{"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":"2026-09-12T21:53:47.25342Z","iopub.execute_input":"2026-09-12T21:53:47.254518Z","iopub.status.idle":"2026-09-12T21:53:47.259889Z","shell.execute_reply.started":"2026-09-12T21:53:47.254475Z","shell.execute_reply":"2026-09-12T21:53:47.258835Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"!python --version","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T21:53:47.261488Z","iopub.execute_input":"2026-09-12T21:53:47.262081Z","iopub.status.idle":"2026-09-12T21:53:48.273183Z","shell.execute_reply.started":"2026-09-12T21:53:47.262046Z","shell.execute_reply":"2026-09-12T21:53:48.272208Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"!uname --all","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T21:53:48.27473Z","iopub.execute_input":"2026-09-12T21:53:48.27499Z","iopub.status.idle":"2026-09-12T21:53:49.275068Z","shell.execute_reply.started":"2026-09-12T21:53:48.274966Z","shell.execute_reply":"2026-09-12T21:53:49.274113Z"}},"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":"2026-09-12T21:53:49.276644Z","iopub.execute_input":"2026-09-12T21:53:49.27696Z","iopub.status.idle":"2026-09-12T21:53:58.586374Z","shell.execute_reply.started":"2026-09-12T21:53:49.276933Z","shell.execute_reply":"2026-09-12T21:53:58.585633Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T21:53:58.588722Z","iopub.execute_input":"2026-09-12T21:53:58.589082Z","iopub.status.idle":"2026-09-12T21:53:59.592849Z","shell.execute_reply.started":"2026-09-12T21:53:58.589057Z","shell.execute_reply":"2026-09-12T21:53:59.591878Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -l","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T21:53:59.594475Z","iopub.execute_input":"2026-09-12T21:53:59.594857Z","iopub.status.idle":"2026-09-12T21:54:00.635485Z","shell.execute_reply.started":"2026-09-12T21:53:59.594821Z","shell.execute_reply":"2026-09-12T21:54:00.634543Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls test1/ | wc -l","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T21:54:00.637027Z","iopub.execute_input":"2026-09-12T21:54:00.637336Z","iopub.status.idle":"2026-09-12T21:54:01.724489Z","shell.execute_reply.started":"2026-09-12T21:54:00.637311Z","shell.execute_reply":"2026-09-12T21:54:01.723072Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls train/ | wc -l","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T21:54:01.726227Z","iopub.execute_input":"2026-09-12T21:54:01.726684Z","iopub.status.idle":"2026-09-12T21:54:02.825612Z","shell.execute_reply.started":"2026-09-12T21:54:01.726654Z","shell.execute_reply":"2026-09-12T21:54:02.824669Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"#ls train/","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T21:54:02.827086Z","iopub.execute_input":"2026-09-12T21:54:02.827402Z","iopub.status.idle":"2026-09-12T21:54:02.831963Z","shell.execute_reply.started":"2026-09-12T21:54:02.827373Z","shell.execute_reply":"2026-09-12T21:54:02.830942Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -U train | head -n 10","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T21:54:02.833265Z","iopub.execute_input":"2026-09-12T21:54:02.833883Z","iopub.status.idle":"2026-09-12T21:54:03.908232Z","shell.execute_reply.started":"2026-09-12T21:54:02.833857Z","shell.execute_reply":"2026-09-12T21:54:03.906957Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -U test1 | head -n 10","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T21:54:03.909944Z","iopub.execute_input":"2026-09-12T21:54:03.910678Z","iopub.status.idle":"2026-09-12T21:54:04.950133Z","shell.execute_reply.started":"2026-09-12T21:54:03.91065Z","shell.execute_reply":"2026-09-12T21:54:04.949109Z"}},"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":"2026-09-12T21:54:04.951644Z","iopub.execute_input":"2026-09-12T21:54:04.952045Z","iopub.status.idle":"2026-09-12T21:54:05.865701Z","shell.execute_reply.started":"2026-09-12T21:54:04.952015Z","shell.execute_reply":"2026-09-12T21:54:05.864647Z"},"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":"2026-09-12T21:54:05.867061Z","iopub.execute_input":"2026-09-12T21:54:05.867721Z","iopub.status.idle":"2026-09-12T21:54:06.759459Z","shell.execute_reply.started":"2026-09-12T21:54:05.867691Z","shell.execute_reply":"2026-09-12T21:54:06.758613Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"!python --version","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T21:54:06.764205Z","iopub.execute_input":"2026-09-12T21:54:06.764539Z","iopub.status.idle":"2026-09-12T21:54:07.774728Z","shell.execute_reply.started":"2026-09-12T21:54:06.764514Z","shell.execute_reply":"2026-09-12T21:54:07.77373Z"}},"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":"2026-09-12T21:54:07.776207Z","iopub.execute_input":"2026-09-12T21:54:07.776467Z","iopub.status.idle":"2026-09-12T21:54:07.781773Z","shell.execute_reply.started":"2026-09-12T21:54:07.776445Z","shell.execute_reply":"2026-09-12T21:54:07.780844Z"}},"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":"2026-09-12T21:54:07.782928Z","iopub.execute_input":"2026-09-12T21:54:07.783471Z","iopub.status.idle":"2026-09-12T21:54:07.791669Z","shell.execute_reply.started":"2026-09-12T21:54:07.783449Z","shell.execute_reply":"2026-09-12T21:54:07.790836Z"},"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":"2026-09-12T21:54:07.792808Z","iopub.execute_input":"2026-09-12T21:54:07.793343Z","iopub.status.idle":"2026-09-12T21:54:07.800619Z","shell.execute_reply.started":"2026-09-12T21:54:07.793308Z","shell.execute_reply":"2026-09-12T21:54:07.799625Z"},"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":"2026-09-12T21:54:07.801805Z","iopub.execute_input":"2026-09-12T21:54:07.802403Z","iopub.status.idle":"2026-09-12T21:54:07.811838Z","shell.execute_reply.started":"2026-09-12T21:54:07.802371Z","shell.execute_reply":"2026-09-12T21:54:07.810955Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -l","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T21:54:07.813027Z","iopub.execute_input":"2026-09-12T21:54:07.813304Z","iopub.status.idle":"2026-09-12T21:54:08.826388Z","shell.execute_reply.started":"2026-09-12T21:54:07.813283Z","shell.execute_reply":"2026-09-12T21:54:08.825441Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -l dataset_dogs_vs_cats/train","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T21:54:08.827792Z","iopub.execute_input":"2026-09-12T21:54:08.828097Z","iopub.status.idle":"2026-09-12T21:54:09.831473Z","shell.execute_reply.started":"2026-09-12T21:54:08.828071Z","shell.execute_reply":"2026-09-12T21:54:09.83037Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -l dataset_dogs_vs_cats/test #validation","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T21:54:09.833078Z","iopub.execute_input":"2026-09-12T21:54:09.833392Z","iopub.status.idle":"2026-09-12T21:54:10.845532Z","shell.execute_reply.started":"2026-09-12T21:54:09.833366Z","shell.execute_reply":"2026-09-12T21:54:10.844553Z"}},"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":"2026-09-12T21:54:10.846976Z","iopub.execute_input":"2026-09-12T21:54:10.847275Z","iopub.status.idle":"2026-09-12T21:54:13.799201Z","shell.execute_reply.started":"2026-09-12T21:54:10.84725Z","shell.execute_reply":"2026-09-12T21:54:13.798426Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"print(src)\nprint(dst)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T21:54:13.800553Z","iopub.execute_input":"2026-09-12T21:54:13.800909Z","iopub.status.idle":"2026-09-12T21:54:13.805807Z","shell.execute_reply.started":"2026-09-12T21:54:13.800879Z","shell.execute_reply":"2026-09-12T21:54:13.804883Z"}},"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":"2026-09-12T21:54:13.807045Z","iopub.execute_input":"2026-09-12T21:54:13.807949Z","iopub.status.idle":"2026-09-12T21:54:16.038627Z","shell.execute_reply.started":"2026-09-12T21:54:13.807913Z","shell.execute_reply":"2026-09-12T21:54:16.037251Z"},"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":"2026-09-12T21:54:16.040593Z","iopub.execute_input":"2026-09-12T21:54:16.041055Z","iopub.status.idle":"2026-09-12T21:54:18.222325Z","shell.execute_reply.started":"2026-09-12T21:54:16.041015Z","shell.execute_reply":"2026-09-12T21:54:18.220903Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"!pip -q install livelossplot==0.5.5","metadata":{"execution":{"iopub.status.busy":"2026-09-12T21:54:18.22418Z","iopub.execute_input":"2026-09-12T21:54:18.224571Z","iopub.status.idle":"2026-09-12T21:54:26.47239Z","shell.execute_reply.started":"2026-09-12T21:54:18.224532Z","shell.execute_reply":"2026-09-12T21:54:26.471013Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"from