{ "cells": [ { "cell_type": "markdown", "metadata": {}, "source": [ "\n", "
\n", "\n", "- \n", "\n", " View in Colab\n", "\n", "\n", "- \n", "\n", " GitHub source\n", "\n", "\n", "
" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "# Train ECG Denosier\n", "\n", "__Date created:__ 2024/08/13 \n", "\n", "__Last Modified:__ 2024/07/17 \n", "\n", "__Description:__ Train, evaluate, and export ECG denoiser model from scratch\n", "\n", "\n", "## Overview \n", "\n", "In this guide, we will train an ECG denoiser to remove noise and artifacts from raw ECG signals. \n", "Once trained, we demonstrate how to evaluate the model and export it for inference for both TF Lite and TF Lite for Micro.\n", "\n", "__Input__\n", "\n", "- **Sensor**: ECG \n", "- **Location**: Wrist\n", "- **Sampling Rate**: 100 Hz\n", "- **Frame Size**: 2.56 seconds\n", "\n", "__Datasets__\n", "\n", "- **[Synthetic](https://ambiqai.github.io/heartkit/datasets/synthetic/)**: Synthetic ECG signals from PhysioKit\n", "- **[PTB-XL](https://ambiqai.github.io/heartkit/datasets/ptbxl/)**: The PTB-XL is a large publicly available electrocardiography dataset. \n", "It contains 21837 clinical 12-lead ECGs from 18885 patients of 10 second length. The ECGs are sampled at 500 Hz and are annotated by up to two cardiologists.\n" ] }, { "cell_type": "code", "execution_count": 1, "metadata": {}, "outputs": [], "source": [ "!pip install -q --disable-pip-version-check heartkit" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Setup" ] }, { "cell_type": "code", "execution_count": 2, "metadata": {}, "outputs": [], "source": [ "import os\n", "os.environ['TF_CPP_MIN_LOG_LEVEL'] = '3'\n", "import contextlib\n", "from pathlib import Path\n", "import tempfile\n", "import keras\n", "import heartkit as hk\n", "import numpy as np\n", "import neuralspot_edge as nse\n", "import matplotlib.pyplot as plt" ] }, { "cell_type": "code", "execution_count": 3, "metadata": {}, "outputs": [], "source": [ "# Be sure to set the dataset path to the correct location\n", "datasets_dir = Path(os.getenv('HK_DATASET_PATH', './datasets'))\n", "\n", "plot_theme = hk.utils.dark_theme\n", "nse.utils.silence_tensorflow()\n", "hk.utils.setup_plotting(plot_theme)\n", "logger = nse.utils.setup_logger(__name__)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Create preprocess/augmentation pipeline\n", "\n", "Since our goal is to denoise ECG signals, we need to create an augmentation pipeline to generate noisy samples. \n", "\n", "We will leverage `neuralspot-edge` preprocessing layers to create the following augmentations:\n", "\n", "* Baseline wander: Simulate baseline wander by adding a low frequency sine signal\n", "* Powerline noise: Simulate powerline noise by adding a 50 Hz sinusoidal signal \n", "* Amplitude warp: Simulate amplitude warp by randomly scaling along a low frequency sine wave\n", "* Gaussian noise: Simulate lead noise by adding random noise following a Gaussian distribution\n", "* Background noise: Add real noise captured from NSTDB dataset\n" ] }, { "cell_type": "code", "execution_count": 4, "metadata": {}, "outputs": [], "source": [ "preprocesses = [hk.NamedParams(\n", " name=\"layer_norm\",\n", " params=dict(\n", " epsilon=0.01\n", " )\n", ")]\n", "\n", "augmentations = [hk.NamedParams(\n", " name=\"random_noise_distortion\",\n", " params=dict(\n", " amplitude=[0.1, 1.5],\n", " frequency=[0.5, 1.5],\n", " name=\"baseline_wander\"\n", " )\n", "), hk.NamedParams(\n", " name=\"random_sine_wave\",\n", " params=dict(\n", " amplitude=[0, 0.05],\n", " frequency=[45, 50],\n", " auto_vectorize=False,\n", " name=\"powerline_noise\"\n", " )\n", "), hk.NamedParams(\n", " name=\"amplitude_warp\",\n", " params=dict(\n", " amplitude=[0.9, 1.1],\n", " frequency=[0.5, 1.5],\n", " name=\"amplitude_warp\"\n", " )\n", "), hk.NamedParams(\n", " name=\"random_noise\",\n", " params=dict(\n", " factor=[0.1, 0.5],\n", " name=\"random_noise\"\n", " )\n", "), hk.NamedParams(\n", " name=\"random_background_noise\",\n", " params=dict(\n", " amplitude=[0.1, 0.5],\n", " num_noises=2,\n", " name=\"nstdb\"\n", " )\n", ")]\n" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Define TCN model architecture\n", "\n", "For this task, we are going to leverage a customized __TCN__ model architecture that is smaller and can handle 1D signals. The model consists of 5 TCN blocks with a depth of 1. Each block leverages dilated depthwise-separable convolutions along with inverted expansion and squeeze and excitation layers. The model is followed by a 1D convolutional layer. " ] }, { "cell_type": "code", "execution_count": 5, "metadata": {}, "outputs": [], "source": [ "mbconv_blocks = [\n", " dict(depth=1, branch=1, filters=16, kernel=(1, 7), dilation=(1, 1), dropout=0, ex_ratio=1, se_ratio=0, norm=\"batch\"),\n", " dict(depth=1, branch=1, filters=24, kernel=(1, 