{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.10.12","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"nvidiaTeslaT4","dataSources":[{"sourceId":3362,"databundleVersionId":31148,"sourceType":"competition"}],"dockerImageVersionId":30627,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":true}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"# This Python 3 environment comes with many helpful analytics libraries installed\n# It is defined by the kaggle/python Docker image: https://github.com/kaggle/docker-python\n# For example, here's several helpful packages to load\n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n\n# Input data files are available in the read-only \"../input/\" directory\n# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\n\nimport os\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))\n\n# You can write up to 20GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using \"Save & Run All\" \n# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true,"execution":{"iopub.status.busy":"2025-03-03T14:12:30.236693Z","iopub.execute_input":"2025-03-03T14:12:30.237180Z","iopub.status.idle":"2025-03-03T14:12:30.246847Z","shell.execute_reply.started":"2025-03-03T14:12:30.237143Z","shell.execute_reply":"2025-03-03T14:12:30.246198Z"}},"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":{"trusted":true,"execution":{"iopub.status.busy":"2025-03-03T14:12:30.248058Z","iopub.execute_input":"2025-03-03T14:12:30.248296Z","iopub.status.idle":"2025-03-03T14:12:43.615926Z","shell.execute_reply.started":"2025-03-03T14:12:30.248276Z","shell.execute_reply":"2025-03-03T14:12:43.614973Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"!ls -l","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-03-03T14:12:43.617044Z","iopub.execute_input":"2025-03-03T14:12:43.617320Z","iopub.status.idle":"2025-03-03T14:12:44.616209Z","shell.execute_reply.started":"2025-03-03T14:12:43.617297Z","shell.execute_reply":"2025-03-03T14:12:44.615101Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls test1/ |wc -l","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-03-03T14:12:44.617583Z","iopub.execute_input":"2025-03-03T14:12:44.617842Z","iopub.status.idle":"2025-03-03T14:12:45.661783Z","shell.execute_reply.started":"2025-03-03T14:12:44.617820Z","shell.execute_reply":"2025-03-03T14:12:45.660723Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls train/ |wc -l","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-03-03T14:12:45.664094Z","iopub.execute_input":"2025-03-03T14:12:45.664409Z","iopub.status.idle":"2025-03-03T14:12:46.745078Z","shell.execute_reply.started":"2025-03-03T14:12:45.664361Z","shell.execute_reply":"2025-03-03T14:12:46.744179Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"ls train/","metadata":{"execution":{"iopub.status.busy":"2025-02-28T13:29:48.767617Z","iopub.execute_input":"2025-02-28T13:29:48.767891Z","iopub.status.idle":"2025-02-28T13:29:49.02562Z","shell.execute_reply.started":"2025-02-28T13:29:48.767866Z","shell.execute_reply":"2025-02-28T13:29:49.024871Z"}}},{"cell_type":"code","source":"# plot dog 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 + '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":{"trusted":true,"execution":{"iopub.status.busy":"2025-03-03T14:12:46.746438Z","iopub.execute_input":"2025-03-03T14:12:46.746729Z","iopub.status.idle":"2025-03-03T14:12:47.737727Z","shell.execute_reply.started":"2025-03-03T14:12:46.746705Z","shell.execute_reply":"2025-03-03T14:12:47.736885Z"}},"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":{"trusted":true,"execution":{"iopub.status.busy":"2025-03-03T14:12:47.738877Z","iopub.execute_input":"2025-03-03T14:12:47.739534Z","iopub.status.idle":"2025-03-03T14:12:48.666783Z","shell.execute_reply.started":"2025-03-03T14:12:47.739498Z","shell.execute_reply":"2025-03-03T14:12:48.666003Z"}},"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":"2025-03-03T14:12:48.668209Z","iopub.execute_input":"2025-03-03T14:12:48.668867Z","iopub.status.idle":"2025-03-03T14:12:48.795487Z","shell.execute_reply.started":"2025-03-03T14:12:48.668830Z","shell.execute_reply":"2025-03-03T14:12:48.794745Z"}},"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":{"trusted":true,"execution":{"iopub.status.busy":"2025-03-03T14:12:48.796422Z","iopub.execute_input":"2025-03-03T14:12:48.796634Z","iopub.status.idle":"2025-03-03T14:12:48.801122Z","shell.execute_reply.started":"2025-03-03T14:12:48.796616Z","shell.execute_reply":"2025-03-03T14:12:48.800177Z"}},"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":{"trusted":true,"execution":{"iopub.status.busy":"2025-03-03T14:12:48.802209Z","iopub.execute_input":"2025-03-03T14:12:48.802491Z","iopub.status.idle":"2025-03-03T14:12:48.815260Z","shell.execute_reply.started":"2025-03-03T14:12:48.802469Z","shell.execute_reply":"2025-03-03T14:12:48.814416Z"}},"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":{"trusted":true,"execution":{"iopub.status.busy":"2025-03-03T14:12:48.816268Z","iopub.execute_input":"2025-03-03T14:12:48.816508Z","iopub.status.idle":"2025-03-03T14:12:48.827564Z","shell.execute_reply.started":"2025-03-03T14:12:48.816488Z","shell.execute_reply":"2025-03-03T14:12:48.826744Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -l dataset_dogs_vs_cats/train/dogs/","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-03-03T14:12:48.828435Z","iopub.execute_input":"2025-03-03T14:12:48.828647Z","iopub.status.idle":"2025-03-03T14:12:49.832839Z","shell.execute_reply.started":"2025-03-03T14:12:48.828628Z","shell.execute_reply":"2025-03-03T14:12:49.831922Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -l","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-03-03T14:12:49.834402Z","iopub.execute_input":"2025-03-03T14:12:49.834784Z","iopub.status.idle":"2025-03-03T14:12:50.834558Z","shell.execute_reply.started":"2025-03-03T14:12:49.834749Z","shell.execute_reply":"2025-03-03T14:12:50.833645Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -l dataset_dogs_vs_cats/train","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-03-03T14:12:50.838599Z","iopub.execute_input":"2025-03-03T14:12:50.838850Z","iopub.status.idle":"2025-03-03T14:12:51.834998Z","shell.execute_reply.started":"2025-03-03T14:12:50.838828Z","shell.execute_reply":"2025-03-03T14:12:51.833853Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -l dataset_dogs_vs_cats/test","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-03-03T14:12:51.836465Z","iopub.execute_input":"2025-03-03T14:12:51.836742Z","iopub.status.idle":"2025-03-03T14:12:52.841526Z","shell.execute_reply.started":"2025-03-03T14:12:51.836720Z","shell.execute_reply":"2025-03-03T14:12:52.840429Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# seed random number generator\nseed(1)\n# define ratio of pictures to use for validation\nval_ratio = 0.25\n# copy training dataset images into subdirectories\nsrc_directory = 'train/'\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":{"trusted":true,"execution":{"iopub.status.busy":"2025-03-03T14:12:52.843247Z","iopub.execute_input":"2025-03-03T14:12:52.844090Z","iopub.status.idle":"2025-03-03T14:12:55.132670Z","shell.execute_reply.started":"2025-03-03T14:12:52.844061Z","shell.execute_reply":"2025-03-03T14:12:55.131924Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"!ls -l dataset_dogs_vs_cats/train/dogs | wc -l","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-03-03T14:12:55.133731Z","iopub.execute_input":"2025-03-03T14:12:55.134037Z","iopub.status.idle":"2025-03-03T14:12:56.207028Z","shell.execute_reply.started":"2025-03-03T14:12:55.134012Z","shell.execute_reply":"2025-03-03T14:12:56.205964Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"!ls -l dataset_dogs_vs_cats/train/cats | wc -l","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-03-03T14:12:56.208414Z","iopub.execute_input":"2025-03-03T14:12:56.208698Z","iopub.status.idle":"2025-03-03T14:12:57.323293Z","shell.execute_reply.started":"2025-03-03T14:12:56.208674Z","shell.execute_reply":"2025-03-03T14:12:57.322434Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"!pip -q install livelossplot==0.5.5","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-03-03T14:12:57.324863Z","iopub.execute_input":"2025-03-03T14:12:57.325709Z","iopub.status.idle":"2025-03-03T14:13:07.394571Z","shell.execute_reply.started":"2025-03-03T14:12:57.325669Z","shell.execute_reply":"2025-03-03T14:13:07.393563Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"from livelossplot import PlotLossesKeras","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-03-03T14:13:07.395882Z","iopub.execute_input":"2025-03-03T14:13:07.396184Z","iopub.status.idle":"2025-03-03T14:13:07.412047Z","shell.execute_reply.started":"2025-03-03T14:13:07.396160Z","shell.execute_reply":"2025-03-03T14:13:07.411320Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"Prepare Final Dataset","metadata":{}},{"cell_type":"code","source":"#start tutorial\n#Develop a Baseline CNN Model","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-03-03T14:13:07.412943Z","iopub.execute_input":"2025-03-03T14:13:07.413203Z","iopub.status.idle":"2025-03-03T14:13:07.417091Z","shell.execute_reply.started":"2025-03-03T14:13:07.413182Z","shell.execute_reply":"2025-03-03T14:13:07.416311Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"CNN Model","metadata":{}},{"cell_type":"code","source":"\n# 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":"2025-03-03T14:13:07.418262Z","iopub.execute_input":"2025-03-03T14:13:07.418527Z","iopub.status.idle":"2025-03-03T14:13:07.426115Z","shell.execute_reply.started":"2025-03-03T14:13:07.418506Z","shell.execute_reply":"2025-03-03T14:13:07.425418Z"}},"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    # save plot to file\n    filename = sys.argv[0].split('/')[-1]\n    pyplot.savefig(filename + '_plot.png')\n    pyplot.show()\n    pyplot.close()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-03-03T14:13:07.427310Z","iopub.execute_input":"2025-03-03T14:13:07.427552Z","iopub.status.idle":"2025-03-03T14:13:07.438594Z","shell.execute_reply.started":"2025-03-03T14:13:07.427533Z","shell.execute_reply":"2025-03-03T14:13:07.437826Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# MobileNetV2","metadata":{}},{"cell_type":"code","source":"# save the final model to file\nfrom keras.applications.mobilenet_v2 import MobileNetV2 \nfrom keras.applications.nasnet import NASNetLarge\nfrom keras.applications.xception import Xception\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","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-03-03T14:13:07.439640Z","iopub.execute_input":"2025-03-03T14:13:07.439997Z","iopub.status.idle":"2025-03-03T14:13:07.448916Z","shell.execute_reply.started":"2025-03-03T14:13:07.439969Z","shell.execute_reply":"2025-03-03T14:13:07.448175Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"xcep_model = Xception(include_top=False, input_shape=(299, 299, 3))\nxcep_model.summary()","metadata":{"execution":{"iopub.status.busy":"2024-01-27T04:11:23.494572Z","iopub.execute_input":"2024-01-27T04:11:23.495217Z","iopub.status.idle":"2024-01-27T04:11:26.579883Z","shell.execute_reply.started":"2024-01-27T04:11:23.495182Z","shell.execute_reply":"2024-01-27T04:11:26.578335Z"}}},{"cell_type":"code","source":"from keras.preprocessing.image import ImageDataGenerator\n# create data generator\ndatagen = ImageDataGenerator(\n    rescale=1./255,\n    rotation_range=40,\n    width_shift_range=0.2,\n    