I want to deploy object detection on ZYNQ104, but I am a fresh man on machine learning and FPGA, can I use emulator to do it? I do not have an FPGA yet, but I want to do experiment to compare it.
Before start working on actual FPGA, we could evaluate with TSIM (cycle-accurate simulation) in TVM; For experiments with vision models, please refer to Deploy Pretrained Vision Model from MxNet on VTA, and there you can setup SIM/TSIM based simulation of vision tasks like object detection.
I met some problems on MXNET, no module named mxnet, although I have pip install, but I can not import it from setting->interpreter. So are there any simple sample I can run asap about deploy object detection on FPGA through TVM ? Thank you so much. And how can I design experiment about TVM, for example, compared FPGA with gpu through tvm