\n
\n - Part 1: Loading Dataset 📖
\n - \n Part 2: EDA 🔎\n
\n - \n Part 3: CNN Model 🧿\n
\n - \n Part 4 : Data Augmentation 🖼️\n
\n \n ","metadata":{}},{"cell_type":"markdown","source":"\n
\n ⮞ Part 1 : Loading Dataset \n
\n","metadata":{}},{"cell_type":"code","source":"!pip install numpy pandas opencv-python tqdm glob2 keras scikit-learn matplotlib","metadata":{"execution":{"iopub.status.busy":"2024-10-23T12:28:17.883585Z","iopub.execute_input":"2024-10-23T12:28:17.883954Z","iopub.status.idle":"2024-10-23T12:28:31.287226Z","shell.execute_reply.started":"2024-10-23T12:28:17.883859Z","shell.execute_reply":"2024-10-23T12:28:31.286490Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\nimport cv2\nimport os\nfrom tqdm import tqdm\nfrom glob import glob\nfrom keras.utils import np_utils\nfrom sklearn.model_selection import train_test_split\nimport matplotlib.pyplot as plt\nimport matplotlib.image as mpimg\n\nfrom keras.preprocessing.image import ImageDataGenerator\nfrom keras.models import Sequential, Model\nfrom keras.layers import Conv2D, MaxPooling2D, Flatten, Dense, Dropout, BatchNormalization, GlobalAveragePooling2D\n\n","metadata":{"execution":{"iopub.status.busy":"2024-10-23T12:28:31.289392Z","iopub.execute_input":"2024-10-23T12:28:31.289707Z","iopub.status.idle":"2024-10-23T12:28:41.844813Z","shell.execute_reply.started":"2024-10-23T12:28:31.289664Z","shell.execute_reply":"2024-10-23T12:28:41.843963Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df = pd.read_csv('../input/state-farm-distracted-driver-detection/driver_imgs_list.csv')\ndf.head(5)","metadata":{"execution":{"iopub.status.busy":"2024-10-23T12:28:41.845866Z","iopub.execute_input":"2024-10-23T12:28:41.846093Z","iopub.status.idle":"2024-10-23T12:28:41.907792Z","shell.execute_reply.started":"2024-10-23T12:28:41.846062Z","shell.execute_reply":"2024-10-23T12:28:41.907031Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Groupby subjects\nby_drivers = df.groupby('subject') \n#Group unique drivers\nunique_drivers = by_drivers.groups.keys() # drivers id\n\nprint('There are : ',len(unique_drivers), ' unique drivers')\nprint('There is a mean of ',round(df.groupby('subject').count()['classname'].mean()), ' images by driver.')","metadata":{"execution":{"iopub.status.busy":"2024-10-23T12:28:41.909375Z","iopub.execute_input":"2024-10-23T12:28:41.909596Z","iopub.status.idle":"2024-10-23T12:28:41.940035Z","shell.execute_reply.started":"2024-10-23T12:28:41.909568Z","shell.execute_reply":"2024-10-23T12:28:41.939401Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"num_classes = 10","metadata":{"execution":{"iopub.status.busy":"2024-10-23T12:28:41.940879Z","iopub.execute_input":"2024-10-23T12:28:41.941057Z","iopub.status.idle":"2024-10-23T12:28:41.944706Z","shell.execute_reply.started":"2024-10-23T12:28:41.941033Z","shell.execute_reply":"2024-10-23T12:28:41.943853Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#Read with opencv\ndef get_image(path, img_rows, img_cols, color_type=3):\n \n if color_type == 1:\n img = cv2.imread(path, cv2.IMREAD_GRAYSCALE)\n elif color_type == 3:\n img = cv2.imread(path, cv2.IMREAD_COLOR)\n img = cv2.resize(img, (img_rows, img_cols)) # Reduce size\n return img\n\n#Loading training dataset\ndef train_data_load(img_rows=64, img_cols=64, color_type=3):\n train_images=[]\n train_labels=[]\n \n #Loop over the training folder\n for classes in tqdm(range(num_classes)):\n print('Loading directory c{}'.format(classes))\n files = glob(os.path.join('../input/state-farm-distracted-driver-detection/imgs/train/c' + str(classes), '*.jpg'))\n for file in files:\n img = get_image(file, img_rows, img_cols, color_type)\n train_images.append(img)\n train_labels.append(classes)\n return train_images, train_labels\n\ndef read_and_normalize_train_data(img_rows, img_cols, color_type):\n X, labels = train_data_load(img_rows, img_cols, color_type)\n y = np_utils.to_categorical(labels, 10)\n x_train, x_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)\n x_train = np.array(x_train, dtype=np.uint8).reshape(-1,img_rows,img_cols,color_type)\n x_test = np.array(x_test, dtype=np.uint8).reshape(-1,img_rows,img_cols,color_type)\n \n return x_train, x_test, y_train, y_test\n\n#Loading validation dataset\ndef load_test(size=200000, img_rows=64, img_cols=64, color_type=3):\n \"\"\"\n Same as above but for validation dataset\n \"\"\"\n path = os.path.join('../input/state-farm-distracted-driver-detection/imgs/test', '*.jpg')\n files = sorted(glob(path))\n X_test, X_test_id = [], []\n total = 0\n files_size = len(files)\n for file in tqdm(files):\n if total >= size or total >= files_size:\n break\n file_base = os.path.basename(file)\n img = get_image(file, img_rows, img_cols, color_type)\n X_test.append(img)\n X_test_id.append(file_base)\n total += 1\n return X_test, X_test_id\n\ndef read_and_normalize_sampled_test_data(size, img_rows, img_cols, color_type=3):\n test_data, test_ids = load_test(size, img_rows, img_cols, color_type) \n test_data = np.array(test_data, dtype=np.uint8)\n test_data = test_data.reshape(-1,img_rows,img_cols,color_type)\n return test_data, test_ids\n ","metadata":{"execution":{"iopub.status.busy":"2024-10-23T12:28:41.945950Z","iopub.execute_input":"2024-10-23T12:28:41.946162Z","iopub.status.idle":"2024-10-23T12:28:41.963455Z","shell.execute_reply.started":"2024-10-23T12:28:41.946136Z","shell.execute_reply":"2024-10-23T12:28:41.962752Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"pip install np_utils\n","metadata":{"execution":{"iopub.status.busy":"2024-10-23T12:28:41.964933Z","iopub.execute_input":"2024-10-23T12:28:41.965213Z","iopub.status.idle":"2024-10-23T12:28:52.829880Z","shell.execute_reply.started":"2024-10-23T12:28:41.965161Z","shell.execute_reply":"2024-10-23T12:28:52.828975Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"img_rows = 64\nimg_cols = 64\ncolor_type = 1\nnb_test_samples = 200\n\n#Loading train images \nx_train, x_test, y_train, y_test = read_and_normalize_train_data(img_rows, img_cols, color_type)\n\n#Loading validation images \ntest_files, test_targets = read_and_normalize_sampled_test_data(nb_test_samples, img_rows, img_cols, color_type)","metadata":{"execution":{"iopub.status.busy":"2024-10-23T12:28:52.831405Z","iopub.execute_input":"2024-10-23T12:28:52.831665Z","iopub.status.idle":"2024-10-23T12:33:59.140104Z","shell.execute_reply.started":"2024-10-23T12:28:52.831624Z","shell.execute_reply":"2024-10-23T12:33:59.139278Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"\n
\n ⮞ Part 2 : EDA \n
\n","metadata":{}},{"cell_type":"markdown","source":"### Data visualisation\n ","metadata":{}},{"cell_type":"code","source":"import plotly.express as px\npx.histogram(df, x=\"classname\", color=\"classname\", title=\"Number of images by categories \")\n","metadata":{"execution":{"iopub.status.busy":"2024-10-23T12:33:59.141206Z","iopub.execute_input":"2024-10-23T12:33:59.141462Z","iopub.status.idle":"2024-10-23T12:34:05.148738Z","shell.execute_reply.started":"2024-10-23T12:33:59.141432Z","shell.execute_reply":"2024-10-23T12:34:05.148007Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Find the frequency of images per driver\ndrivers_id = pd.DataFrame((df['subject'].value_counts()).reset_index())\ndrivers_id.columns = ['driver_id', 'Counts']\npx.histogram(drivers_id, x=\"driver_id\",y=\"Counts\" ,color=\"driver_id\", title=\"Number of images by subjects \")","metadata":{"execution":{"iopub.status.busy":"2024-10-23T12:34:05.151345Z","iopub.execute_input":"2024-10-23T12:34:05.151577Z","iopub.status.idle":"2024-10-23T12:34:05.340942Z","shell.execute_reply.started":"2024-10-23T12:34:05.151547Z","shell.execute_reply":"2024-10-23T12:34:05.340162Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Images overview\n","metadata":{}},{"cell_type":"code","source":"activity_map = {'c0': 'Safe driving', \n 'c1': 'Texting - right', \n 'c2': 'Talking on the phone - right', \n 'c3': 'Texting - left', \n 'c4': 'Talking on the phone - left', \n 'c5': 'Operating the radio', \n 'c6': 'Drinking', \n 'c7': 'Reaching behind', \n 'c8': 'Hair and makeup', \n 'c9': 'Talking to passenger'}\n\n\nplt.figure(figsize = (12, 20))\nimage_count = 1\nBASE_URL = '../input/state-farm-distracted-driver-detection/imgs/train/'\nfor directory in os.listdir(BASE_URL):\n if directory[0] != '.':\n for i, file in enumerate(os.listdir(BASE_URL + directory)):\n if i == 1:\n break\n else:\n fig = plt.subplot(5, 2, image_count)\n image_count += 1\n image = mpimg.imread(BASE_URL + directory + '/' + file)\n plt.imshow(image)\n plt.title(activity_map[directory])","metadata":{"execution":{"iopub.status.busy":"2024-10-23T12:34:05.342219Z","iopub.execute_input":"2024-10-23T12:34:05.342767Z","iopub.status.idle":"2024-10-23T12:34:07.616262Z","shell.execute_reply.started":"2024-10-23T12:34:05.342724Z","shell.execute_reply":"2024-10-23T12:34:07.615492Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"\n
\n ⮞ Part 3 : CNN Model \n
\n","metadata":{}},{"cell_type":"markdown","source":"### Architecture :\n\n* 3 Convolutionnal layers (with Relu, Maxpooling and dropout)\n* A flatten layer\n* 2 Dense layers with Relu and Dropouts\n* 1 Dense layer with softmax for the classification","metadata":{}},{"cell_type":"code","source":"batch_size = 50\nn_epochs = 100","metadata":{"execution":{"iopub.status.busy":"2024-10-23T12:34:07.617453Z","iopub.execute_input":"2024-10-23T12:34:07.617706Z","iopub.status.idle":"2024-10-23T12:34:07.621460Z","shell.execute_reply.started":"2024-10-23T12:34:07.617676Z","shell.execute_reply":"2024-10-23T12:34:07.620806Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def create_model():\n \n model = Sequential()\n \n #CNN1\n model.add(Conv2D(32, (3,3), activation='relu', input_shape=(img_rows, img_cols, color_type)))\n model.add(BatchNormalization())\n model.add(Conv2D(32,(3,3), activation='relu', padding='same'))\n model.add(BatchNormalization(axis=3))\n model.add(MaxPooling2D(pool_size=(2,2), padding='same'))\n model.add(Dropout(0.3))\n \n #CNN2\n model.add(Conv2D(64, (3,3), activation='relu', input_shape=(img_rows, img_cols, color_type)))\n model.add(BatchNormalization())\n model.add(Conv2D(64,(3,3), activation='relu', padding='same'))\n model.add(BatchNormalization(axis=3))\n model.add(MaxPooling2D(pool_size=(2,2), padding='same'))\n model.add(Dropout(0.3))\n \n #CNN3\n model.add(Conv2D(128, (3,3), activation='relu', input_shape=(img_rows, img_cols, color_type)))\n model.add(BatchNormalization())\n model.add(Conv2D(128,(3,3), activation='relu', padding='same'))\n model.add(BatchNormalization(axis=3))\n model.add(MaxPooling2D(pool_size=(2,2), padding='same'))\n model.add(Dropout(0.3))\n \n \n #Output\n model.add(Flatten())\n model.add(Dense(512, activation='relu'))\n model.add(BatchNormalization())\n model.add(Dropout(0.5))\n model.add(Dense(128, activation='relu'))\n