Error when customizing the deepstream_tlt_apps

Accelerated Computing Intelligent Video Analytics TAO Toolkit
1

Hi, I was running the sample app in this git repo. I ran the sample config with the given pretrained model on Xavier successfully. But when I move my customized tlt 2.0 trained model to the sample app and ran the same command

dewei@dewei-desktop:~/deepstream_tlt_apps$ ./deepstream-custom -c pgie_yolo_tlt_config.txt -i /home/dewei/deepstream_tlt_apps/outfile.h264 -b 1 -d
Now playing: pgie_yolo_tlt_config.txt

as the given config and model, I got stuck with the following error message:

Using winsys: x11 
Opening in BLOCKING MODE 
0:00:00.211150899 24086   0x55876bd4c0 INFO                 nvinfer gstnvinfer.cpp:602:gst_nvinfer_logger:<primary-nvinference-engine> NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::buildModel() <nvdsinfer_context_impl.cpp:1591> [UID = 1]: Trying to create engine from model files
ERROR: [TRT]: UffParser: Could not read buffer.
parseModel: Failed to parse UFF model
ERROR: failed to build network since parsing model errors.
ERROR: Failed to create network using custom network creation function
ERROR: Failed to get cuda engine from custom library API
0:00:01.526612825 24086   0x55876bd4c0 ERROR                nvinfer gstnvinfer.cpp:596:gst_nvinfer_logger:<primary-nvinference-engine> NvDsInferContext[UID 1]: Error in NvDsInferContextImpl::buildModel() <nvdsinfer_context_impl.cpp:1611> [UID = 1]: build engine file failed
Bus error (core dumped)

I attached my configyolo_labels.txt (136 Bytes) and label.txt below. Thanks.pgie_yolo_tlt_config.txt (2.6 KB)

I cannot upload my custom tlt trained model because it’s not allowed by the forum system.

3

Please try again with your own key. Below should be your key during your training.

tlt-model-key=nvidia_tlt

5

hi! I got the same question:

ERROR: …/nvdsinfer/nvdsinfer_func_utils.cpp:31 [TRT]: UffParser: Could not read buffer.
parseModel: Failed to parse UFF model
ERROR: tlt/tlt_decode.cpp:274 failed to build network since parsing model errors.
ERROR: …/nvdsinfer/nvdsinfer_model_builder.cpp:797 Failed to create network using custom network creation function
ERROR: …/nvdsinfer/nvdsinfer_model_builder.cpp:862 Failed to get cuda engine from custom library API
0:00:00.545433637 22197 0x557ef7243780 ERROR nvinfer gstnvinfer.cpp:596:gst_nvinfer_logger:<primary_gie> NvDsInferContext[UID 1]: Error in NvDsInferContextImpl::buildModel() <nvdsinfer_context_impl.cpp:1611> [UID = 1]: build engine file failed

I wrote my api_key in the config file :
tlt-model-key=bTVydDMwZzRlNjgz####################0OGI4LTk3OGItZmVjZGNlZDQxOWU3

6

Your error seems to be similar to TLT-deepstream sample app error - #26 by wdw0908.
Please check if it helps.