I would like to use TLT for people defection and deploy in my Jetson Nano.
I don’t have Nvidia enabled laptop or computer.
I couldn’t find any tutorials instructions as how to implement in Google Cloud or Amazon cloud platforms TLT?
Could anyone pls give me directions?
The TLT is designed to run on x86 systems with an NVIDIA GPU (e.g., GPU-powered workstation, DGX system) or can be run in any cloud with an NVIDIA GPU. For inference, models can be deployed on any edge device such as an embedded Jetson platform or in a data center with GPUs like T4 or A100.
End user can run TLT training via the cloud devices.
In forum, some users can have similar experiences.
His … My issue is … I have created a docker image for detectnet_v2 model on my GPU system. I am having my data and all related files on the GCP bucket. I am trying to run the docker such that it will create a directory inside the docker image and copy all the data/related files which are on the bucket inside that directory and start the training on my GPU system. I am sharing some screenshots which showed my dir structure:
this is my bucket where I am having all the files and images inside t…
Hardware Platform: GPU (Tesla T4)
DeepStream Version: 5.0
TensorRT Version: 188.8.131.52
NVIDIA GPU Driver Version: 440.33.01
Cuda Version: 10.2
Cudnn Version: 7.6.5
Ubuntu Version: 18.04
I installed deepstream and TensorRt and I’m trying to run some examples but I have a problem while trying to build the deepstream_tlt_apps:
make: Entering directory ‘/home/rockefella09/deepstream_tlt_apps/nvdsinfer_customparser_dssd_tlt’
g++ -o libnvds_infercustomparser_dssd_tlt.so nvdsinfer_custombboxp…
TLT Converter Fails
Question about running NGC for TLT3.0
TLT Detectnet TrafficCamNet training not working - #9 by Morganh
Errors in Training, 0 or Nan mAP, Low Loss, Tutorial Config