{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"}},"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\nimport zipfile\nimport shutil\n\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":"2023-05-16T00:22:40.858625Z","iopub.execute_input":"2023-05-16T00:22:40.859317Z","iopub.status.idle":"2023-05-16T00:22:40.88301Z","shell.execute_reply.started":"2023-05-16T00:22:40.859282Z","shell.execute_reply":"2023-05-16T00:22:40.881929Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"zip_ref = zipfile.ZipFile('/kaggle/input/dogs-vs-cats/train.zip', 'r')\nzip_ref.extractall('/kaggle/working')\nzip_ref.close()","metadata":{"execution":{"iopub.status.busy":"2023-05-16T00:22:47.296523Z","iopub.execute_input":"2023-05-16T00:22:47.296939Z","iopub.status.idle":"2023-05-16T00:22:58.209772Z","shell.execute_reply.started":"2023-05-16T00:22:47.296907Z","shell.execute_reply":"2023-05-16T00:22:58.2088Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"base_dir = '/kaggle/working'\ntrain_dir = os.path.join(base_dir, 'train')\nvalidation_dir = os.path.join(base_dir, 'validation')\n\nos.mkdir(validation_dir)\n\n# Directory with our training cat pictures\ntrain_cats_dir = os.path.join(train_dir, 'cats')\nos.mkdir(train_cats_dir)\n\n# Directory with our training dog pictures\ntrain_dogs_dir = os.path.join(train_dir, 'dogs')\nos.mkdir(train_dogs_dir)\n\n# Directory with our validation cat pictures\nvalidation_cats_dir = os.path.join(validation_dir, 'cats')\nos.mkdir(validation_cats_dir)\n\n# Directory with our validation dog pictures\nvalidation_dogs_dir = os.path.join(validation_dir, 'dogs')\nos.mkdir(validation_dogs_dir)\n\nprint(len(os.listdir(validation_dir)))","metadata":{"execution":{"iopub.status.busy":"2023-05-16T00:22:58.211736Z","iopub.execute_input":"2023-05-16T00:22:58.21207Z","iopub.status.idle":"2023-05-16T00:22:58.221744Z","shell.execute_reply.started":"2023-05-16T00:22:58.212039Z","shell.execute_reply":"2023-05-16T00:22:58.220725Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Move dogs and cats images in separate folder.\nfiles = os.listdir(train_dir)\n\n# Split the original training set into a reduced training set and a\n# validation set. \nvalidation_split = 0.2\ntrain_split = 0.8\n\nindex = 0\nlength_train_dir = len(files) # length of the train dir\n\nprint(length_train_dir)","metadata":{"execution":{"iopub.status.busy":"2023-05-16T00:22:58.223163Z","iopub.execute_input":"2023-05-16T00:22:58.224149Z","iopub.status.idle":"2023-05-16T00:22:58.247895Z","shell.execute_reply.started":"2023-05-16T00:22:58.224116Z","shell.execute_reply":"2023-05-16T00:22:58.247084Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Too slow training . I limited the size ot the data set for conveniance !!","metadata":{}},{"cell_type":"code","source":"while index < length_train_dir :\n    filename = files[index]\n    if 'cat' in filename and filename.endswith(\"jpg\") and (len(os.listdir(train_cats_dir)) < 1000):\n        src = os.path.join(train_dir, filename)\n        dst = os.path.join(train_cats_dir, filename)\n        shutil.move(src, dst)\n    elif 'dog' in filename and filename.endswith(\"jpg\") and (len(os.listdir(train_dogs_dir)) < 1000):\n        src = os.path.join(train_dir, filename)\n        dst = os.path.join(train_dogs_dir, filename)\n        shutil.move(src, dst)\n    elif 'cat' in filename and filename.endswith(\"jpg\") and (len(os.listdir(validation_cats_dir)) < 500):\n        src = os.path.join(train_dir, filename)\n        dst = os.path.join(validation_cats_dir, filename)\n        shutil.move(src, dst)\n    elif 'dog' in filename and filename.endswith(\"jpg\") and (len(os.listdir(validation_dogs_dir)) <500):\n        src = os.path.join(train_dir, filename)\n        dst = os.path.join(validation_dogs_dir, filename)\n        shutil.move(src, dst)\n    index += 