search

nvdla / vp

Virtual Platform for NVDLA
Other
136 stars 81 forks source link

object detection inference #22

Open Adithyak1998 opened 6 years ago

Adithyak1998 commented 6 years ago

In what format can we expect the object detection inference output (output.dimg) to be? Are both the coordinates and the labels supposed to be in the same output file?

And what is the significance on negative numbers in the output. In my result, I got all negative numbers. Does it mean that there was no object found?

output_vp

zhouweiscut commented 5 years ago

hi, how do you open file output.dimg ? gedit ? i run ./nvdla_runtime and it shows "test pass", but when i open output.dimg with vim, it comes out messy code.

shgoupf commented 5 years ago

hi, how do you open file output.dimg ? gedit ? i run ./nvdla_runtime and it shows "test pass", but when i open output.dimg with vim, it comes out messy code.

Use --rawdump in nvdla_runtime you will get the output in readable text format.