search

ceccocats / tkDNN

Deep neural network library and toolkit to do high performace inference on NVIDIA jetson platforms
GNU General Public License v2.0
718 stars 209 forks source link

NetworkRT doesn't support 2D input and output layers #175

Open nightduck opened 3 years ago

nightduck commented 3 years ago

The layers used in the dataDim_t struct is naturally 5 dimensional. NetworkRT reduces them to 3 by filling dimensions in with a 1. Eg 1x224x224x3x1. However, calling getBindingDimensions on a layer will return a struct that pads it with zeros, due to a quirk of a TensorRT call. dataDim_t has a method that will return the total number of elements in it, but if a dimension is zero, this total is always zero. So all 2D layers look empty.

I'm submitted a pull request so the dataDim_t struct can be initialized in a way to correct these zeros into ones.

mive93 commented 3 years ago

Thank you, we'll look into that in the next days