Interface API
Reference information for the Interface
API.
eva.Interface
A high-level interface for training and validating a machine learning model.
This class provides a convenient interface to connect a model, data, and trainer to train and validate a model.
fit
Perform model training and evaluation out-of-place.
This method uses the specified trainer to fit the model using the provided data.
Example use cases:
- Using a model consisting of a frozen backbone and a head, the backbone will generate the embeddings on the fly which are then used as input features to train the head on the downstream task specified by the given dataset.
- Fitting only the head network using a dataset that loads pre-computed embeddings.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
trainer |
Trainer
|
The base trainer to use but not modify. |
required |
model |
ModelModule
|
The model module to use but not modify. |
required |
data |
DataModule
|
The data module. |
required |
Source code in src/eva/core/interface/interface.py
predict
Perform model prediction out-of-place.
This method performs inference with a pre-trained foundation model to compute embeddings.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
trainer |
Trainer
|
The base trainer to use but not modify. |
required |
model |
ModelModule
|
The model module to use but not modify. |
required |
data |
DataModule
|
The data module. |
required |
Source code in src/eva/core/interface/interface.py
predict_fit
Combines the predict and fit commands in one method.
This method performs the following two steps: 1. predict: perform inference with a pre-trained foundation model to compute embeddings. 2. fit: training the head network using the embeddings generated in step 1.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
trainer |
Trainer
|
The base trainer to use but not modify. |
required |
model |
ModelModule
|
The model module to use but not modify. |
required |
data |
DataModule
|
The data module. |
required |