7), dilation=(1, 1), dropout=0, ex_ratio=1, se_ratio=2, norm=\"batch\"),\n", " dict(depth=1, branch=1, filters=32, kernel=(1, 7), dilation=(1, 2), dropout=0, ex_ratio=1, se_ratio=2, norm=\"batch\"),\n", " dict(depth=1, branch=1, filters=40, kernel=(1, 7), dilation=(1, 4), dropout=0, ex_ratio=1, se_ratio=2, norm=\"batch\"),\n", " dict(depth=1, branch=1, filters=48, kernel=(1, 7), dilation=(1, 8), dropout=0, ex_ratio=1, se_ratio=2, norm=\"batch\")\n", "]\n", "\n", "architecture = dict(\n", " name=\"tcn\",\n", " params=dict(\n", " input_kernel=(1, 7),\n", " input_norm=\"batch\",\n", " blocks=mbconv_blocks,\n", " output_kernel=(1, 7),\n", " include_top=True,\n", " use_logits=True,\n", " model_name=\"tcn\"\n", " )\n", ")\n" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Configure datasets\n", "\n", "Capturing noise-free ECG signals is challenging due to the presence of various artifacts. Therefore, we use a combination of synthetic and controlled, real-world datasets as our training data. HeartKit exposes an ECG Synthetic dataset generator provided by PhysioKit. \n" ] }, { "cell_type": "code", "execution_count": 6, "metadata": {}, "outputs": [], "source": [ "datasets = [\n", " hk.NamedParams(\n", " name=\"ecg-synthetic\",\n", " params=dict(\n", " num_pts=5000,\n", " params=dict(\n", " presets=[\"SR\", \"AFIB\", \"ant_STEMI\", \"LAHB\", \"LPHB\", \"high_take_off\", \"LBBB\", \"random_morphology\"],\n", " preset_weights=[24, 8, 1, 1, 1, 1, 1, 0],\n", " duration=10,\n", " sample_rate=100,\n", " heart_rate=[40, 160],\n", " impedance=[1, 2],\n", " p_multiplier=[0.7, 1.3],\n", " t_multiplier=[0.7, 1.3],\n", " noise_multiplier=[0, 0.01],\n", " voltage_factor=[800, 1000]\n", " )\n", " )\n", " ),\n", " hk.NamedParams(\n", " name=\"ptbxl\",\n", " params=dict(\n", " path=datasets_dir / \"ptbxl\",\n", " )\n", " )\n", "]\n" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Task configuration\n", "\n", "Here we provide the constants that we will use throughout the guide. For better performance, adjust parameters as needed such as `BATCH_SIZE`, `EPOCHS`, and `LEARNING_RATE`." ] }, { "cell_type": "code", "execution_count": 7, "metadata": {}, "outputs": [], "source": [ "params = hk.HKTaskParams(\n", " # Common arguments\n", " name=\"hk-ecg-denoiser\",\n", " job_dir=Path(tempfile.gettempdir()) / \"hk-ecg-denoiser\",\n", " # Dataset arguments\n", " datasets=datasets,\n", " # Signal arguments\n", " sampling_rate=100,\n", " frame_size=256,\n", " # Dataloader arguments\n", " samples_per_patient=5,\n", " val_samples_per_patient=10,\n", " test_samples_per_patient=10,\n", " # Preprocessing/Augmentation arguments\n", " preprocesses=preprocesses,\n", " augmentations=augmentations,\n", " # Class arguments\n", " num_classes=1,\n", " class_map={0: 0},\n", " class_names=[\"DENOISE\"],\n", " # Split arguments\n", " val_patients=0.1,\n", " val_size=10000,\n", " test_size=10000,\n", " val_file=\"val.pkl\",\n", " test_file=\"val.pkl\",\n", " # Model arguments\n", " model_file=\"model.keras\",\n", " architecture=architecture,\n", " # Training parameters\n", " lr_rate=1e-3,\n", " lr_cycles=1,\n", " batch_size=256,\n", " buffer_size=25000,\n", " epochs=100,\n", " steps_per_epoch=50,\n", " val_metric=\"loss\",\n", " class_weights=\"balanced\",\n", " # Evaluation arguments\n", " threshold=0.5,\n", " val_metric_threshold=0.98,\n", " # Export parameters\n", " tflm_var_name=\"ecg_denoise_flatbuffer\",\n", " tflm_file=\"ecg_denoise_flatbuffer.h\",\n", " # Demo params\n", " backend=\"pc\",\n", " demo_size=800,\n", " display_report=True,\n", " # Extra arguments\n", " verbose=1,\n", " seed=42\n", ")" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Load denoise task \n", "\n", "HeartKit provides a __TaskFactory__ that includes a number ready-to-use tasks. Each task provides methods for training, evaluating, exporting, and demoing. We will grab the __denoise__ task and configure it for our use case." ] }, { "cell_type": "code", "execution_count": 8, "metadata": {}, "outputs": [], "source": [ "task = hk.TaskFactory.get(\"denoise\")" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Download the datasets\n", "\n", "We will download the synthetic and PTB-XL datasets using `heartkit`. If already downloaded, this step will be skipped." ] }, { "cell_type": "code", "execution_count": 9, "metadata": {}, "outputs": [], "source": [ "task.download(params=params)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Visualize the data\n", "\n", "Let's visualize a sample ECG signal from the synthetic dataset. Note this contains no noise or artifacts. Augmentations will be applied later to generate noisy samples for training." ] }, { "cell_type": "code", "execution_count": 10, "metadata": {}, "outputs": [ { "data": { "image/png": "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", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "ds = hk.DatasetFactory.get(params.datasets[0].name)(\n", " cacheable=False,\n", " **params.datasets[0].params\n", ")\n", "\n", "ds_gen = ds.signal_generator(\n", " patient_generator=nse.utils.uniform_id_generator(ds.get_test_patient_ids()),\n", " frame_size=params.frame_size,\n", " samples_per_patient=params.samples_per_patient,\n", " target_rate=params.sampling_rate,\n", ")\n", "ecg = next(ds_gen)\n", "\n", "ts = np.arange(0, len(ecg)) / params.sampling_rate\n", "fig, ax = plt.subplots(1, 1, figsize=(9, 4))\n", "ax.plot(ts, ecg, color=plot_theme.primary_color, lw=3)\n", "fig.suptitle(\"Raw ECG Signal\")\n", "ax.set_xlabel(\"Time (s)\")\n", "ax.set_ylabel(\"Amplitude\")\n", "fig.tight_layout()\n", "fig.show()\n" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Visualize augmented data\n", "\n", "Let's visualize the augmented data to understand how the augmentations affect the ECG signals." ] }, { "cell_type": "code", "execution_count": 11, "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "WARNING: All log messages before absl::InitializeLog() is called are written to STDERR\n", "I0000 00:00:1723838156.202266 751181 cuda_executor.cc:1015] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero. See more at https://github.com/torvalds/linux/blob/v6.0/Documentation/ABI/testing/sysfs-bus-pci#L344-L355\n", "I0000 00:00:1723838156.222145 751181 cuda_executor.cc:1015] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero. See more at https://github.com/torvalds/linux/blob/v6.0/Documentation/ABI/testing/sysfs-bus-pci#L344-L355\n", "I0000 00:00:1723838156.222246 751181 cuda_executor.cc:1015] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero. See more at https://github.com/torvalds/linux/blob/v6.0/Documentation/ABI/testing/sysfs-bus-pci#L344-L355\n", "I0000 00:00:1723838156.223422 751181 cuda_executor.cc:1015] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero. See more at https://github.com/torvalds/linux/blob/v6.0/Documentation/ABI/testing/sysfs-bus-pci#L344-L355\n", "I0000 00:00:1723838156.223495 751181 cuda_executor.cc:1015] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero. See more at https://github.com/torvalds/linux/blob/v6.0/Documentation/ABI/testing/sysfs-bus-pci#L344-L355\n", "I0000 00:00:1723838156.223541 751181 cuda_executor.cc:1015] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero. See more at https://github.com/torvalds/linux/blob/v6.0/Documentation/ABI/testing/sysfs-bus-pci#L344-L355\n", "I0000 00:00:1723838156.268697 751181 cuda_executor.cc:1015] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero. See more at https://github.com/torvalds/linux/blob/v6.0/Documentation/ABI/testing/sysfs-bus-pci#L344-L355\n", "I0000 00:00:1723838156.268787 751181 cuda_executor.cc:1015] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero. See more at https://github.com/torvalds/linux/blob/v6.0/Documentation/ABI/testing/sysfs-bus-pci#L344-L355\n", "I0000 00:00:1723838156.268844 751181 cuda_executor.cc:1015] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero. See more at https://github.com/torvalds/linux/blob/v6.0/Documentation/ABI/testing/sysfs-bus-pci#L344-L355\n" ] } ], "source": [ "preprocessor = hk.datasets.create_augmentation_pipeline(\n", " augmentations=params.preprocesses,\n", " sampling_rate=params.sampling_rate,\n", ")\n", "\n", "augmenter = hk.datasets.create_augmentation_pipeline(\n", " augmentations=params.augmentations,\n", " sampling_rate=params.sampling_rate,\n", ")" ] }, { "cell_type": "code", "execution_count": 12, "metadata": {}, "outputs": [ { "data": { "image/png": "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", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "aug_ecg = augmenter(preprocessor(keras.ops.convert_to_tensor(np.reshape(ecg, (1, -1, 1)))), training=True)\n", "aug_ecg = aug_ecg.numpy().squeeze()\n", "\n", "ts = np.arange(0, len(aug_ecg)) / params.sampling_rate\n", "fig, ax = plt.subplots(1, 1, figsize=(9, 4))\n", "plt.plot(ts, aug_ecg, color=plot_theme.primary_color, lw=3)\n", "fig.suptitle(\"Augmented ECG Signal\")\n", "ax.set_xlabel(\"Time (s)\")\n", "ax.set_ylabel(\"Amplitude\")\n", "plt.tight_layout()\n", "plt.show()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Visualize the model\n", "\n", "Let's view the first several layers of the model to understand the architecture better." ] }, { "cell_type": "code", "execution_count": 13, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
Model: \"TCN\"\n",
       "
\n" ], "text/plain": [ "\u001b[1mModel: \"TCN\"\u001b[0m\n" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "text/html": [ "
┏━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━┓\n",
       "┃ Layer (type)        ┃ Output Shape      ┃    Param # ┃ Connected to      ┃\n",
