{"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":"2025-02-15T02:20:44.519586Z","iopub.execute_input":"2025-02-15T02:20:44.519899Z","iopub.status.idle":"2025-02-15T02:20:44.52658Z","shell.execute_reply.started":"2025-02-15T02:20:44.519868Z","shell.execute_reply":"2025-02-15T02:20:44.525661Z"},"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":"2025-02-15T02:20:44.527756Z","iopub.execute_input":"2025-02-15T02:20:44.52808Z","iopub.status.idle":"2025-02-15T02:20:57.786932Z","shell.execute_reply.started":"2025-02-15T02:20:44.528051Z","shell.execute_reply":"2025-02-15T02:20:57.786246Z"},"trusted":true},"outputs":[],"execution_count":null},{"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":"2025-02-15T02:20:57.787867Z","iopub.execute_input":"2025-02-15T02:20:57.788101Z","iopub.status.idle":"2025-02-15T02:20:58.767065Z","shell.execute_reply.started":"2025-02-15T02:20:57.788082Z","shell.execute_reply":"2025-02-15T02:20:58.766243Z"},"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":"2025-02-15T02:20:58.768209Z","iopub.execute_input":"2025-02-15T02:20:58.768868Z","iopub.status.idle":"2025-02-15T02:20:59.707583Z","shell.execute_reply.started":"2025-02-15T02:20:58.768833Z","shell.execute_reply":"2025-02-15T02:20:59.706722Z"},"trusted":true},"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":"2025-02-15T02:20:59.708691Z","iopub.execute_input":"2025-02-15T02:20:59.709024Z","iopub.status.idle":"2025-02-15T02:20:59.713121Z","shell.execute_reply.started":"2025-02-15T02:20:59.709001Z","shell.execute_reply":"2025-02-15T02:20:59.712321Z"},"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":"\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":"2025-02-15T02:20:59.71563Z","iopub.execute_input":"2025-02-15T02:20:59.715904Z","iopub.status.idle":"2025-02-15T02:20:59.724229Z","shell.execute_reply.started":"2025-02-15T02:20:59.71588Z","shell.execute_reply":"2025-02-15T02:20:59.723546Z"},"trusted":true},"outputs":[],"execution_count":null},{"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":"2025-02-15T02:20:59.725102Z","iopub.execute_input":"2025-02-15T02:20:59.725341Z","iopub.status.idle":"2025-02-15T02:20:59.734644Z","shell.execute_reply.started":"2025-02-15T02:20:59.725322Z","shell.execute_reply":"2025-02-15T02:20:59.733653Z"},"trusted":true},"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":"2025-02-15T02:20:59.735953Z","iopub.execute_input":"2025-02-15T02:20:59.736441Z","iopub.status.idle":"2025-02-15T02:21:02.422055Z","shell.execute_reply.started":"2025-02-15T02:20:59.736403Z","shell.execute_reply":"2025-02-15T02:21:02.421045Z"},"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":"2025-02-15T02:21:02.423036Z","iopub.execute_input":"2025-02-15T02:21:02.423275Z","iopub.status.idle":"2025-02-15T02:21:03.516668Z","shell.execute_reply.started":"2025-02-15T02:21:02.423254Z","shell.execute_reply":"2025-02-15T02:21:03.51557Z"},"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":"2025-02-15T02:21:03.518335Z","iopub.execute_input":"2025-02-15T02:21:03.519058Z","iopub.status.idle":"2025-02-15T02:21:04.598294Z","shell.execute_reply.started":"2025-02-15T02:21:03.519018Z","shell.execute_reply":"2025-02-15T02:21:04.597173Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"!pip -q install livelossplot==0.5.5","metadata":{"execution":{"iopub.status.busy":"2025-02-15T02:21:04.600098Z","iopub.execute_input":"2025-02-15T02:21:04.600968Z","iopub.status.idle":"2025-02-15T02:21:14.327712Z","shell.execute_reply.started":"2025-02-15T02:21:04.600929Z","shell.execute_reply":"2025-02-15T02:21:14.326622Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"from livelossplot import PlotLossesKeras","metadata":{"execution":{"iopub.status.busy":"2025-02-15T02:21:14.32946Z","iopub.execute_input":"2025-02-15T02:21:14.330331Z","iopub.status.idle":"2025-02-15T02:21:14.344714Z","shell.execute_reply.started":"2025-02-15T02:21:14.330293Z","shell.execute_reply":"2025-02-15T02:21:14.34404Z"},"trusted":true},"outputs":[],"execution_count":null},{"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":"2025-02-15T02:21:14.345827Z","iopub.execute_input":"2025-02-15T02:21:14.346138Z","iopub.status.idle":"2025-02-15T02:21:14.350949Z","shell.execute_reply.started":"2025-02-15T02:21:14.346109Z","shell.execute_reply":"2025-02-15T02:21:14.350144Z"},"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":"","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"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":"2025-02-15T02:21:14.351908Z","iopub.execute_input":"2025-02-15T02:21:14.352202Z","iopub.status.idle":"2025-02-15T02:21:15.040262Z","shell.execute_reply.started":"2025-02-15T02:21:14.352175Z","shell.execute_reply":"2025-02-15T02:21:15.039534Z"},"trusted":true},"outputs":[],"execution_count":null},{"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":"2025-02-15T02:21:15.041219Z","iopub.execute_input":"2025-02-15T02:21:15.041462Z","iopub.status.idle":"2025-02-15T02:21:17.007113Z","shell.execute_reply.started":"2025-02-15T02:21:15.04144Z","shell.execute_reply":"2025-02-15T02:21:17.006285Z"},"trusted":true},"outputs":[],"execution_count":null},{"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