{"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":"none","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":"markdown","source":"![photo.jpg](attachment:b0581b55-6eba-4d0e-b97f-919e24fccbac.jpg)","metadata":{},"attachments":{"b0581b55-6eba-4d0e-b97f-919e24fccbac.jpg":{"image/jpeg":"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"}}},{"cell_type":"markdown","source":"# Project Overview\nThis notebook made for the to DataTalksClub Machine Learning Zoomcamp Capstone Project 1 and is made by Lokman Efe and is about Dog or Cat Classification.\n\nMy Kaggle Profile: https://www.kaggle.com/lokmanefe\n\nMy GitHub Profile: https://github.com/lokicik\n\nMy LinkedIn Profile: https://www.linkedin.com/in/lokmanefe/\n\nFeel free to reach out! ✌\n\n\nYou should download the dataset and change the variables' paths in the scripts to dataset's path but I suggest you to run the scripts in Kaggle notebooks and don't download the data, it would be easier since you wouldn't have to download the data, which is over 100 mb's. I developed the project on Kaggle too, so you don't have to change the dataset paths in the scripts, you just have to add the data to your notebook if you work on Kaggle.\n\n# Project Presentation\nI would like to introduce my most comprehensive project to date! I have completed the project \"Dog or Cat Classification (CNN) deployed with AWS Lambda\" which I developed as the Capstone Project 1 of the Machine Learning Zoomcamp organized by DataTalksClub and presented by Alexey Grigorev. I had the opportunity to apply all the techniques I learned, and I gave my all to this project. I look forward to your feedback and hope for positive reviews!\n\n## Description of the Problem\nIn the digital age, the sheer volume of images available on the internet poses a challenge \nfor effective categorization. One prevalent domain is the classification of images \ninto distinct categories, such as identifying whether an image contains a dog or a cat. \nThis task is not only time-consuming but also prone to human error, making it a prime \ncandidate for automation.\n\n## Problem Solution\nThis project focuses on developing an image classification \nsystem capable of identifying images whether it's a dog or a cat.\nLeveraging state-of-the-art deep learning techniques, a convolutional neural network (CNN) \nis trained to analyze and learn distinctive features present in dog and cat images.\n\n## Dataset (https://www.kaggle.com/competitions/dogs-vs-cats/data)\nThe training archive contains 25,000 images of dogs and cats. \nTrain an algorithm on these files and predict the labels for test1.zip (1 = dog, 0 = cat).\n\n","metadata":{}},{"cell_type":"markdown","source":"# Project Requirements (Evaluation Criteria)\n* Problem description\n* EDA\n* Model training\n* Exporting notebook to script\n* Model deployment\n* Reproducibility\n* Dependency and environment management\n* Containerization\n* Cloud deployment","metadata":{}},{"cell_type":"markdown","source":"# Imports","metadata":{}},{"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 in \nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\nimport seaborn as sns\nimport cv2\nimport matplotlib.pyplot as plt\nimport tensorflow as tf\nfrom tensorflow.keras.models import Sequential\nfrom tensorflow.keras.layers import Dense, Flatten, Dropout, Activation, Conv2D, MaxPooling2D\nfrom tensorflow.keras.optimizers import Adam\nfrom tensorflow.keras.callbacks import EarlyStopping\nfrom keras.preprocessing.image import ImageDataGenerator\nfrom sklearn.model_selection import train_test_split\nfrom kerastuner.tuners import RandomSearch","metadata":{"execution":{"iopub.status.busy":"2023-12-17T23:03:20.321789Z","iopub.execute_input":"2023-12-17T23:03:20.322025Z","iopub.status.idle":"2023-12-17T23:03:34.610070Z","shell.execute_reply.started":"2023-12-17T23:03:20.322003Z","shell.execute_reply":"2023-12-17T23:03:34.609121Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# Adding the data","metadata":{}},{"cell_type":"code","source":"import os\nprint(os.listdir(\"../input\"))\n\nimport zipfile\n\nwith zipfile.ZipFile(\"/kaggle/input/dogs-vs-cats/train.zip\",\"r\") as z:\n    z.extractall(\".