{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.10.12","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"nvidiaTeslaT4","dataSources":[{"sourceId":3362,"databundleVersionId":31148,"sourceType":"competition"}],"dockerImageVersionId":30627,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":true}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"# This Python 3 environment comes with many helpful analytics libraries installed\n# It is defined by the kaggle/python Docker image: https://github.com/kaggle/docker-python\n# For example, here's several helpful packages to load\n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n\n# Input data files are available in the read-only \"../input/\" directory\n# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\n\nimport os\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))\n\n# You can write up to 20GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using \"Save & Run All\" \n# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","execution":{"iopub.status.busy":"2024-02-04T19:10:19.620443Z","iopub.execute_input":"2024-02-04T19:10:19.620929Z","iopub.status.idle":"2024-02-04T19:10:19.628151Z","shell.execute_reply.started":"2024-02-04T19:10:19.620897Z","shell.execute_reply":"2024-02-04T19:10:19.627301Z"},"trusted":true},"execution_count":null,"outputs":[]},{"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":"2024-02-04T19:10:19.633372Z","iopub.execute_input":"2024-02-04T19:10:19.634025Z","iopub.status.idle":"2024-02-04T19:10:35.763000Z","shell.execute_reply.started":"2024-02-04T19:10:19.633998Z","shell.execute_reply":"2024-02-04T19:10:35.762029Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"!ls train","metadata":{"execution":{"iopub.status.busy":"2024-01-08T06:57:18.293035Z","iopub.execute_input":"2024-01-08T06:57:18.293457Z","iopub.status.idle":"2024-01-08T06:57:19.311078Z","shell.execute_reply.started":"2024-01-08T06:57:18.293422Z","shell.execute_reply":"2024-01-08T06:57:19.309969Z"}}},{"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":"2024-02-04T19:10:35.764718Z","iopub.execute_input":"2024-02-04T19:10:35.765011Z","iopub.status.idle":"2024-02-04T19:10:36.939575Z","shell.execute_reply.started":"2024-02-04T19:10:35.764979Z","shell.execute_reply":"2024-02-04T19:10:36.938746Z"},"trusted":true},"execution_count":null,"outputs":[]},{"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":"2024-02-04T19:10:36.940790Z","iopub.execute_input":"2024-02-04T19:10:36.941076Z","iopub.status.idle":"2024-02-04T19:10:38.021578Z","shell.execute_reply.started":"2024-02-04T19:10:36.941050Z","shell.execute_reply":"2024-02-04T19:10:38.020669Z"},"trusted":true},"execution_count":null,"outputs":[]},{"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":"2024-02-04T19:10:38.022820Z","iopub.execute_input":"2024-02-04T19:10:38.023110Z","iopub.status.idle":"2024-02-04T19:10:51.173766Z","shell.execute_reply.started":"2024-02-04T19:10:38.023081Z","shell.execute_reply":"2024-02-04T19:10:51.172981Z"},"trusted":true},"execution_count":null,"outputs":[]},{"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":"\n# 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":"2024-02-04T19:10:51.176058Z","iopub.execute_input":"2024-02-04T19:10:51.176596Z","iopub.status.idle":"2024-02-04T19:10:51.181081Z","shell.execute_reply.started":"2024-02-04T19:10:51.176568Z","shell.execute_reply":"2024-02-04T19:10:51.180200Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# create directories\ndataset_home = 'dataset_dogs_vs_cats/'\nsubdirs = ['train/', 'test/']\nfor subdir in subdirs:\n\t# create label subdirectories\n\tlabeldirs = ['dogs/', 'cats/']\n\tfor labldir in labeldirs:\n\t\tnewdir = dataset_home + subdir + labldir\n\t\tmakedirs(newdir, exist_ok=True)","metadata":{"execution":{"iopub.status.busy":"2024-02-04T19:10:51.182147Z","iopub.execute_input":"2024-02-04T19:10:51.182515Z","iopub.status.idle":"2024-02-04T19:10:51.215125Z","shell.execute_reply.started":"2024-02-04T19:10:51.182491Z","shell.execute_reply":"2024-02-04T19:10:51.214217Z"},"trusted":true},"execution_count":null,"outputs":[]},{"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":"2024-02-04T19:10:51.216253Z","iopub.execute_input":"2024-02-04T19:10:51.216503Z","iopub.status.idle":"2024-02-04T19:10:53.821868Z","shell.execute_reply.started":"2024-02-04T19:10:51.216480Z","shell.execute_reply":"2024-02-04T19:10:53.820896Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"!ls -l dataset_dogs_vs_cats/train/dogs | wc -l","metadata":{"execution":{"iopub.status.busy":"2024-02-04T19:10:53.823045Z","iopub.execute_input":"2024-02-04T19:10:53.823330Z","iopub.status.idle":"2024-02-04T19:10:54.890265Z","shell.execute_reply.started":"2024-02-04T19:10:53.823306Z","shell.execute_reply":"2024-02-04T19:10:54.889307Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"!ls -l dataset_dogs_vs_cats/train/cats | wc -l","metadata":{"execution":{"iopub.status.busy":"2024-02-04T19:10:54.891601Z","iopub.execute_input":"2024-02-04T19:10:54.891902Z","iopub.status.idle":"2024-02-04T19:10:55.929871Z","shell.execute_reply.started":"2024-02-04T19:10:54.891874Z","shell.execute_reply":"2024-02-04T19:10:55.928769Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"!pip -q install livelossplot==0.5.5","metadata":{"execution":{"iopub.status.busy":"2024-02-04T19:10:55.931346Z","iopub.execute_input":"2024-02-04T19:10:55.931641Z","iopub.status.idle":"2024-02-04T19:11:10.591218Z","shell.execute_reply.started":"2024-02-04T19:10:55.931613Z","shell.execute_reply":"2024-02-04T19:11:10.589931Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from livelossplot import PlotLossesKeras","metadata":{"execution":{"iopub.status.busy":"2024-02-04T19:11:10.592625Z","iopub.execute_input":"2024-02-04T19:11:10.592940Z","iopub.status.idle":"2024-02-04T19:11:10.608355Z","shell.execute_reply.started":"2024-02-04T19:11:10.592912Z","shell.execute_reply":"2024-02-04T19:11:10.607499Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Prepare Final Dataset","metadata":{}},{"cell_type":"code","source":"# save the final model to file\nfrom keras.applications.vgg16 import VGG16\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":"2024-02-04T19:11:10.609453Z","iopub.execute_input":"2024-02-04T19:11:10.609756Z","iopub.status.idle":"2024-02-04T19:11:10.614900Z","shell.execute_reply.started":"2024-02-04T19:11:10.609723Z","shell.execute_reply":"2024-02-04T19:11:10.614039Z"},"trusted":true},"execution_count":null,"outputs":[]},{"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":"","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"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":"2024-02-04T19:11:10.616202Z","iopub.execute_input":"2024-02-04T19:11:10.616796Z","iopub.status.idle":"2024-02-04T19:11:11.627801Z","shell.execute_reply.started":"2024-02-04T19:11:10.616763Z","shell.execute_reply":"2024-02-04T19:11:11.627112Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# load model\nmodel = VGG16(\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))\n\n","metadata":{"execution":{"iopub.status.busy":"2024-02-04T19:11:11.632383Z","iopub.execute_input":"2024-02-04T19:11:11.632728Z","iopub.status.idle":"2024-02-04T19:11:13.565357Z","shell.execute_reply.started":"2024-02-04T19:11:11.632700Z","shell.execute_reply":"2024-02-04T19:11:13.564434Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# mark