Is it possible to expose the tensor of intermediate layers?

I want to access the raw tensors of any layer in a network. Is this possible using the DeepStream Python bindings? or even C++ code?

There is no update from you for a period, assuming this is not an issue anymore. Hence we are closing this topic. If need further support, please open a new one. Thanks

Hi @amr.mustafa ,
Currently, DeepStream only supports to expose the tensor data of the network output layer. You can set the layer you want to expose to be output layer using “output-blob-names=” option in nvinfer plugin, and then get the tensor data.


This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.