\")\n    \nwith zipfile.ZipFile(\"/kaggle/input/dogs-vs-cats/test1.zip\",\"r\") as z:\n    z.extractall(\".\")","metadata":{"execution":{"iopub.status.busy":"2023-12-17T23:03:34.611674Z","iopub.execute_input":"2023-12-17T23:03:34.612187Z","iopub.status.idle":"2023-12-17T23:03:49.190358Z","shell.execute_reply.started":"2023-12-17T23:03:34.612156Z","shell.execute_reply":"2023-12-17T23:03:49.189427Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"main_dir = \"/kaggle/working/\"\ntrain_dir = \"train\"\npath = os.path.join(main_dir,train_dir)","metadata":{"execution":{"iopub.status.busy":"2023-12-17T23:03:49.191476Z","iopub.execute_input":"2023-12-17T23:03:49.191783Z","iopub.status.idle":"2023-12-17T23:03:49.196447Z","shell.execute_reply.started":"2023-12-17T23:03:49.191755Z","shell.execute_reply":"2023-12-17T23:03:49.195563Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"for p in os.listdir(path):\n    category = p.split(\".\")[0]\n    img_array = cv2.imread(os.path.join(path,p),cv2.IMREAD_GRAYSCALE)\n    new_img_array = cv2.resize(img_array, dsize=(80, 80))\n    plt.imshow(new_img_array,cmap=\"gray\")\n    break","metadata":{"execution":{"iopub.status.busy":"2023-12-17T23:03:49.198502Z","iopub.execute_input":"2023-12-17T23:03:49.198779Z","iopub.status.idle":"2023-12-17T23:03:49.545468Z","shell.execute_reply.started":"2023-12-17T23:03:49.198754Z","shell.execute_reply":"2023-12-17T23:03:49.544639Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"X = []\ny = []\nconvert = lambda category : int(category == 'dog')\ndef create_test_data(path):\n    for p in os.listdir(path):\n        category = p.split(\".\")[0]\n        category = convert(category)\n        img_array = cv2.imread(os.path.join(path,p),cv2.IMREAD_GRAYSCALE)\n        new_img_array = cv2.resize(img_array, dsize=(80, 80))\n        X.append(new_img_array)\n        y.append(category)","metadata":{"execution":{"iopub.status.busy":"2023-12-17T23:03:49.546672Z","iopub.execute_input":"2023-12-17T23:03:49.547004Z","iopub.status.idle":"2023-12-17T23:03:49.553213Z","shell.execute_reply.started":"2023-12-17T23:03:49.546972Z","shell.execute_reply":"2023-12-17T23:03:49.552246Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"create_test_data(path)\nX = np.array(X).reshape(-1, 80,80,1)\ny = np.array(y)\nX = X/255.0","metadata":{"execution":{"iopub.status.busy":"2023-12-17T23:04:06.891556Z","iopub.execute_input":"2023-12-17T23:04:06.892272Z","iopub.status.idle":"2023-12-17T23:04:29.330795Z","shell.execute_reply.started":"2023-12-17T23:04:06.892238Z","shell.execute_reply":"2023-12-17T23:04:29.329987Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# EDA (Exploratory Data Analysis)","metadata":{}},{"cell_type":"code","source":"# Display sample images\nplt.figure(figsize=(12, 12))\nfor i in range(9):\n    plt.subplot(3, 3, i + 1)\n    plt.imshow(X[i].reshape(80, 80), cmap='gray')\n    plt.title(f\"Label: {y[i]}\")\n    plt.axis('off')\nplt.show()","metadata":{"execution":{"iopub.status.busy":"2023-12-18T00:24:10.707565Z","iopub.execute_input":"2023-12-18T00:24:10.708627Z","iopub.status.idle":"2023-12-18T00:24:11.552479Z","shell.execute_reply.started":"2023-12-18T00:24:10.708588Z","shell.execute_reply":"2023-12-18T00:24:11.551486Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Visualize class distribution with percentage values on top of the bars\nplt.figure(figsize=(4, 4))\nax = sns.countplot(x=y)\nplt.title('Class