loaded layers as not trainable\nfor index, layer in enumerate(model.layers[:15]):\n    print(index, layer.name, layer.output_shape)\n    layer.trainable = False\n    \nfor index, layer in enumerate(model.layers[15:]):\n    print(index, layer.name, layer.output_shape)\n    layer.trainable = True","metadata":{"execution":{"iopub.status.busy":"2024-02-04T19:11:13.566970Z","iopub.execute_input":"2024-02-04T19:11:13.567343Z","iopub.status.idle":"2024-02-04T19:11:13.576331Z","shell.execute_reply.started":"2024-02-04T19:11:13.567307Z","shell.execute_reply":"2024-02-04T19:11:13.575448Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"model.layers[-1].output","metadata":{"execution":{"iopub.status.busy":"2024-02-04T19:11:13.577434Z","iopub.execute_input":"2024-02-04T19:11:13.577688Z","iopub.status.idle":"2024-02-04T19:11:13.592634Z","shell.execute_reply.started":"2024-02-04T19:11:13.577666Z","shell.execute_reply":"2024-02-04T19:11:13.591812Z"},"trusted":true},"execution_count":null,"outputs":[]},{"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=0.0001, momentum=0.9)\nmy_model.compile(optimizer=opt, loss='binary_crossentropy', metrics=['accuracy'])\nmy_model.summary()","metadata":{"execution":{"iopub.status.busy":"2024-02-04T19:11:13.593621Z","iopub.execute_input":"2024-02-04T19:11:13.593927Z","iopub.status.idle":"2024-02-04T19:11:13.694305Z","shell.execute_reply.started":"2024-02-04T19:11:13.593885Z","shell.execute_reply":"2024-02-04T19:11:13.693492Z"},"trusted":true},"execution_count":null,"outputs":[]},{"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()])\n# evaluate model\n_, acc = my_model.evaluate_generator(test_it, steps=len(test_it), verbose=1)\n\nprint('> %.3f' % (acc * 100.0))\n\nimport matplotlib.pyplot as plt\n\ndef summarize_diagnostics(history):\n    # Plot loss\n    plt.subplot(211)\n    plt.title('Cross Entropy Loss')\n    plt.plot(history.history['loss'], color='blue', label='train')\n    plt.plot(history.history['val_loss'], color='orange', label='test')\n    \n    # Plot accuracy\n    plt.subplot(212)\n    plt.title('Classification Accuracy')\n    plt.plot(history.history['accuracy'], color='blue', label='train')\n    plt.plot(history.history['val_accuracy'], color='orange', label='test')\n    \n    # Show the plot\n    plt.show()\n# learning curves\nsummarize_diagnostics(history)\n","metadata":{"execution":{"iopub.status.busy":"2024-02-04T19:11:13.695507Z","iopub.execute_input":"2024-02-04T19:11:13.695766Z","iopub.status.idle":"2024-02-04T19:22:57.116517Z","shell.execute_reply.started":"2024-02-04T19:11:13.695742Z","shell.execute_reply":"2024-02-04T19:22:57.115532Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"best_model = 'vgg16_model.hdf5'\nmy_model.save(best_model)\n\nfrom keras.models import load_model\n\nbest_model = load_model(best_model)\nbest_model.evaluate(test_it, verbose=1)","metadata":{"execution":{"iopub.status.busy":"2024-02-04T19:24:37.812555Z","iopub.execute_input":"2024-02-04T19:24:37.812941Z","iopub.status.idle":"2024-02-04T19:25:55.915996Z","shell.execute_reply.started":"2024-02-04T19:24:37.812910Z","shell.execute_reply":"2024-02-04T19:25:55.915150Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Make