{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.10.13","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"none","dataSources":[{"sourceId":5048,"databundleVersionId":868335,"sourceType":"competition"}],"dockerImageVersionId":30733,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"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\n# import numpy as np # linear algebra\n# import 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\n# import os\n# for 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":"2024-06-05T17:04:07.002508Z","iopub.execute_input":"2024-06-05T17:04:07.002851Z","iopub.status.idle":"2024-06-05T17:04:07.00859Z","shell.execute_reply.started":"2024-06-05T17:04:07.002822Z","shell.execute_reply":"2024-06-05T17:04:07.007672Z"},"trusted":true},"execution_count":1,"outputs":[]},{"cell_type":"markdown","source":"#### Step 1: Converting data to a generator object","metadata":{}},{"cell_type":"code","source":"# converting data to a dict\n# in which key is class name of the driver which denotes the distraction\n# and values are all the image of driver\n\nimport csv\ndata = {}\nwith open('/kaggle/input/state-farm-distracted-driver-detection/driver_imgs_list.csv') as f:\n # read the csv file\n reader = csv.reader(f)\n next(reader)\n # 2nd index in row is the name of the image\n # 1st index in row is the class of the emotion\n for row in reader:\n key = row[1]\n if key in data:\n data[key].append(row[2])\n else:\n data[key] = [row[2]]\n \ndata.keys()","metadata":{"execution":{"iopub.status.busy":"2024-06-05T17:04:07.010902Z","iopub.execute_input":"2024-06-05T17:04:07.011272Z","iopub.status.idle":"2024-06-05T17:04:07.067264Z","shell.execute_reply.started":"2024-06-05T17:04:07.011238Z","shell.execute_reply":"2024-06-05T17:04:07.066427Z"},"trusted":true},"execution_count":2,"outputs":[{"execution_count":2,"output_type":"execute_result","data":{"text/plain":"dict_keys(['c0', 'c1', 'c2', 'c3', 'c4', 'c5', 'c6', 'c7', 'c8', 'c9'])"},"metadata":{}}]},{"cell_type":"code","source":"import shutil\nshutil.rmtree('master_data')","metadata":{"execution":{"iopub.status.busy":"2024-06-05T17:04:08.186823Z","iopub.execute_input":"2024-06-05T17:04:08.187773Z","iopub.status.idle":"2024-06-05T17:04:08.714195Z","shell.execute_reply.started":"2024-06-05T17:04:08.187729Z","shell.execute_reply":"2024-06-05T17:04:08.713034Z"},"trusted":true},"execution_count":3,"outputs":[{"traceback":["\u001b[0;31m---------------------------------------------------------------------------\u001b[0m","\u001b[0;31mFileNotFoundError\u001b[0m Traceback (most recent call last)","Cell \u001b[0;32mIn[3], line 2\u001b[0m\n\u001b[1;32m 1\u001b[0m \u001b[38;5;28;01mimport\u001b[39;00m \u001b[38;5;21;01mshutil\u001b[39;00m\n\u001b[0;32m----> 2\u001b[0m \u001b[43mshutil\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mrmtree\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[38;5;124;43mmaster_data\u001b[39;49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[43m)\u001b[49m\n","File \u001b[0;32m/opt/conda/lib/python3.10/shutil.py:715\u001b[0m, in \u001b[0;36mrmtree\u001b[0;34m(path, ignore_errors, onerror)\u001b[0m\n\u001b[1;32m 713\u001b[0m orig_st \u001b[38;5;241m=\u001b[39m os\u001b[38;5;241m.