{"metadata":{"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"language_info":{"name":"python","version":"3.10.15","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"tpu1vmV38","dataSources":[{"sourceId":59093,"databundleVersionId":7469972,"sourceType":"competition"},{"sourceId":7526248,"sourceType":"datasetVersion","datasetId":4308295},{"sourceId":6127,"sourceType":"modelInstanceVersion","modelInstanceId":4598,"modelId":2797}],"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":false},"papermill":{"default_parameters":{},"duration":3846.080383,"end_time":"2024-01-14T04:20:19.064569","environment_variables":{},"exception":null,"input_path":"__notebook__.ipynb","output_path":"__notebook__.ipynb","parameters":{},"start_time":"2024-01-14T03:16:12.984186","version":"2.4.0"},"widgets":{"application/vnd.jupyter.widget-state+json":{"state":{"08983a9c6aff42578980f4f7113c3ee2":{"model_module":"@jupyter-widgets/controls","model_module_version":"1.5.0","model_name":"HTMLModel","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HTMLView","description":"","description_tooltip":null,"layout":"IPY_MODEL_4411aefc021d46d0ada7b645eb53ec48","placeholder":"โ€‹","style":"IPY_MODEL_09a10a8cf9334c51857397ed50398c8e","value":"Searching best thr : 100%"}},"09a10a8cf9334c51857397ed50398c8e":{"model_module":"@jupyter-widgets/controls","model_module_version":"1.5.0","model_name":"DescriptionStyleModel","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"DescriptionStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","description_width":""}},"1f3989a0c01248328e16875075e9d1c4":{"model_module":"@jupyter-widgets/controls","model_module_version":"1.5.0","model_name":"HBoxModel","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HBoxModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HBoxView","box_style":"","children":["IPY_MODEL_08983a9c6aff42578980f4f7113c3ee2","IPY_MODEL_22cfcc0a7cc6455fbf3bb7c788c8a4e1","IPY_MODEL_c8392e8075224e3b8a020a16c1a08447"],"layout":"IPY_MODEL_6cec9a2c2fac450d87248aed8dd62f86"}},"22cfcc0a7cc6455fbf3bb7c788c8a4e1":{"model_module":"@jupyter-widgets/controls","model_module_version":"1.5.0","model_name":"FloatProgressModel","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"FloatProgressModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"ProgressView","bar_style":"success","description":"","description_tooltip":null,"layout":"IPY_MODEL_dffe80502d954bdea0bbb6353dbf5515","max":20,"min":0,"orientation":"horizontal","style":"IPY_MODEL_7ce1b34a4f864a42a6619eec82311eb0","value":20}},"4411aefc021d46d0ada7b645eb53ec48":{"model_module":"@jupyter-widgets/base","model_module_version":"1.2.0","model_name":"LayoutModel","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"6cec9a2c2fac450d87248aed8dd62f86":{"model_module":"@jupyter-widgets/base","model_module_version":"1.2.0","model_name":"LayoutModel","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"7ce1b34a4f864a42a6619eec82311eb0":{"model_module":"@jupyter-widgets/controls","model_module_version":"1.5.0","model_name":"ProgressStyleModel","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"ProgressStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","bar_color":null,"description_width":""}},"83fe40a0b8f047cc8602206909d42361":{"model_module":"@jupyter-widgets/base","model_module_version":"1.2.0","model_name":"LayoutModel","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"9384babdb7054d55aecdf3e989ddc926":{"model_module":"@jupyter-widgets/controls","model_module_version":"1.5.0","model_name":"DescriptionStyleModel","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"DescriptionStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","description_width":""}},"c8392e8075224e3b8a020a16c1a08447":{"model_module":"@jupyter-widgets/controls","model_module_version":"1.5.0","model_name":"HTMLModel","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HTMLView","description":"","description_tooltip":null,"layout":"IPY_MODEL_83fe40a0b8f047cc8602206909d42361","placeholder":"โ€‹","style":"IPY_MODEL_9384babdb7054d55aecdf3e989ddc926","value":" 20/20 [04:34<00:00, 12.66s/it]"}},"dffe80502d954bdea0bbb6353dbf5515":{"model_module":"@jupyter-widgets/base","model_module_version":"1.2.0","model_name":"LayoutModel","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}}},"version_major":2,"version_minor":0}}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"markdown","source":"
\"Keras
\nThis starter notebook is provided by the Keras team.