1","metadata":{"execution":{"iopub.status.busy":"2023-05-16T00:22:58.250346Z","iopub.execute_input":"2023-05-16T00:22:58.251128Z","iopub.status.idle":"2023-05-16T00:23:17.316384Z","shell.execute_reply.started":"2023-05-16T00:22:58.251093Z","shell.execute_reply":"2023-05-16T00:23:17.315421Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_cat_fnames = os.listdir(train_cats_dir)\nprint(train_cat_fnames[:10])\n\ntrain_dog_fnames = os.listdir(train_dogs_dir)\ntrain_dog_fnames.sort()\nprint(train_dog_fnames[:10])","metadata":{"execution":{"iopub.status.busy":"2023-05-16T00:23:17.317824Z","iopub.execute_input":"2023-05-16T00:23:17.318184Z","iopub.status.idle":"2023-05-16T00:23:17.327237Z","shell.execute_reply.started":"2023-05-16T00:23:17.318151Z","shell.execute_reply":"2023-05-16T00:23:17.326104Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print('total training cat images:', len(os.listdir(train_cats_dir)))\nprint('total training dog images:', len(os.listdir(train_dogs_dir)))\nprint('total validation cat images:', len(os.listdir(validation_cats_dir)))\nprint('total validation dog images:', len(os.listdir(validation_dogs_dir)))","metadata":{"execution":{"iopub.status.busy":"2023-05-16T00:23:17.329184Z","iopub.execute_input":"2023-05-16T00:23:17.32962Z","iopub.status.idle":"2023-05-16T00:23:17.34003Z","shell.execute_reply.started":"2023-05-16T00:23:17.329588Z","shell.execute_reply":"2023-05-16T00:23:17.339031Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":" For both cats and dogs, i limited the size for  2000 training images and 1000 test images.","metadata":{}},{"cell_type":"markdown","source":"## Data Augmentation","metadata":{}},{"cell_type":"code","source":"from tensorflow.keras.preprocessing.image import ImageDataGenerator\n\ndatagen = ImageDataGenerator(\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')","metadata":{"execution":{"iopub.status.busy":"2023-05-16T00:23:17.341379Z","iopub.execute_input":"2023-05-16T00:23:17.342354Z","iopub.status.idle":"2023-05-16T00:23:23.958126Z","shell.execute_reply.started":"2023-05-16T00:23:17.34232Z","shell.execute_reply":"2023-05-16T00:23:23.957206Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Adding rescale, rotation_range, width_shift_range, height_shift_range,\n# shear_range, zoom_range, and horizontal flip to our ImageDataGenerator\ntrain_datagen = 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\n# Note that the validation data should not be augmented!\nval_datagen = ImageDataGenerator(rescale=1./255)\n\n# Flow training images in batches of 32 using train_datagen generator\ntrain_generator = train_datagen.flow_from_directory(\n        train_dir,  # This is the source directory for training images\n        target_size=(150, 150),  # All images will be resized to 150x150\n        batch_size=20,\n        # Since we use binary_crossentropy loss, we need binary labels\n        class_mode='binary')\n\n# Flow validation images in batches of 32 using val_datagen generator\nvalidation_generator = val_datagen.flow_from_directory(\n        validation_dir,\n        target_size=(150, 150),\n        batch_size=20,\n        class_mode='binary')","metadata":{"execution":{"iopub.status.busy":"2023-05-16T00:23:23.959393Z","iopub.execute_input":"2023-05-16T00:23:23.960988Z","iopub.status.idle":"2023-05-16T00:23:24.213833Z","shell.execute_reply.started":"2023-05-16T00:23:23.96095Z","shell.execute_reply":"2023-05-16T00:23:24.21297Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Adding Dropout","metadata":{}},{"cell_type":"code","source":"from tensorflow.keras import layers\nfrom tensorflow.keras import Model\nfrom tensorflow.keras.optimizers import RMSprop","metadata":{"execution":{"iopub.status.busy":"2023-05-16T00:23:24.215048Z","iopub.execute_input":"2023-05-16T00:23:24.216059Z","iopub.status.idle":"2023-05-16T00:23:24.221365Z","shell.execute_reply.started":"2023-05-16T00:23:24.216023Z","shell.execute_reply":"2023-05-16T00:23:24.220426Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Meu código","metadata":{}},{"cell_type":"code","source":"from