- 新着としてマーク
- ブックマーク
- 購読
- ミュート
- RSS フィードを購読する
- ハイライト
- 印刷
- 不適切なコンテンツを報告
Haven't seen anything to suggest the NCS supports this, but just wanted to double check that there's no back prop support in the current API ( 2.05 ), and that any arbitrary layer in the model cannot be read out using updated weights.
Many thanks..
コピーされたリンク
2 返答(返信)
- 新着としてマーク
- ブックマーク
- 購読
- ミュート
- RSS フィードを購読する
- ハイライト
- 印刷
- 不適切なコンテンツを報告
@Jay The NCS is designed to be used with models that are ready for deployment, therefore there isn't any back propagation or training related support in the NCSDK. If any changes are to be made to the model (layers, weights, etc), it must be done before compiling the model for the NCSDK. Once a model is converted to a Movidius graph file format, changes cannot be made to the model.