","metadata":{"execution":{"iopub.execute_input":"2024-01-10T05:24:31.308329Z","iopub.status.busy":"2024-01-10T05:24:31.307595Z","iopub.status.idle":"2024-01-10T05:24:31.313088Z","shell.execute_reply":"2024-01-10T05:24:31.312113Z","shell.execute_reply.started":"2024-01-10T05:24:31.308287Z"},"papermill":{"duration":0.011755,"end_time":"2024-01-14T03:16:16.447481","exception":false,"start_time":"2024-01-14T03:16:16.435726","status":"completed"},"tags":[]}},{"cell_type":"markdown","source":"# HMS - Harmful Brain Activity Classification with [KerasCV](https://github.com/keras-team/keras-cv) and [Keras](https://github.com/keras-team/keras)\n\n> The objective of this competition is to classify seizures and other patterns of harmful brain activity in critically ill patients\n\nThis notebook guides you through the process of training and inferring a Deep Learning model, specifically EfficientNetV2, using KerasCV on the competition dataset. Specificaclly, this notebook uses spectrogram of the eeg data to classify the patterns.\n\nFun fact: This notebook is backend-agnostic, supporting TensorFlow, PyTorch, and JAX. Utilizing KerasCV and Keras allows us to choose our preferred backend. Explore more details on [Keras](https://keras.io/keras_core/announcement/).\n\nIn this notebook, you will learn:\n\n* Loading the data efficiently using [`tf.data`](https://www.tensorflow.org/guide/data).\n* Creating the model using KerasCV presets.\n* Training the model.\n* Inference and Submission on test data.\n\n**Note**: For a more in-depth understanding of KerasCV, refer to the [KerasCV guides](https://keras.io/guides/keras_cv/).","metadata":{}},{"cell_type":"markdown","source":"# ๐Ÿ›  | Install Libraries \n\nSince internet access is **disabled** during inference, we cannot install libraries in the usual `!pip install ` manner. Instead, we need to install libraries from local files. In the following cell, we will install libraries from our local files. The installation code stays very similar - we just use the `filepath` instead of the `filename` of the library. So now the code is `!pip install `. \n\n> The `filepath` of these local libraries look quite complicated, but don't be intimidated! Also `--no-deps` argument ensures that we are not installing any additional libraries.","metadata":{"papermill":{"duration":0.011416,"end_time":"2024-01-14T03:16:16.470167","exception":false,"start_time":"2024-01-14T03:16:16.458751","status":"completed"},"tags":[]}},{"cell_type":"code","source":"!pip install -q /kaggle/input/kerasv3-lib-ds/keras_cv-0.8.2-py3-none-any.whl --no-deps\n!pip install -q /kaggle/input/kerasv3-lib-ds/tensorflow-2.15.0.post1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl --no-deps\n!pip install -q /kaggle/input/kerasv3-lib-ds/keras-3.0.4-py3-none-any.whl --no-deps","metadata":{"execution":{"iopub.status.busy":"2024-10-20T16:25:09.071323Z","iopub.execute_input":"2024-10-20T16:25:09.071899Z","iopub.status.idle":"2024-10-20T16:25:55.715778Z","shell.execute_reply.started":"2024-10-20T16:25:09.071866Z","shell.execute_reply":"2024-10-20T16:25:55.714750Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# ๐Ÿ“š | Import Libraries ","metadata":{"papermill":{"duration":0.010878,"end_time":"2024-01-14T03:17:49.510159","exception":false,"start_time":"2024-01-14T03:17:49.499281","status":"completed"},"tags":[]}},{"cell_type":"code","source":"from tqdm.notebook import tqdm\n","metadata":{"execution":{"iopub.status.busy":"2024-10-20T16:25:55.717532Z","iopub.execute_input":"2024-10-20T16:25:55.717815Z","iopub.status.idle":"2024-10-20T16:25:55.737131Z","shell.execute_reply.started":"2024-10-20T16:25:55.717786Z","shell.execute_reply":"2024-10-20T16:25:55.736343Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import os\nos.environ[\"KERAS_BACKEND\"] = \"jax\" # you can also use tensorflow or torch\n\nimport keras_cv\nimport keras\nfrom keras import ops\nimport tensorflow as tf\n\nimport cv2\nimport pandas as pd\nimport numpy as np\nfrom glob import glob\nfrom tqdm import tqdm\nimport joblib\n\nimport matplotlib.pyplot as plt ","metadata":{"papermill":{"duration":10.671979,"end_time":"2024-01-14T03:18:00.193134","exception":false,"start_time":"2024-01-14T03:17:49.521155","status":"completed"},"tags":[],"_kg_hide-output":true,"execution":{"iopub.status.busy":"2024-10-20T16:25:55.737999Z","iopub.execute_input":"2024-10-20T16:25:55.738229Z","iopub.status.idle":"2024-10-20T16:26:32.885343Z","shell.execute_reply.started":"2024-10-20T16:25:55.738205Z","shell.execute_reply":"2024-10-20T16:26:32.884369Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"## Library Versions","metadata":{"papermill":{"duration":0.010958,"end_time":"2024-01-14T03:18:00.215704","exception":false,"start_time":"2024-01-14T03:18:00.204746","status":"completed"},"tags":[]}},{"cell_type":"code","source":"print(\"TensorFlow:\", tf.__version__)\nprint(\"Keras:\", keras.__version__)\nprint(\"KerasCV:\", keras_cv.__version__)","metadata":{"papermill":{"duration":0.019435,"end_time":"2024-01-14T03:18:00.246368","exception":false,"start_time":"2024-01-14T03:18:00.226933","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2024-10-20T16:26:32.887387Z","iopub.execute_input":"2024-10-20T16:26:32.887844Z","iopub.status.idle":"2024-10-20T16:26:32.892485Z","shell.execute_reply.started":"2024-10-20T16:26:32.887816Z","shell.execute_reply":"2024-10-20T16:26:32.891608Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# โš™๏ธ | Configuration","metadata":{"papermill":{"duration":0.010922,"end_time":"2024-01-14T03:18:00.26855","exception":false,"start_time":"2024-01-14T03:18:00.257628","status":"completed"},"tags":[]}},{"cell_type":"code","source":"class CFG:\n verbose = 1 # Verbosity\n seed = 42 # Random seed\n preset = \"efficientnetv2_b2_imagenet\" # Name of