keras.models import Sequential\nfrom keras.layers import Conv2D, MaxPooling2D\nfrom keras.layers import Activation, Dropout, Flatten, Dense","metadata":{"execution":{"iopub.status.busy":"2023-05-16T00:24:55.411174Z","iopub.execute_input":"2023-05-16T00:24:55.411603Z","iopub.status.idle":"2023-05-16T00:24:55.422124Z","shell.execute_reply.started":"2023-05-16T00:24:55.411569Z","shell.execute_reply":"2023-05-16T00:24:55.421157Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"modelo = Sequential()\nmodelo.add(Conv2D(filters=32, kernel_size=(3,3),input_shape=(150,150,3), activation='relu',))\nmodelo.add(MaxPooling2D(pool_size=(2, 2)))\nmodelo.add(Conv2D(filters=64, kernel_size=(3,3),activation='relu',))\nmodelo.add(MaxPooling2D(pool_size=(2, 2)))\nmodelo.add(Conv2D(filters=64, kernel_size=(3,3),activation='relu',))\nmodelo.add(MaxPooling2D(pool_size=(2, 2)))\nmodelo.add(Flatten())\nmodelo.add(Dense(128))\nmodelo.add(Activation('relu'))\nmodelo.add(Dropout(0.5))\nmodelo.add(Dense(1))\nmodelo.add(Activation('sigmoid'))\nmodelo.compile(loss='binary_crossentropy',\n optimizer='adam',\n metrics=['acc'])","metadata":{"execution":{"iopub.status.busy":"2023-05-16T00:41:42.845306Z","iopub.execute_input":"2023-05-16T00:41:42.84568Z","iopub.status.idle":"2023-05-16T00:41:42.963385Z","shell.execute_reply.started":"2023-05-16T00:41:42.84565Z","shell.execute_reply":"2023-05-16T00:41:42.962355Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"modelo.summary()","metadata":{"execution":{"iopub.status.busy":"2023-05-16T00:37:14.915859Z","iopub.execute_input":"2023-05-16T00:37:14.916551Z","iopub.status.idle":"2023-05-16T00:37:14.955558Z","shell.execute_reply.started":"2023-05-16T00:37:14.916506Z","shell.execute_reply":"2023-05-16T00:37:14.954818Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Training","metadata":{}},{"cell_type":"code","source":"history = modelo.fit_generator(\n      train_generator,\n      steps_per_epoch=100,\n      epochs=2,\n      validation_data=validation_generator,\n      validation_steps=50,\n      verbose=2)","metadata":{"execution":{"iopub.status.busy":"2023-05-16T00:37:22.182236Z","iopub.execute_input":"2023-05-16T00:37:22.182802Z","iopub.status.idle":"2023-05-16T00:37:22.4695Z","shell.execute_reply.started":"2023-05-16T00:37:22.182768Z","shell.execute_reply":"2023-05-16T00:37:22.468189Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Training and  Accuracy  visualisation for cnn","metadata":{"execution":{"iopub.status.busy":"2023-05-03T03:57:22.018868Z","iopub.execute_input":"2023-05-03T03:57:22.019289Z","iopub.status.idle":"2023-05-03T03:57:22.023244Z","shell.execute_reply.started":"2023-05-03T03:57:22.01922Z","shell.execute_reply":"2023-05-03T03:57:22.022338Z"}}},{"cell_type":"code","source":"%matplotlib inline\n\nimport matplotlib.pyplot as plt\nimport matplotlib.image as mpimg\n\n# Retrieve a list of accuracy results on training and validation data\n# sets for each training epoch\nacc = history.history['acc']\nval_acc = history.history['val_acc']\n\n# Retrieve a list of list results on training and validation data\n# sets for each training epoch\nloss = history.history['loss']\nval_loss = history.history['val_loss']\n\n# Get number of epochs\nepochs = range(len(acc))\n\n# Plot training and validation accuracy per epoch\nplt.plot(epochs, acc,label=\"Training accuracy\")\nplt.plot(epochs, val_acc,label=\"validation accuracy\")\nplt.title('Training and validation accuracy')\nplt.legend()\n\nplt.figure()\n\n# Plot training and validation loss per epoch\nplt.plot(epochs, loss,label=\"Training loss\")\nplt.plot(epochs, val_loss,label=\"validation loss\")\nplt.legend()\nplt.title('Training and validation loss')","metadata":{"execution":{"iopub.status.busy":"2023-05-16T00:33:31.260235Z","iopub.execute_input":"2023-05-16T00:33:31.260598Z","iopub.status.idle":"2023-05-16T00:33:31.928905Z","shell.execute_reply.started":"2023-05-16T00:33:31.260564Z","shell.execute_reply":"2023-05-16T00:33:31.927986Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from