livelossplot import PlotLossesKeras","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T21:54:26.474016Z","iopub.execute_input":"2026-09-12T21:54:26.474329Z","iopub.status.idle":"2026-09-12T21:54:26.479516Z","shell.execute_reply.started":"2026-09-12T21:54:26.474303Z","shell.execute_reply":"2026-09-12T21:54:26.478783Z"}},"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":"2026-09-12T21:54:26.480754Z","iopub.execute_input":"2026-09-12T21:54:26.48108Z","iopub.status.idle":"2026-09-12T21:54:26.489548Z","shell.execute_reply.started":"2026-09-12T21:54:26.481048Z","shell.execute_reply":"2026-09-12T21:54:26.488626Z"}},"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":"2026-09-12T21:54:26.490751Z","iopub.execute_input":"2026-09-12T21:54:26.491092Z","iopub.status.idle":"2026-09-12T21:54:26.497979Z","shell.execute_reply.started":"2026-09-12T21:54:26.49107Z","shell.execute_reply":"2026-09-12T21:54:26.497065Z"}},"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":"2026-09-12T21:54:26.499142Z","iopub.execute_input":"2026-09-12T21:54:26.499842Z","iopub.status.idle":"2026-09-12T21:54:26.50635Z","shell.execute_reply.started":"2026-09-12T21:54:26.499809Z","shell.execute_reply":"2026-09-12T21:54:26.505395Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"model_1 = define_model_1()\nprint(model_1.summary())","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T21:54:26.50849Z","iopub.execute_input":"2026-09-12T21:54:26.509162Z","iopub.status.idle":"2026-09-12T21:54:26.580837Z","shell.execute_reply.started":"2026-09-12T21:54:26.50914Z","shell.execute_reply":"2026-09-12T21:54:26.579971Z"}},"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":"2026-09-12T21:54:26.581942Z","iopub.execute_input":"2026-09-12T21:54:26.582251Z","iopub.status.idle":"2026-09-12T21:54:26.587541Z","shell.execute_reply.started":"2026-09-12T21:54:26.582229Z","shell.execute_reply":"2026-09-12T21:54:26.586784Z"}},"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":"2026-09-12T21:54:26.588636Z","iopub.execute_input":"2026-09-12T21:54:26.589178Z","iopub.status.idle":"2026-09-12T21:54:26.645983Z","shell.execute_reply.started":"2026-09-12T21:54:26.589137Z","shell.execute_reply":"2026-09-12T21:54:26.645175Z"}},"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\ninputs = Input(shape=(200, 200, 3))\n\n# Construct the forward pass of the computational graph\nx = Conv2D(32, (3, 3), activation='relu')(inputs)\nx = MaxPooling2D((2, 2))(x)\nx = Flatten()(x)\nx = Dense(128, activation='relu')(x)\n\n# Define the output tensor with the target objective function representation\noutputs = Dense(2, activation='softmax')(x)\n\n# Instantiate the formal model architecture\nmodel = Model(inputs=inputs, outputs=outputs)\n\nprint(model.summary())","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T21:54:26.64708Z","iopub.execute_input":"2026-09-12T21:54:26.647391Z","iopub.status.idle":"2026-09-12T21:54:26.704772Z","shell.execute_reply.started":"2026-09-12T21:54:26.647361Z","shell.execute_reply":"2026-09-12T21:54:26.70395Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"datagen = ImageDataGenerator(rescale=1.0/255.0)\ntype(datagen)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T21:54:26.705854Z","iopub.execute_input":"2026-09-12T21:54:26.706171Z","iopub.status.idle":"2026-09-12T21:54:26.712771Z","shell.execute_reply.started":"2026-09-12T21:54:26.706141Z","shell.execute_reply":"2026-09-12T21:54:26.711872Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls dataset_dogs_vs_cats/train/","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T21:54:26.713928Z","iopub.execute_input":"2026-09-12T21:54:26.714485Z","iopub.status.idle":"2026-09-12T21:54:27.722523Z","shell.execute_reply.started":"2026-09-12T21:54:26.714462Z","shell.execute_reply":"2026-09-12T21:54:27.721628Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"IMAGE_SIZE = 224\nBATCH_SIZE = 64\nEPOCHS = 