djl
djl copied to clipboard
pytorch and djl
if the return value of forwards function in pytorch is a tuple of some tensors with different dimensions,what should i do to deal with such a problem in DJL lib in java
@yufengsjtu
If the output is complicated data type that DJL is not able to automatically map it to NDList
, you have to use IValue
directly. see: https://github.com/deepjavalibrary/djl/blob/master/engines/pytorch/pytorch-engine/src/test/java/ai/djl/pytorch/integration/IValueTest.java#L201