Distribution (0: Cat, 1: Dog)')\n\n# Add percentage values on top of the bars\ntotal = len(y)\nfor p in ax.patches:\n    percentage = '{:.1f}%'.format(100 * p.get_height() / total)\n    d = p.get_x() + p.get_width() / 2 - 0.05\n    z = p.get_height() + 0.1\n    ax.text(d, z, percentage, ha='center', va='bottom', fontsize=8, color='black')\n\nplt.show()","metadata":{"execution":{"iopub.status.busy":"2023-12-18T00:24:11.913857Z","iopub.execute_input":"2023-12-18T00:24:11.914150Z","iopub.status.idle":"2023-12-18T00:24:12.175640Z","shell.execute_reply.started":"2023-12-18T00:24:11.914124Z","shell.execute_reply":"2023-12-18T00:24:12.174740Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"### Splitting the data for train and validation","metadata":{}},{"cell_type":"code","source":"X_train, X_val, y_train, y_val = train_test_split(X, y, test_size=0.2, random_state=42)","metadata":{"execution":{"iopub.status.busy":"2023-12-17T23:04:43.872609Z","iopub.execute_input":"2023-12-17T23:04:43.872975Z","iopub.status.idle":"2023-12-17T23:04:44.383123Z","shell.execute_reply.started":"2023-12-17T23:04:43.872943Z","shell.execute_reply":"2023-12-17T23:04:44.382112Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# Training a base model","metadata":{}},{"cell_type":"code","source":"# Define the Deep Learning Model\nmodel = Sequential()\n\n# Convolutional layers\nmodel.add(Conv2D(32, (3, 3), input_shape=(80, 80, 1), activation='relu'))\nmodel.add(MaxPooling2D(pool_size=(2, 2)))\nmodel.add(Conv2D(64, (3, 3), activation='relu'))\nmodel.add(MaxPooling2D(pool_size=(2, 2)))\n\n# Flatten and connect Dense layers\nmodel.add(Flatten())\nmodel.add(Dense(128, activation='relu'))\nmodel.add(Dropout(0.5))\nmodel.add(Dense(64, activation='relu'))\nmodel.add(Dropout(0.5))\n\n# Output layer with a single neuron and sigmoid activation for binary classification\nmodel.add(Dense(1, activation='sigmoid'))","metadata":{"execution":{"iopub.status.busy":"2023-12-17T23:04:45.965626Z","iopub.execute_input":"2023-12-17T23:04:45.966323Z","iopub.status.idle":"2023-12-17T23:04:50.188386Z","shell.execute_reply.started":"2023-12-17T23:04:45.966277Z","shell.execute_reply":"2023-12-17T23:04:50.187555Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Compile the model with optimizer and loss function\nmodel.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])","metadata":{"execution":{"iopub.status.busy":"2023-12-17T23:04:50.189755Z","iopub.execute_input":"2023-12-17T23:04:50.190025Z","iopub.status.idle":"2023-12-17T23:04:50.206524Z","shell.execute_reply.started":"2023-12-17T23:04:50.190001Z","shell.execute_reply":"2023-12-17T23:04:50.205839Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Data augmentation\ndatagen = ImageDataGenerator(\n    shear_range=0.2,\n    zoom_range=0.2,\n    horizontal_flip=True,\n)\n\n# Create augmented data generators\ntrain_generator = datagen.flow(X_train, y_train, batch_size=32)\nval_generator = datagen.flow(X_val, y_val, batch_size=32)","metadata":{"execution":{"iopub.status.busy":"2023-12-17T23:04:50.882958Z","iopub.execute_input":"2023-12-17T23:04:50.883410Z","iopub.status.idle":"2023-12-17T23:04:51.224117Z","shell.execute_reply.started":"2023-12-17T23:04:50.883366Z","shell.execute_reply":"2023-12-17T23:04:51.222815Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Early stopping callback\nearly_stopping = EarlyStopping(monitor='val_loss', patience=3, restore_best_weights=True)","metadata":{"execution":{"iopub.status.busy":"2023-12-17T23:04:53.298923Z","iopub.execute_input":"2023-12-17T23:04:53.299302Z","iopub.status.idle":"2023-12-17T23:04:53.303769Z","shell.execute_reply.started":"2023-12-17T23:04:53.299270Z","shell.execute_reply":"2023-12-17T23:04:53.302849Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Train the model