* Execute the inference for the input tensors. * * @param inputs The input tensors, when there is single input for the model, * inputs param should be a Tensor. For models with multiple inputs, * inputs params should be in either Tensor[] if the input order is fixed, * or
(inputs: Tensor|Tensor[]|NamedTensorMap, config?: ModelPredictConfig)
| 91 | * for model with multiple outputs. Tensor[] is not used. |
| 92 | */ |
| 93 | predict(inputs: Tensor|Tensor[]|NamedTensorMap, config?: ModelPredictConfig): |
| 94 | Tensor|Tensor[]|NamedTensorMap { |
| 95 | setAssets(this.assets); |
| 96 | return this.graphModel.predict(inputs, config); |
| 97 | } |
| 98 | |
| 99 | /** |
| 100 | * Execute the inference for the input tensors and return activation |