pretrained classifier\n image_size = [400, 300] # Input image size\n epochs = 13 # Training epochs\n batch_size = 64 # Batch size\n lr_mode = \"cos\" # LR scheduler mode from one of \"cos\", \"step\", \"exp\"\n drop_remainder = True # Drop incomplete batches\n num_classes = 6 # Number of classes in the dataset\n fold = 0 # Which fold to set as validation data\n class_names = ['Seizure', 'LPD', 'GPD', 'LRDA','GRDA', 'Other']\n label2name = dict(enumerate(class_names))\n name2label = {v:k for k, v in label2name.items()}","metadata":{"papermill":{"duration":0.018795,"end_time":"2024-01-14T03:18:00.298534","exception":false,"start_time":"2024-01-14T03:18:00.279739","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2024-10-20T16:26:32.893615Z","iopub.execute_input":"2024-10-20T16:26:32.893897Z","iopub.status.idle":"2024-10-20T16:26:32.908816Z","shell.execute_reply.started":"2024-10-20T16:26:32.893868Z","shell.execute_reply":"2024-10-20T16:26:32.908011Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# โ™ป๏ธ | Reproducibility \nSets value for random seed to produce similar result in each run.","metadata":{"papermill":{"duration":0.010907,"end_time":"2024-01-14T03:18:00.32063","exception":false,"start_time":"2024-01-14T03:18:00.309723","status":"completed"},"tags":[]}},{"cell_type":"code","source":"keras.utils.set_random_seed(CFG.seed)","metadata":{"papermill":{"duration":0.018371,"end_time":"2024-01-14T03:18:00.350074","exception":false,"start_time":"2024-01-14T03:18:00.331703","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2024-10-20T16:26:32.909851Z","iopub.execute_input":"2024-10-20T16:26:32.910385Z","iopub.status.idle":"2024-10-20T16:26:32.918626Z","shell.execute_reply.started":"2024-10-20T16:26:32.910354Z","shell.execute_reply":"2024-10-20T16:26:32.917894Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# ๐Ÿ“ | Dataset Path ","metadata":{"papermill":{"duration":0.010888,"end_time":"2024-01-14T03:18:00.372053","exception":false,"start_time":"2024-01-14T03:18:00.361165","status":"completed"},"tags":[]}},{"cell_type":"code","source":"BASE_PATH = \"/kaggle/input/hms-harmful-brain-activity-classification\"\n\nSPEC_DIR = \"/tmp/dataset/hms-hbac\"\nos.makedirs(SPEC_DIR+'/train_spectrograms', exist_ok=True)\nos.makedirs(SPEC_DIR+'/test_spectrograms', exist_ok=True)","metadata":{"papermill":{"duration":0.017704,"end_time":"2024-01-14T03:18:00.400852","exception":false,"start_time":"2024-01-14T03:18:00.383148","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2024-10-20T16:26:32.919619Z","iopub.execute_input":"2024-10-20T16:26:32.920145Z","iopub.status.idle":"2024-10-20T16:26:32.929651Z","shell.execute_reply.started":"2024-10-20T16:26:32.920116Z","shell.execute_reply":"2024-10-20T16:26:32.928867Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# ๐Ÿ“– | Meta Data ","metadata":{"papermill":{"duration":0.011434,"end_time":"2024-01-14T03:18:00.472401","exception":false,"start_time":"2024-01-14T03:18:00.460967","status":"completed"},"tags":[]}},{"cell_type":"code","source":"# Train + Valid\ndf = pd.read_csv(f'{BASE_PATH}/train.csv')\ndf['eeg_path'] = f'{BASE_PATH}/train_eegs/'+df['eeg_id'].astype(str)+'.parquet'\ndf['spec_path'] = f'{BASE_PATH}/train_spectrograms/'+df['spectrogram_id'].astype(str)+'.parquet'\ndf['spec2_path'] = f'{SPEC_DIR}/train_spectrograms/'+df['spectrogram_id'].astype(str)+'.npy'\ndf['class_name'] = df.expert_consensus.copy()\ndf['class_label'] = df.expert_consensus.map(CFG.name2label)\ndisplay(df.head(2))\n\n# Test\ntest_df = pd.read_csv(f'{BASE_PATH}/test.csv')\ntest_df['eeg_path'] = f'{BASE_PATH}/test_eegs/'+test_df['eeg_id'].astype(str)+'.parquet'\ntest_df['spec_path'] = f'{BASE_PATH}/test_spectrograms/'+test_df['spectrogram_id'].astype(str)+'.parquet'\ntest_df['spec2_path'] = f'{SPEC_DIR}/test_spectrograms/'+test_df['spectrogram_id'].astype(str)+'.npy'\ndisplay(test_df.head(2))","metadata":{"execution":{"iopub.status.busy":"2024-10-20T16:26:32.930700Z","iopub.execute_input":"2024-10-20T16:26:32.931420Z","iopub.status.idle":"2024-10-20T16:26:33.373796Z","shell.execute_reply.started":"2024-10-20T16:26:32.931387Z","shell.execute_reply":"2024-10-20T16:26:33.372971Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"## Convert `.parquet` to `.npy`\n\nTo facilitate easier data loading, we will convert the EEG spectrograms from `parquet` to `npy` format. This process involves saving the spectrogram data, and since the content of the files remains the same, no significant changes are made. \n\n> It's worth noting that the `time` column is excluded, as it is not part of the spectrogram.","metadata":{}},{"cell_type":"code","source":"# Define a function to process a single eeg_id\ndef process_spec(spec_id, split=\"train\"):\n spec_path = f\"{BASE_PATH}/{split}_spectrograms/{spec_id}.parquet\"\n spec = pd.read_parquet(spec_path)\n spec = spec.fillna(0).values[:, 1:].T # fill NaN values with 0, transpose for (Time, Freq) -> (Freq, Time)\n spec = spec.astype(\"float32\")\n np.save(f\"{SPEC_DIR}/{split}_spectrograms/{spec_id}.npy\", spec)\n\n# Get unique spec_ids of train and valid data\nspec_ids = df[\"spectrogram_id\"].unique()\n\n# Parallelize