| | |
| | | y = self.decoder(h) |
| | | return y |
| | | |
| | | |
| | | def export_dummy_inputs(self): |
| | | length = 120 |
| | | text_indexes = torch.randint(0, self.embed.num_embeddings, (2, length)).type(torch.int32) |
| | | text_lengths = torch.tensor([length-20, length], dtype=torch.int32) |
| | | return (text_indexes, text_lengths) |
| | | |
| | | |
| | | def export_input_names(self): |
| | | return ['inputs', 'text_lengths'] |
| | | return ["inputs", "text_lengths"] |
| | | |
| | | |
| | | def export_output_names(self): |
| | | return ['logits'] |
| | | return ["logits"] |
| | | |
| | | |
| | | def export_dynamic_axes(self): |
| | | return { |
| | | 'inputs': { |
| | | 0: 'batch_size', |
| | | 1: 'feats_length' |
| | | "inputs": {0: "batch_size", 1: "feats_length"}, |
| | | "text_lengths": { |
| | | 0: "batch_size", |
| | | }, |
| | | 'text_lengths': { |
| | | 0: 'batch_size', |
| | | }, |
| | | 'logits': { |
| | | 0: 'batch_size', |
| | | 1: 'logits_length' |
| | | }, |
| | | "logits": {0: "batch_size", 1: "logits_length"}, |
| | | } |
| | | |
| | | |
| | | def export_name(self): |
| | | return "model.onnx" |