{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.10.13","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"tpu1vmV38","dataSources":[{"sourceId":3362,"databundleVersionId":31148,"sourceType":"competition"}],"dockerImageVersionId":30627,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"# This Python 3 environment comes with many helpful analytics libraries installed\n# It is defined by the kaggle/python Docker image: https://github.com/kaggle/docker-python\n# For example, here's several helpful packages to load\n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n\n# Input data files are available in the read-only \"../input/\" directory\n# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\n\nimport os\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))\n\n# You can write up to 20GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using \"Save & Run All\" \n# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","execution":{"iopub.status.busy":"2025-02-28T10:14:43.467043Z","iopub.execute_input":"2025-02-28T10:14:43.467450Z","iopub.status.idle":"2025-02-28T10:14:43.856292Z","shell.execute_reply.started":"2025-02-28T10:14:43.467412Z","shell.execute_reply":"2025-02-28T10:14:43.855451Z"},"trusted":true},"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":"2025-02-28T10:14:43.857660Z","iopub.execute_input":"2025-02-28T10:14:43.857954Z","iopub.status.idle":"2025-02-28T10:14:57.377804Z","shell.execute_reply.started":"2025-02-28T10:14:43.857929Z","shell.execute_reply":"2025-02-28T10:14:57.377001Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"!ls -l","metadata":{"execution":{"iopub.status.busy":"2025-02-28T10:14:57.378895Z","iopub.execute_input":"2025-02-28T10:14:57.379264Z","iopub.status.idle":"2025-02-28T10:14:57.507430Z","shell.execute_reply.started":"2025-02-28T10:14:57.379225Z","shell.execute_reply":"2025-02-28T10:14:57.506226Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls test1/ |wc -l","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-02-28T10:14:57.510329Z","iopub.execute_input":"2025-02-28T10:14:57.511175Z","iopub.status.idle":"2025-02-28T10:14:57.684406Z","shell.execute_reply.started":"2025-02-28T10:14:57.511141Z","shell.execute_reply":"2025-02-28T10:14:57.683266Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls train/ |wc -l","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-02-28T10:14:57.686520Z","iopub.execute_input":"2025-02-28T10:14:57.687073Z","iopub.status.idle":"2025-02-28T10:14:57.907225Z","shell.execute_reply.started":"2025-02-28T10:14:57.687028Z","shell.execute_reply":"2025-02-28T10:14:57.906165Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls train/","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-02-28T10:14:57.908507Z","iopub.execute_input":"2025-02-28T10:14:57.908768Z","iopub.status.idle":"2025-02-28T10:14:58.167677Z","shell.execute_reply.started":"2025-02-28T10:14:57.908741Z","shell.execute_reply":"2025-02-28T10:14:58.166495Z"},"collapsed":true,"jupyter":{"outputs_hidden":true}},"outputs":[],"execution_count":null},{"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":{"execution":{"iopub.status.busy":"2025-02-28T10:14:58.169045Z","iopub.execute_input":"2025-02-28T10:14:58.169316Z","iopub.status.idle":"2025-02-28T10:15:00.040105Z","shell.execute_reply.started":"2025-02-28T10:14:58.169288Z","shell.execute_reply":"2025-02-28T10:15:00.039284Z"},"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":"2025-02-28T10:15:00.041142Z","iopub.execute_input":"2025-02-28T10:15:00.041474Z","iopub.status.idle":"2025-02-28T10:15:00.808087Z","shell.execute_reply.started":"2025-02-28T10:15:00.041447Z","shell.execute_reply":"2025-02-28T10:15:00.807282Z"},"trusted":true},"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":"2025-02-28T10:15:00.810568Z","iopub.execute_input":"2025