Converting efficientdet-tf1 trained model to deepstream engine

• Hardware (T4/V100/Xavier/Nano/etc)
• Network Type Efficientdet-tf1
• Tao version:

I am trying to convert Efficientdet-tf1 model to deepstream engine.
I tried to follow this command
efficientdet_tf1 gen_trt_engine. But the error is

efficientdet: error: invalid choice: 'gen_trt_engine' (choose from 'train', 'prune', 'inference', 'export', 'evaluate', 'dataset_convert')
root@cadf0713c5f7:/workspace/Nyan/tao_source_codes_v5.0.0/notebooks/tao_launcher_starter_kit/efficientdet_tf1/results/unpruned/export#                                   -r . \
>                                   -k nvidia_tao \
>                                   --data_type fp16 \
>                                   --engine_file model.etlt.onnx_b1_fp16.engine \
>                                   --max_batch_size 12 \
>                                   --min_batch_size 1 \
>                                   --opt_batch_size 1 \
>                                   --batch_size 1
bash: -r: command not found

Which command can I use?

I think you are running in tao pytorch container.
Please use tao deploy container instead.

I am using this container

Yes, it is not tao deploy container. You can use deploy container instead.

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