       "┡━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━┩\n",
       "│ inputs (InputLayer) │ (None, 256, 1)    │          0 │ -                 │\n",
       "├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
       "│ reshape (Reshape)   │ (None, 1, 256, 1) │          0 │ inputs[0][0]      │\n",
       "├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
       "│ ENC.CN              │ (None, 1, 256, 1) │          7 │ reshape[0][0]     │\n",
       "│ (DepthwiseConv2D)   │                   │            │                   │\n",
       "├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
       "│ ENC.BN              │ (None, 1, 256, 1) │          4 │ ENC.CN[0][0]      │\n",
       "│ (BatchNormalizatio… │                   │            │                   │\n",
       "├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
       "│ B1.D1.DW.B1.CN      │ (None, 1, 256, 1) │          7 │ ENC.BN[0][0]      │\n",
       "│ (DepthwiseConv2D)   │                   │            │                   │\n",
       "├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
       "│ B1.D1.DW.B1.BN      │ (None, 1, 256, 1) │          4 │ B1.D1.DW.B1.CN[0… │\n",
       "│ (BatchNormalizatio… │                   │            │                   │\n",
       "├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
       "│ B1.D1.DW.ACT        │ (None, 1, 256, 1) │          0 │ B1.D1.DW.B1.BN[0… │\n",
       "│ (Activation)        │                   │            │                   │\n",
       "├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
       "│ B1.D1.PW.B1.CN      │ (None, 1, 256,    │         16 │ B1.D1.DW.ACT[0][… │\n",
       "│ (Conv2D)            │ 16)               │            │                   │\n",
       "├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
       "│ B1.D1.PW.B1.BN      │ (None, 1, 256,    │         64 │ B1.D1.PW.B1.CN[0… │\n",
       "│ (BatchNormalizatio… │ 16)               │            │                   │\n",
       "├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
       "│ B1.D1.PW.ACT        │ (None, 1, 256,    │          0 │ B1.D1.PW.B1.BN[0… │\n",
       "│ (Activation)        │ 16)               │            │                   │\n",
       "├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
       "│ B2.D1.DW.B1.CN      │ (None, 1, 256,    │        112 │ B1.D1.PW.ACT[0][… │\n",
       "│ (DepthwiseConv2D)   │ 16)               │            │                   │\n",
       "└─────────────────────┴───────────────────┴────────────┴───────────────────┘\n",
       "
\n" ], "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┃\u001b[1m \u001b[0m\u001b[1mConnected to \u001b[0m\u001b[1m \u001b[0m┃\n", "┡━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━┩\n", "│ inputs (\u001b[38;5;33mInputLayer\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m256\u001b[0m, \u001b[38;5;34m1\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │ - │\n", "├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n", "│ reshape (\u001b[38;5;33mReshape\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m1\u001b[0m, \u001b[38;5;34m256\u001b[0m, \u001b[38;5;34m1\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │ inputs[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m] │\n", "├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n", "│ ENC.CN │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m1\u001b[0m, \u001b[38;5;34m256\u001b[0m, \u001b[38;5;34m1\u001b[0m) │ \u001b[38;5;34m7\u001b[0m │ reshape[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m] │\n", "│ (\u001b[38;5;33mDepthwiseConv2D\u001b[0m) │ │ │ │\n", "├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n", "│ ENC.BN │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m1\u001b[0m, \u001b[38;5;34m256\u001b[0m, \u001b[38;5;34m1\u001b[0m) │ \u001b[38;5;34m4\u001b[0m │ ENC.CN[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m] │\n", "│ (\u001b[38;5;33mBatchNormalizatio…\u001b[0m │ │ │ │\n", "├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n", "│ B1.D1.DW.B1.CN │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m1\u001b[0m, \u001b[38;5;34m256\u001b[0m, \u001b[38;5;34m1\u001b[0m) │ \u001b[38;5;34m7\u001b[0m │ ENC.BN[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m] │\n", "│ (\u001b[38;5;33mDepthwiseConv2D\u001b[0m) │ │ │ │\n", "├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n", "│ B1.D1.DW.B1.BN │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m1\u001b[0m, \u001b[38;5;34m256\u001b[0m, \u001b[38;5;34m1\u001b[0m) │ \u001b[38;5;34m4\u001b[0m │ B1.D1.DW.B1.CN[\u001b[38;5;34m0\u001b[0m… │\n", "│ (\u001b[38;5;33mBatchNormalizatio…\u001b[0m │ │ │ │\n", "├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n", "│ B1.D1.DW.ACT │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m1\u001b[0m, \u001b[38;5;34m256\u001b[0m, \u001b[38;5;34m1\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │ B1.D1.DW.B1.BN[\u001b[38;5;34m0\u001b[0m… │\n", "│ (\u001b[38;5;33mActivation\u001b[0m) │ │ │ │\n", "├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n", "│ B1.D1.PW.B1.CN │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m1\u001b[0m, \u001b[38;5;34m256\u001b[0m, │ \u001b[38;5;34m16\u001b[0m │ B1.D1.DW.ACT[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m…\u001b[0m │\n", "│ (\u001b[38;5;33mConv2D\u001b[0m) │ \u001b[38;5;34m16\u001b[0m) │ │ │\n", "├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n", "│ B1.D1.PW.B1.BN │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m1\u001b[0m, \u001b[38;5;34m256\u001b[0m, │ \u001b[38;5;34m64\u001b[0m │ B1.D1.PW.B1.CN[\u001b[38;5;34m0\u001b[0m… │\n", "│ (\u001b[38;5;33mBatchNormalizatio…\u001b[0m │ \u001b[38;5;34m16\u001b[0m) │ │ │\n", "├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n", "│ B1.D1.PW.ACT │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m1\u001b[0m, \u001b[38;5;34m256\u001b[0m, │ \u001b[38;5;34m0\u001b[0m │ B1.D1.PW.B1.BN[\u001b[38;5;34m0\u001b[0m… │\n", "│ (\u001b[38;5;33mActivation\u001b[0m) │ \u001b[38;5;34m16\u001b[0m) │ │ │\n", "├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n", "│ B2.D1.DW.B1.CN │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m1\u001b[0m, \u001b[38;5;34m256\u001b[0m, │ \u001b[38;5;34m112\u001b[0m │ B1.D1.PW.ACT[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m…\u001b[0m │\n", "│ (\u001b[38;5;33mDepthwiseConv2D\u001b[0m) │ \u001b[38;5;34m16\u001b[0m) │ │ │\n", "└─────────────────────┴───────────────────┴────────────┴───────────────────┘\n" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "text/html": [ "
 Total params: 10,223 (39.93 KB)\n",
       "
\n" ], "text/plain": [ "\u001b[1m Total params: \u001b[0m\u001b[38;5;34m10,223\u001b[0m (39.93 KB)\n" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "text/html": [ "
 Trainable params: 9,675 (37.79 KB)\n",
       "
\n" ], "text/plain": [ "\u001b[1m Trainable params: \u001b[0m\u001b[38;5;34m9,675\u001b[0m (37.79 KB)\n" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "text/html": [ "
 Non-trainable params: 548 (2.14 KB)\n",
       "
\n" ], "text/plain": [ "\u001b[1m Non-trainable params: \u001b[0m\u001b[38;5;34m548\u001b[0m (2.14 KB)\n" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "model = nse.models.tcn.tcn_from_object(\n", " x=keras.Input(shape=(params.frame_size, 1), name='inputs'),\n", " params=architecture[\"params\"],\n", " num_classes=1\n", ")\n", "model.summary(layer_range=('inputs', model.layers[10].name))" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Train the model" ] }, { "cell_type": "code", "execution_count": 14, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
INFO     Creating synthetic dataset cache with 5000 patients                                   ecg_synthetic.py:159\n",
       "
\n" ], "text/plain": [ "\u001b[34mINFO \u001b[0m Creating synthetic dataset cache with \u001b[1;36m5000\u001b[0m patients \u001b]8;id=172088;file:///workspaces/heartkit/heartkit/datasets/ecg_synthetic.py\u001b\\\u001b[2mecg_synthetic.py\u001b[0m\u001b]8;;\u001b\\\u001b[2m:\u001b[0m\u001b]8;id=461477;file:///workspaces/heartkit/heartkit/datasets/ecg_synthetic.py#159\u001b\\\u001b[2m159\u001b[0m\u001b]8;;\u001b\\\n" ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stderr", "output_type": "stream", "text": [ "Building ecg-synthetic cache: 100%|██████████| 5000/5000 [00:57<00:00, 86.91it/s] \n" ] }, { "data": { "text/html": [ "
INFO     Validation steps per epoch: 39                                                              datasets.py:85\n",
       "
\n" ], "text/plain": [ "\u001b[34mINFO \u001b[0m Validation steps per epoch: \u001b[1;36m39\u001b[0m \u001b]8;id=99779;file:///workspaces/heartkit/heartkit/tasks/denoise/datasets.py\u001b\\\u001b[2mdatasets.py\u001b[0m\u001b]8;;\u001b\\\u001b[2m:\u001b[0m\u001b]8;id=277033;file:///workspaces/heartkit/heartkit/tasks/denoise/datasets.py#85\u001b\\\u001b[2m85\u001b[0m\u001b]8;;\u001b\\\n" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "text/html": [ "
\n"
      ],
      "text/plain": []
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Training:   0%|           0/100 ETA: ?s,  ?epochs/sWARNING: All log messages before absl::InitializeLog() is called are written to STDERR\n",
      "I0000 00:00:1723838225.604155  751478 service.cc:146] XLA service 0x7a52b8001f20 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:\n",
      "I0000 00:00:1723838225.604174  751478 service.cc:154]   StreamExecutor device (0): NVIDIA GeForce RTX 4090, Compute Capability 8.9\n",
      "I0000 00:00:1723838232.858832  751478 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.\n",