-02-28T10:15:00.810825Z","iopub.status.idle":"2025-02-28T10:15:14.880152Z","shell.execute_reply.started":"2025-02-28T10:15:00.810800Z","shell.execute_reply":"2025-02-28T10:15:14.879038Z"}},"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":"2025-02-28T10:15:14.881271Z","iopub.execute_input":"2025-02-28T10:15:14.881776Z","iopub.status.idle":"2025-02-28T10:15:14.886274Z","shell.execute_reply.started":"2025-02-28T10:15:14.881745Z","shell.execute_reply":"2025-02-28T10:15:14.885453Z"},"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":"2025-02-28T10:15:14.887463Z","iopub.execute_input":"2025-02-28T10:15:14.887961Z","iopub.status.idle":"2025-02-28T10:15:14.898505Z","shell.execute_reply.started":"2025-02-28T10:15:14.887931Z","shell.execute_reply":"2025-02-28T10:15:14.897645Z"},"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":"2025-02-28T10:15:14.899637Z","iopub.execute_input":"2025-02-28T10:15:14.899909Z","iopub.status.idle":"2025-02-28T10:15:14.910109Z","shell.execute_reply.started":"2025-02-28T10:15:14.899879Z","shell.execute_reply":"2025-02-28T10:15:14.909339Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -l dataset_dogs_vs_cats/train/dogs/","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-02-28T10:15:14.910917Z","iopub.execute_input":"2025-02-28T10:15:14.911178Z","iopub.status.idle":"2025-02-28T10:15:15.058372Z","shell.execute_reply.started":"2025-02-28T10:15:14.911152Z","shell.execute_reply":"2025-02-28T10:15:15.057398Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -l","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-02-28T10:15:15.059623Z","iopub.execute_input":"2025-02-28T10:15:15.059872Z","iopub.status.idle":"2025-02-28T10:15:15.191224Z","shell.execute_reply.started":"2025-02-28T10:15:15.059846Z","shell.execute_reply":"2025-02-28T10:15:15.190003Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -l dataset_dogs_vs_cats/train","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-02-28T10:15:15.192751Z","iopub.execute_input":"2025-02-28T10:15:15.193069Z","iopub.status.idle":"2025-02-28T10:15:15.324678Z","shell.execute_reply.started":"2025-02-28T10:15:15.193036Z","shell.execute_reply":"2025-02-28T10:15:15.323763Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -l dataset_dogs_vs_cats/test","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-02-28T10:15:15.326058Z","iopub.execute_input":"2025-02-28T10:15:15.326342Z","iopub.status.idle":"2025-02-28T10:15:15.455361Z","shell.execute_reply.started":"2025-02-28T10:15:15.326309Z","shell.execute_reply":"2025-02-28T10:15:15.454577Z"}},"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":{"execution":{"iopub.status.busy":"2025-02-28T10:15:15.456746Z","iopub.execute_input":"2025-02-28T10:15:15.457078Z","iopub.status.idle":"2025-02-28T10:15:18.313735Z","shell.execute_reply.started":"2025-02-28T10:15:15.457044Z","shell.execute_reply":"2025-02-28T10:15:18.312990Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"!ls -l dataset_dogs_vs_cats/train/dogs | wc -l","metadata":{"execution":{"iopub.status.busy":"2025-02-28T10:15:18.314859Z","iopub.execute_input":"2025-02-28T10:15:18.315565Z","iopub.status.idle":"2025-02-28T10:15:18.528419Z","shell.execute_reply.started":"2025-02-28T10:15:18.315534Z","shell.execute_reply":"2025-02-28T10:15:18.527480Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"!ls -l dataset_dogs_vs_cats/train/cats | wc -l","metadata":{"execution":{"iopub.status.busy":"2025-02-28T10:15:18.529718Z","iopub.execute_input":"2025-02-28T10:15:18.529965Z","iopub.status.idle":"2025-02-28T10:15:18.741807Z","shell.execute_reply.started":"2025-02-28T10:15:18.529937Z","shell.execute_reply":"2025-02-28T10:15:18.741040Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"!pip -q install