Model Zoo

A number of pre-trained models are available for download to use in your own project. These models are trained on the datasets listed below and are available in TensorFlow flatbuffer formats.

ECG Denoising

The following table provides the latest performance and accuracy results for denoising models.

NAME	DATASET	FS	DURATION	MODEL	PARAMS	FLOPS	METRIC
DEN-TCN-SM	Synthetic, PTB-XL	100Hz	2.5s	TCN	3.3K	1.0M	96.7% COSIM
DEN-TCN-LG	Synthetic, PTB-XL	100Hz	2.5s	TCN	6.3K	1.8M	97.4% COSIM

ECG Segmentation

The following table provides the latest performance and accuracy results for ECG segmentation models.

NAME	DATASET	FS	DURATION	# CLASSES	MODEL	PARAMS	FLOPS	METRIC
SEG-2-TCN-SM	Icentia11K, PTB-XL	100Hz	2.5s	2	TCN	4K	1.2M	96.9% IoU
SEG-4-TCN-SM	LUDB, Synthetic	100Hz	2.5s	4	TCN	7K	2.1M	78.7% IoU
SEG-4-TCN-LG	LUDB, Synthetic	100Hz	2.5s	4	TCN	10K	3.9M	80.2% IoU

Rhythm Classification

The following table provides the latest performance and accuracy results for rhythm classification models.

NAME	DATASET	FS	DURATION	# CLASSES	MODEL	PARAMS	FLOPS	METRIC
ARR-2-EFF-SM	Icentia11K, PTB-XL, LSAD	100Hz	5s	2	EfficientNetV2	18K	1.2M	99.5% F1
ARR-4-EFF-SM	LSAD	100Hz	5s	4	EfficientNetV2	39K	2.2M	95.3% F1

Beat Classification

The following table provides the latest performance and accuracy results for beat classification models.

NAME	DATASET	FS	DURATION	# CLASSES	MODEL	PARAMS	FLOPS	METRIC
BC-2-EFF-SM	Icentia11k	100Hz	5s	2	EfficientNetV2	28K	1.8M	97.5% F1
BC-3-EFF-SM	Icentia11k	100Hz	5s	3	EfficientNetV2	28K	1.8M	94.0% F1