with augmented data and early stopping\nhistory = model.fit(\n    train_generator,\n    epochs=10,\n    validation_data=val_generator,\n    callbacks=[early_stopping]\n)","metadata":{"execution":{"iopub.status.busy":"2023-12-17T23:04:56.559321Z","iopub.execute_input":"2023-12-17T23:04:56.559696Z","iopub.status.idle":"2023-12-17T23:08:46.076111Z","shell.execute_reply.started":"2023-12-17T23:04:56.559664Z","shell.execute_reply":"2023-12-17T23:08:46.075166Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"### Evaluate the performance","metadata":{}},{"cell_type":"code","source":"# Evaluate the model performance on the validation set\nval_loss, val_accuracy = model.evaluate(X_val, y_val)\nprint(f\"Validation Loss: {val_loss}, Validation Accuracy: {val_accuracy}\")","metadata":{"execution":{"iopub.status.busy":"2023-12-17T23:09:20.954474Z","iopub.execute_input":"2023-12-17T23:09:20.955078Z","iopub.status.idle":"2023-12-17T23:09:22.273132Z","shell.execute_reply.started":"2023-12-17T23:09:20.955031Z","shell.execute_reply":"2023-12-17T23:09:22.272164Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"The validation accuracy for the base model is: 0.78","metadata":{}},{"cell_type":"code","source":"# Evaluate the model performance on the training data\nmodel_loss, model_accuracy = model.evaluate(X, y)\nprint(f\"Train Loss: {model_loss}, Train Accuracy: {model_accuracy}\")","metadata":{"execution":{"iopub.status.busy":"2023-12-17T23:09:23.126929Z","iopub.execute_input":"2023-12-17T23:09:23.127546Z","iopub.status.idle":"2023-12-17T23:09:29.628763Z","shell.execute_reply.started":"2023-12-17T23:09:23.127515Z","shell.execute_reply":"2023-12-17T23:09:29.627855Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# ##############################\n## I am going to try to create a preprocess function for the prediction here","metadata":{}},{"cell_type":"code","source":"!wget \"https://unsplash.com/photos/9vvEXgi95Tc/download?ixid=M3wxMjA3fDB8MXxhbGx8fHx8fHx8fHwxNzAyODU0NzM2fA&force=true\" -O image.jpg","metadata":{"execution":{"iopub.status.busy":"2023-12-17T23:12:30.449240Z","iopub.execute_input":"2023-12-17T23:12:30.450221Z","iopub.status.idle":"2023-12-17T23:12:31.911380Z","shell.execute_reply.started":"2023-12-17T23:12:30.450180Z","shell.execute_reply":"2023-12-17T23:12:31.910328Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"from tensorflow.keras.preprocessing.image import load_img\nimport numpy as np\n\ndef preprocess(X):\n      if isinstance(X, np.ndarray):\n        # Already a NumPy array, just normalize\n        X = X/255.0\n        return X\n      else:\n        # Convert PIL image to NumPy array\n        X = np.array(X)\n        # Assuming RGB image, convert to grayscale \n        X = X[:, :, 0]\n        # Reshape and normalize\n        X = np.array(X).reshape(-1,80, 80, 1)\n        X = X/255.0\n        return X\n\nimg = load_img('/kaggle/working/image.jpg', target_size=(80, 80))\nU = preprocess(img)\n\npreds = model.predict(U)","metadata":{"execution":{"iopub.status.busy":"2023-12-18T00:24:49.482665Z","iopub.execute_input":"2023-12-18T00:24:49.483436Z","iopub.status.idle":"2023-12-18T00:24:49.625679Z","shell.execute_reply.started":"2023-12-18T00:24:49.483402Z","shell.execute_reply":"2023-12-18T00:24:49.624908Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"preds","metadata":{"execution":{"iopub.status.busy":"2023-12-18T00:24:51.697828Z","iopub.execute_input":"2023-12-18T00:24:51.698517Z","iopub.status.idle":"2023-12-18T00:24:51.704382Z","shell.execute_reply.started":"2023-12-18T00:24:51.698483Z","shell.execute_reply":"2023-12-18T00:24:51.703396Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"Seems like the structure works, let's keep