While Deepstream build the tensort engine I account this error.
Building the TensorRT Engine
ERROR: [TRT]: 10: Could not find any implementation for node conv_1 + batchnorm_1.
ERROR: [TRT]: 10: [optimizer.cpp::computeCosts::3869] Error Code 10: Internal Error (Could not find any implementation for node conv_1 + batchnorm_1.)
Building engine failed
Failed to build CUDA engine
ERROR: ../nvdsinfer/nvdsinfer_model_builder.cpp:728 Failed to create network using custom network creation function
ERROR: ../nvdsinfer/nvdsinfer_model_builder.cpp:794 Failed to get cuda engine from custom library API
0:00:16.939002562 138382 0x61a3b6d5ad00 ERROR nvinfer gstnvinfer.cpp:676:gst_nvinfer_logger:<primary_gie> NvDsInferContext[UID 1]: Error in NvDsInferContextImpl::buildModel() <nvdsinfer_context_impl.cpp:2126> [UID = 1]: build engine file failed
0:00:16.944859996 138382 0x61a3b6d5ad00 ERROR nvinfer gstnvinfer.cpp:676:gst_nvinfer_logger:<primary_gie> NvDsInferContext[UID 1]: Error in NvDsInferContextImpl::generateBackendContext() <nvdsinfer_context_impl.cpp:2212> [UID = 1]: build backend context failed
0:00:16.944918082 138382 0x61a3b6d5ad00 ERROR nvinfer gstnvinfer.cpp:676:gst_nvinfer_logger:<primary_gie> NvDsInferContext[UID 1]: Error in NvDsInferContextImpl::initialize() <nvdsinfer_context_impl.cpp:1351> [UID = 1]: generate backend failed, check config file settings
I using docker container with image nvcr.io/nvidia/deepstream:6.4-gc-triton-devel.
Here is nvidia-smi inside container.
Mon Oct 14 04:05:41 2024
+-----------------------------------------------------------------------------------------+
| NVIDIA-SMI 560.35.03 Driver Version: 560.35.03 CUDA Version: 12.6 |
|-----------------------------------------+------------------------+----------------------+
| GPU Name Persistence-M | Bus-Id Disp.A | Volatile Uncorr. ECC |
| Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. |
| | | MIG M. |
|=========================================+========================+======================|
| 0 Tesla M40 24GB Off | 00000000:02:00.0 Off | 0 |
| N/A 71C P0 157W / 250W | 3177MiB / 23040MiB | 95% Default |
| | | N/A |
+-----------------------------------------+------------------------+----------------------+
+-----------------------------------------------------------------------------------------+
| Processes: |
| GPU GI CI PID Type Process name GPU Memory |
| ID ID Usage |
|=========================================================================================|
+-----------------------------------------------------------------------------------------+