      "Training: 100%|██████████ 100/100 ETA: 00:00s,   1.59s/epochs"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[1m39/39\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 975us/step - cos: 0.7118 - loss: 0.0511 - mae: 0.1445 - mse: 0.0452 - snr: 11.9220\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "
INFO     [VAL SET]COS=0.7079, LOSS=0.0528, MAE=0.1466, MSE=0.0469, SNR=11.9038                         train.py:149\n",
       "
\n"
      ],
      "text/plain": [
       "\u001b[34mINFO    \u001b[0m \u001b[1m[\u001b[0mVAL SET\u001b[1m]\u001b[0m\u001b[33mCOS\u001b[0m=\u001b[1;36m0\u001b[0m\u001b[1;36m.7079\u001b[0m, \u001b[33mLOSS\u001b[0m=\u001b[1;36m0\u001b[0m\u001b[1;36m.0528\u001b[0m, \u001b[33mMAE\u001b[0m=\u001b[1;36m0\u001b[0m\u001b[1;36m.1466\u001b[0m, \u001b[33mMSE\u001b[0m=\u001b[1;36m0\u001b[0m\u001b[1;36m.0469\u001b[0m, \u001b[33mSNR\u001b[0m=\u001b[1;36m11\u001b[0m\u001b[1;36m.9038\u001b[0m                         \u001b]8;id=347748;file:///workspaces/heartkit/heartkit/tasks/denoise/train.py\u001b\\\u001b[2mtrain.py\u001b[0m\u001b]8;;\u001b\\\u001b[2m:\u001b[0m\u001b]8;id=260161;file:///workspaces/heartkit/heartkit/tasks/denoise/train.py#149\u001b\\\u001b[2m149\u001b[0m\u001b]8;;\u001b\\\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "task.train(params)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Model evaluation\n",
    "\n",
    "Now that we have trained the model, we will evaluate the model on the test dataset. Similar to training, we will provide the high-level configuration to the task process."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "
INFO     Creating synthetic dataset cache with 5000 patients                                   ecg_synthetic.py:159\n",
       "
\n"
      ],
      "text/plain": [
       "\u001b[34mINFO    \u001b[0m Creating synthetic dataset cache with \u001b[1;36m5000\u001b[0m patients                                   \u001b]8;id=288389;file:///workspaces/heartkit/heartkit/datasets/ecg_synthetic.py\u001b\\\u001b[2mecg_synthetic.py\u001b[0m\u001b]8;;\u001b\\\u001b[2m:\u001b[0m\u001b]8;id=256787;file:///workspaces/heartkit/heartkit/datasets/ecg_synthetic.py#159\u001b\\\u001b[2m159\u001b[0m\u001b]8;;\u001b\\\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Building ecg-synthetic cache: 100%|██████████| 5000/5000 [00:57<00:00, 87.16it/s] \n"
     ]
    },
    {
     "data": {
      "text/html": [
       "
\n"
      ],
      "text/plain": []
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[1m39/39\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 25ms/step - cos: 0.7238 - loss: 0.0443 - mae: 0.1328 - mse: 0.0384 - snr: 12.3671\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "
INFO     [TEST SET] COS=0.7245, LOSS=0.0437, MAE=0.1316, MSE=0.0377, SNR=12.3787                     evaluate.py:37\n",
       "
\n"
      ],
      "text/plain": [
       "\u001b[34mINFO    \u001b[0m \u001b[1m[\u001b[0mTEST SET\u001b[1m]\u001b[0m \u001b[33mCOS\u001b[0m=\u001b[1;36m0\u001b[0m\u001b[1;36m.7245\u001b[0m, \u001b[33mLOSS\u001b[0m=\u001b[1;36m0\u001b[0m\u001b[1;36m.0437\u001b[0m, \u001b[33mMAE\u001b[0m=\u001b[1;36m0\u001b[0m\u001b[1;36m.1316\u001b[0m, \u001b[33mMSE\u001b[0m=\u001b[1;36m0\u001b[0m\u001b[1;36m.0377\u001b[0m, \u001b[33mSNR\u001b[0m=\u001b[1;36m12\u001b[0m\u001b[1;36m.3787\u001b[0m                     \u001b]8;id=893749;file:///workspaces/heartkit/heartkit/tasks/denoise/evaluate.py\u001b\\\u001b[2mevaluate.py\u001b[0m\u001b]8;;\u001b\\\u001b[2m:\u001b[0m\u001b]8;id=218337;file:///workspaces/heartkit/heartkit/tasks/denoise/evaluate.py#37\u001b\\\u001b[2m37\u001b[0m\u001b]8;;\u001b\\\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "task.evaluate(params)\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Export model to TF Lite / TFLM\n",
    "\n",
    "Once we have trained and evaluated the model, we need to export the model into a format that can be used for inference on the edge. Currently, we export the model to TensorFlow Lite flatbuffer format. This will also generate a C header file that can be used with TensorFlow Lite for Microcontrollers (TFLM).\n",
    "\n",
    "For this model, we will export as a 32-bit floating point model.\n",
    " \n",
    "__NOTE:__ We utilize `CONCRETE` mode to lower the model to concrete functions before converting. This is because TF (MLIR) fails to properly lower the dilated convolutional layers."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [],
   "source": [
    "quantization = hk.QuantizationParams(\n",
    "    enabled=True,\n",
    "    format=\"FP32\",\n",
    "    io_type=\"float32\",\n",
    "    conversion=\"CONCRETE\",\n",
    ")\n",
    "params.quantization = quantization"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "
INFO     Creating synthetic dataset cache with 5000 patients                                   ecg_synthetic.py:159\n",
       "
\n"
      ],