going.","metadata":{}},{"cell_type":"markdown","source":"# ########################","metadata":{}},{"cell_type":"markdown","source":"### Visualizations","metadata":{}},{"cell_type":"code","source":"# Plot loss history\nplt.figure(figsize=[8,6])\nplt.plot(history.history['loss'],'r',linewidth=3.0)\nplt.plot(history.history['val_loss'],'b',linewidth=3.0)\nplt.legend(['Training Loss', 'Validation Loss'],fontsize=14)\nplt.xlabel('Epochs ',fontsize=16)\nplt.ylabel('Loss',fontsize=16)\nplt.title('Loss Curves',fontsize=16)\n\n\n# Plot accuracy history\nplt.figure(figsize=[8,6])\nplt.plot(history.history['accuracy'],'r',linewidth=3.0)\nplt.plot(history.history['val_accuracy'],'b',linewidth=3.0)\nplt.legend(['Training Accuracy', 'Validation Accuracy'],fontsize=14)\nplt.xlabel('Epochs ',fontsize=16)\nplt.ylabel('Accuracy',fontsize=16)\nplt.title('Accuracy Curves',fontsize=16)","metadata":{"execution":{"iopub.status.busy":"2023-12-17T23:18:00.598799Z","iopub.execute_input":"2023-12-17T23:18:00.599214Z","iopub.status.idle":"2023-12-17T23:18:01.263313Z","shell.execute_reply.started":"2023-12-17T23:18:00.599181Z","shell.execute_reply":"2023-12-17T23:18:01.262367Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"Epoch 9 might be the ideal option here.","metadata":{}},{"cell_type":"markdown","source":"# Hyperparameter Optimization","metadata":{}},{"cell_type":"code","source":"def build_model(hp):\n    model = Sequential()\n    model.add(Conv2D(hp.Int('conv1_units', min_value=128, max_value=256, step=64), (3, 3), input_shape=(80, 80, 1), activation='relu'))\n    model.add(MaxPooling2D(pool_size=(2, 2)))\n    model.add(Conv2D(hp.Int('conv2_units', min_value=128, max_value=256, step=64), (3, 3), activation='relu'))\n    model.add(MaxPooling2D(pool_size=(2, 2)))\n    model.add(Flatten())\n    model.add(Dense(hp.Int('dense1_units', min_value=128, max_value=256, step=64), activation='relu'))\n    model.add(Dropout(0.5))\n    model.add(Dense(hp.Int('dense2_units', min_value=128, max_value=256, step=64), activation='relu'))\n    model.add(Dropout(0.5))\n    model.add(Dense(1, activation='sigmoid'))\n\n    model.compile(\n        optimizer=Adam(hp.Choice('learning_rate', values=[1e-3, 1e-4])), # More rates can be added here\n        loss='binary_crossentropy',\n        metrics=['accuracy']\n    )\n\n    return model","metadata":{"execution":{"iopub.status.busy":"2023-12-17T23:18:05.497294Z","iopub.execute_input":"2023-12-17T23:18:05.498214Z","iopub.status.idle":"2023-12-17T23:18:05.507356Z","shell.execute_reply.started":"2023-12-17T23:18:05.498178Z","shell.execute_reply":"2023-12-17T23:18:05.506422Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"tuner = RandomSearch(\n    build_model,\n    objective='val_accuracy',\n    max_trials=10,  # Adjust the number of trials as needed\n    directory='keras_tuner_dir',\n    project_name='cats_vs_dogs'\n)\n\ntuner.search(\n    train_generator,\n    epochs=10,\n    validation_data=val_generator,\n    callbacks=[EarlyStopping(monitor='val_loss', patience=3, restore_best_weights=True)]\n)","metadata":{"execution":{"iopub.status.busy":"2023-12-17T23:18:21.553866Z","iopub.execute_input":"2023-12-17T23:18:21.554929Z","iopub.status.idle":"2023-12-18T00:01:37.049562Z","shell.execute_reply.started":"2023-12-17T23:18:21.554891Z","shell.execute_reply":"2023-12-18T00:01:37.048624Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Get the best model from the search\nbest_model = tuner.get_best_models(num_models=1)[0]","metadata":{"execution":{"iopub.status.busy":"2023-12-18T00:02:42.032180Z","iopub.execute_input":"2023-12-18T00:02:42.032604Z","iopub.status.idle":"2023-12-18T00:02:42.666722Z","shell.execute_reply.started":"2023-12-18T00:02:42.032567Z","shell.execute_reply":"2023-12-18T00:02:42.665908Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"tuner.results_summary()","metadata":{"execution":{"iopub.status.busy":"2023-12-18T01:04:11.445965Z","iopub.execute_input":"2023-12-18T01:04:11.446872Z","iopub.status.idle":"2023-12-18T01:04:11.452956Z","shell.execute_reply.started":"2023-12-18T01:04:11.446840Z","shell.execute_reply":"2023-12-18T01:04:11.451946Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"### Evaluate