crowdkit.learning.crowd_layer.CrowdLayer
| Source code
CrowdLayer( self, num_labels: int, n_workers: int, conn_type: str = 'mw', device: Optional[device] = None, dtype: Optional[dtype] = None)
CrowdLayer module for classification tasks.
This method applies a worker-specific transformation of the logits. There are four types of transformations:
Filipe Rodrigues and Francisco Pereira. Deep Learning from Crowds.
Proceedings of the AAAI Conference on Artificial Intelligence, 32(1), 2018.
https://doi.org/10.1609/aaai.v32i1.11506
Examples:
from crowdkit.learning import CrowdLayerimport torchinput = torch.randn(3, 5)workers = torch.tensor([0, 1, 0])cl = CrowdLayer(5, 2, conn_type="mw")cl(input, workers)
Method | Description |
---|---|
forward | Forward pass. |
Last updated: March 31, 2023