30","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T21:54:27.724157Z","iopub.execute_input":"2026-09-12T21:54:27.725004Z","iopub.status.idle":"2026-09-12T21:54:27.729959Z","shell.execute_reply.started":"2026-09-12T21:54:27.724966Z","shell.execute_reply":"2026-09-12T21:54:27.729006Z"}},"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":"2026-09-12T21:54:27.730969Z","iopub.execute_input":"2026-09-12T21:54:27.731256Z","iopub.status.idle":"2026-09-12T21:54:32.112101Z","shell.execute_reply.started":"2026-09-12T21:54:27.731233Z","shell.execute_reply":"2026-09-12T21:54:32.111367Z"}},"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":"2026-09-12T21:54:32.113067Z","iopub.execute_input":"2026-09-12T21:54:32.113682Z","iopub.status.idle":"2026-09-12T21:54:32.119933Z","shell.execute_reply.started":"2026-09-12T21:54:32.113647Z","shell.execute_reply":"2026-09-12T21:54:32.118933Z"}},"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":"2026-09-12T21:54:32.12121Z","iopub.execute_input":"2026-09-12T21:54:32.121897Z","iopub.status.idle":"2026-09-12T21:54:32.131097Z","shell.execute_reply.started":"2026-09-12T21:54:32.121864Z","shell.execute_reply":"2026-09-12T21:54:32.130072Z"}},"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":"2026-09-12T21:54:32.140973Z","iopub.execute_input":"2026-09-12T21:54:32.141381Z","iopub.status.idle":"2026-09-12T21:54:32.145002Z","shell.execute_reply.started":"2026-09-12T21:54:32.141358Z","shell.execute_reply":"2026-09-12T21:54:32.144098Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# learning curves\n# summarize_diagnostics(history_1)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T21:54:32.146204Z","iopub.execute_input":"2026-09-12T21:54:32.146518Z","iopub.status.idle":"2026-09-12T21:54:32.153218Z","shell.execute_reply.started":"2026-09-12T21:54:32.146487Z","shell.execute_reply":"2026-09-12T21:54:32.152306Z"}},"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":"2026-09-12T21:54:32.154364Z","iopub.execute_input":"2026-09-12T21:54:32.154826Z","iopub.status.idle":"2026-09-12T21:54:32.162852Z","shell.execute_reply.started":"2026-09-12T21:54:32.154793Z","shell.execute_reply":"2026-09-12T21:54:32.161931Z"}},"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":"2026-09-12T21:54:32.163892Z","iopub.execute_input":"2026-09-12T21:54:32.164197Z","iopub.status.idle":"2026-09-12T21:54:33.180549Z","shell.execute_reply.started":"2026-09-12T21:54:32.164168Z","shell.execute_reply":"2026-09-12T21:54:33.179546Z"}},"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":"2026-09-12T21:54:33.182001Z","iopub.execute_input":"2026-09-12T21:54:33.182306Z","iopub.status.idle":"2026-09-12T21:54:33.188224Z","shell.execute_reply.started":"2026-09-12T21:54:33.182281Z","shell.execute_reply":"2026-09-12T21:54:33.187313Z"}},"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":"2026-09-12T21:54:33.190373Z","iopub.execute_input":"2026-09-12T21:54:33.190753Z","iopub.status.idle":"2026-09-12T21:54:33.197449Z","shell.execute_reply.started":"2026-09-12T21:54:33.190711Z","shell.execute_reply":"2026-09-12T21:54:33.196722Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# image_files[:5], type(image_files), len(image_files)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T21:54:33.199045Z","iopub.execute_input":"2026-09-12T21:54:33.199385Z","iopub.status.idle":"2026-09-12T21:54:33.206256Z","shell.execute_reply.started":"2026-09-12T21:54:33.199352Z","shell.execute_reply":"2026-09-12T21:54:33.205449Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# test_df.describe()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T21:54:33.207481Z","iopub.execute_input":"2026-09-12T21:54:33.208065Z","iopub.status.idle":"2026-09-12T21:54:33.21443Z","shell.execute_reply.started":"2026-09-12T21:54:33.208034Z","shell.execute_reply":"2026-09-12T21:54:33.213627Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# test_df.loc[1]","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T21:54:33.215577Z","iopub.execute_input":"2026-09-12T21:54:33.215974Z","iopub.status.idle":"2026-09-12T21:54:33.222549Z","shell.execute_reply.started":"2026-09-12T21:54:33.215916Z","shell.execute_reply":"2026-09-12T21:54:33.221758Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# test_df.sample(5)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T21:54:33.223623Z","iopub.execute_input":"2026-09-12T21:54:33.22393Z","iopub.status.idle":"2026-09-12T21:54:33.232048Z","shell.execute_reply.started":"2026-09-12T21:54:33.223901Z","shell.execute_reply":"2026-09-12T21:54:33.231236Z"}},"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":"2026-09-12T21:54:33.233097Z","iopub.execute_input":"2026-09-12T21:54:33.233433Z","iopub.status.idle":"2026-09-12T21:54:33.240145Z","shell.execute_reply.started":"2026-09-12T21:54:33.233412Z","shell.execute_reply":"2026-09-12T21:54:33.239411Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"IMAGE_SIZE","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T21:54:33.24117Z","iopub.execute_input":"2026-09-12T21:54:33.241821Z","iopub.status.idle":"2026-09-12T21:54:33.251752Z","shell.execute_reply.started":"2026-09-12T21:54:33.241788Z","shell.execute_reply":"2026-09-12T21:54:33.251001Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"test_it = 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":"2026-09-12T21:54:33.253001Z","iopub.execute_input":"2026-09-12T21:54:33.25335Z","iopub.status.idle":"2026-09-12T21:54:34.356554Z","shell.execute_reply.started":"2026-09-12T21:54:33.25332Z","shell.execute_reply":"2026-09-12T21:54:34.355531Z"}},"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":"2026-09-12T21:54:34.357908Z","iopub.execute_input":"2026-09-12T21:54:34.358244Z","iopub.status.idle":"2026-09-12T21:54:34.364385Z","shell.execute_reply.started":"2026-09-12T21:54:34.358212Z","shell.execute_reply":"2026-09-12T21:54:34.363517Z"}},"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":"2026-09-12T21:54:34.365663Z","iopub.execute_input":"2026-09-12T21:54:34.366362Z","iopub.status.idle":"2026-09-12T21:54:43.056349Z","shell.execute_reply.started":"2026-09-12T21:54:34.366329Z","shell.execute_reply":"2026-09-12T21:54:43.055132Z"}},"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":"2026-09-12T21:54:43.057483Z","iopub.execute_input":"2026-09-12T21:54:43.058069Z","iopub.status.idle":"2026-09-12T21:54:51.438385Z","shell.execute_reply.started":"2026-09-12T21:54:43.058042Z","shell.execute_reply":"2026-09-12T21:54:51.436955Z"}},"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,"jupyter":{"source_hidden":true},"execution":{"iopub.status.busy":"2026-09-12T21:54:51.439647Z","iopub.execute_input":"2026-09-12T21:54:51.439965Z","iopub.status.idle":"2026-09-12T21:54:51.445953Z","shell.execute_reply.started":"2026-09-12T21:54:51.43994Z","shell.execute_reply":"2026-09-12T21:54:51.445089Z"}},"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":"2026-09-12T21:54:51.447168Z","iopub.execute_input":"2026-09-12T21:54:51.447467Z","iopub.status.idle":"2026-09-12T21:54:59.397096Z","shell.execute_reply.started":"2026-09-12T21:54:51.44744Z","shell.execute_reply":"2026-09-12T21:54:59.395179Z"}},"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":"2026-09-12T21:54:59.398501Z","iopub.execute_input":"2026-09-12T21:54:59.398837Z","iopub.status.idle":"2026-09-12T21:54:59.403946Z","shell.execute_reply.started":"2026-09-12T21:54:59.398807Z","shell.execute_reply":"2026-09-12T21:54:59.402916Z"}},"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":"2026-09-12T21:54:59.405033Z","iopub.execute_input":"2026-09-12T21:54:59.405389Z","iopub.status.idle":"2026-09-12T21:54:59.413382Z","shell.execute_reply.started":"2026-09-12T21:54:59.405357Z","shell.execute_reply":"2026-09-12T21:54:59.412333Z"}},"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":"2026-09-12T21:54:59.4146Z","iopub.execute_input":"2026-09-12T21:54:59.414926Z","iopub.status.idle":"2026-09-12T21:54:59.760315Z","shell.execute_reply.started":"2026-09-12T21:54:59.414893Z","shell.execute_reply":"2026-09-12T21:54:59.759651Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Load model\nmodel_vgg16_top = VGG16(include_top=True, input_shape=(IMAGE_SIZE, IMAGE_SIZE, 3))\nmodel_vgg16_top.summary()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T21:54:59.761672Z","iopub.execute_input":"2026-09-12T21:54:59.762289Z","iopub.status.idle":"2026-09-12T21:55:02.019341Z","shell.execute_reply.started":"2026-09-12T21:54:59.762237Z","shell.execute_reply":"2026-09-12T21:55:02.018477Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Load model\nmodel_16_feature_extractor = VGG16(include_top=False, input_shape=(IMAGE_SIZE, IMAGE_SIZE, 