the performance","metadata":{}},{"cell_type":"code","source":"# Evaluate the model performance on the validation set\nval_loss, val_accuracy = best_model.evaluate(X_val, y_val)\nprint(f\"Validation Loss: {val_loss}, Validation Accuracy: {val_accuracy}\")","metadata":{"execution":{"iopub.status.busy":"2023-12-18T00:02:44.620414Z","iopub.execute_input":"2023-12-18T00:02:44.620743Z","iopub.status.idle":"2023-12-18T00:02:47.425855Z","shell.execute_reply.started":"2023-12-18T00:02:44.620718Z","shell.execute_reply":"2023-12-18T00:02:47.424969Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Evaluate the model performance on the training data\nmodel_loss, model_accuracy = best_model.evaluate(X, y)\nprint(f\"Train Loss: {model_loss}, Train Accuracy: {model_accuracy}\")","metadata":{"execution":{"iopub.status.busy":"2023-12-18T00:02:49.695925Z","iopub.execute_input":"2023-12-18T00:02:49.696303Z","iopub.status.idle":"2023-12-18T00:03:02.142295Z","shell.execute_reply.started":"2023-12-18T00:02:49.696271Z","shell.execute_reply":"2023-12-18T00:03:02.141349Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"### Let's train the best model for more epochs and get better results","metadata":{}},{"cell_type":"code","source":"history = best_model.fit(\n    train_generator,\n    epochs=30,  # Adjust the number of additional epochs as needed\n    validation_data=val_generator,\n    callbacks=[EarlyStopping(monitor='val_loss', patience=4, restore_best_weights=True)]\n)","metadata":{"execution":{"iopub.status.busy":"2023-12-18T00:03:39.473467Z","iopub.execute_input":"2023-12-18T00:03:39.474145Z","iopub.status.idle":"2023-12-18T00:19:26.988142Z","shell.execute_reply.started":"2023-12-18T00:03:39.474095Z","shell.execute_reply":"2023-12-18T00:19:26.987356Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"### Evaluate the performance","metadata":{}},{"cell_type":"code","source":"# Evaluate the model performance on the validation set\nval_loss, val_accuracy = best_model.evaluate(X_val, y_val)\nprint(f\"Validation Loss: {val_loss}, Validation Accuracy: {val_accuracy}\")","metadata":{"execution":{"iopub.status.busy":"2023-12-18T00:19:34.895507Z","iopub.execute_input":"2023-12-18T00:19:34.895875Z","iopub.status.idle":"2023-12-18T00:19:37.449456Z","shell.execute_reply.started":"2023-12-18T00:19:34.895845Z","shell.execute_reply":"2023-12-18T00:19:37.448673Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Evaluate the model performance on the training data\nmodel_loss, model_accuracy = best_model.evaluate(X, y)\nprint(f\"Train Loss: {model_loss}, Train Accuracy: {model_accuracy}\")","metadata":{"execution":{"iopub.status.busy":"2023-12-18T00:19:39.805501Z","iopub.execute_input":"2023-12-18T00:19:39.806169Z","iopub.status.idle":"2023-12-18T00:19:52.128221Z","shell.execute_reply.started":"2023-12-18T00:19:39.806136Z","shell.execute_reply":"2023-12-18T00:19:52.127238Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"### Visualizations","metadata":{}},{"cell_type":"code","source":"# Plot loss history\nplt.figure(figsize=[8, 6])\nplt.plot(history.history['loss'], 'r', linewidth=3.0)\nplt.plot(history.history['val_loss'], 'b', linewidth=3.0)\nplt.legend(['Training Loss', 'Validation Loss'], fontsize=14)\nplt.xlabel('Epochs', fontsize=16)\nplt.ylabel('Loss', fontsize=16)\nplt.title('Loss Curves', fontsize=16)\nplt.show()\n\n# Plot accuracy history\nplt.figure(figsize=[8, 6])\nplt.plot(history.history['accuracy'], 'r', linewidth=3.0)\nplt.plot(history.history['val_accuracy'], 