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.
Model licenses are specific to each release and its data sources. Public downloads do not imply commercial-use permission or a BSD license for weights. See the licensing policy; historical models have not yet received a complete per-artifact provenance and licensing review.
The following table provides the latest performance and accuracy results for sleep detection models.
| NAME | LOCATION | # CLASSES | MODEL | PARAMS | FLOPS | ACCURACY | AP |
|---|---|---|---|---|---|---|---|
| SD-2-TCN-SM | Wrist | 2 | TCN | 9K | 1.5M/hr | 95.9% | 94.5% |
The following table provides the latest performance and accuracy results for sleep staging models.
| NAME | LOCATION | # CLASSES | MODEL | PARAMS | FLOPS | ACCURACY | AP |
|---|---|---|---|---|---|---|---|
| SS-2-TCN-SM | Wrist | 2 | TCN | 10K | 1.7M/hr | 88.9% | 96.0% |
| SS-3-TCN-SM | Wrist | 3 | TCN | 11K | 1.9M/hr | 84.4% | 91.8% |
| SS-4-TCN-SM | Wrist | 4 | TCN | 26K | 4.2M/hr | 75.5% | 81.6% |
| SS-5-TCN-SM | Wrist | 5 | TCN | 28K | 4.6M/hr | 68.4% | 74.1% |
The following table provides the latest performance and accuracy results for sleep apnea detection models.
| NAME | LOCATION | # CLASSES | MODEL | PARAMS | FLOPS | ACCURACY | F1 |
|---|---|---|---|---|---|---|---|
| SA-2-TCN-SM | Wrist | 2 | TCN | 5K | 20M/hr | 91.0% | 91.0% |