How can I use Multitask Classification model?

[kty5177]

Please provide the following information when requesting support.

• Hardware (T4/V100/Xavier/Nano/etc)
• Network Type (Detectnet_v2/Faster_rcnn/Yolo_v4/LPRnet/Mask_rcnn/Classification/etc)
• TLT Version (Please run “tlt info --verbose” and share “docker_tag” here)
• Training spec file(If have, please share here)
• How to reproduce the issue ? (This is for errors. Please share the command line and the detailed log here.)

Hi all,
How can I use multitask image classification model (NVIDIA TAO Documentation) in tlt v3.0?
There is no sample code or jupyter notebook in that (tlt-streamanalytics:v3.0-dp-py3) docker image.
Also, It doesn’t work with commnad “tlt multitask_classification ~” in same environment.
Should I use different docker image? or Is it not supported yet?
Thank you.

[Morganh]

Multitask is available in 3.0 docker instead of 3.0-dp docker.
You need to update the tlt version.

pip3 install --upgrade nvidia-tlt

Please download jupyter notebook from https://docs.nvidia.com/tlt/tlt-user-guide/text/tlt_quick_start_guide.html#use-the-examples

wget --content-disposition https://api.ngc.nvidia.com/v2/resources/nvidia/tlt_cv_samples/versions/v1.1.0/zip -O tlt_cv_samples_v1.1.0.zip
unzip -u tlt_cv_samples_v1.1.0.zip -d ./tlt_cv_samples_v1.1.0 && rm -rf tlt_cv_samples_v1.1.0.zip && cd ./tlt_cv_samples_v1.1.0

More info is in https://docs.nvidia.com/tlt/tlt-user-guide/text/multitask_image_classification.html