'b', linewidth=3.0)\nplt.legend(['Training Accuracy', 'Validation Accuracy'], fontsize=14)\nplt.xlabel('Epochs', fontsize=16)\nplt.ylabel('Accuracy', fontsize=16)\nplt.title('Accuracy Curves', fontsize=16)\nplt.show()","metadata":{"execution":{"iopub.status.busy":"2023-12-18T00:19:54.666101Z","iopub.execute_input":"2023-12-18T00:19:54.666939Z","iopub.status.idle":"2023-12-18T00:19:55.269460Z","shell.execute_reply.started":"2023-12-18T00:19:54.666899Z","shell.execute_reply":"2023-12-18T00:19:55.268493Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"Epoch 14 might be the ideal option.","metadata":{}},{"cell_type":"markdown","source":"# Save the model as TFLite","metadata":{}},{"cell_type":"code","source":"# Save the model for further use\nbest_model.save('dog_cat_classifier.h5')\n\nconverter = tf.lite.TFLiteConverter.from_keras_model(best_model)\n\ntflite_model = converter.convert()\n\n\nwith open('dog_cat_classifier.tflite', 'wb') as f_out:\n    f_out.write(tflite_model)","metadata":{"execution":{"iopub.status.busy":"2023-12-18T00:20:09.342002Z","iopub.execute_input":"2023-12-18T00:20:09.342908Z","iopub.status.idle":"2023-12-18T00:20:14.074361Z","shell.execute_reply.started":"2023-12-18T00:20:09.342871Z","shell.execute_reply":"2023-12-18T00:20:14.073495Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# This dataset actually belongs to an old Kaggle competition, if submissions were still open, we could submit a csv with the code below:","metadata":{}},{"cell_type":"markdown","source":"## Prediction on the test data","metadata":{}},{"cell_type":"code","source":"# Apply the model to predict on test data\ntest_dir = \"test1\"\ntest_path = os.path.join(main_dir,test_dir)\ntest_data = []\nfor p in os.listdir(test_path):\n    img_array = cv2.imread(os.path.join(test_path,p),cv2.IMREAD_GRAYSCALE)\n    new_img_array = cv2.resize(img_array, dsize=(80, 80))\n    test_data.append(new_img_array)\n\ntest_data = np.array(test_data).reshape(-1, 80, 80, 1)\ntest_data = test_data/255.0\n\npredictions = model.predict(test_data)","metadata":{"execution":{"iopub.status.busy":"2023-12-18T00:21:06.165812Z","iopub.execute_input":"2023-12-18T00:21:06.166182Z","iopub.status.idle":"2023-12-18T00:21:19.270526Z","shell.execute_reply.started":"2023-12-18T00:21:06.166150Z","shell.execute_reply":"2023-12-18T00:21:19.269529Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"print(predictions)","metadata":{"execution":{"iopub.status.busy":"2023-12-18T00:21:19.272111Z","iopub.execute_input":"2023-12-18T00:21:19.272413Z","iopub.status.idle":"2023-12-18T00:21:19.278097Z","shell.execute_reply.started":"2023-12-18T00:21:19.272387Z","shell.execute_reply":"2023-12-18T00:21:19.276975Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"## Creating a .csv file","metadata":{}},{"cell_type":"code","source":"# Assuming predictions is a 2D array with values between 0 and 1\npredictions = model.predict(test_data)\n\n# Convert the predictions to labels (0 or 1)\nbinary_predictions = (predictions > 0.5).astype(int)\n\n# Get the filenames from the test directory\ntest_filenames = os.listdir(test_path)\n\n# Extract the IDs from the filenames\nids = [int(filename.split('.')[0]) for filename in test_filenames]\n\n# Create a DataFrame with \"id\" and \"label\" columns\nsubmission_df = pd.DataFrame({'id': ids, 'label': binary_predictions.flatten()})\n\n# Save the DataFrame to a CSV file\nsubmission_df.to_csv('submission.csv', index=False)","metadata":{"execution":{"iopub.status.busy":"2023-12-18T00:21:19.279153Z","iopub.execute_input":"2023-12-18T00:21:19.279409Z","iopub.status.idle":"2023-12-18T00:21:21.182189Z","shell.execute_reply.started":"2023-12-18T00:21:19.279386Z","shell.execute_reply":"2023-12-18T00:21:21.181104Z"},"trusted":true},"outputs":[],"execution_count":null}]}