Skip to content

Index

Foundation Task API

The objective of this task is to create a foundation model that can be used to build downstream models for other tasks. In heartKIT, the foundation model is trained using SimCLR- using two augmented leads as input.

Classes:

Classes

FoundationTask

heartKIT Foundation Task

Functions

train staticmethod 
train(params: HKTaskParams)

Train model for foundation task using SimCLR

Parameters:

Source code in heartkit/tasks/foundation/__init__.py 
25
26
27
28
29
30
31
32
@staticmethod
def train(params: HKTaskParams):
    """Train model for foundation task using SimCLR

    Args:
        params (HKTaskParams): Task parameters
    """
    train(params)
evaluate staticmethod 
evaluate(params: HKTaskParams)

Evaluate model for foundation task using SimCLR

Parameters:

Source code in heartkit/tasks/foundation/__init__.py 
34
35
36
37
38
39
40
41
@staticmethod
def evaluate(params: HKTaskParams):
    """Evaluate model for foundation task using SimCLR

    Args:
        params (HKTaskParams): Task parameters
    """
    evaluate(params)
export staticmethod 
export(params: HKTaskParams)

Export foundation task model

Parameters:

Source code in heartkit/tasks/foundation/__init__.py 
43
44
45
46
47
48
49
50
@staticmethod
def export(params: HKTaskParams):
    """Export foundation task model

    Args:
        params (HKTaskParams): Task parameters
    """
    export(params)
demo staticmethod 
demo(params: HKTaskParams)

Run demo for foundation task model

Parameters:

Source code in heartkit/tasks/foundation/__init__.py 
52
53
54
55
56
57
58
59
@staticmethod
def demo(params: HKTaskParams):
    """Run demo for foundation task model

    Args:
        params (HKTaskParams): Task parameters
    """
    demo(params)