3))\nmodel_16_feature_extractor.summary()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T21:55:02.020551Z","iopub.execute_input":"2026-09-12T21:55:02.02088Z","iopub.status.idle":"2026-09-12T21:55:02.359722Z","shell.execute_reply.started":"2026-09-12T21:55:02.020856Z","shell.execute_reply":"2026-09-12T21:55:02.358764Z"}},"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":"2026-09-12T21:55:02.360836Z","iopub.execute_input":"2026-09-12T21:55:02.361071Z","iopub.status.idle":"2026-09-12T21:55:02.366288Z","shell.execute_reply.started":"2026-09-12T21:55:02.361051Z","shell.execute_reply":"2026-09-12T21:55:02.365297Z"}},"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":"2026-09-12T21:55:02.367419Z","iopub.execute_input":"2026-09-12T21:55:02.367878Z","iopub.status.idle":"2026-09-12T21:55:02.379384Z","shell.execute_reply.started":"2026-09-12T21:55:02.367847Z","shell.execute_reply":"2026-09-12T21:55:02.378358Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"model_16_feature_extractor.layers[-1].output","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T21:55:02.380578Z","iopub.execute_input":"2026-09-12T21:55:02.381147Z","iopub.status.idle":"2026-09-12T21:55:02.389339Z","shell.execute_reply.started":"2026-09-12T21:55:02.381124Z","shell.execute_reply":"2026-09-12T21:55:02.388354Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"flat1 = Flatten()(model_16_feature_extractor.layers[-1].output)\nprint(flat1.shape)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T21:55:02.390413Z","iopub.execute_input":"2026-09-12T21:55:02.390803Z","iopub.status.idle":"2026-09-12T21:55:02.402215Z","shell.execute_reply.started":"2026-09-12T21:55:02.390781Z","shell.execute_reply":"2026-09-12T21:55:02.401392Z"}},"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":"2026-09-12T21:55:02.403343Z","iopub.execute_input":"2026-09-12T21:55:02.404195Z","iopub.status.idle":"2026-09-12T21:55:02.418164Z","shell.execute_reply.started":"2026-09-12T21:55:02.404171Z","shell.execute_reply":"2026-09-12T21:55:02.417464Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"output = Dense(1, activation='sigmoid')(class1)\nprint(output.shape)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T21:55:02.419072Z","iopub.execute_input":"2026-09-12T21:55:02.419377Z","iopub.status.idle":"2026-09-12T21:55:02.432651Z","shell.execute_reply.started":"2026-09-12T21:55:02.419356Z","shell.execute_reply":"2026-09-12T21:55:02.431744Z"}},"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, loss='binary_crossentropy', metrics=['accuracy'])","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T21:55:02.433727Z","iopub.execute_input":"2026-09-12T21:55:02.434022Z","iopub.status.idle":"2026-09-12T21:55:02.448187Z","shell.execute_reply.started":"2026-09-12T21:55:02.433993Z","shell.execute_reply":"2026-09-12T21:55:02.44753Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"print(model_vgg16.summary())","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T21:55:02.449103Z","iopub.execute_input":"2026-09-12T21:55:02.449573Z","iopub.status.idle":"2026-09-12T21:55:02.499364Z","shell.execute_reply.started":"2026-09-12T21:55:02.449551Z","shell.execute_reply":"2026-09-12T21:55:02.498417Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"id(train_it), id(val_it)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T21:55:02.500325Z","iopub.execute_input":"2026-09-12T21:55:02.500787Z","iopub.status.idle":"2026-09-12T21:55:02.505759Z","shell.execute_reply.started":"2026-09-12T21:55:02.500765Z","shell.execute_reply":"2026-09-12T21:55:02.504898Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"model_vgg16 = define_model_vgg16()\nprint(model_vgg16)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T21:55:02.506848Z","iopub.execute_input":"2026-09-12T21:55:02.507537Z","iopub.status.idle":"2026-09-12T21:55:02.854494Z","shell.execute_reply.started":"2026-09-12T21:55:02.507514Z","shell.execute_reply":"2026-09-12T21:55:02.853645Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# fit model\nimport tensorflow as tf\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        # Note: reset_states() is strictly for stateful RNNs (LSTMs/GRUs). \n        # For a feed-forward CNN like VGG16, this method has no effect and can be removed.