968Z","iopub.status.idle":"2026-09-17T21:54:18.660338Z","shell.execute_reply.started":"2026-09-17T21:54:10.042928Z","shell.execute_reply":"2026-09-17T21:54:18.658625Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"stop","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T21:54:18.662216Z","iopub.execute_input":"2026-09-17T21:54:18.662733Z","iopub.status.idle":"2026-09-17T21:54:18.722804Z","shell.execute_reply.started":"2026-09-17T21:54:18.662682Z","shell.execute_reply":"2026-09-17T21:54:18.721596Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# InceptionV3","metadata":{}},{"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},"outputs":[],"execution_count":null},{"cell_type":"code","source":"model_inceptionv3 = define_model_inceptionv3()\nprint(id(model_inceptionv3))\n# model_inceptionv3.summary()","metadata":{"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},"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},"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}]}