Dumi Loghin

@hehaichi You can start by implementing the smart contracts for micro/macro benchmarks for that particular blockchain. As a guide, see the smart contract implementations for Ethereum and Hyperledger: https://github.com/ooibc88/blockbench/tree/master/benchmark/contracts

I observed something similar on (1) Nvidia Jetson Nano and (2) Nvidia RTX 2080 Ti with `ssd_mobilenet_v2_coco_2018_03_29` model. Native Tensorflow is about 3x and 10x faster than TensorRT model on...

\+ 1 here I tried to add support for au55n but I encountered some issues. Please see below. Looking at the project structure, we need to add the following for...