Prediction","metadata":{}},{"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":{"execution":{"iopub.status.busy":"2024-02-04T19:26:21.549539Z","iopub.execute_input":"2024-02-04T19:26:21.550245Z","iopub.status.idle":"2024-02-04T19:26:21.555116Z","shell.execute_reply.started":"2024-02-04T19:26:21.550210Z","shell.execute_reply":"2024-02-04T19:26:21.554094Z"},"trusted":true},"execution_count":null,"outputs":[]},{"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":{"execution":{"iopub.status.busy":"2024-02-04T19:22:57.877837Z","iopub.status.idle":"2024-02-04T19:22:57.878154Z","shell.execute_reply.started":"2024-02-04T19:22:57.877998Z","shell.execute_reply":"2024-02-04T19:22:57.878013Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"!pip install livelossplot","metadata":{"execution":{"iopub.status.busy":"2024-02-04T19:32:03.266121Z","iopub.execute_input":"2024-02-04T19:32:03.266531Z","iopub.status.idle":"2024-02-04T19:32:14.921378Z","shell.execute_reply.started":"2024-02-04T19:32:03.266498Z","shell.execute_reply":"2024-02-04T19:32:14.920217Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import keras\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\nfrom livelossplot import PlotLossesKeras\n\nkeras.applications.ResNet50V2(\n    include_top=False,\n    weights=\"imagenet\",\n    input_tensor=None,\n    input_shape=None,\n    pooling=None,\n    classes=2,\n    classifier_activation=\"softmax\",\n)\nfrom keras.applications import ResNet50V2\n\n# Load model\nmodel1 = ResNet50V2(input_shape=(224, 224, 3))\nprint(model1.summary())\n\n# Mark loaded layers as not trainable\nfor index, layer in enumerate(model1.layers[:15]):\n    print(index, layer.name, layer.output_shape)\n    layer.trainable = False\n    \nfor index, layer in enumerate(model1.layers[15:]):\n    print(index, layer.name, layer.output_shape)\n    layer.trainable = True\n\nmodel1.layers[-1].output\n\n# Add new classifier layers\nflat1 = Flatten()(model1.layers[-1].output)\nclass1 = Dense(128, activation='relu', kernel_initializer='he_uniform')(flat1)\noutput = Dense(1, activation='sigmoid')(class1)\n\n# Define new model\nmy_model1 = Model(inputs=model1.inputs, outputs=output)\n\n# Compile model\nopt = SGD(lr=0.0001, momentum=0.9)\nmy_model1.compile(optimizer=opt, loss='binary_crossentropy', metrics=['accuracy'])\nmy_model1.summary()\n\n# Fit model\nmy_model1.reset_states()\nhistory1 = my_model1.fit(train_it, \n                         validation_data=test_it, \n                         epochs=2, \n                         verbose=1,\n                         callbacks=[PlotLossesKeras()],\n                         batch_size=16)  \n\n# Evaluate model\n_, acc = my_model1.evaluate_generator(test_it, steps=len(test_it), verbose=1)\nprint('> %.3f' % (acc * 100.0))\n\nimport matplotlib.pyplot as plt\n\ndef summarize_diagnostics(history1):\n    # Plot loss\n    plt.subplot(211)\n    plt.title('Cross Entropy Loss')\n    plt.plot(history1.history['loss'], color='blue', label='train')\n    plt.plot(history1.history['val_loss'], color='orange', label='test')\n    \n    # Plot accuracy\n    plt.subplot(212)\n    plt.title('Classification Accuracy')\n    plt.plot(history1.history['accuracy'], color='blue', label='train')\n    plt.plot(history1.history['val_accuracy'], color='orange', label='test')\n    \n    # Show the plot\n    plt.show()\n\n# Plot learning curves\nsummarize_diagnostics(history1)\n\n# Save best model\nbest_model1 = 'ResNet50V2_model.hdf5'\nmy_model1.save(best_model1)\n","metadata":{"execution":{"iopub.status.busy":"2024-02-04T19:54:36.469132Z","iopub.execute_input":"2024-02-04T19:54:36.470141Z","iopub.status.idle":"2024-02-04T20:06:20.242690Z","shell.execute_reply.started":"2024-02-04T19:54:36.470105Z","shell.execute_reply":"2024-02-04T20:06:20.241617Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import keras\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\nfrom livelossplot import