\n        model_vgg16.reset_states() \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=1, \n            verbose=1,\n            callbacks=[PlotLossesKeras()]\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=1, \n        verbose=1,\n        callbacks=[PlotLossesKeras()]\n    )","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T21:55:02.855559Z","iopub.execute_input":"2026-09-12T21:55:02.855982Z","iopub.status.idle":"2026-09-12T21:56:29.198374Z","shell.execute_reply.started":"2026-09-12T21:55:02.855955Z","shell.execute_reply":"2026-09-12T21:56:29.197652Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# learning curves\nsummarize_diagnostics(model_vgg16_history)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T21:56:29.199527Z","iopub.execute_input":"2026-09-12T21:56:29.199959Z","iopub.status.idle":"2026-09-12T21:56:29.452341Z","shell.execute_reply.started":"2026-09-12T21:56:29.199928Z","shell.execute_reply":"2026-09-12T21:56:29.451627Z"}},"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":"2026-09-12T21:56:29.453714Z","iopub.execute_input":"2026-09-12T21:56:29.454087Z","iopub.status.idle":"2026-09-12T21:56:46.841849Z","shell.execute_reply.started":"2026-09-12T21:56:29.454051Z","shell.execute_reply":"2026-09-12T21:56:46.840834Z"}},"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":"2026-09-12T21:56:46.843343Z","iopub.execute_input":"2026-09-12T21:56:46.84387Z","iopub.status.idle":"2026-09-12T21:57:15.899264Z","shell.execute_reply.started":"2026-09-12T21:56:46.84383Z","shell.execute_reply":"2026-09-12T21:57:15.898484Z"}},"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":"2026-09-12T21:57:15.900523Z","iopub.execute_input":"2026-09-12T21:57:15.900929Z","iopub.status.idle":"2026-09-12T21:57:44.131231Z","shell.execute_reply.started":"2026-09-12T21:57:15.900894Z","shell.execute_reply":"2026-09-12T21:57:44.130193Z"}},"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":"2026-09-12T21:57:44.132485Z","iopub.execute_input":"2026-09-12T21:57:44.133151Z","iopub.status.idle":"2026-09-12T21:57:44.151565Z","shell.execute_reply.started":"2026-09-12T21:57:44.133111Z","shell.execute_reply":"2026-09-12T21:57:44.150885Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"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'}","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T21:57:44.152733Z","iopub.execute_input":"2026-09-12T21:57:44.153053Z","iopub.status.idle":"2026-09-12T21:57:45.25597Z","shell.execute_reply.started":"2026-09-12T21:57:44.153023Z","shell.execute_reply":"2026-09-12T21:57:45.255172Z"}},"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":"2026-09-12T21:57:45.256966Z","iopub.execute_input":"2026-09-12T21:57:45.257804Z","iopub.status.idle":"2026-09-12T21:57:53.222476Z","shell.execute_reply.started":"2026-09-12T21:57:45.25776Z","shell.execute_reply":"2026-09-12T21:57:53.221124Z"}},"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":"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,"execution":{"iopub.status.busy":"2026-09-12T21:57:53.22407Z","iopub.execute_input":"2026-09-12T21:57:53.224443Z","iopub.status.idle":"2026-09-12T21:57:53.233335Z","shell.execute_reply.started":"2026-09-12T21:57:53.224418Z","shell.execute_reply":"2026-09-12T21:57:53.232254Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"model_inceptionv3 = define_model_inceptionv3()\nprint(id(model_inceptionv3))\n# model_inceptionv3.summary()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T21:57:53.234458Z","iopub.execute_input":"2026-09-12T21:57:53.234835Z","iopub.status.idle":"2026-09-12T21:58:00.865855Z","shell.execute_reply.started":"2026-09-12T21:57:53.234802Z","shell.execute_reply":"2026-09-12T21:58:00.865Z"}},"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":"2026-09-12T21:58:00.866944Z","iopub.execute_input":"2026-09-12T21:58:00.867221Z","iopub.status.idle":"2026-09-12T21:58:00.873145Z","shell.execute_reply.started":"2026-09-12T21:58:00.867196Z","shell.execute_reply":"2026-09-12T21:58:00.872154Z"}},"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":"2026-09-12T21:58:00.874412Z","iopub.execute_input":"2026-09-12T21:58:00.874762Z","iopub.status.idle":"2026-09-12T21:58:00.885458Z","shell.execute_reply.started":"2026-09-12T21:58:00.874731Z","shell.execute_reply":"2026-09-12T21:58:00.884642Z"}},"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":"print(train_it.class_indices)\nprint(val_it.class_indices)\nprint(model_inceptionv3.output_shape)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T22:18:09.798741Z","iopub.execute_input":"2026-09-12T22:18:09.799442Z","iopub.status.idle":"2026-09-12T22:18:09.80421Z","shell.execute_reply.started":"2026-09-12T22:18:09.799412Z","shell.execute_reply":"2026-09-12T22:18:09.803273Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"print(train_it.image_shape)\nprint(val_it.image_shape)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T22:18:30.176768Z","iopub.execute_input":"2026-09-12T22:18:30.177134Z","iopub.status.idle":"2026-09-12T22:18:30.182317Z","shell.execute_reply.started":"2026-09-12T22:18:30.177103Z","shell.execute_reply":"2026-09-12T22:18:30.181315Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"model_inceptionv3.compile(\n    