Model Card for ECGDenoiserNL

• Collection: NeuralLib: Deep Learning Models for Biosignals Processing

• Description: GRU-based model for ECG peak detection

{
    "architecture": "GRUseq2seq",
    "model_name": "ECGDenoiserNL",
    "train_dataset": "ptb-xl+mit-bih-noise",
    "task": "ecg denoising",
    "gpu_model": "NVIDIA RTX 6000 Ada Generation",
    "epochs": 68,
    "optimizer": "Adam (\nParameter Group 0\n    amsgrad: False\n    betas: (0.9, 0.999)\n    capturable: False\n    differentiable: False\n    eps: 1e-08\n    foreach: None\n    fused: None\n    initial_lr: 0.005\n    lr: 0.005\n    maximize: False\n    weight_decay: 1e-05\n)",
    "learning_rate": 0.005,
    "validation_loss": 0.002906219568103552,
    "training_time": 6940.027687549591,
    "retraining": false
}


## Hyperparameters

bidirectional: true
dropout: 0
hid_dim: 64
learning_rate: 0.005
model_name: ECGDenoiserNL
multi_label: false
n_features: 1
n_layers: 2
num_classes: NA
task: regression


# Example

import torch

from production_models import ECGDenoiserNL

model = ECGDenoiserNL()

signal = torch.rand(1, 100, 1)  # Example input signal

predictions = model.predict(signal)

print(predictions)