":"2025-02-15T02:21:17.008268Z","iopub.execute_input":"2025-02-15T02:21:17.008651Z","iopub.status.idle":"2025-02-15T02:21:17.021905Z","shell.execute_reply.started":"2025-02-15T02:21:17.008614Z","shell.execute_reply":"2025-02-15T02:21:17.020705Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"model.layers[-1].output","metadata":{"execution":{"iopub.status.busy":"2025-02-15T02:21:17.023Z","iopub.execute_input":"2025-02-15T02:21:17.023361Z","iopub.status.idle":"2025-02-15T02:21:17.497071Z","shell.execute_reply.started":"2025-02-15T02:21:17.023324Z","shell.execute_reply":"2025-02-15T02:21:17.496209Z"},"trusted":true},"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=0.0001, momentum=0.9)\nmy_model.compile(optimizer=opt, loss='binary_crossentropy', metrics=['accuracy'])\nmy_model.summary()","metadata":{"execution":{"iopub.status.busy":"2025-02-15T02:21:17.498216Z","iopub.execute_input":"2025-02-15T02:21:17.498536Z","iopub.status.idle":"2025-02-15T02:21:17.582617Z","shell.execute_reply.started":"2025-02-15T02:21:17.498507Z","shell.execute_reply":"2025-02-15T02:21:17.581742Z"},"trusted":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()])\n# evaluate model\n_, acc = model.evaluate_generator(test_it, steps=len(test_it), verbose=1)\nprint('> %.3f' % (acc * 100.0))\n# learning curves\nsummarize_diagnostics(history)\n\nbest_model = 'vgg16_model.hdf5'\nmy_model.save(best_model)","metadata":{"execution":{"iopub.status.busy":"2025-02-15T02:21:17.583639Z","iopub.execute_input":"2025-02-15T02:21:17.583901Z","iopub.status.idle":"2025-02-15T02:31:26.097571Z","shell.execute_reply.started":"2025-02-15T02:21:17.583879Z","shell.execute_reply":"2025-02-15T02:31:26.096147Z"},"trusted":true},"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":"2025-02-15T02:31:26.098415Z","iopub.status.idle":"2025-02-15T02:31:26.09873Z","shell.execute_reply.started":"2025-02-15T02:31:26.098563Z","shell.execute_reply":"2025-02-15T02:31:26.098575Z"}},"outputs":[],"execution_count":null},{"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":{"trusted":true,"execution":{"iopub.status.busy":"2025-02-15T02:31:26.100128Z","iopub.status.idle":"2025-02-15T02:31:26.100533Z","shell.execute_reply.started":"2025-02-15T02:31:26.100366Z","shell.execute_reply":"2025-02-15T02:31:26.100384Z"}},"outputs":[],"execution_count":null},{"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,"execution":{"iopub.status.busy":"2025-02-15T02:31:26.102118Z","iopub.status.idle":"2025-02-15T02:31:26.102402Z","shell.execute_reply.started":"2025-02-15T02:31:26.102269Z","shell.execute_reply":"2025-02-15T02:31:26.102282Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"from keras.callbacks import EarlyStopping, ReduceLROnPlateau\n\n# Using early stopping and learning rate reduction to improve training\nearly_stopping = EarlyStopping(monitor='val_loss', patience=5, restore_best_weights=True)\nreduce_lr = ReduceLROnPlateau(monitor='val_loss', factor=0.1, patience=3)\n\n# Train the model for more epochs (e.g., 20 epochs) with early stopping and learning rate reduction\nhistory = my_model.fit(train_it, \n                       validation_data=test_it, \n                       epochs=20,  # Increase epochs\n                       verbose=1,\n                       callbacks=[PlotLossesKeras(), early_stopping, reduce_lr])\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-02-15T02:48:19.685427Z","iopub.execute_input":"2025-02-15T02:48:19.686171Z","iopub.status.idle":"2025-02-15T04:12:01.216034Z","shell.execute_reply.started":"2025-02-15T02:48:19.686139Z","shell.execute_reply":"2025-02-15T04:12:01.214911Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import random\nimport matplotlib.pyplot as plt\nimport numpy as np\n\n# Function to load and preprocess image\ndef load_image(filename):\n    img = load_img(filename, target_size=(224, 224))\n    img = img_to_array(img)\n    img = np.expand_dims(img, axis=0)  # Add batch dimension\n    img = img.astype('float32') / 255.0  # Normalize the image\n    return img\n\n# Randomize and predict for 10 images (5 from each class)\ntest_images = []\ntest_dirs = ['dogs', 'cats']\nfor label in test_dirs:\n    class_folder = f'dataset_dogs_vs_cats/test/{label}/'\n    image_files = os.listdir(class_folder)\n    selected_images = random.sample(image_files, 5)  # Select 5 random images\n    for image in selected_images:\n        test_images.append(os.path.join(class_folder, image))\n\n# Predict and display results for the randomized images\nfor img_path in test_images:\n    img = load_image(img_path)\n    result = my_model.predict(img)\n    \n    # Display the image and the prediction\n    img_show = load_img(img_path)\n    plt.imshow(img_show)\n    plt.title(f\"Prediction: {'Dog' if result[0] > 0.5 else 'Cat'}\")\n    plt.show()\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-02-15T04:12:01.217868Z","iopub.execute_input":"2025-02-15T04:12:01.218555Z","iopub.status.idle":"2025-02-15T04:12:05.113422Z","shell.execute_reply.started":"2025-02-15T04:12:01.218514Z","shell.execute_reply":"2025-02-15T04:12:05.112556Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null}]}