\u001b[39mlstat(path)\n\u001b[1;32m 714\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mException\u001b[39;00m:\n\u001b[0;32m--> 715\u001b[0m \u001b[43monerror\u001b[49m\u001b[43m(\u001b[49m\u001b[43mos\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mlstat\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mpath\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43msys\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mexc_info\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 716\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m\n\u001b[1;32m 717\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n","File \u001b[0;32m/opt/conda/lib/python3.10/shutil.py:713\u001b[0m, in \u001b[0;36mrmtree\u001b[0;34m(path, ignore_errors, onerror)\u001b[0m\n\u001b[1;32m 710\u001b[0m \u001b[38;5;66;03m# Note: To guard against symlink races, we use the standard\u001b[39;00m\n\u001b[1;32m 711\u001b[0m \u001b[38;5;66;03m# lstat()/open()/fstat() trick.\u001b[39;00m\n\u001b[1;32m 712\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m--> 713\u001b[0m orig_st \u001b[38;5;241m=\u001b[39m \u001b[43mos\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mlstat\u001b[49m\u001b[43m(\u001b[49m\u001b[43mpath\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 714\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mException\u001b[39;00m:\n\u001b[1;32m 715\u001b[0m onerror(os\u001b[38;5;241m.\u001b[39mlstat, path, sys\u001b[38;5;241m.\u001b[39mexc_info())\n","\u001b[0;31mFileNotFoundError\u001b[0m: [Errno 2] No such file or directory: 'master_data'"],"ename":"FileNotFoundError","evalue":"[Errno 2] No such file or directory: 'master_data'","output_type":"error"}]},{"cell_type":"code","source":"# getting a dir structure required by ImageGenerator\nimport os\nos.mkdir('master_data')\nos.mkdir('master_data/training')\nos.mkdir('master_data/testing')\ndistraction_list = list(data.keys())\nfor distraction_class in distraction_list:\n os.mkdir(os.path.join('master_data/training', distraction_class))\n os.mkdir(os.path.join('master_data/testing', distraction_class))","metadata":{"execution":{"iopub.status.busy":"2024-06-05T17:04:10.044208Z","iopub.execute_input":"2024-06-05T17:04:10.044576Z","iopub.status.idle":"2024-06-05T17:04:10.052252Z","shell.execute_reply.started":"2024-06-05T17:04:10.044545Z","shell.execute_reply":"2024-06-05T17:04:10.051162Z"},"trusted":true},"execution_count":4,"outputs":[]},{"cell_type":"code","source":"# now I will put images of the emotion in emotion directory\n# will divide the image emotion wise in 80% in testing data\n# and 20 % in testing data, so split_size = 0.8\n\nfrom shutil import copyfile\nsplit_size = 0.8\n\nfor class_label, images in data.items():\n train_size = int(split_size * len(images))\n\n # split images in training and testing directory\n train_images = images[:train_size]\n test_images = images[train_size:]\n\n # copy images in train dir\n for image in train_images:\n source = os.path.join(\"/kaggle/input/state-farm-distracted-driver-detection/imgs/train\", class_label, image)\n dest = os.path.join(\"master_data/training\", class_label, image)\n copyfile(source, dest)\n \n # copy images in test dir\n for image in test_images:\n source = os.path.join(\"/kaggle/input/state-farm-distracted-driver-detection/imgs/train\", class_label, image)\n dest = os.path.join(\"master_data/testing\", class_label, image)\n copyfile(source, dest)","metadata":{"execution":{"iopub.status.busy":"2024-06-05T17:04:11.281858Z","iopub.execute_input":"2024-06-05T17:04:11.282337Z","iopub.status.idle":"2024-06-05T17:07:48.141597Z","shell.execute_reply.started":"2024-06-05T17:04:11.282305Z","shell.execute_reply":"2024-06-05T17:07:48.140617Z"},"trusted":true},"execution_count":5,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"#### Building the model","metadata":{}},{"cell_type":"code","source":"import tensorflow as tf\nfrom tensorflow.keras.preprocessing.image import ImageDataGenerator\nfrom tensorflow.keras.optimizers import Adam\nfrom tensorflow.keras.callbacks import EarlyStopping\nfrom tensorflow.keras.layers import Conv2D, MaxPooling2D, Dense, Flatten, Dropout, InputLayer,BatchNormalization","metadata":{"execution":{"iopub.status.busy":"2024-06-05T17:07:48.143632Z","iopub.execute_input":"2024-06-05T17:07:48.144042Z","iopub.status.idle":"2024-06-05T17:08:02.015562Z","shell.execute_reply.started":"2024-06-05T17:07:48.144006Z","shell.execute_reply":"2024-06-05T17:08:02.014668Z"},"trusted":true},"execution_count":6,"outputs":[{"name":"stderr","text":"2024-06-05 17:07:50.042206: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered\n2024-06-05 17:07:50.042309: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered\n2024-06-05 17:07:50.173816: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered\n","output_type":"stream"}]},{"cell_type":"code","source":"model = tf.keras.models.Sequential()\nmodel.add(BatchNormalization())\nmodel.add(Conv2D(32,(3,3),activation='relu',padding='same'))\nmodel.add(BatchNormalization(axis = 3))\nmodel.add(MaxPooling2D(pool_size=(2,2),padding='same'))\nmodel.add(Dropout(0.3))\n\n## CNN 2\nmodel.add(Conv2D(64,(3,3),activation='relu',padding='same'))\nmodel.add(BatchNormalization())\nmodel.add(Conv2D(64,(3,3),activation='relu',padding='same'))\nmodel.add(BatchNormalization(axis = 3))\nmodel.add(MaxPooling2D(pool_size=(2,2),padding='same'))\nmodel.add(Dropout(0.3))\n\n## CNN 3\nmodel.add(Conv2D(128,(3,3),activation='relu',padding='same'))\nmodel.add(BatchNormalization())\nmodel.add(Conv2D(128,(3,3),activation='relu',padding='same'))\nmodel.add(BatchNormalization(axis = 3))\nmodel.add(MaxPooling2D(pool_size=(2,2),padding='same'))\nmodel.add(Dropout(0.5))\n\n## Output\nmodel.add(Flatten())\nmodel.add(Dense(512,activation='relu'))\nmodel.add(BatchNormalization())\nmodel.add(Dropout(0.5))\nmodel.add(Dense(128,activation='relu'))\nmodel.add(Dropout(0.25))\nmodel.add(Dense(10,activation='softmax'))","metadata":{"execution":{"iopub.status.busy":"2024-06-05T17:14:35.761912Z","iopub.execute_input":"2024-06-05T17:14:35.762314Z","iopub.status.idle":"2024-06-05T17:14:35.81194Z","shell.execute_reply.started":"2024-06-05T17:14:35.762284Z","shell.execute_reply":"2024-06-05T17:14:35.811209Z"},"trusted":true},"execution_count":15,"outputs":[]},{"cell_type":"code","source":"","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"model.compile(optimizer=Adam(learning_rate=0.01), \n loss='categorical_crossentropy', \n