the processing using joblib for training data\n_ = joblib.Parallel(n_jobs=-1, backend=\"loky\")(\n joblib.delayed(process_spec)(spec_id, \"train\")\n for spec_id in tqdm(spec_ids, total=len(spec_ids))\n)\n\n# Get unique spec_ids of test data\ntest_spec_ids = test_df[\"spectrogram_id\"].unique()\n\n# Parallelize the processing using joblib for test data\n_ = joblib.Parallel(n_jobs=-1, backend=\"loky\")(\n joblib.delayed(process_spec)(spec_id, \"test\")\n for spec_id in tqdm(test_spec_ids, total=len(test_spec_ids))\n)","metadata":{"papermill":{"duration":0.86264,"end_time":"2024-01-14T03:18:01.346487","exception":false,"start_time":"2024-01-14T03:18:00.483847","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2024-10-20T16:26:33.375012Z","iopub.execute_input":"2024-10-20T16:26:33.375351Z","iopub.status.idle":"2024-10-20T16:27:17.212883Z","shell.execute_reply.started":"2024-10-20T16:26:33.375320Z","shell.execute_reply":"2024-10-20T16:27:17.211875Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# ๐Ÿš | DataLoader\n\nThis DataLoader first reads `npy` spectrogram files and extracts labeled subsamples using specified `offset` values. Then, it converts the spectrogram data into `log spectrogram` and applies the popular signal augmentation `MixUp`.\n\n> Note that, we are converting the mono channel signal to a 3-channel signal for using \"ImageNet\" weights of pretrained model.","metadata":{"papermill":{"duration":0.011843,"end_time":"2024-01-14T03:18:01.457956","exception":false,"start_time":"2024-01-14T03:18:01.446113","status":"completed"},"tags":[]}},{"cell_type":"code","source":"def build_augmenter(dim=CFG.image_size):\n augmenters = [\n keras_cv.layers.MixUp(alpha=2.0),\n keras_cv.layers.RandomCutout(height_factor=(1.0, 1.0),\n width_factor=(0.06, 0.1)), # freq-masking\n keras_cv.layers.RandomCutout(height_factor=(0.06, 0.1),\n width_factor=(1.0, 1.0)), # time-masking\n ]\n \n def augment(img, label):\n data = {\"images\":img, \"labels\":label}\n for augmenter in augmenters:\n if tf.random.uniform([]) < 0.5:\n data = augmenter(data, training=True)\n return data[\"images\"], data[\"labels\"]\n \n return augment\n\n\ndef build_decoder(with_labels=True, target_size=CFG.image_size, dtype=32):\n def decode_signal(path, offset=None):\n # Read .npy files and process the signal\n file_bytes = tf.io.read_file(path)\n sig = tf.io.decode_raw(file_bytes, tf.float32)\n sig = sig[1024//dtype:] # Remove header tag\n sig = tf.reshape(sig, [400, -1])\n \n # Extract labeled subsample from full spectrogram using \"offset\"\n if offset is not None: \n offset = offset // 2 # Only odd values are given\n sig = sig[:, offset:offset+300]\n \n # Pad spectrogram to ensure the same input shape of [400, 300]\n pad_size = tf.math.maximum(0, 300 - tf.shape(sig)[1])\n sig = tf.pad(sig, [[0, 0], [0, pad_size]])\n sig = tf.reshape(sig, [400, 300])\n \n # Log spectrogram \n sig = tf.clip_by_value(sig, tf.math.exp(-4.0), tf.math.exp(8.0)) # avoid 0 in log\n sig = tf.math.log(sig)\n \n # Normalize spectrogram\n sig -= tf.math.reduce_mean(sig)\n sig /= tf.math.reduce_std(sig) + 1e-6\n \n # Mono channel to 3 channels to use \"ImageNet\" weights\n sig = tf.tile(sig[..., None], [1, 1, 3])\n return sig\n \n def decode_label(label):\n label = tf.one_hot(label, CFG.num_classes)\n label = tf.cast(label, tf.float32)\n label = tf.reshape(label, [CFG.num_classes])\n return label\n \n def decode_with_labels(path, offset=None, label=None):\n sig = decode_signal(path, offset)\n label = decode_label(label)\n return (sig, label)\n \n return decode_with_labels if with_labels else decode_signal\n\n\ndef build_dataset(paths, offsets=None, labels=None, batch_size=32, cache=True,\n decode_fn=None, augment_fn=None,\n augment=False, repeat=True, shuffle=1024, \n cache_dir=\"\", drop_remainder=False):\n if cache_dir != \"\" and cache is True:\n os.makedirs(cache_dir, exist_ok=True)\n \n if decode_fn is None:\n decode_fn = build_decoder(labels is not None)\n \n if augment_fn is None:\n augment_fn = build_augmenter()\n \n AUTO = tf.data.experimental.AUTOTUNE\n slices = (paths, offsets) if labels is None else (paths, offsets, labels)\n \n ds = tf.data.Dataset.from_tensor_slices(slices)\n ds = ds.map(decode_fn, num_parallel_calls=AUTO)\n ds = ds.cache(cache_dir) if cache else ds\n ds = ds.repeat() if repeat else ds\n if shuffle: \n ds = ds.shuffle(shuffle, seed=CFG.seed)\n opt = tf.data.Options()\n opt.experimental_deterministic = False\n ds = ds.with_options(opt)\n ds = ds.batch(batch_size, drop_remainder=drop_remainder)\n ds = ds.map(augment_fn, num_parallel_calls=AUTO) if augment else ds\n ds = ds.prefetch(AUTO)\n return ds","metadata":{"papermill":{"duration":0.039133,"end_time":"2024-01-14T03:18:01.509017","exception":false,"start_time":"2024-01-14T03:18:01.469884","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2024-10-20T16:27:17.216973Z","iopub.execute_input":"2024-10-20T16:27:17.217791Z","iopub.status.idle":"2024-10-20T16:27:17.239092Z","shell.execute_reply.started":"2024-10-20T16:27:17.217730Z","shell.execute_reply":"2024-10-20T16:27:17.238338Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# ๐Ÿ”ช | Data Split\n\nIn the following code snippet, the data is divided into `5` folds. Note that, the `groups` argument is used to prevent any overlap of patients between the training and validation sets, thus avoiding potential **data leakage** issues. Additionally, each split is stratified based on the `class_label`, ensuring a uniform distribution of class labels in each fold.","metadata":{"papermill":{"duration":0.012174,"end_time":"2024-01-14T03:18:01.538524","exception":false,"start_time":"2024-01-14T03:18:01.52635","status":"completed"},"tags":[]}},{"cell_type":"code","source":"from sklearn.model_selection import StratifiedGroupKFold\n\nsgkf = StratifiedGroupKFold(n_splits=5, shuffle=True, random_state=CFG.seed)\n\ndf[\"fold\"] = -1\ndf.reset_index(drop=True, inplace=True)\nfor fold, (train_idx, valid_idx) in enumerate(\n sgkf.split(df, y=df[\"class_label\"], groups=df[\"patient_id\"])\n):\n df.loc[valid_idx, \"fold\"] = fold\ndf.groupby([\"fold\", \"class_name\"])[[\"eeg_id\"]].count().T","metadata":{"papermill":{"duration":0.037496,"end_time":"2024-01-14T03:18:01.587924","exception":false,"start_time":"2024-01-14T03:18:01.550428","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2024-10-20T16:27:17.240170Z","iopub.execute_input":"2024-10-20T16:27:17.240435Z","iopub.status.idle":"2024-10-20T16:27:22.115090Z","shell.execute_reply.started":"2024-10-20T16:27:17.240409Z","shell.execute_reply":"2024-10-20T16:27:22.114413Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"## Build Train & Valid Dataset\n\nOnly first sample for each `spectrogram_id` is used in order to keep the dataset size managable. Feel free to train on full data.","metadata":{"papermill":{"duration":0.011875,"end_time":"2024-01-14T03:18:01.611955","exception":false,"start_time":"2024-01-14T03:18:01.60008","status":"completed"},"tags":[]}},{"cell_type":"code","source":"# Sample from full data\nsample_df = df.groupby(\"spectrogram_id\").head(1).reset_index(drop=True)\ntrain_df = sample_df[sample_df.fold != CFG.fold]\nvalid_df = sample_df[sample_df.fold == CFG.fold]\nprint(f\"# Num Train: {len(train_df)} | Num Valid: {len(valid_df)}\")\n\n# Train\ntrain_paths = train_df.spec2_path.values\ntrain_offsets = train_df.spectrogram_label_offset_seconds.values.astype(int)\ntrain_labels = train_df.class_label.values\ntrain_ds = build_dataset(train_paths, train_offsets, train_labels, batch_size=CFG.batch_size,\n repeat=True, shuffle=True, augment=True, cache=True)\n\n# Valid\nvalid_paths = valid_df.spec2_path.values\nvalid_offsets = valid_df.spectrogram_label_offset_seconds.values.astype(int)\nvalid_labels = valid_df.class_label.values\nvalid_ds = build_dataset(valid_paths, valid_offsets, valid_labels, batch_size=CFG.batch_size,\n repeat=False, shuffle=False, augment=False, cache=True)","metadata":{"execution":{"iopub.status.busy":"2024-10-20T16:27:22.116105Z","iopub.execute_input":"2024-10-20T16:27:22.116541Z","iopub.status.idle":"2024-10-20T16:27:23.040277Z","shell.execute_reply.started":"2024-10-20T16:27:22.116511Z","shell.execute_reply":"2024-10-20T16:27:23.039362Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"## Dataset Check\n\nLet's visualize some samples from the dataset.","metadata":{}},{"cell_type":"code","source":"imgs, tars = next(iter(train_ds))\n\nnum_imgs = 8\nplt.figure(figsize=(4*4, num_imgs//4*5))\nfor i in range(num_imgs):\n plt.subplot(num_imgs//4, 4, i + 1)\n img = imgs[i].numpy()[...,0] # Adjust as per your image data format\n img -= img.min()\n img /= img.max() + 1e-4\n tar = CFG.label2name[np.argmax(tars[i].numpy())]\n plt.imshow(img)\n plt.title(f\"Target: {tar}\")\n plt.axis('off')\n \nplt.tight_layout()\nplt.show()","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2024-10-20T16:27:23.041647Z","iopub.execute_input":"2024-10-20T16:27:23.041938Z","iopub.status.idle":"2024-10-20T16:27:26.300350Z","shell.execute_reply.started":"2024-10-20T16:27:23.041909Z","shell.execute_reply":"2024-10-20T16:27:26.299498Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# Using ResNet and other models","metadata":{}},{"cell_type":"code","source":"from tensorflow.keras import layers, models\n\ndef identity_block(input_tensor, filters):\n f1, f2, f3 = filters\n\n x = layers.Conv2D(f1, (1, 1))(input_tensor)\n x = layers.BatchNormalization()(x)\n x = layers.ReLU()(x)\n\n x = layers.Conv2D(f2, (3, 3), padding='same')(x)\n x = layers.BatchNormalization()(x)\n x = layers.ReLU()(x)\n\n x = layers.Conv2D(f3, (1, 1))(x)\n x = layers.BatchNormalization()(x)\n\n x = layers.add([x, input_tensor])\n x = layers.ReLU()(x)\n return x\n\ndef conv_block(input_tensor, filters, strides=(2, 2)):\n f1, f2, f3 = filters\n\n x = layers.Conv2D(f1, (1, 1), strides=strides)(input_tensor)\n x = layers.BatchNormalization()(x)\n x = layers.ReLU()(x)\n\n x = layers.Conv2D(f2, (3, 3), padding='same')(x)\n x = layers.BatchNormalization()(x)\n x = layers.ReLU()(x)\n\n x = layers.Conv2D(f3, (1, 1))(x)\n x = layers.BatchNormalization()(x)\n\n shortcut = layers.Conv2D(f3, (1, 1), strides=strides)(input_tensor)\n shortcut = layers.BatchNormalization()(shortcut)\n\n x = layers.add([x, shortcut])\n