model.add(BatchNormalization())\n model.add(Dropout(0.25))\n model.add(Dense(10,activation='softmax'))\n \n \n return model","metadata":{"execution":{"iopub.status.busy":"2024-10-23T12:34:07.622535Z","iopub.execute_input":"2024-10-23T12:34:07.622744Z","iopub.status.idle":"2024-10-23T12:34:07.636633Z","shell.execute_reply.started":"2024-10-23T12:34:07.622718Z","shell.execute_reply":"2024-10-23T12:34:07.636010Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"model = create_model()\n\n#Details about the model\nmodel.summary()\n\nmodel.compile(optimizer='rmsprop', loss='categorical_crossentropy', metrics=['accuracy'])\n","metadata":{"execution":{"iopub.status.busy":"2024-10-23T12:34:07.637582Z","iopub.execute_input":"2024-10-23T12:34:07.637762Z","iopub.status.idle":"2024-10-23T12:34:11.957047Z","shell.execute_reply.started":"2024-10-23T12:34:07.637738Z","shell.execute_reply":"2024-10-23T12:34:11.956285Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"#### Training model","metadata":{}},{"cell_type":"code","source":"history = model.fit(x_train, y_train,\n validation_data=(x_test, y_test),\n epochs=n_epochs, batch_size=batch_size, verbose=1)\n\nprint('History of the training',history.history)\n","metadata":{"execution":{"iopub.status.busy":"2024-10-23T12:34:11.958286Z","iopub.execute_input":"2024-10-23T12:34:11.958980Z","iopub.status.idle":"2024-10-23T12:43:45.989782Z","shell.execute_reply.started":"2024-10-23T12:34:11.958931Z","shell.execute_reply":"2024-10-23T12:43:45.988910Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def plot_train_history(history):\n \"\"\"\n Plot the validation accuracy and validation loss over epochs\n \"\"\"\n # Summarize history for accuracy\n plt.plot(history.history['accuracy'])\n plt.plot(history.history['val_accuracy'])\n plt.title('Model accuracy')\n plt.ylabel('accuracy')\n plt.xlabel('epoch')\n plt.legend(['train', 'test'], loc='upper left')\n plt.show()\n\n # Summarize history for loss\n plt.plot(history.history['loss'])\n plt.plot(history.history['val_loss'])\n plt.title('Model loss')\n plt.ylabel('loss')\n plt.xlabel('epoch')\n plt.legend(['train', 'test'], loc='upper left')\n plt.show()\n \nplot_train_history(history)","metadata":{"execution":{"iopub.status.busy":"2024-10-23T12:43:45.991057Z","iopub.execute_input":"2024-10-23T12:43:45.991324Z","iopub.status.idle":"2024-10-23T12:43:46.414864Z","shell.execute_reply.started":"2024-10-23T12:43:45.991287Z","shell.execute_reply":"2024-10-23T12:43:46.414146Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Prediction on test set","metadata":{}},{"cell_type":"code","source":"def plot_test_class(model, test_files, image_number, color_type=1):\n \"\"\"\n Function that tests or model on test images and show the results\n \"\"\"\n img_brute = test_files[image_number]\n img_brute = cv2.resize(img_brute,(img_rows,img_cols))\n plt.imshow(img_brute, cmap='gray')\n\n new_img = img_brute.reshape(-1,img_rows,img_cols,color_type)\n\n y_prediction = model.predict(new_img, batch_size=batch_size, verbose=1)\n print('Y prediction: {}'.format(y_prediction))\n print('Predicted: {}'.format(activity_map.get('c{}'.format(np.argmax(y_prediction)))))\n \n plt.show()","metadata":{"execution":{"iopub.status.busy":"2024-10-23T12:43:46.415933Z","iopub.execute_input":"2024-10-23T12:43:46.416148Z","iopub.status.idle":"2024-10-23T12:43:46.422687Z","shell.execute_reply.started":"2024-10-23T12:43:46.416119Z","shell.execute_reply":"2024-10-23T12:43:46.421983Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"score1 = model.evaluate(x_test, y_test, verbose=1)\n","metadata":{"execution":{"iopub.status.busy":"2024-10-23T12:43:46.423633Z","iopub.execute_input":"2024-10-23T12:43:46.423814Z","iopub.status.idle":"2024-10-23T12:43:47.171539Z","shell.execute_reply.started":"2024-10-23T12:43:46.423790Z","shell.execute_reply":"2024-10-23T12:43:47.170793Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print('Loss: ', score1[0])\nprint('Accuracy: ', score1[1]*100, ' %')","metadata":{"execution":{"iopub.status.busy":"2024-10-23T12:43:47.172693Z","iopub.execute_input":"2024-10-23T12:43:47.172924Z","iopub.status.idle":"2024-10-23T12:43:47.178345Z","shell.execute_reply.started":"2024-10-23T12:43:47.172895Z","shell.execute_reply":"2024-10-23T12:43:47.177539Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"for i in range(20):\n plot_test_class(model, test_files, i)","metadata":{"execution":{"iopub.status.busy":"2024-10-23T12:43:47.179438Z","iopub.execute_input":"2024-10-23T12:43:47.179656Z","iopub.status.idle":"2024-10-23T12:43:51.489031Z","shell.execute_reply.started":"2024-10-23T12:43:47.179628Z","shell.execute_reply":"2024-10-23T12:43:51.488447Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"\n
\n ⮞ Part 4 : Data Augmentation\n
\n","metadata":{}},{"cell_type":"code","source":"# Using ImageDataGenerator from keras\ntrain_datagen = ImageDataGenerator(rescale = 1.0/255, \n shear_range = 0.2, \n zoom_range = 0.2, \n horizontal_flip = True, \n validation_split = 0.2)\n\ntest_datagen = ImageDataGenerator(rescale=1.0/ 255, validation_split = 0.2)","metadata":{"execution":{"iopub.status.busy":"2024-10-23T12:43:51.490383Z","iopub.execute_input":"2024-10-23T12:43:51.490623Z","iopub.status.idle":"2024-10-23T12:43:51.495733Z","shell.execute_reply.started":"2024-10-23T12:43:51.490591Z","shell.execute_reply":"2024-10-23T12:43:51.495006Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"nb_train_samples = x_train.shape[0]\nnb_validation_samples = x_test.shape[0]\ntraining_generator = train_datagen.flow(x_train, y_train, batch_size=batch_size)\nvalidation_generator = test_datagen.flow(x_test, y_test, batch_size=batch_size)","metadata":{"execution":{"iopub.status.busy":"2024-10-23T12:43:51.496821Z","iopub.execute_input":"2024-10-23T12:43:51.497029Z","iopub.status.idle":"2024-10-23T12:43:52.399881Z","shell.execute_reply.started":"2024-10-23T12:43:51.497001Z","shell.execute_reply":"2024-10-23T12:43:52.398984Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Training with data augmentation","metadata":{}},{"cell_type":"code","source":"history_v2 = model.fit_generator(training_generator,\n steps_per_epoch = nb_train_samples // batch_size,\n epochs = n_epochs, \n verbose = 1,\n validation_data = validation_generator,\n validation_steps = nb_validation_samples // batch_size)","metadata":{"execution":{"iopub.status.busy":"2024-10-23T12:43:52.401013Z","iopub.execute_input":"2024-10-23T12:43:52.401230Z","iopub.status.idle":"2024-10-23T12:59:09.725519Z","shell.execute_reply.started":"2024-10-23T12:43:52.401203Z","shell.execute_reply":"2024-10-23T12:59:09.724734Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"\n# Lưu mô hình\nmodel.save('/kaggle/working/my_model.h5')","metadata":{"execution":{"iopub.status.busy":"2024-10-23T12:59:09.727019Z","iopub.execute_input":"2024-10-23T12:59:09.727286Z","iopub.status.idle":"2024-10-23T12:59:09.859350Z","shell.execute_reply.started":"2024-10-23T12:59:09.727232Z","shell.execute_reply":"2024-10-23T12:59:09.858680Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from tensorflow.keras.models import load_model\nloaded_model = load_model('my_model.h5')\n\n# In ra thông tin mô