Description
I am creating a trash pickup robot for my school’s engineering program. Right now, I am using the jetson orin nano and the jetson-inference project in order to create a trash detection model. Right now, I am having trouble because I can only import custom datasets from open images v7, but I would like to access more datasets, as open images has a limited number of classes, and I only find a few of them to be useful. The problem is that the system runs uses csv files and I was wondering if there was a way to add files from online in bulk.
Environment
TensorRT Version:
GPU Type: 1024-core NVIDIA Ampere architecture GPU with 32 Tensor Cores
Nvidia Driver Version: Jetson Linux 36.4
CUDA Version:
CUDNN Version:
Operating System + Version: Jetson orin nano
Python Version (if applicable): 3
TensorFlow Version (if applicable):
PyTorch Version (if applicable):
Baremetal or Container (if container which image + tag):
RePlease attach or include links to any models, data, files, or scripts necessary to reproduce your issue. (Github repo, Google Drive, Dropbox, etc.)Relevant Files
i am using jetson-inference/docs/pytorch-ssd.md at c038530ebf718e6867c4458c3e439406020732ff · dusty-nv/jetson-inference · GitHub as my guide