x = layers.ReLU()(x)\n return x\n\ndef build_resnet50(input_shape, num_classes):\n input_tensor = layers.Input(shape=input_shape)\n\n x = layers.Conv2D(64, (7, 7), strides=(2, 2), padding='same')(input_tensor)\n x = layers.BatchNormalization()(x)\n x = layers.ReLU()(x)\n x = layers.MaxPooling2D((3, 3), strides=(2, 2))(x)\n\n x = conv_block(x, [64, 64, 256], strides=(1, 1))\n x = identity_block(x, [64, 64, 256])\n x = identity_block(x, [64, 64, 256])\n\n x = conv_block(x, [128, 128, 512])\n x = identity_block(x, [128, 128, 512])\n x = identity_block(x, [128, 128, 512])\n x = identity_block(x, [128, 128, 512])\n\n x = conv_block(x, [256, 256, 1024])\n x = identity_block(x, [256, 256, 1024])\n x = identity_block(x, [256, 256, 1024])\n x = identity_block(x, [256, 256, 1024])\n x = identity_block(x, [256, 256, 1024])\n x = identity_block(x, [256, 256, 1024])\n\n x = conv_block(x, [512, 512, 2048])\n x = identity_block(x, [512, 512, 2048])\n x = identity_block(x, [512, 512, 2048])\n\n x = layers.GlobalAveragePooling2D()(x)\n x = layers.Dense(num_classes, activation='softmax')(x)\n\n model = models.Model(input_tensor, x)\n return model\n\n# Example of creating the ResNet50 model\ninput_shape = (224, 224, 3)\nnum_classes = 6 # Set according to your dataset\nresnet50_model = build_resnet50(input_shape, num_classes)\nresnet50_model.summary()\n","metadata":{"execution":{"iopub.status.busy":"2024-10-20T16:27:26.301502Z","iopub.execute_input":"2024-10-20T16:27:26.301765Z","iopub.status.idle":"2024-10-20T16:27:39.039443Z","shell.execute_reply.started":"2024-10-20T16:27:26.301741Z","shell.execute_reply":"2024-10-20T16:27:39.038562Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# ๐Ÿ” | Loss & Metric\n\nThe evaluation metric in this competition is **KL Divergence**, defined as,\n\n$$\nD_{\\text{KL}}(P \\parallel Q) = \\sum_{i} P(i) \\log\\left(\\frac{P(i)}{Q(i)}\\right)\n$$\n\nWhere:\n- $P$ is the true distribution.\n- $Q$ is the predicted distribution.\n\nInterestingly, as KL Divergence is differentiable, we can directly use it as our loss function. Thus, we don't need to use a third-party metric like **Accuracy** to evaluate our model. Therefore, `valid_loss` can stand alone as an indicator for our evaluation. In keras, we already have impelementation for KL Divergence loss so we only need to import it.","metadata":{}},{"cell_type":"code","source":"LOSS = keras.losses.KLDivergence()","metadata":{"execution":{"iopub.status.busy":"2024-10-20T16:27:39.040845Z","iopub.execute_input":"2024-10-20T16:27:39.041140Z","iopub.status.idle":"2024-10-20T16:27:39.610809Z","shell.execute_reply.started":"2024-10-20T16:27:39.041112Z","shell.execute_reply":"2024-10-20T16:27:39.609839Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# ๐Ÿค– | Modeling\n\nThis notebook uses the `EfficientNetV2 B2` from KerasCV's collection of pretrained models. To explore other models, simply modify the `preset` in the `CFG` (config). Check the [KerasCV website](https://keras.io/api/keras_cv/models/tasks/image_classifier/) for a list of available pretrained models.","metadata":{"papermill":{"duration":0.016849,"end_time":"2024-01-14T03:18:38.613991","exception":false,"start_time":"2024-01-14T03:18:38.597142","status":"completed"},"tags":[]}},{"cell_type":"code","source":"# Build Classifier\n#model = keras_cv.models.ImageClassifier.from_preset(\n # CFG.preset, num_classes=CFG.num_classes\n#)\n\n# Compile the model \nresnet50_model.compile(optimizer=keras.optimizers.Adam(learning_rate=1e-4),\n loss=LOSS)\n\n# Model Sumamry\nresnet50_model.summary()","metadata":{"papermill":{"duration":10.446166,"end_time":"2024-01-14T03:18:49.186176","exception":false,"start_time":"2024-01-14T03:18:38.74001","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2024-10-20T16:27:39.611855Z","iopub.execute_input":"2024-10-20T16:27:39.612172Z","iopub.status.idle":"2024-10-20T16:27:39.949683Z","shell.execute_reply.started":"2024-10-20T16:27:39.612139Z","shell.execute_reply":"2024-10-20T16:27:39.948703Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# โš“ | LR Schedule\n\nA well-structured learning rate schedule is essential for efficient model training, ensuring optimal convergence and avoiding issues such as overshooting or stagnation.","metadata":{"papermill":{"duration":0.016209,"end_time":"2024-01-14T03:18:49.21924","exception":false,"start_time":"2024-01-14T03:18:49.203031","status":"completed"},"tags":[]}},{"cell_type":"code","source":"import math\n\ndef get_lr_callback(batch_size=8, mode='cos', epochs=10, plot=False):\n lr_start, lr_max, lr_min = 5e-5, 6e-6 * batch_size, 1e-5\n lr_ramp_ep, lr_sus_ep, lr_decay = 3, 0, 0.75\n\n def lrfn(epoch): # Learning rate update function\n if epoch < lr_ramp_ep: lr = (lr_max - lr_start) / lr_ramp_ep * epoch + lr_start\n elif epoch < lr_ramp_ep + lr_sus_ep: lr = lr_max\n elif mode == 'exp': lr = (lr_max - lr_min) * lr_decay**(epoch - lr_ramp_ep - lr_sus_ep) + lr_min\n elif mode == 'step': lr = lr_max * lr_decay**((epoch - lr_ramp_ep - lr_sus_ep) // 2)\n elif mode == 'cos':\n decay_total_epochs, decay_epoch_index = epochs - lr_ramp_ep - lr_sus_ep + 3, epoch - lr_ramp_ep - lr_sus_ep\n phase = math.pi * decay_epoch_index / decay_total_epochs\n lr = (lr_max - lr_min) * 0.5 * (1 + math.cos(phase)) + lr_min\n return lr\n\n if plot: # Plot lr curve if plot is True\n plt.figure(figsize=(10, 5))\n plt.plot(np.arange(epochs), [lrfn(epoch) for epoch in np.arange(epochs)], marker='o')\n plt.xlabel('epoch'); plt.ylabel('lr')\n plt.title('LR Scheduler')\n plt.show()\n\n return keras.callbacks.LearningRateScheduler(lrfn, verbose=False) # Create lr callback","metadata":{"papermill":{"duration":0.028945,"end_time":"2024-01-14T03:18:49.264535","exception":false,"start_time":"2024-01-14T03:18:49.23559","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2024-10-20T16:27:39.950956Z","iopub.execute_input":"2024-10-20T16:27:39.951711Z","iopub.status.idle":"2024-10-20T16:27:39.959358Z","shell.execute_reply.started":"2024-10-20T16:27:39.951676Z","shell.execute_reply":"2024-10-20T16:27:39.958434Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"lr_cb = get_lr_callback(CFG.batch_size, mode=CFG.lr_mode, plot=True)","metadata":{"papermill":{"duration":0.297147,"end_time":"2024-01-14T03:18:49.578089","exception":false,"start_time":"2024-01-14T03:18:49.280942","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2024-10-20T16:27:39.960336Z","iopub.execute_input":"2024-10-20T16:27:39.960593Z","iopub.status.idle":"2024-10-20T16:27:40.578545Z","shell.execute_reply.started":"2024-10-20T16:27:39.960566Z","shell.execute_reply":"2024-10-20T16:27:40.577663Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# ๐Ÿ’พ | Model Checkpointing","metadata":{"papermill":{"duration":0.017199,"end_time":"2024-01-14T03:18:49.613648","exception":false,"start_time":"2024-01-14T03:18:49.596449","status":"completed"},"tags":[]}},{"cell_type":"code","source":"ckpt_cb = keras.callbacks.ModelCheckpoint(\"best_model.keras\",\n monitor='val_loss',\n save_best_only=True,\n save_weights_only=False,\n mode='min')","metadata":{"papermill":{"duration":0.024529,"end_time":"2024-01-14T03:18:49.655708","exception":false,"start_time":"2024-01-14T03:18:49.631179","status":"completed"},"tags":[],"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# ๐Ÿš‚ | Training","metadata":{"papermill":{"duration":0.01671,"end_time":"2024-01-14T03:18:49.689354","exception":false,"start_time":"2024-01-14T03:18:49.672644","status":"completed"},"tags":[]}},{"cell_type":"code","source":"history = resnet50_model.fit(\n train_ds, \n epochs=CFG.epochs,\n callbacks=[lr_cb, ckpt_cb], \n steps_per_epoch=len(train_df)//CFG.batch_size,\n validation_data=valid_ds, \n verbose=CFG.verbose\n)","metadata":{"papermill":{"duration":3374.692199,"end_time":"2024-01-14T04:15:04.398389","exception":false,"start_time":"2024-01-14T03:18:49.70619","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2024-10-20T16:27:40.585543Z","iopub.execute_input":"2024-10-20T16:27:40.586000Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# Attention CNN","metadata":{}},{"cell_type":"code","source":"import tensorflow as tf\nfrom tensorflow.keras.layers import Conv2D, BatchNormalization, Activation, GlobalAveragePooling2D, Dense, Multiply, Add, Input, MaxPooling2D, Dropout\nfrom tensorflow.keras.models import Model\n\ndef attention_block(x):\n attention = GlobalAveragePooling2D()(x)\n attention = Dense(x.shape[-1], activation='relu')(attention)\n attention = Dense(x.shape[-1], activation='sigmoid')(attention)\n return Multiply()([x, attention])\n\ndef HybridCNN_Attention(input_shape, num_classes):\n inputs = Input(shape=input_shape)\n\n # Initial Conv Block\n x = Conv2D(64, (3, 3), padding='same')(inputs)\n x = BatchNormalization()(x)\n x = Activation('relu')(x)\n\n # Conv Block 1\n x = Conv2D(128, (3, 3), padding='same')(x)\n x = BatchNormalization()(x)\n x = Activation('relu')(x)\n x = attention_block(x)\n x = MaxPooling2D(pool_size=(2, 2))(x)\n\n # Conv Block 2\n x = Conv2D(256, (3, 3), padding='same')(x)\n x = BatchNormalization()(x)\n x = Activation('relu')(x)\n x = attention_block(x)\n x = MaxPooling2D(pool_size=(2, 2))(x)\n\n # Conv Block 3\n x = Conv2D(512, (3, 3), padding='same')(x)\n x = BatchNormalization()(x)\n x = Activation('relu')(x)\n x = attention_block(x)\n x = MaxPooling2D(pool_size=(2, 2))(x)\n\n # Global Average Pooling\n x = GlobalAveragePooling2D()(x)\n\n # Fully connected layer\n x = Dense(1024, activation='relu')(x)\n x = Dropout(0.5)(x)\n\n # Output layer\n outputs = Dense(num_classes, activation='softmax')(x)\n\n # Model definition\n model = Model(inputs, outputs)\n return model\n\n# Set input shape to match your dataset\ninput_shape = (200, 150, 3)\n\nnum_classes = 6 # Set according to your dataset\nattcnn = HybridCNN_Attention(input_shape, num_classes)\n# Compile the model \nattcnn.compile(optimizer=keras.optimizers.Adam(learning_rate=1e-4),\n loss=LOSS)\n\n# Model Sumamry\nattcnn.summary()","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"history = attcnn.fit(\n train_ds, \n epochs=CFG.epochs,\n callbacks=[lr_cb, ckpt_cb], \n steps_per_epoch=len(train_df)//CFG.batch_size,\n validation_data=valid_ds, \n verbose=CFG.verbose,\n batch_size=16\n)","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import tensorflow as tf\nfrom tensorflow.keras.layers import Conv2D, BatchNormalization, Activation, GlobalAveragePooling2D, Dense, Multiply, Add, Input, MaxPooling2D, Dropout\nfrom tensorflow.keras.models import Model\n\ndef attention_block(x):\n \"\"\"Attention block to enhance feature maps.