optimizer='adam',\n    loss='sparse_categorical_crossentropy',\n    metrics=['accuracy']\n)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T22:21:49.836647Z","iopub.execute_input":"2026-09-12T22:21:49.837477Z","iopub.status.idle":"2026-09-12T22:21:49.854493Z","shell.execute_reply.started":"2026-09-12T22:21:49.837444Z","shell.execute_reply":"2026-09-12T22:21:49.853514Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import tensorflow as tf\nfrom tensorflow.keras.preprocessing.image import ImageDataGenerator\nfrom tensorflow.keras import layers, models\nfrom tensorflow.keras.applications import InceptionV3\n\n# 1. นิยามโครงสร้างโมเดลใหม่ทั้งหมด\nbase_model = InceptionV3(weights='imagenet', include_top=False, input_shape=(299, 299, 3))\nbase_model.trainable = False\n\nx = base_model.output\nx = layers.GlobalAveragePooling2D()(x)\nx = layers.Dense(128, activation='relu')(x)\noutputs = layers.Dense(1, activation='sigmoid')(x)\n\nmodel_inceptionv3 = models.Model(inputs=base_model.input, outputs=outputs)\n\n# 2. Compile โมเดล\nmodel_inceptionv3.compile(\n    optimizer='adam',\n    loss='binary_crossentropy',\n    metrics=['accuracy']\n)\n\n# 3. Fit โมเดล\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,\n    verbose=1\n)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T22:41:02.533367Z","iopub.execute_input":"2026-09-12T22:41:02.533845Z","iopub.status.idle":"2026-09-12T22:44:15.68289Z","shell.execute_reply.started":"2026-09-12T22:41:02.533812Z","shell.execute_reply":"2026-09-12T22:44:15.682123Z"}},"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":"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":"2026-09-12T22:44:38.487276Z","iopub.execute_input":"2026-09-12T22:44:38.488048Z","iopub.status.idle":"2026-09-12T22:44:38.495182Z","shell.execute_reply.started":"2026-09-12T22:44:38.488016Z","shell.execute_reply":"2026-09-12T22:44:38.494265Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# plot_images_with_labels(images, labels, \"Dog-Cat\", \"Training\")","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T21:58:02.008159Z","iopub.status.idle":"2026-09-12T21:58:02.0085Z","shell.execute_reply.started":"2026-09-12T21:58:02.008354Z","shell.execute_reply":"2026-09-12T21:58:02.008369Z"}},"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":"2026-09-12T21:58:02.010021Z","iopub.status.idle":"2026-09-12T21:58:02.010349Z","shell.execute_reply.started":"2026-09-12T21:58:02.010205Z","shell.execute_reply":"2026-09-12T21:58:02.01022Z"}},"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":"2026-09-12T21:58:02.011697Z","iopub.status.idle":"2026-09-12T21:58:02.012024Z","shell.execute_reply.started":"2026-09-12T21:58:02.011874Z","shell.execute_reply":"2026-09-12T21:58:02.011889Z"}},"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":"2026-09-12T22:44:43.935691Z","iopub.execute_input":"2026-09-12T22:44:43.936719Z","iopub.status.idle":"2026-09-12T22:45:11.781751Z","shell.execute_reply.started":"2026-09-12T22:44:43.936687Z","shell.execute_reply":"2026-09-12T22:45:11.780957Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import tensorflow as tf\n\nimages_to_predict = tf.image.resize(\n    images_to_predict,\n    (299, 299)\n)\n\nprint(images_to_predict.shape)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T22:52:32.772167Z","iopub.execute_input":"2026-09-12T22:52:32.773016Z","iopub.status.idle":"2026-09-12T22:52:32.785861Z","shell.execute_reply.started":"2026-09-12T22:52:32.772983Z","shell.execute_reply":"2026-09-12T22:52:32.784971Z"}},"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":"2026-09-12T22:52:45.213531Z","iopub.execute_input":"2026-09-12T22:52:45.213906Z","iopub.status.idle":"2026-09-12T22:52:47.869549Z","shell.execute_reply.started":"2026-09-12T22:52:45.21388Z","shell.execute_reply":"2026-09-12T22:52:47.868883Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"Make Prediction","metadata":{}},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null}]}