height_shift_range=0.2,\n    shear_range=0.2,\n    zoom_range=0.2,\n    horizontal_flip=True,\n    fill_mode='nearest'\n)\n# prepare iterator\ntrain_it = datagen.flow_from_directory('dataset_dogs_vs_cats/train/',\n    class_mode='binary', batch_size=64, target_size=(224, 224))\ntest_it = datagen.flow_from_directory('dataset_dogs_vs_cats/test/',\n    class_mode='binary', batch_size=64, target_size=(224, 224))","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-03-03T14:13:07.449771Z","iopub.execute_input":"2025-03-03T14:13:07.449973Z","iopub.status.idle":"2025-03-03T14:13:08.142015Z","shell.execute_reply.started":"2025-03-03T14:13:07.449955Z","shell.execute_reply":"2025-03-03T14:13:08.141202Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# load model\nmodel = NASNetLarge(\n    include_top=False,\n    input_shape=(224, 224, 3)\n    )\nprint(model.summary())\n#model = Xception(include_top=False, input_shape=(299, 299, 3))","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-03-03T14:13:08.143014Z","iopub.execute_input":"2025-03-03T14:13:08.143263Z","iopub.status.idle":"2025-03-03T14:13:22.551593Z","shell.execute_reply.started":"2025-03-03T14:13:08.143242Z","shell.execute_reply":"2025-03-03T14:13:22.550669Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# mark loaded layers as not trainable\nfor index, layer in enumerate(model.layers):\n    print(index, layer.name, layer.output_shape)\n    layer.trainable = False\n    \nfor index, layer in enumerate(model.layers[-30:]):\n    print(index, layer.name, layer.output_shape)\n    layer.trainable = True","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-03-03T14:13:22.552922Z","iopub.execute_input":"2025-03-03T14:13:22.553198Z","iopub.status.idle":"2025-03-03T14:13:22.619875Z","shell.execute_reply.started":"2025-03-03T14:13:22.553174Z","shell.execute_reply":"2025-03-03T14:13:22.619005Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"model.layers[-1].output","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-03-03T14:13:22.620820Z","iopub.execute_input":"2025-03-03T14:13:22.621059Z","iopub.status.idle":"2025-03-03T14:13:22.627213Z","shell.execute_reply.started":"2025-03-03T14:13:22.621039Z","shell.execute_reply":"2025-03-03T14:13:22.626335Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# add new classifier layers\nflat1 = Flatten()(model.layers[-1].output)\nclass1 = Dense(128, activation='relu', kernel_initializer='he_uniform')(flat1)\noutput = Dense(1, activation='sigmoid')(class1)\n# define new model\nmy_model = Model(inputs=model.inputs, outputs=output)\n# compile model\nopt = SGD(lr=0.001, momentum=0.9)\nmy_model.compile(optimizer=opt, loss='binary_crossentropy', metrics=['accuracy'])\nmy_model.summary()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-03-03T14:13:22.628221Z","iopub.execute_input":"2025-03-03T14:13:22.628773Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":" # fit model\nmy_model.reset_states()\nhistory = my_model.fit(train_it, \n                    steps_per_epoch=len(train_it),\n                    validation_data=test_it, \n                    validation_steps=len(test_it), \n                    epochs=2, verbose=1,\n                    callbacks=[PlotLossesKeras()])","metadata":{"trusted":true,"execution":{"iopub.status.idle":"2025-03-03T14:27:10.659633Z","shell.execute_reply.started":"2025-03-03T14:13:25.373715Z","shell.execute_reply":"2025-03-03T14:27:10.658935Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# evaluate model\n_, acc = my_model.evaluate(test_it, steps=len(test_it), verbose=1)\nprint('> %.3f' % (acc * 100.0))","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-03-03T14:27:10.660771Z","iopub.execute_input":"2025-03-03T14:27:10.661008Z","iopub.status.idle":"2025-03-03T14:28:51.728922Z","shell.execute_reply.started":"2025-03-03T14:27:10.660988Z","shell.execute_reply":"2025-03-03T14:28:51.728063Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# learning