Action recognition

• Hardware (T4/V100/Xavier/Nano/etc) - v100
• Network Type - action_recognition_net
• TLT Version (Please run “tlt info --verbose” and share “docker_tag” here)
format_version: 2.0
toolkit_version: 3.22.05
published_date: 05/25/2022

After successfully training the model I got an error while evaluating the trained model. Attaching the error screenshot below.

help me out. thanks!

You can refer to GPU-optimized AI, Machine Learning, & HPC Software | NVIDIA NGC

"=" in the checkpoint file name should removed before using the checkpoint in command.

can you explain a bit more…where I can find checkpoint file and where I have to make changes?

There is no update from you for a period, assuming this is not an issue anymore. Hence we are closing this topic. If need further support, please open a new one. Thanks

Can you share the result of below command?
$ tao action_recognition run cat /specs/evaluate_rgb_i3d.yaml

This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.