This was talked about in another issue (#30) but I would like to make this a seperate topic.
PR: #44

Works great with yolo4v but does not work with yolov4-tiny.
For reference: I am using the standard yolov4-tiny that is packaged with the repo.

nvidia@nvidia:~/tkDNN$ python3 darknetTR.py build/yolo4tiny_fp16.rt --video=demo/yolo_test.mp4
build/yolo4tiny_fp16.rt
New NetworkRT (TensorRT v6.01)
Float16 support: 1
Int8 support: 1
DLAs: 2
Cant deserialize Plugin
/home/nvidia/tkDNN/src/NetworkRT.cpp:821
Aborting...

As far as I am concerned, the c++ api and python api call the same code:
detNN->init(net, n_classes, n_batch);

Is there anything I should test or change? I really can't locate why this would happen since building and running the FP16 on C++ works perfect.