Triton server inference model placement

• Hardware Platform (Jetson / GPU) tesla T4
• DeepStream Version 6.1
• JetPack Version (valid for Jetson only)
• TensorRT Version 7.1
• NVIDIA GPU Driver Version (valid for GPU only) tesla T4

im using the docker nvcr.io/nvidia/tritonserver:22.01-py3

i do not see model loaded , could you let me in whcih folder it has to placed
------------------------------------------------±-------+

I0218 01:50:30.783690 1 server.cc:589]
±------±--------±-------+
| Model | Version | Status |
±------±--------±-------+
±------±--------±-------+

I0218 01:50:30.783794 1 tritonserver.cc:1865]
±---------------------------------±--------

its working now .

Could some one tell me which python file from the client has to be referred for Video Inferencing . ???

root@ip-172-31-11-102:/workspace/install/python# ls
ensemble_image_client.py simple_grpc_custom_repeat.py simple_http_health_metadata.py
grpc_client.py simple_grpc_health_metadata.py simple_http_infer_client.py
grpc_explicit_byte_content_client.py simple_grpc_infer_client.py simple_http_model_control.py
grpc_explicit_int8_content_client.py simple_grpc_model_control.py simple_http_sequence_sync_infer_client.py
grpc_explicit_int_content_client.py simple_grpc_sequence_stream_infer_client.py simple_http_shm_client.py
grpc_image_client.py simple_grpc_sequence_sync_infer_client.py simple_http_shm_string_client.py
image_client.py simple_grpc_shm_client.py simple_http_string_infer_client.py
memory_growth_test.py simple_grpc_shm_string_client.py tritonclient-2.18.0-py3-none-any.whl
reuse_infer_objects_client.py simple_grpc_string_infer_client.py tritonclient-2.18.0-py3-none-manylinux1_x86_64.whl
simple_grpc_async_infer_client.py simple_http_async_infer_client.py
simple_grpc_cudashm_client.py simple_http_cudashm_client.py

could someone tell , how ‘model.plan’ has to be configured . i have a ‘TLT model’ , And i have to create model Repository structure .

i get the below error

I0219 17:15:07.642644 1 server.cc:589]
±-----------------±-----+
| Repository Agent | Path |
±-----------------±-----+
±-----------------±-----+

I0219 17:15:07.642597 1 server.cc:546]
±------------±------------------------------------------------------------------------±-------+
| Backend | Path | Config |
±------------±------------------------------------------------------------------------±-------+
| pytorch | /opt/tritonserver/backends/pytorch/libtriton_pytorch.so | {} |
| tensorflow | /opt/tritonserver/backends/tensorflow1/libtriton_tensorflow1.so | {} |
| onnxruntime | /opt/tritonserver/backends/onnxruntime/libtriton_onnxruntime.so | {} |
| openvino | /opt/tritonserver/backends/openvino_2021_2/libtriton_openvino_2021_2.so | {} |
±------------±------------------------------------------------------------------------±-------+

I0219 17:15:07.642644 1 server.cc:589]
±--------------±--------±--------------------------------------------------------+
| Model | Version | Status |
±--------------±--------±--------------------------------------------------------+
| Helmet_model | 1 | UNAVAILABLE: Internal: unable to create TensorRT engine |
| densenet_onnx | 1 | READY |
±--------------±--------±--------------------------------------------------------+

I0219 17:15:07.642756 1 tritonserver.cc:1865]
±---------------------------------±---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
| Option | Value |
±---------------------------------±---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
| server_id | triton |
| server_version | 2.18.0 |
| server_extensions | classification sequence model_repository model_repository(unload_dependents) schedule_policy model_configuration system_shared_memory cuda_shared_memory binary_tensor_data statistics |
| model_repository_path[0] | /models |
| model_control_mode | MODE_NONE |
| strict_model_config | 1 |
| rate_limit | OFF |
| pinned_memory_pool_byte_size | 268435456 |
| cuda_memory_pool_byte_size{0} | 67108864 |
| response_cache_byte_size | 0 |
| min_supported_compute_capability | 6.0 |
| strict_readiness | 1 |
| exit_timeout | 30 |
±---------------------------------±-----------------------------------------------------------------------------------------------------------------------------------

Hi @h9945394143
Sorry for delay! Will check and reply ASAP.

Moving this topic to TAO forum.

@h9945394143
Could you please follow Integrating TAO CV Models with Triton Inference Server — TAO Toolkit 3.21.11 documentation ?

sure will follow it ,

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