\"\"\"\n attention = GlobalAveragePooling2D()(x)\n attention = Dense(x.shape[-1], activation='relu')(attention)\n attention = Dense(x.shape[-1], activation='sigmoid')(attention)\n return Multiply()([x, attention])\n\ndef EfficientNetV2B2_Attention(input_shape, num_classes):\n \"\"\"Hybrid CNN architecture using EfficientNetV2B2 backbone with attention blocks.\"\"\"\n \n # Load EfficientNetV2B2 as the backbone\n base_model = tf.keras.applications.EfficientNetV2B2(\n include_top=False,\n weights='imagenet',\n input_shape=input_shape\n )\n \n # Freeze the base model layers\n base_model.trainable = False\n\n # Input layer\n inputs = Input(shape=input_shape)\n\n # Base model (EfficientNetV2B2)\n x = base_model(inputs, training=False)\n\n # Attention on the backbone output\n x = attention_block(x)\n\n # Further convolutional blocks (optional)\n # Conv Block 1\n x = Conv2D(128, (3, 3), padding='same')(x)\n x = BatchNormalization()(x)\n x = Activation('relu')(x)\n x = attention_block(x)\n x = MaxPooling2D(pool_size=(2, 2))(x)\n\n # Conv Block 2\n x = Conv2D(256, (3, 3), padding='same')(x)\n x = BatchNormalization()(x)\n x = Activation('relu')(x)\n x = attention_block(x)\n x = MaxPooling2D(pool_size=(2, 2))(x)\n\n # Global Average Pooling\n x = GlobalAveragePooling2D()(x)\n\n # Fully connected layer\n x = Dense(1024, activation='relu')(x)\n x = Dropout(0.5)(x)\n\n # Output layer\n outputs = Dense(num_classes, activation='softmax')(x)\n\n # Model definition\n model = Model(inputs, outputs)\n return model\n\n# Set input shape to match your dataset\ninput_shape = (400,300, 3)\n\nnum_classes = 6 # Set according to your dataset\nEff_improved = EfficientNetV2B2_Attention(input_shape, num_classes)\n\n# Compile the model \nEff_improved.compile(optimizer=keras.optimizers.Adam(learning_rate=1e-4),\n loss=LOSS)\n\n\n# Model Summary\nEff_improved.summary()\n","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"history = Eff_improved.fit(\n train_ds, \n epochs=20,\n callbacks=[lr_cb, ckpt_cb], \n steps_per_epoch=len(train_df)//CFG.batch_size,\n validation_data=valid_ds, \n verbose=CFG.verbose\n)","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Build Classifier\neffnet_V2 = keras_cv.models.ImageClassifier.from_preset(\n \"efficientnetv2_b2_imagenet\", num_classes=CFG.num_classes\n)\n\n# Compile the model \neffnet_V2.compile(optimizer=keras.optimizers.Adam(learning_rate=1e-4),\n loss=LOSS)\n\n# Model Sumamry\neffnet_V2.summary()","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"history =effnet_V2.fit(\n train_ds, \n epochs=CFG.epochs,\n callbacks=[lr_cb, ckpt_cb], \n steps_per_epoch=len(train_df)//CFG.batch_size,\n validation_data=valid_ds, \n verbose=CFG.verbose\n)","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# ๐Ÿงช | Prediction","metadata":{"papermill":{"duration":0.693309,"end_time":"2024-01-14T04:15:05.731839","exception":false,"start_time":"2024-01-14T04:15:05.03853","status":"completed"},"tags":[]}},{"cell_type":"markdown","source":"## Load Best Model","metadata":{"papermill":{"duration":0.632183,"end_time":"2024-01-14T04:15:06.991143","exception":false,"start_time":"2024-01-14T04:15:06.35896","status":"completed"},"tags":[]}},{"cell_type":"code","source":"model.load_weights(\"best_model.keras\")","metadata":{"papermill":{"duration":20.428261,"end_time":"2024-01-14T04:15:28.044401","exception":false,"start_time":"2024-01-14T04:15:07.61614","status":"completed"},"tags":[],"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"## Build Test Dataset","metadata":{"papermill":{"duration":0.703901,"end_time":"2024-01-14T04:20:09.745279","exception":false,"start_time":"2024-01-14T04:20:09.041378","status":"completed"},"tags":[]}},{"cell_type":"code","source":"test_paths = test_df.spec2_path.values\ntest_ds = build_dataset(test_paths, batch_size=min(CFG.batch_size, len(test_df)),\n repeat=False, shuffle=False, cache=False, augment=False)","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"## Inference","metadata":{}},{"cell_type":"code","source":"preds = model.predict(test_ds)","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# ๐Ÿ“ฉ | Submission","metadata":{}},{"cell_type":"code","source":"pred_df = test_df[[\"eeg_id\"]].copy()\ntarget_cols = [x.lower()+'_vote' for x in CFG.class_names]\npred_df[target_cols] = preds.tolist()\n\nsub_df = pd.read_csv(f'{BASE_PATH}/sample_submission.csv')\nsub_df = sub_df[[\"eeg_id\"]].copy()\nsub_df = sub_df.merge(pred_df, on=\"eeg_id\", how=\"left\")\nsub_df.to_csv(\"submission.csv\", index=False)\nsub_df.head()","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# ๐Ÿ“Œ | Reference\n* [HMS-HBAC: ResNet34d Baseline [Training]](https://www.kaggle.com/code/ttahara/hms-hbac-resnet34d-baseline-training) \n* [EfficientNetB2 Starter - [LB 0.57]](https://www.kaggle.com/code/cdeotte/efficientnetb2-starter-lb-0-57)","metadata":{}}]}