livelossplot==0.5.5","metadata":{"execution":{"iopub.status.busy":"2025-02-28T10:15:18.743071Z","iopub.execute_input":"2025-02-28T10:15:18.743324Z","iopub.status.idle":"2025-02-28T10:15:24.914296Z","shell.execute_reply.started":"2025-02-28T10:15:18.743296Z","shell.execute_reply":"2025-02-28T10:15:24.913281Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"from livelossplot import PlotLossesKeras","metadata":{"execution":{"iopub.status.busy":"2025-02-28T10:15:24.915734Z","iopub.execute_input":"2025-02-28T10:15:24.916020Z","iopub.status.idle":"2025-02-28T10:15:24.928047Z","shell.execute_reply.started":"2025-02-28T10:15:24.915989Z","shell.execute_reply":"2025-02-28T10:15:24.927235Z"},"trusted":true},"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":"2025-02-28T10:15:24.928943Z","iopub.execute_input":"2025-02-28T10:15:24.929205Z","iopub.status.idle":"2025-02-28T10:15:24.939697Z","shell.execute_reply.started":"2025-02-28T10:15:24.929178Z","shell.execute_reply":"2025-02-28T10:15:24.939084Z"}},"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":"2025-02-28T10:15:24.940469Z","iopub.execute_input":"2025-02-28T10:15:24.940680Z","iopub.status.idle":"2025-02-28T10:15:24.952429Z","shell.execute_reply.started":"2025-02-28T10:15:24.940658Z","shell.execute_reply":"2025-02-28T10:15:24.951850Z"}},"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":"2025-02-28T10:15:24.955470Z","iopub.execute_input":"2025-02-28T10:15:24.955695Z","iopub.status.idle":"2025-02-28T10:15:24.964003Z","shell.execute_reply.started":"2025-02-28T10:15:24.955673Z","shell.execute_reply":"2025-02-28T10:15:24.963404Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# ResNet50V2","metadata":{}},{"cell_type":"code","source":"# save the final model to file\nfrom keras.applications.resnet_v2 import ResNet50V2\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":{"execution":{"iopub.status.busy":"2025-02-28T11:20:26.501706Z","iopub.execute_input":"2025-02-28T11:20:26.502203Z","iopub.status.idle":"2025-02-28T11:20:26.506632Z","shell.execute_reply.started":"2025-02-28T11:20:26.502168Z","shell.execute_reply":"2025-02-28T11:20:26.505913Z"},"trusted":true},"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":{"execution":{"iopub.status.busy":"2025-02-28T11:20:30.898582Z","iopub.execute_input":"2025-02-28T11:20:30.899022Z","iopub.status.idle":"2025-02-28T11:20:31.687895Z","shell.execute_reply.started":"2025-02-28T11:20:30.898947Z","shell.execute_reply":"2025-02-28T11:20:31.687028Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# load model\nmodel = ResNet50V2(\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":{"execution":{"iopub.status.busy":"2025-02-28T11:20:32.865949Z","iopub.execute_input":"2025-02-28T11:20:32.866598Z","iopub.status.idle":"2025-02-28T11:20:35.316762Z","shell.execute_reply.started":"2025-02-28T11:20:32.866564Z","shell.execute_reply":"2025-02-28T11:20:35.315758Z"},"trusted":true,"collapsed":true,"jupyter":{"outputs_hidden":true}},"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[-5:]):\n    print(index, layer.name, layer.output_shape)\n    layer.trainable = True","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-02-28T11:20:41.902453Z","iopub.execute_input":"2025-02-28T11:20:41.902800Z","iopub.status.idle":"2025-02-28T11:20:41.920669Z","shell.execute_reply.started":"2025-02-28T11:20:41.902772Z","shell.execute_reply":"2025-02-28T11:20:41.919655Z"},"collapsed":true,"jupyter":{"outputs_hidden":true}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"model.layers[-1].output","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-02-28T11:21:41.069871Z","iopub.execute_input":"2025-02-28T11:21:41.070242Z","iopub.status.idle":"2025-02-28T11:21:41.076614Z","shell.execute_reply.started":"2025-02-28T11:21:41.070210Z","shell.execute_reply":"2025-02-28T11:21:41.075542Z"}},"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":"2025-02-28