Failed to create network using custom network creation function (TAO models)

Accelerated Computing Intelligent Video Analytics TAO Toolkit
,
#1

Hi, I have use the Emotion, Facenet and Faciallandmark model in my graph and everything run smoothly before I build the container image. This is the error message when running the container image.

NvDsInferCudaEngineGetFromTltModel: Failed to open TLT encoded model file /opt/nvidia/deepstream/deepstream-6.0/samples/models/tao_pretrained_models
ERROR: …/nvdsinfer/nvdsinfer_model_builder.cpp:724 Failed to create network using custom network creation function
ERROR: …/nvdsinfer/nvdsinfer_model_builder.cpp:789 Failed to get cuda engine from custom library API
0:00:00.466387509 1 0x7f95f58224a0 ERROR nvinfer gstnvinfer.cpp:632:gst_nvinfer_logger:<nvinfer_bin_nvinfer> NvDsInferContext[UID 2]: Error in NvDsInferContextImpl::buildModel() <nvdsinfer_context_impl.cpp:1934> [UID = 2]: build engine file failed

What could be the possible reasons for this? Thanks.

#2

Make sure the key is correct in each config file.

#3

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