Tao: error: invalid choice: 'tlt-converter'

[EbinJose]

TensorRT Version7.2.1.6
Quadro RTX 5000 dual GPU
Driver Version: 455.23.05
CUDA Version: 11.1
Ubuntu 18.04
python 3.6
Yolo_v4

nvidia/tao/tao-toolkit-tf:
docker_registry: nvcr.io
docker_tag: v3.21.08-py3

I am converting etlt to trt and using yolo v4 sample

> # Convert to TensorRT engine (INT8).
> !tlt tlt-converter  -k $KEY  \
>                     -d 3,384,1248 \
>                     -o BatchedNMS \
>                     -c $USER_EXPERIMENT_DIR/export/cal.bin \
>                     -e $USER_EXPERIMENT_DIR/export/trt.engine \
>                     -b 8 \
>                     -m 16 \
>                     -t int8 \
>                     -i nchw \
>                     $USER_EXPERIMENT_DIR/export/yolov4_resnet18_epoch_070.etlt

/home/vaaan/.local/lib/python3.7/site-packages/tlt/init.py:20: DeprecationWarning:
The nvidia-tlt package will be deprecated soon. Going forward please migrate to using the nvidia-tao package.

warnings.warn(message, DeprecationWarning)
~/.tao_mounts.json wasn’t found. Falling back to obtain mount points and docker configs from ~/.tlt_mounts.json.
Please note that this will be deprecated going forward.
usage: tao [-h]
{list,stop,info,augment,bpnet,classification,converter,detectnet_v2,dssd,emotionnet,faster_rcnn,fpenet,gazenet,gesturenet,heartratenet,intent_slot_classification,lprnet,mask_rcnn,multitask_classification,n_gram,punctuation_and_capitalization,question_answering,retinanet,speech_to_text,speech_to_text_citrinet,ssd,text_classification,token_classification,unet,yolo_v3,yolo_v4}
…
tao: error: invalid choice: ‘tlt-converter’ (choose from ‘list’, ‘stop’, ‘info’, ‘augment’, ‘bpnet’, ‘classification’, ‘converter’, ‘detectnet_v2’, ‘dssd’, ‘emotionnet’, ‘faster_rcnn’, ‘fpenet’, ‘gazenet’, ‘gesturenet’, ‘heartratenet’, ‘intent_slot_classification’, ‘lprnet’, ‘mask_rcnn’, ‘multitask_classification’, ‘n_gram’, ‘punctuation_and_capitalization’, ‘question_answering’, ‘retinanet’, ‘speech_to_text’, ‘speech_to_text_citrinet’, ‘ssd’, ‘text_classification’, ‘token_classification’, ‘unet’, ‘yolo_v3’, ‘yolo_v4’)

I am getting this error. can you help me solve this

[Morganh]

Please follow latest user guide. Migrating to TAO Toolkit — TAO Toolkit 3.22.05 documentation
For v3.21.08-py3 model, it is ‘converter’.
The “tlt-converter” is the old one of “converter” inside the docker.

[EbinJose]

we can run inference using etlt right on my pc using deepstream

[Morganh]

Yes, user can deploy etlt model in deepstream and run inference.

[EbinJose]

do you have any documentation how to run inference on yoloV4 on deepstream

[Morganh]

https://docs.nvidia.com/tao/tao-toolkit/text/object_detection/yolo_v4.html#deploying-to-deepstream