T11:21:42.511312Z","iopub.execute_input":"2025-02-28T11:21:42.511656Z","iopub.status.idle":"2025-02-28T11:21:42.909357Z","shell.execute_reply.started":"2025-02-28T11:21:42.511628Z","shell.execute_reply":"2025-02-28T11:21:42.908551Z"},"collapsed":true,"jupyter":{"outputs_hidden":true}},"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.busy":"2025-02-28T11:21:56.357722Z","iopub.execute_input":"2025-02-28T11:21:56.358096Z","iopub.status.idle":"2025-02-28T11:37:26.705412Z","shell.execute_reply.started":"2025-02-28T11:21:56.358068Z","shell.execute_reply":"2025-02-28T11:37:26.704488Z"}},"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":"2025-02-28T11:37:58.920609Z","iopub.execute_input":"2025-02-28T11:37:58.920944Z","iopub.status.idle":"2025-02-28T11:39:55.135454Z","shell.execute_reply.started":"2025-02-28T11:37:58.920915Z","shell.execute_reply":"2025-02-28T11:39:55.134307Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# learning curves\nsummarize_diagnostics(history)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-02-28T11:42:32.241253Z","iopub.execute_input":"2025-02-28T11:42:32.241650Z","iopub.status.idle":"2025-02-28T11:42:32.578825Z","shell.execute_reply.started":"2025-02-28T11:42:32.241616Z","shell.execute_reply":"2025-02-28T11:42:32.578019Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"best_model = 'ResNet50V2_model.hdf5'\nmy_model.save(best_model)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-02-28T11:42:54.744551Z","iopub.execute_input":"2025-02-28T11:42:54.745105Z","iopub.status.idle":"2025-02-28T11:42:55.252987Z","shell.execute_reply.started":"2025-02-28T11:42:54.745035Z","shell.execute_reply":"2025-02-28T11:42:55.251984Z"}},"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":"2025-02-28T11:43:51.853350Z","iopub.execute_input":"2025-02-28T11:43:51.853706Z","iopub.status.idle":"2025-02-28T11:43:51.858568Z","shell.execute_reply.started":"2025-02-28T11:43:51.853678Z","shell.execute_reply":"2025-02-28T11:43:51.857448Z"}},"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":"2025-02-28T11:43:53.053214Z","iopub.execute_input":"2025-02-28T11:43:53.054006Z","iopub.status.idle":"2025-02-28T11:45:49.157543Z","shell.execute_reply.started":"2025-02-28T11:43:53.053958Z","shell.execute_reply":"2025-02-28T11:45:49.156626Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"Make Prediction","metadata":{}},{"cell_type":"code","source":"\n# load and prepare the image\ndef load_image(filename):\n\t# load the image\n\timg = load_img(filename, target_size=(224, 224))\n\t# convert to array\n\timg = img_to_array(img)\n\t# reshape into a single sample with 3 channels\n\timg = img.reshape(1, 224, 224, 3)\n\t# center pixel data\n\timg = img.astype('float32')\n\timg = img - [123.68, 116.779, 103.939]\n\treturn img\n\n# load an image and predict the class\ndef run_example():\n\t# load the image\n\timg = load_image('sample_image.jpg')\n\t# load model\n\tmodel = load_model('final_model.h5')\n\t# predict the class\n\tresult = model.predict(img)\n\tprint(result[0])\n\n# entry point, run the example\nrun_example()","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import matplotlib.pyplot as plt","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-02-28T11:46:16.762310Z","iopub.execute_input":"2025-02-28T11:46:16.763281Z","iopub.status.idle":"2025-02-28T11:46:16.766910Z","shell.execute_reply.started":"2025-02-28T11:46:16.763244Z","shell.execute_reply":"2025-02-28T11:46:16.766152Z"}},"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":"2025-02-28T11:46:44.476695Z","iopub.execute_input":"2025-02-28T11:46:44.477576Z","iopub.status.idle":"2025-02-28T11:46:47.353125Z","shell.execute_reply.started":"2025-02-28T11:46:44.477539Z","shell.execute_reply":"2025-02-28T11:46:47.352269Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null}]}