      "text/plain": [
       "\u001b[34mINFO    \u001b[0m Creating synthetic dataset cache with \u001b[1;36m5000\u001b[0m patients                                   \u001b]8;id=313048;file:///workspaces/heartkit/heartkit/datasets/ecg_synthetic.py\u001b\\\u001b[2mecg_synthetic.py\u001b[0m\u001b]8;;\u001b\\\u001b[2m:\u001b[0m\u001b]8;id=514688;file:///workspaces/heartkit/heartkit/datasets/ecg_synthetic.py#159\u001b\\\u001b[2m159\u001b[0m\u001b]8;;\u001b\\\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "
\n"
      ],
      "text/plain": []
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "
[08/16/24 20:02:23] WARNING  WARNING:absl:Please consider providing the trackable_obj argument in the  lite.py:2166\n",
       "                             from_concrete_functions. Providing without the trackable_obj argument is              \n",
       "                             deprecated and it will use the deprecated conversion path.                            \n",
       "
\n"
      ],
      "text/plain": [
       "\u001b[2;36m[08/16/24 20:02:23]\u001b[0m\u001b[2;36m \u001b[0m\u001b[31mWARNING \u001b[0m WARNING:absl:Please consider providing the trackable_obj argument in the  \u001b]8;id=520246;file:///workspaces/heartkit/.venv/lib/python3.12/site-packages/tensorflow/lite/python/lite.py\u001b\\\u001b[2mlite.py\u001b[0m\u001b]8;;\u001b\\\u001b[2m:\u001b[0m\u001b]8;id=384487;file:///workspaces/heartkit/.venv/lib/python3.12/site-packages/tensorflow/lite/python/lite.py#2166\u001b\\\u001b[2m2166\u001b[0m\u001b]8;;\u001b\\\n",
       "\u001b[2;36m                    \u001b[0m         from_concrete_functions. Providing without the trackable_obj argument is  \u001b[2m            \u001b[0m\n",
       "\u001b[2;36m                    \u001b[0m         deprecated and it will use the deprecated conversion path.                \u001b[2m            \u001b[0m\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "
INFO     Validating model results                                                                      export.py:83\n",
       "
\n"
      ],
      "text/plain": [
       "\u001b[34mINFO    \u001b[0m Validating model results                                                                      \u001b]8;id=941295;file:///workspaces/heartkit/heartkit/tasks/denoise/export.py\u001b\\\u001b[2mexport.py\u001b[0m\u001b]8;;\u001b\\\u001b[2m:\u001b[0m\u001b]8;id=727514;file:///workspaces/heartkit/heartkit/tasks/denoise/export.py#83\u001b\\\u001b[2m83\u001b[0m\u001b]8;;\u001b\\\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "I0000 00:00:1723838543.688860  751181 cuda_executor.cc:1015] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero. See more at https://github.com/torvalds/linux/blob/v6.0/Documentation/ABI/testing/sysfs-bus-pci#L344-L355\n",
      "I0000 00:00:1723838543.688944  751181 devices.cc:67] Number of eligible GPUs (core count >= 8, compute capability >= 0.0): 1\n",
      "I0000 00:00:1723838543.689113  751181 cuda_executor.cc:1015] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero. See more at https://github.com/torvalds/linux/blob/v6.0/Documentation/ABI/testing/sysfs-bus-pci#L344-L355\n",
      "I0000 00:00:1723838543.689169  751181 cuda_executor.cc:1015] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero. See more at https://github.com/torvalds/linux/blob/v6.0/Documentation/ABI/testing/sysfs-bus-pci#L344-L355\n",
      "I0000 00:00:1723838543.689214  751181 cuda_executor.cc:1015] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero. See more at https://github.com/torvalds/linux/blob/v6.0/Documentation/ABI/testing/sysfs-bus-pci#L344-L355\n",
      "I0000 00:00:1723838543.689287  751181 cuda_executor.cc:1015] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero. See more at https://github.com/torvalds/linux/blob/v6.0/Documentation/ABI/testing/sysfs-bus-pci#L344-L355\n",
      "I0000 00:00:1723838543.689333  751181 cuda_executor.cc:1015] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero. See more at https://github.com/torvalds/linux/blob/v6.0/Documentation/ABI/testing/sysfs-bus-pci#L344-L355\n",
      "W0000 00:00:1723838543.815333  751181 tf_tfl_flatbuffer_helpers.cc:392] Ignored output_format.\n",
      "W0000 00:00:1723838543.815348  751181 tf_tfl_flatbuffer_helpers.cc:395] Ignored drop_control_dependency.\n",
      "INFO: Created TensorFlow Lite XNNPACK delegate for CPU.\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "
INFO     [TF METRICS] LOSS=0.0396 MAE=0.1357 MSE=0.0396 RMSE=0.1991 COSINE=0.7178                      export.py:90\n",
       "
\n"
      ],
      "text/plain": [