keras.models import Sequential, save_model, load_model\nsave_model(model, 'dog_vs_cat_cnn_model.h5')","metadata":{"execution":{"iopub.status.busy":"2023-05-03T04:15:00.715708Z","iopub.execute_input":"2023-05-03T04:15:00.716053Z","iopub.status.idle":"2023-05-03T04:15:00.915914Z","shell.execute_reply.started":"2023-05-03T04:15:00.716026Z","shell.execute_reply":"2023-05-03T04:15:00.914943Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### FCN","metadata":{}},{"cell_type":"code","source":"from keras.models import Sequential\nfrom keras.layers import Dense, Flatten\nfrom keras.optimizers import SGD","metadata":{"execution":{"iopub.status.busy":"2023-05-03T04:15:43.697853Z","iopub.execute_input":"2023-05-03T04:15:43.698249Z","iopub.status.idle":"2023-05-03T04:15:43.702634Z","shell.execute_reply.started":"2023-05-03T04:15:43.698201Z","shell.execute_reply":"2023-05-03T04:15:43.701681Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"model = Sequential()\nmodel.add(Flatten(input_shape=(150, 150, 3)))\nmodel.add(Dense(256, activation='relu'))\nmodel.add(Dense(128, activation='relu'))\nmodel.add(Dense(1, activation='sigmoid'))","metadata":{"execution":{"iopub.status.busy":"2023-05-03T04:15:44.744009Z","iopub.execute_input":"2023-05-03T04:15:44.744368Z","iopub.status.idle":"2023-05-03T04:15:44.797405Z","shell.execute_reply.started":"2023-05-03T04:15:44.744339Z","shell.execute_reply":"2023-05-03T04:15:44.796469Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"model.compile(optimizer=SGD(lr=0.001),\n              loss='binary_crossentropy',\n              metrics=['accuracy'])","metadata":{"execution":{"iopub.status.busy":"2023-05-03T04:15:51.046856Z","iopub.execute_input":"2023-05-03T04:15:51.047187Z","iopub.status.idle":"2023-05-03T04:15:51.061165Z","shell.execute_reply.started":"2023-05-03T04:15:51.04716Z","shell.execute_reply":"2023-05-03T04:15:51.05928Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"history2 = model.fit(train_generator,\n          steps_per_epoch=100,\n          epochs=50,\n          validation_data=validation_generator,\n          validation_steps=50)","metadata":{"execution":{"iopub.status.busy":"2023-05-03T04:23:56.649649Z","iopub.execute_input":"2023-05-03T04:23:56.649975Z","iopub.status.idle":"2023-05-03T04:35:27.322422Z","shell.execute_reply.started":"2023-05-03T04:23:56.649948Z","shell.execute_reply":"2023-05-03T04:35:27.321475Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Retrieve a list of accuracy results on training and validation data\n# sets for each training epoch\nacc2 = history2.history['accuracy']\nval_acc2 = history2.history['val_accuracy']\n\n# Retrieve a list of list results on training and validation data\n# sets for each training epoch\nloss2 = history2.history['loss']\nval_loss2 = history2.history['val_loss']\n\n# Get number of epochs\nepochs2 = range(len(acc2))\n\n# Plot training and validation accuracy per epoch\nplt.plot(epochs2, acc2,label=\"Training accuracy\")\nplt.plot(epochs2, val_acc2,label=\"validation accuracy\")\nplt.title('Training and validation accuracy')\nplt.legend()\n\nplt.figure()\n\n# Plot training and validation loss per epoch\nplt.plot(epochs2, loss2,label=\"Training loss\")\nplt.plot(epochs2, val_loss2,label=\"validation loss\")\nplt.legend()\nplt.title('Training and validation loss')","metadata":{"execution":{"iopub.status.busy":"2023-05-03T04:35:41.208596Z","iopub.execute_input":"2023-05-03T04:35:41.20896Z","iopub.status.idle":"2023-05-03T04:35:41.79842Z","shell.execute_reply.started":"2023-05-03T04:35:41.208929Z","shell.execute_reply":"2023-05-03T04:35:41.797602Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"The graph thell us that **convolution neural network** do a better job than **full neural network** for  the image classification in the same condition","metadata":{}},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}