Downstream model forward pass, input X will be the (batched) output from self.input_transform
(self, X)
| 121 | return sum(p.numel() for p in self.parameters() if p.requires_grad) |
| 122 | |
| 123 | def forward(self, X): |
| 124 | """ |
| 125 | Downstream model forward pass, input X will be the (batched) output from self.input_transform |
| 126 | """ |
| 127 | raise NotImplementedError('Base model is an abstract class!') |
| 128 | |
| 129 | def raw_predict(self, X) -> Dict[str, Tensor]: |
| 130 | X_feats = X['data'] |
nothing calls this directly
no outgoing calls
no test coverage detected