Create lpr engine file
vinodbukya6 opened this issue · 7 comments
Hi, I am working on License plate recognition problem. When I run deepstream app i am facing following issue.
**Starting pipeline
0:00:00.209260524 226 0x1a87b20 INFO nvinfer gstnvinfer.cpp:638:gst_nvinfer_logger: NvDsInferContext[UID 3]: Info from NvDsInferContextImpl::buildModel() <nvdsinfer_context_impl.cpp:1914> [UID = 3]: Trying to create engine from model files
WARNING: [TRT]: onnx2trt_utils.cpp:364: Your ONNX model has been generated with INT64 weights, while TensorRT does not natively support INT64. Attempting to cast down to INT32.
WARNING: [TRT]: ShapedWeights.cpp:173: Weights td_dense/kernel:0 has been transposed with permutation of (1, 0)! If you plan on overwriting the weights with the Refitter API, the new weights must be pre-transposed.
WARNING: [TRT]: Tensor DataType is determined at build time for tensors not marked as input or output.
WARNING: [TRT]: Detected invalid timing cache, setup a local cache instead
python3: /dvs/p4/build/sw/rel/gpgpu/MachineLearning/myelin_trt8/src/compiler/optimizer/cublas_impl.cpp:477: void add_heuristic_results_to_tactics(std::vector<cublasLtMatmulHeuristicResult_t>&, std::vectormyelin::ir::tactic_attribute_t&, myelin::ir::tactic_attribute_t&, bool): Assertion `false && "Invalid size written"' failed.
Aborted (core dumped)**
I am using DS 6.0. Can anyone please help me on how to solve this issue?
0:00:01.256299095 30248 0x3a1bca0 WARN nvinfer gstnvinfer.cpp:635:gst_nvinfer_logger: NvDsInferContext[UID 3]: Warning from NvDsInferContextImpl::deserializeEngineAndBackend() <nvdsinfer_context_impl.cpp:1889> [UID = 3]: deserialize engine from file :/opt/nvidia/deepstream/deepstream-6.0/sources/deepstream_python_apps/deepstream_lpr_app/models/LP/LPR/us_lprnet_baseline18_deployable.etlt_b16_gpu0_fp16.engine failed
0:00:01.256360773 30248 0x3a1bca0 WARN nvinfer gstnvinfer.cpp:635:gst_nvinfer_logger: NvDsInferContext[UID 3]: Warning from NvDsInferContextImpl::generateBackendContext() <nvdsinfer_context_impl.cpp:1996> [UID = 3]: deserialize backend context from engine from file :/opt/nvidia/deepstream/deepstream-6.0/sources/deepstream_python_apps/deepstream_lpr_app/models/LP/LPR/us_lprnet_baseline18_deployable.etlt_b16_gpu0_fp16.engine failed, try rebuild
0:00:01.256391192 30248 0x3a1bca0 INFO nvinfer gstnvinfer.cpp:638:gst_nvinfer_logger: NvDsInferContext[UID 3]: Info from NvDsInferContextImpl::buildModel() <nvdsinfer_context_impl.cpp:1914> [UID = 3]: Trying to create engine from model files
WARNING: [TRT]: onnx2trt_utils.cpp:364: Your ONNX model has been generated with INT64 weights, while TensorRT does not natively support INT64. Attempting to cast down to INT32.
WARNING: [TRT]: ShapedWeights.cpp:173: Weights td_dense/kernel:0 has been transposed with permutation of (1, 0)! If you plan on overwriting the weights with the Refitter API, the new weights must be pre-transposed.
WARNING: [TRT]: Tensor DataType is determined at build time for tensors not marked as input or output.
WARNING: [TRT]: Detected invalid timing cache, setup a local cache instead
python3: /dvs/p4/build/sw/rel/gpgpu/MachineLearning/myelin_trt8/src/compiler/optimizer/cublas_impl.cpp:477: void add_heuristic_results_to_tactics(std::vector<cublasLtMatmulHeuristicResult_t>&, std::vectormyelin::ir::tactic_attribute_t&, myelin::ir::tactic_attribute_t&, bool): Assertion `false && "Invalid size written"' failed.
Aborted (core dumped)
The same error I am also facing.
Hi, edit -L -lnvinfer -L -lnvparsers in Makefile and make. It works fine.
yeah okay
@vinodbukya6 were you able to resolve ??
python3: /dvs/p4/build/sw/rel/gpgpu/MachineLearning/myelin_trt8/src/compiler/optimizer/cublas_impl.cpp:477: void add_heuristic_results_to_tactics(std::vector<cublasLtMatmulHeuristicResult_t>&, std::vectormyelin::ir::tactic_attribute_t&, myelin::ir::tactic_attribute_t&, bool): Assertion false && "Invalid size written"' failed.`
No, I am also facing the same issue. Not solved.
Hi @imSrbh, Any updates on the issue. Got any leads?
Hi, LPR engine file created using tlt-converter and followed mentioned steps.
Deepstream 5.1, cuda 11.1, TensorRT 7.2.
It's working fine for command:
python3 deepstream_lpr_app.py 1 2 0 file:///opt/nvidia/deepstream/deepstream-5.1/samples/streams/lpr-test1.mp4 out.mp4
Thank you so much.