curves\nsummarize_diagnostics(history)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-03-03T14:28:51.730190Z","iopub.execute_input":"2025-03-03T14:28:51.730877Z","iopub.status.idle":"2025-03-03T14:28:52.162819Z","shell.execute_reply.started":"2025-03-03T14:28:51.730850Z","shell.execute_reply":"2025-03-03T14:28:52.162130Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"best_model = 'NASNetLarge_model.hdf5'\nmy_model.save(best_model)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-03-03T14:28:52.163728Z","iopub.execute_input":"2025-03-03T14:28:52.163956Z","iopub.status.idle":"2025-03-03T14:28:54.485950Z","shell.execute_reply.started":"2025-03-03T14:28:52.163936Z","shell.execute_reply":"2025-03-03T14:28:54.485222Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# make a prediction for a new image.\nfrom keras.preprocessing.image import load_img\nfrom keras.preprocessing.image import img_to_array\nfrom keras.models import load_model\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-03-03T14:28:54.487967Z","iopub.execute_input":"2025-03-03T14:28:54.488237Z","iopub.status.idle":"2025-03-03T14:28:54.492338Z","shell.execute_reply.started":"2025-03-03T14:28:54.488214Z","shell.execute_reply":"2025-03-03T14:28:54.491555Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"best_model = load_model(best_model)\nbest_model.evaluate(test_it, verbose=1)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-03-03T14:28:54.493272Z","iopub.execute_input":"2025-03-03T14:28:54.493509Z","iopub.status.idle":"2025-03-03T14:30:51.142933Z","shell.execute_reply.started":"2025-03-03T14:28:54.493490Z","shell.execute_reply":"2025-03-03T14:30:51.142231Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"Make Prediction","metadata":{}},{"cell_type":"code","source":"import matplotlib.pyplot as plt","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-03-03T14:30:51.144117Z","iopub.execute_input":"2025-03-03T14:30:51.144404Z","iopub.status.idle":"2025-03-03T14:30:51.148401Z","shell.execute_reply.started":"2025-03-03T14:30:51.144360Z","shell.execute_reply":"2025-03-03T14:30:51.147507Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import random\ndef predict_random_images(test_dir, model, class_names):\n    img_size=(224, 224)\n    images = []  # เก็บ path รูปภาพ\n    labels = []  # เก็บ label จริง\n\n    # เลือก 5 รูปจากแต่ละ class\n    for label in class_names:\n        folder = os.path.join(test_dir, label)\n        files = random.sample(list(os.listdir(folder)), 5)\n        for f in files:\n            images.append(os.path.join(folder, f))\n            labels.append(label)\n\n    # Plot\n    fig, axes = plt.subplots(2, 5, figsize=(12, 6))\n    for i, (img_path, true_label) in enumerate(zip(images, labels)):\n        img = load_img(img_path, target_size=img_size)\n        img_array = img_to_array(img) / 255\n        img_array = np.expand_dims(img_array, axis=0)\n\n        pred = model.predict(img_array)[0]  # ค่าระหว่าง 0-1\n        pred_label = class_names[1] if pred > 0.5 else class_names[0]\n\n        axes[i // 5, i % 5].imshow(img)\n        axes[i // 5, i % 5].set_title(f\"Pred: {pred_label}\\nTrue: {true_label}\", fontsize=10)\n        axes[i // 5, i % 5].axis(\"off\")\n\n    plt.tight_layout()\n    plt.show()\npredict_random_images(\"dataset_dogs_vs_cats/test/\", best_model, [\"cats\", \"dogs\"])\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-03-03T14:30:51.149339Z","iopub.execute_input":"2025-03-03T14:30:51.149646Z","iopub.status.idle":"2025-03-03T14:30:58.453598Z","shell.execute_reply.started":"2025-03-03T14:30:51.149615Z","shell.execute_reply":"2025-03-03T14:30:58.452737Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null}]}