PlotLossesKeras\n\nkeras.applications.ResNet101(\n    include_top=False,\n    weights=\"imagenet\",\n    input_tensor=None,\n    input_shape=None,\n    pooling=None,\n    classes=2,\n    classifier_activation=\"softmax\",\n)\nfrom keras.applications import ResNet101\n\n# Load model\nmodel2 = ResNet101(input_shape=(224, 224, 3))\nprint(model2.summary())\n\n# Mark loaded layers as not trainable\nfor index, layer in enumerate(model2.layers[:15]):\n    print(index, layer.name, layer.output_shape)\n    layer.trainable = False\n    \nfor index, layer in enumerate(model2.layers[15:]):\n    print(index, layer.name, layer.output_shape)\n    layer.trainable = True\n\nmodel2.layers[-1].output\n\n# Add new classifier layers\nflat1 = Flatten()(model2.layers[-1].output)\nclass1 = Dense(128, activation='relu', kernel_initializer='he_uniform')(flat1)\noutput = Dense(1, activation='sigmoid')(class1)\n\n# Define new model\nmy_model2 = Model(inputs=model2.inputs, outputs=output)\n\n# Compile model\nopt = SGD(lr=0.0001, momentum=0.9)\nmy_model2.compile(optimizer=opt, loss='binary_crossentropy', metrics=['accuracy'])\nmy_model2.summary()\n\n# Fit model\nmy_model2.reset_states()\nhistory2 = my_model2.fit(train_it, \n                         validation_data=test_it, \n                         epochs=2, \n                         verbose=1,\n                         callbacks=[PlotLossesKeras()],\n                         batch_size=16)  \n\n# Evaluate model\n_, acc = my_model2.evaluate_generator(test_it, steps=len(test_it), verbose=1)\nprint('> %.3f' % (acc * 100.0))\n\nimport matplotlib.pyplot as plt\n\ndef summarize_diagnostics(history2):\n    # Plot loss\n    plt.subplot(211)\n    plt.title('Cross Entropy Loss')\n    plt.plot(history2.history['loss'], color='blue', label='train')\n    plt.plot(history2.history['val_loss'], color='orange', label='test')\n    \n    # Plot accuracy\n    plt.subplot(212)\n    plt.title('Classification Accuracy')\n    plt.plot(history2.history['accuracy'], color='blue', label='train')\n    plt.plot(history2.history['val_accuracy'], color='orange', label='test')\n    \n    # Show the plot\n    plt.show()\n\n# Plot learning curves\nsummarize_diagnostics(history2)\n\n# Save best model\nbest_model2 = 'ResNet101_model.hdf5'\nmy_model2.save(best_model2)\n","metadata":{"execution":{"iopub.status.busy":"2024-02-04T20:13:33.038306Z","iopub.execute_input":"2024-02-04T20:13:33.038705Z","iopub.status.idle":"2024-02-04T20:28:45.245131Z","shell.execute_reply.started":"2024-02-04T20:13:33.038674Z","shell.execute_reply":"2024-02-04T20:28:45.244083Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import keras\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\nfrom livelossplot import PlotLossesKeras\n\nkeras.applications.MobileNet(\n    input_shape=None,\n    alpha=1.0,\n    depth_multiplier=1,\n    dropout=0.001,\n    include_top=False,\n    weights=\"imagenet\",\n    input_tensor=None,\n    pooling=None,\n    classes=2,\n    classifier_activation=\"softmax\",\n)\nfrom keras.applications import MobileNet\n\n# Load model\nmodel3 = MobileNet(input_shape=(224, 224, 3))\nprint(model3.summary())\n\n# Mark loaded layers as not trainable\nfor index, layer in enumerate(model3.layers[:15]):\n    print(index, layer.name, layer.output_shape)\n    layer.trainable = False\n    \nfor index, layer in enumerate(model3.layers[15:]):\n    print(index, layer.name, layer.output_shape)\n    layer.trainable = True\n\nmodel3.layers[-1].output\n\n# Add new classifier layers\nflat1 = Flatten()(model3.layers[-1].output)\nclass1 = Dense(128, activation='relu', kernel_initializer='he_uniform')(flat1)\noutput = Dense(1, activation='sigmoid')(class1)\n\n# Define new model\nmy_model3 = Model(inputs=model3.inputs, outputs=output)\n\n# Compile model\nopt = SGD(lr=0.0001, momentum=0.9)\nmy_model3.compile(optimizer=opt, loss='binary_crossentropy', metrics=['accuracy'])\nmy_model3.summary()\n\n# Fit model\nmy_model3.reset_states()\nhistory3 = my_model3.fit(train_it, \n                         validation_data=test_it, \n                         epochs=2, \n                         verbose=1,\n                         callbacks=[PlotLossesKeras()],\n                         batch_size=16)  \n\n# Evaluate model\n_, acc = my_model3.evaluate_generator(test_it, steps=len(test_it), verbose=1)\nprint('> %.3f' % (acc * 100.0))\n\nimport matplotlib.pyplot as plt\n\ndef summarize_diagnostics(history3):\n    # Plot loss\n    plt.subplot(211)\n    plt.title('Cross Entropy Loss')\n    plt.plot(history3.history['loss'], color='blue', label='train')\n    plt.plot(history3.history['val_loss'], color='orange', label='test')\n    \n    # Plot accuracy\n    plt.subplot(212)\n    plt.title('Classification Accuracy')\n    plt.plot(history3.history['accuracy'], color='blue', label='train')\n    plt.plot(history3.history['val_accuracy'], color='orange', label='test')\n    \n    # Show the plot\n    plt.show()\n\n# Plot learning curves\nsummarize_diagnostics(history3)\n\n# Save best model\nbest_model3 = 'MobileNet_model.hdf5'\nmy_model3.save(best_model3)\n","metadata":{"execution":{"iopub.status.busy":"2024-02-04T20:31:48.885810Z","iopub.execute_input":"2024-02-04T20:31:48.886789Z","iopub.status.idle":"2024-02-04T20:43:06.528463Z","shell.execute_reply.started":"2024-02-04T20:31:48.886752Z","shell.execute_reply":"2024-02-04T20:43:06.527350Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import keras\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\nfrom livelossplot import PlotLossesKeras\n\nkeras.applications.DenseNet121(\n    include_top=False,\n    weights=\"imagenet\",\n    input_tensor=None,\n    input_shape=None,\n    pooling=None,\n    classes=2,\n    classifier_activation=\"softmax\",\n)\nfrom keras.applications import DenseNet121\n\n# Load model\nmodel4 = DenseNet121(input_shape=(224, 224, 3))\nprint(model4.summary())\n\n# Mark loaded layers as not trainable\nfor index, layer in enumerate(model4.layers[:15]):\n    print(index, layer.name, layer.output_shape)\n    layer.trainable = False\n    \nfor index, layer in enumerate(model4.layers[15:]):\n    print(index, layer.name, layer.output_shape)\n    layer.trainable = True\n\nmodel4.layers[-1].output\n\n# Add new classifier layers\nflat1 = Flatten()(model4.layers[-1].output)\nclass1 = Dense(128, activation='relu', kernel_initializer='he_uniform')(flat1)\noutput = Dense(1, activation='sigmoid')(class1)\n\n# Define new model\nmy_model4 = Model(inputs=model4.inputs, outputs=output)\n\n# Compile model\nopt = SGD(lr=0.0001, momentum=0.9)\nmy_model4.compile(optimizer=opt, loss='binary_crossentropy', metrics=['accuracy'])\nmy_model4.summary()\n\n# Fit model\nmy_model4.reset_states()\nhistory4 = my_model4.fit(train_it, \n                         validation_data=test_it, \n                         epochs=2, \n                         verbose=1,\n                         callbacks=[PlotLossesKeras()],\n                         batch_size=16)  \n\n# Evaluate model\n_, acc = my_model4.evaluate_generator(test_it, steps=len(test_it), verbose=1)\nprint('> %.3f' % (acc * 100.0))\n\nimport matplotlib.pyplot as plt\n\ndef summarize_diagnostics(history4):\n    # Plot loss\n    plt.subplot(211)\n    plt.title('Cross Entropy Loss')\n    