hình\nloaded_model.summary()\n","metadata":{"execution":{"iopub.status.busy":"2024-10-23T12:59:09.860400Z","iopub.execute_input":"2024-10-23T12:59:09.860622Z","iopub.status.idle":"2024-10-23T12:59:10.177959Z","shell.execute_reply.started":"2024-10-23T12:59:09.860595Z","shell.execute_reply":"2024-10-23T12:59:10.177154Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import cv2\nimport numpy as np\nfrom tensorflow.keras.models import load_model\nfrom tensorflow.keras.preprocessing import image\nimport matplotlib.pyplot as plt\n\n# Đường dẫn đến mô hình đã lưu\nmodel_path = 'my_model.h5'\n\n# Load mô hình\nloaded_model = load_model(model_path)\n\n# Đường dẫn đến ảnh cần kiểm tra\nimage_path = '/kaggle/input/dsadasd/truck-driver.jpg'\n\n# Kích thước ảnh đầu vào của mô hình\nimg_width, img_height = 64, 64\n\n# Hàm tiền xử lý ảnh\n\ndef preprocess_image(img_path):\n img = cv2.imread(img_path, cv2.IMREAD_GRAYSCALE) # Đọc ảnh grayscale\n img = cv2.resize(img, (img_width, img_height), interpolation=cv2.INTER_AREA) # Thay đổi kích thước\n x = image.img_to_array(img)\n x = np.expand_dims(x, axis=0)\n x = x / 255.0\n return x\n\n# Tiền xử lý ảnh\nimg = preprocess_image(image_path)\n\n# Dự đoán\npredictions = loaded_model.predict(img)\n\n# Lấy lớp dự đoán\npredicted_class = np.argmax(predictions)\n\n# Tên các lớp (dictionary)\nclass_names = {\n 'c0': 'Safe driving',\n 'c1': 'Texting - right',\n 'c2': 'Talking on the phone - right',\n 'c3': 'Texting - left',\n 'c4': 'Talking on the phone - left',\n 'c5': 'Operating the radio',\n 'c6': 'Drinking',\n 'c7': 'Reaching behind',\n 'c8': 'Hair and makeup',\n 'c9': 'Talking to passenger'\n}\n\n# Lấy tên lớp dự đoán\npredicted_class_name = class_names[f\"c{predicted_class}\"]\n\n# In kết quả\nprint(f\"Ảnh: {image_path}\")\nprint(f\"Dự đoán: {predicted_class_name}\")\nprint(f\"Xác suất: {predictions[0][predicted_class]}\")\n\n# Hiển thị ảnh và kết quả bằng matplotlib\noriginal_img = cv2.imread(image_path)\nplt.imshow(cv2.cvtColor(original_img, cv2.COLOR_BGR2RGB)) # Chuyển đổi màu\nplt.title(f\"Prediction: {predicted_class_name}\")\nplt.show()","metadata":{"execution":{"iopub.status.busy":"2024-10-23T13:23:10.852579Z","iopub.execute_input":"2024-10-23T13:23:10.852883Z","iopub.status.idle":"2024-10-23T13:23:12.093109Z","shell.execute_reply.started":"2024-10-23T13:23:10.852850Z","shell.execute_reply":"2024-10-23T13:23:12.092359Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"plot_train_history(history_v2)\n","metadata":{"execution":{"iopub.status.busy":"2024-10-23T12:59:11.009531Z","iopub.execute_input":"2024-10-23T12:59:11.009751Z","iopub.status.idle":"2024-10-23T12:59:11.409525Z","shell.execute_reply.started":"2024-10-23T12:59:11.009723Z","shell.execute_reply":"2024-10-23T12:59:11.408835Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Evaluate and compare the performance of the new model\nscore2 = model.evaluate_generator(validation_generator, nb_validation_samples // batch_size)\nprint(\"Loss for model 1\",score1[0])\nprint(\"Loss for model 2 (data augmentation):\", score2[0])\n\nprint(\"Test accuracy for model 1\",score1[1])\nprint(\"Test accuracy for model 2 (data augmentation):\", score2[1])","metadata":{"execution":{"iopub.status.busy":"2024-10-23T12:59:11.413552Z","iopub.execute_input":"2024-10-23T12:59:11.414129Z","iopub.status.idle":"2024-10-23T12:59:11.904338Z","shell.execute_reply.started":"2024-10-23T12:59:11.414098Z","shell.execute_reply":"2024-10-23T12:59:11.903595Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Conclusion for Data Augmentation\n### Data augmentation makes our model more robust.","metadata":{}}]}