metrics=['acc'])","metadata":{"execution":{"iopub.status.busy":"2024-06-05T17:14:38.389642Z","iopub.execute_input":"2024-06-05T17:14:38.390004Z","iopub.status.idle":"2024-06-05T17:14:38.399952Z","shell.execute_reply.started":"2024-06-05T17:14:38.389975Z","shell.execute_reply":"2024-06-05T17:14:38.399152Z"},"trusted":true},"execution_count":16,"outputs":[]},{"cell_type":"code","source":"model.summary()","metadata":{"execution":{"iopub.status.busy":"2024-06-05T17:14:38.86267Z","iopub.execute_input":"2024-06-05T17:14:38.863295Z","iopub.status.idle":"2024-06-05T17:14:38.894309Z","shell.execute_reply.started":"2024-06-05T17:14:38.863261Z","shell.execute_reply":"2024-06-05T17:14:38.893356Z"},"trusted":true},"execution_count":17,"outputs":[{"output_type":"display_data","data":{"text/plain":"\u001b[1mModel: \"sequential_2\"\u001b[0m\n","text/html":"Model: \"sequential_2\"\n
\n"},"metadata":{}},{"output_type":"display_data","data":{"text/plain":"┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n┃\u001b[1m \u001b[0m\u001b[1mLayer (type) \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1mOutput Shape \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1m Param #\u001b[0m\u001b[1m \u001b[0m┃\n┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n│ batch_normalization_14 │ ? │ \u001b[38;5;34m0\u001b[0m (unbuilt) │\n│ (\u001b[38;5;33mBatchNormalization\u001b[0m) │ │ │\n├─────────────────────────────────┼────────────────────────┼───────────────┤\n│ conv2d_10 (\u001b[38;5;33mConv2D\u001b[0m) │ ? │ \u001b[38;5;34m0\u001b[0m (unbuilt) │\n├─────────────────────────────────┼────────────────────────┼───────────────┤\n│ batch_normalization_15 │ ? │ \u001b[38;5;34m0\u001b[0m (unbuilt) │\n│ (\u001b[38;5;33mBatchNormalization\u001b[0m) │ │ │\n├─────────────────────────────────┼────────────────────────┼───────────────┤\n│ max_pooling2d_6 (\u001b[38;5;33mMaxPooling2D\u001b[0m) │ ? │ \u001b[38;5;34m0\u001b[0m (unbuilt) │\n├─────────────────────────────────┼────────────────────────┼───────────────┤\n│ dropout_10 (\u001b[38;5;33mDropout\u001b[0m) │ ? │ \u001b[38;5;34m0\u001b[0m (unbuilt) │\n├─────────────────────────────────┼────────────────────────┼───────────────┤\n│ conv2d_11 (\u001b[38;5;33mConv2D\u001b[0m) │ ? │ \u001b[38;5;34m0\u001b[0m (unbuilt) │\n├─────────────────────────────────┼────────────────────────┼───────────────┤\n│ batch_normalization_16 │ ? │ \u001b[38;5;34m0\u001b[0m (unbuilt) │\n│ (\u001b[38;5;33mBatchNormalization\u001b[0m) │ │ │\n├─────────────────────────────────┼────────────────────────┼───────────────┤\n│ conv2d_12 (\u001b[38;5;33mConv2D\u001b[0m) │ ? │ \u001b[38;5;34m0\u001b[0m (unbuilt) │\n├─────────────────────────────────┼────────────────────────┼───────────────┤\n│ batch_normalization_17 │ ? │ \u001b[38;5;34m0\u001b[0m (unbuilt) │\n│ (\u001b[38;5;33mBatchNormalization\u001b[0m) │ │ │\n├─────────────────────────────────┼────────────────────────┼───────────────┤\n│ max_pooling2d_7 (\u001b[38;5;33mMaxPooling2D\u001b[0m) │ ? │ \u001b[38;5;34m0\u001b[0m (unbuilt) │\n├─────────────────────────────────┼────────────────────────┼───────────────┤\n│ dropout_11 (\u001b[38;5;33mDropout\u001b[0m) │ ? │ \u001b[38;5;34m0\u001b[0m (unbuilt) │\n├─────────────────────────────────┼────────────────────────┼───────────────┤\n│ conv2d_13 (\u001b[38;5;33mConv2D\u001b[0m) │ ? │ \u001b[38;5;34m0\u001b[0m (unbuilt) │\n├─────────────────────────────────┼────────────────────────┼───────────────┤\n│ batch_normalization_18 │ ? │ \u001b[38;5;34m0\u001b[0m (unbuilt) │\n│ (\u001b[38;5;33mBatchNormalization\u001b[0m) │ │ │\n├─────────────────────────────────┼────────────────────────┼───────────────┤\n│ conv2d_14 (\u001b[38;5;33mConv2D\u001b[0m) │ ? │ \u001b[38;5;34m0\u001b[0m (unbuilt) │\n├─────────────────────────────────┼────────────────────────┼───────────────┤\n│ batch_normalization_19 │ ? │ \u001b[38;5;34m0\u001b[0m (unbuilt) │\n│ (\u001b[38;5;33mBatchNormalization\u001b[0m) │ │ │\n├─────────────────────────────────┼────────────────────────┼───────────────┤\n│ max_pooling2d_8 (\u001b[38;5;33mMaxPooling2D\u001b[0m) │ ? │ \u001b[38;5;34m0\u001b[0m (unbuilt) │\n├─────────────────────────────────┼────────────────────────┼───────────────┤\n│ dropout_12 (\u001b[38;5;33mDropout\u001b[0m) │ ? │ \u001b[38;5;34m0\u001b[0m (unbuilt) │\n├─────────────────────────────────┼────────────────────────┼───────────────┤\n│ flatten_2 (\u001b[38;5;33mFlatten\u001b[0m) │ ? │ \u001b[38;5;34m0\u001b[0m (unbuilt) │\n├─────────────────────────────────┼────────────────────────┼───────────────┤\n│ dense_6 (\u001b[38;5;33mDense\u001b[0m) │ ? │ \u001b[38;5;34m0\u001b[0m (unbuilt) │\n├─────────────────────────────────┼────────────────────────┼───────────────┤\n│ batch_normalization_20 │ ? │ \u001b[38;5;34m0\u001b[0m (unbuilt) │\n│ (\u001b[38;5;33mBatchNormalization\u001b[0m) │ │ │\n├─────────────────────────────────┼────────────────────────┼───────────────┤\n│ dropout_13 (\u001b[38;5;33mDropout\u001b[0m) │ ? │ \u001b[38;5;34m0\u001b[0m (unbuilt) │\n├─────────────────────────────────┼────────────────────────┼───────────────┤\n│ dense_7 (\u001b[38;5;33mDense\u001b[0m) │ ? │ \u001b[38;5;34m0\u001b[0m (unbuilt) │\n├─────────────────────────────────┼────────────────────────┼───────────────┤\n│ dropout_14 (\u001b[38;5;33mDropout\u001b[0m) │ ? │ \u001b[38;5;34m0\u001b[0m (unbuilt) │\n├─────────────────────────────────┼────────────────────────┼───────────────┤\n│ dense_8 (\u001b[38;5;33mDense\u001b[0m) │ ? │ \u001b[38;5;34m0\u001b[0m (unbuilt) │\n└─────────────────────────────────┴────────────────────────┴───────────────┘\n","text/html":"┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n┃ Layer (type) ┃ Output Shape ┃ Param # ┃\n┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n│ batch_normalization_14 │ ? │ 0 (unbuilt) │\n│ (BatchNormalization) │ │ │\n├─────────────────────────────────┼────────────────────────┼───────────────┤\n│ conv2d_10 (Conv2D) │ ? │ 0 (unbuilt) │\n├─────────────────────────────────┼────────────────────────┼───────────────┤\n│ batch_normalization_15 │ ? │ 0 (unbuilt) │\n│ (BatchNormalization) │ │ │\n├─────────────────────────────────┼────────────────────────┼───────────────┤\n│ max_pooling2d_6 (MaxPooling2D) │ ? │ 0 (unbuilt) │\n├─────────────────────────────────┼────────────────────────┼───────────────┤\n│ dropout_10 (Dropout) │ ? │ 0 (unbuilt) │\n├─────────────────────────────────┼────────────────────────┼───────────────┤\n│ conv2d_11 (Conv2D) │ ? │ 0 (unbuilt) │\n├─────────────────────────────────┼────────────────────────┼───────────────┤\n│ batch_normalization_16 │ ? │ 0 (unbuilt) │\n│ (BatchNormalization) │ │ │\n├─────────────────────────────────┼────────────────────────┼───────────────┤\n│ conv2d_12 (Conv2D) │ ? │ 0 (unbuilt) │\n├─────────────────────────────────┼────────────────────────┼───────────────┤\n│ batch_normalization_17 │ ? │ 0 (unbuilt) │\n│ (BatchNormalization) │ │ │\n├─────────────────────────────────┼────────────────────────┼───────────────┤\n│ max_pooling2d_7 (MaxPooling2D) │ ? │ 0 (unbuilt) │\n├─────────────────────────────────┼────────────────────────┼───────────────┤\n│ dropout_11 (Dropout) │ ? │ 0 (unbuilt) │\n├─────────────────────────────────┼────────────────────────┼───────────────┤\n│ conv2d_13 (Conv2D) │ ? │ 0 (unbuilt) │\n├─────────────────────────────────┼────────────────────────┼───────────────┤\n│ batch_normalization_18 │ ? │ 0 (unbuilt) │\n│ (BatchNormalization) │ │ │\n├─────────────────────────────────┼────────────────────────┼───────────────┤\n│ conv2d_14 (Conv2D) │ ? │ 0 (unbuilt) │\n├─────────────────────────────────┼────────────────────────┼───────────────┤\n│ batch_normalization_19 │ ? │ 0 (unbuilt) │\n│ (BatchNormalization) │ │ │\n├─────────────────────────────────┼────────────────────────┼───────────────┤\n│ max_pooling2d_8 (MaxPooling2D) │ ? │ 0 (unbuilt) │\n├─────────────────────────────────┼────────────────────────┼───────────────┤\n│ dropout_12 (Dropout) │ ? │ 0 (unbuilt) │\n├─────────────────────────────────┼────────────────────────┼───────────────┤\n│ flatten_2 (Flatten) │ ? │ 0 (unbuilt) │\n├─────────────────────────────────┼────────────────────────┼───────────────┤\n│ dense_6 (Dense) │ ? │ 0 (unbuilt) │\n├─────────────────────────────────┼────────────────────────┼───────────────┤\n│ batch_normalization_20 │ ? │ 0 (unbuilt) │\n│ (BatchNormalization) │ │ │\n├─────────────────────────────────┼────────────────────────┼───────────────┤\n│ dropout_13 (Dropout) │ ? │ 0 (unbuilt) │\n├─────────────────────────────────┼────────────────────────┼───────────────┤\n│ dense_7 (Dense) │ ? │ 0 (unbuilt) │\n├─────────────────────────────────┼────────────────────────┼───────────────┤\n│ dropout_14 (Dropout) │ ? │ 0 (unbuilt) │\n├─────────────────────────────────┼────────────────────────┼───────────────┤\n│ dense_8 (Dense) │ ? │ 0 (unbuilt) │\n└─────────────────────────────────┴────────────────────────┴───────────────┘\n
\n"},"metadata":{}},{"output_type":"display_data","data":{"text/plain":"\u001b[1m Total params: \u001b[0m\u001b[38;5;34m0\u001b[0m (0.00 B)\n","text/html":" Total params: 0 (0.00 B)\n
\n"},"metadata":{}},{"output_type":"display_data","data":{"text/plain":"\u001b[1m Trainable params: \u001b[0m\u001b[38;5;34m0\u001b[0m (0.00 B)\n","text/html":" Trainable params: 0 (0.00 B)\n
\n"},"metadata":{}},{"output_type":"display_data","data":{"text/plain":"\u001b[1m Non-trainable params: \u001b[0m\u001b[38;5;34m0\u001b[0m (0.00 B)\n","text/html":" Non-trainable params: 0 (0.00 B)\n
\n"},"metadata":{}}]},{"cell_type":"code","source":"train_dir = \"master_data/training\"\ntest_dir = \"master_data/testing\"\n\n# Refs: https://www.tensorflow.org/api_docs/python/tf/keras/preprocessing/image/ImageDataGenerator\n\n# to normalize pixel values we will be dividing each values by 225\ntrain_datagen = ImageDataGenerator(rescale=1.0/225)\n\ntrain_generator = train_datagen.flow_from_directory(\n\n train_dir,\n\n # target size needs to be \n # same as defined in 1st \n # layer of neural network\n target_size = (100, 100),\n\n # denotes categorical classification so it will\n # generate output/labels on name of directories\n class_mode='categorical',\n\n # batch_size is used in epochs\n batch_size=128\n )\n\ntest_datagen = ImageDataGenerator(rescale=1.0/225)\n\ntest_generator = test_datagen.flow_from_directory(\n\n test_dir,\n\n # target size needs to be \n # same as defined in 1st \n # layer of neural network\n target_size = (100, 100),\n\n # denotes categorical classification so it will\n # generate output/labels on name of directories\n class_mode='categorical',\n\n # batch_size is used in epochs\n batch_size=128\n )","metadata":{"execution":{"iopub.status.busy":"2024-06-05T17:08:14.208375Z","iopub.execute_input":"2024-06-05T17:08:14.209001Z","iopub.status.idle":"2024-06-05T17:08:15.696463Z","shell.execute_reply.started":"2024-06-05T17:08:14.20897Z","shell.execute_reply":"2024-06-05T17:08:15.695489Z"},"trusted":true},"execution_count":10,"outputs":[{"name":"stdout","text":"Found 17934 images belonging to 10 classes.\nFound 4490 images belonging to 10 classes.\n","output_type":"stream"}]},{"cell_type":"code","source":"# define early stopping if model accuracy is not improving\nes = EarlyStopping(monitor='val_acc', patience=2, min_delta=0.01)","metadata":{"execution":{"iopub.status.busy":"2024-06-05T17:08:17.298481Z","iopub.execute_input":"2024-06-05T17:08:17.29889Z","iopub.status.idle":"2024-06-05T17:08:17.303867Z","shell.execute_reply.started":"2024-06-05T17:08:17.298857Z","shell.execute_reply":"2024-06-05T17:08:17.302846Z"},"trusted":true},"execution_count":11,"outputs":[]},{"cell_type":"code","source":"# calling fit function on generator\nmodel.fit(train_generator, \n epochs=10, \n verbose = 1, \n validation_data=test_generator,\n callbacks=[es])","metadata":{"execution":{"iopub.status.busy":"2024-06-05T17:14:49.362904Z","iopub.execute_input":"2024-06-05T17:14:49.363528Z","iopub.status.idle":"2024-06-05T17:16:51.831336Z","shell.execute_reply.started":"2024-06-05T17:14:49.363492Z","shell.execute_reply":"2024-06-05T17:16:51.830348Z"},"trusted":true},"execution_count":18,"outputs":[{"name":"stdout","text":"Epoch 1/10\n\u001b[1m 2/141\u001b[0m \u001b[37m━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[1m7s\u001b[0m 56ms/step - acc: 0.1250 - loss: 3.4991 ","output_type":"stream"},{"name":"stderr","text":"W0000 00:00:1717607708.485187 81 graph_launch.cc:671] Fallback to op-by-op mode because memset node breaks graph update\n","output_type":"stream"},{"name":"stdout","text":"\u001b[1m141/141\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 320ms/step - acc: 0.5128 - loss: 1.5997","output_type":"stream"},{"name":"stderr","text":"W0000 00:00:1717607754.965420 82 graph_launch.cc:671] Fallback to op-by-op mode because memset node breaks graph update\n","output_type":"stream"},{"name":"stdout","text":"\u001b[1m141/141\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m74s\u001b[0m 398ms/step - acc: 0.5141 - loss: 1.5951 - val_acc: 0.0913 - val_loss: 16.8129\nEpoch 2/10\n\u001b[1m141/141\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m48s\u001b[0m 325ms/step - acc: 0.8824 - loss: 0.3821 - val_acc: 0.2192 - val_loss: 5.4585\n","output_type":"stream"},{"execution_count":18,"output_type":"execute_result","data":{"text/plain":""},"metadata":{}}]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}