plt.plot(history4.history['loss'], color='blue', label='train')\n    plt.plot(history4.history['val_loss'], color='orange', label='test')\n    \n    # Plot accuracy\n    plt.subplot(212)\n    plt.title('Classification Accuracy')\n    plt.plot(history4.history['accuracy'], color='blue', label='train')\n    plt.plot(history4.history['val_accuracy'], color='orange', label='test')\n    \n    # Show the plot\n    plt.show()\n\n# Plot learning curves\nsummarize_diagnostics(history4)\n\n# Save best model\nbest_model4 = 'DenseNet121_model.hdf5'\nmy_model4.save(best_model4)\n","metadata":{"execution":{"iopub.status.busy":"2024-02-04T20:43:16.014671Z","iopub.execute_input":"2024-02-04T20:43:16.015038Z","iopub.status.idle":"2024-02-04T20:55:26.141519Z","shell.execute_reply.started":"2024-02-04T20:43:16.015008Z","shell.execute_reply":"2024-02-04T20:55:26.140519Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import keras\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\nfrom livelossplot import PlotLossesKeras\n\nkeras.applications.MobileNetV2(\n    alpha=1.0,\n    include_top=False,\n    weights=\"imagenet\",\n    input_tensor=None,\n    pooling=None,\n    classes=2,\n    classifier_activation=\"softmax\",\n)\nfrom keras.applications import MobileNetV2\n\n# Load model\nmodel5 = MobileNetV2(input_shape=(224, 224, 3))\nprint(model5.summary())\n\n# Mark loaded layers as not trainable\nfor index, layer in enumerate(model5.layers[:15]):\n    print(index, layer.name, layer.output_shape)\n    layer.trainable = False\n    \nfor index, layer in enumerate(model5.layers[15:]):\n    print(index, layer.name, layer.output_shape)\n    layer.trainable = True\n\nmodel5.layers[-1].output\n\n# Add new classifier layers\nflat1 = Flatten()(model5.layers[-1].output)\nclass1 = Dense(128, activation='relu', kernel_initializer='he_uniform')(flat1)\noutput = Dense(1, activation='sigmoid')(class1)\n\n# Define new model\nmy_model5 = Model(inputs=model5.inputs, outputs=output)\n\n# Compile model\nopt = SGD(lr=0.0001, momentum=0.9)\nmy_model5.compile(optimizer=opt, loss='binary_crossentropy', metrics=['accuracy'])\nmy_model5.summary()\n\n# Fit model\nmy_model5.reset_states()\nhistory5 = my_model5.fit(train_it, \n                         validation_data=test_it, \n                         epochs=2, \n                         verbose=1,\n                         callbacks=[PlotLossesKeras()],\n                         batch_size=16)  \n\n# Evaluate model\n_, acc = my_model5.evaluate_generator(test_it, steps=len(test_it), verbose=1)\nprint('> %.3f' % (acc * 100.0))\n\nimport matplotlib.pyplot as plt\n\ndef summarize_diagnostics(history5):\n    # Plot loss\n    plt.subplot(211)\n    plt.title('Cross Entropy Loss')\n    plt.plot(history5.history['loss'], color='blue', label='train')\n    plt.plot(history5.history['val_loss'], color='orange', label='test')\n    \n    # Plot accuracy\n    plt.subplot(212)\n    plt.title('Classification Accuracy')\n    plt.plot(history5.history['accuracy'], color='blue', label='train')\n    plt.plot(history5.history['val_accuracy'], color='orange', label='test')\n    \n    # Show the plot\n    plt.show()\n\n# Plot learning curves\nsummarize_diagnostics(history5)\n\n# Save best model\nbest_model5 = 'MobileNetV2_model.hdf5'\nmy_model5.save(best_model5)\n","metadata":{"execution":{"iopub.status.busy":"2024-02-04T21:19:52.121621Z","iopub.execute_input":"2024-02-04T21:19:52.122026Z","iopub.status.idle":"2024-02-04T21:31:15.664327Z","shell.execute_reply.started":"2024-02-04T21:19:52.121993Z","shell.execute_reply":"2024-02-04T21:31:15.663334Z"},"trusted":true},"execution_count":null,"outputs":[]}]}