       "\u001b[34mINFO    \u001b[0m \u001b[1m[\u001b[0mTF METRICS\u001b[1m]\u001b[0m \u001b[33mLOSS\u001b[0m=\u001b[1;36m0\u001b[0m\u001b[1;36m.0396\u001b[0m \u001b[33mMAE\u001b[0m=\u001b[1;36m0\u001b[0m\u001b[1;36m.1357\u001b[0m \u001b[33mMSE\u001b[0m=\u001b[1;36m0\u001b[0m\u001b[1;36m.0396\u001b[0m \u001b[33mRMSE\u001b[0m=\u001b[1;36m0\u001b[0m\u001b[1;36m.1991\u001b[0m \u001b[33mCOSINE\u001b[0m=\u001b[1;36m0\u001b[0m\u001b[1;36m.7178\u001b[0m                      \u001b]8;id=496666;file:///workspaces/heartkit/heartkit/tasks/denoise/export.py\u001b\\\u001b[2mexport.py\u001b[0m\u001b]8;;\u001b\\\u001b[2m:\u001b[0m\u001b]8;id=35165;file:///workspaces/heartkit/heartkit/tasks/denoise/export.py#90\u001b\\\u001b[2m90\u001b[0m\u001b]8;;\u001b\\\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "
INFO     [TFL METRICS] LOSS=0.0396 MAE=0.1357 MSE=0.0396 RMSE=0.1991 COSINE=0.7177                     export.py:91\n",
       "
\n"
      ],
      "text/plain": [
       "\u001b[34mINFO    \u001b[0m \u001b[1m[\u001b[0mTFL METRICS\u001b[1m]\u001b[0m \u001b[33mLOSS\u001b[0m=\u001b[1;36m0\u001b[0m\u001b[1;36m.0396\u001b[0m \u001b[33mMAE\u001b[0m=\u001b[1;36m0\u001b[0m\u001b[1;36m.1357\u001b[0m \u001b[33mMSE\u001b[0m=\u001b[1;36m0\u001b[0m\u001b[1;36m.0396\u001b[0m \u001b[33mRMSE\u001b[0m=\u001b[1;36m0\u001b[0m\u001b[1;36m.1991\u001b[0m \u001b[33mCOSINE\u001b[0m=\u001b[1;36m0\u001b[0m\u001b[1;36m.7177\u001b[0m                     \u001b]8;id=70190;file:///workspaces/heartkit/heartkit/tasks/denoise/export.py\u001b\\\u001b[2mexport.py\u001b[0m\u001b]8;;\u001b\\\u001b[2m:\u001b[0m\u001b]8;id=68341;file:///workspaces/heartkit/heartkit/tasks/denoise/export.py#91\u001b\\\u001b[2m91\u001b[0m\u001b]8;;\u001b\\\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "
INFO     Validation passed (0.0000)                                                                    export.py:99\n",
       "
\n"
      ],
      "text/plain": [
       "\u001b[34mINFO    \u001b[0m Validation passed \u001b[1m(\u001b[0m\u001b[1;36m0.0000\u001b[0m\u001b[1m)\u001b[0m                                                                    \u001b]8;id=375015;file:///workspaces/heartkit/heartkit/tasks/denoise/export.py\u001b\\\u001b[2mexport.py\u001b[0m\u001b]8;;\u001b\\\u001b[2m:\u001b[0m\u001b]8;id=497680;file:///workspaces/heartkit/heartkit/tasks/denoise/export.py#99\u001b\\\u001b[2m99\u001b[0m\u001b]8;;\u001b\\\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# TF dumps a lot of info to stdout, so we redirect it to /dev/null\n",
    "with open(os.devnull, 'w') as devnull:\n",
    "    with contextlib.redirect_stdout(devnull), contextlib.redirect_stderr(devnull):\n",
    "        task.export(params)\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## ECG Denoising Demo\n",
    "\n",
    "Finally, we will demonstrate how to use the trained ECG denoiser model to remove noise and artifacts from raw ECG signals. We will load a sample ECG signal, add noise to it, and then denoise it using the trained model. We will visualize the original, noisy, and denoised ECG signals to compare the results."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [],
   "source": [
    "model = nse.models.load_model(params.model_file)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 9ms/step\n"
     ]
    }
   ],
   "source": [
    "ecg = next(ds_gen)\n",
    "aug_ecg = augmenter(preprocessor(keras.ops.convert_to_tensor(np.reshape(ecg, (1, -1, 1)))), training=True).numpy().squeeze()\n",
    "clean_ecg = model.predict(np.reshape(aug_ecg, (1, -1, 1)))\n",
    "snr = nse.metrics.Snr()\n",
    "snr.update_state(ecg.reshape(1, -1, 1), aug_ecg.reshape(1, -1, 1))\n",
    "aug_snr = snr.result().numpy()\n",
    "snr.reset_state()\n",
    "snr.update_state(ecg.reshape(1, -1, 1), clean_ecg.reshape(1, -1, 1))\n",
    "clean_snr = snr.result().numpy()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "
"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "fig, ax = plt.subplots(3, 1, figsize=(9, 5), sharex=True)\n",
    "ax[0].plot(ts, ecg.squeeze(), color=plot_theme.primary_color, lw=3)\n",
    "ax[1].plot(ts, aug_ecg.squeeze(), color=plot_theme.secondary_color, lw=3)\n",
    "ax[2].plot(ts, clean_ecg.squeeze(), color=plot_theme.tertiary_color, lw=3)\n",
    "\n",
    "ax[0].set_ylabel(\"Reference\")\n",
    "ax[1].set_ylabel(\"Noisy\")\n",
    "ax[2].set_ylabel(\"Denoised\")\n",
    "\n",
    "ax[1].text(0.98, 0.15, f\"{aug_snr:4.02f} dB SNR\", transform=ax[1].transAxes, ha=\"right\", va=\"top\", weight='bold')\n",
    "ax[2].text(0.98, 0.15, f\"{clean_snr:4.02f} dB SNR\", transform=ax[2].transAxes, ha=\"right\", va=\"top\", weight='bold')\n",
    "# Disable y-axis ticks for all plots\n",
    "for axes in ax:\n",
    "    axes.yaxis.set_ticks([])\n",
    "ax[-1].set_xlabel(\"Time (s)\")\n",
    "fig.suptitle(\"ECG Denoising Demo\")\n",
    "fig.tight_layout()\n",
    "fig.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": ".venv",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.12.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}