nghiapq77/face-recognition-deepstream

This is a face recognition app built on DeepStream reference app.

face-recognition-deepstream's Issues

std::invalid_argument

I am trying to run the app but getting this error

./deepstream-app 
[INFO] Loading config...
terminate called after throwing an instance of 'std::invalid_argument'
  what():  stoi
Aborted (core dumped)

Configuration of json files

Hi, I'm trying to launch you repo and can't understand configuration of json files in /home/jetson/face/retina_arcface/data/
Show please the sample of this files.
If it makes any sens I'm using DS6.0 and Yolov5 as a detector

How can generate embedding file ?

I converted model file from .pth to .engine. But i can't generate embedding file .json and .txt.
Could anyone guide me to create .json and .txt from data my image?
Thank for help!

how to create input_embeddingsFile?

Hello, I'm working on your awesome project, i just converted pre-trained weights to trt, now i have trouble in creating input_embeddingsFile file, could you please help me to generate that?

How can I get the landmarks?

How do you scale the shape of input frame to [3,288,320]?

We need to scale the frame to fit the shape of input layer
I just found the offsets=104.0;117.0;123.0

Missing param in cublasLtMatmulDescCreate()

As I can see from official cublas document:
cublasStatus_t cublasLtMatmulDescCreate( cublasLtMatmulDesc_t *matmulDesc, cublasComputeType_t computeType, cudaDataType_t scaleType);
but in src/cosine_similarity.c, line 46:
checkCublasStatus(cublasLtMatmulDescCreate(&operationDesc, dataType));
It seems like you're missing one param there, doesn't it?
Environment: deepstream 5.1, cuda 11.1

output of retina model in custombboxparser

Em chào anh!
Em muốn hỏi về output của model retinaface vì em chưa hiểu đoạn result.detectionConfidence = *(conf + 1); ở line 83 result.detectionConfidence = *(conf + 1); nvdsinfer_custombboxparser.cpp
Tại sao lại là conf + 1?
Mong anh giải đáp giúp e.

Compiler error

git clone https://github.com/nghiapq77/face-recognition-deepstream.git
cd face-recognition-deepstream
mkdir build && cd build && ln -s ../Makefile
make -j$(nproc)

I deploy that at deepstream 6.0.
"cosine_similarity.o" file isn't exist.
"deepstream_app" file isn't exist.

The followintg is my makefile.
Makefile.zip

Version mismatch of the deepstream app and tensorrt engine file.

According to this deepstream app system requirements are as follows:

• GStreamer-1.0
• GStreamer-1.0 Base Plugins
• GStreamer-1.0 gstrtspserver
• X11 client-side library
• Glib json library - json-glib-1.0
• DeepStream 5.0
• CUDA 10.2

But according to this repository https://github.com/nghiapq77/face-recognition-cpp-tensorrt which is used for converting pytorch weight files into tensorrt engine files, requirements are as follows:

• CUDA 11.3
• TensorRT 8.2.2.1
• OpenCV 4.5.5
• SQLite 3.31.1
• Crow 1.0
• Boost 1.79.0
• Python 3.8
• torch 1.11.0+cu113
• torchvision 0.12.0+cu113

As the CUDA version and Tensorrt version do not match, converted engine files can not be used in this app. How can we solve this issue?

App run failed

hello @nghiapq77 I am trying to run the app and getting this erro

No protocol specified
ERROR: ../nvdsinfer/nvdsinfer_func_utils.cpp:33 [TRT]: ../rtSafe/coreReadArchive.cpp (38) - Serialization Error in verifyHeader: 0 (Version tag does not match)
ERROR: ../nvdsinfer/nvdsinfer_func_utils.cpp:33 [TRT]: INVALID_STATE: std::exception
ERROR: ../nvdsinfer/nvdsinfer_func_utils.cpp:33 [TRT]: INVALID_CONFIG: Deserialize the cuda engine failed.
ERROR: ../nvdsinfer/nvdsinfer_model_builder.cpp:1567 Deserialize engine failed from file: /opt/nvidia/deepstream/deepstream-5.0/sources/apps/face-recognition-deepstream/ir50_asia-l2norm-db.engine
0:00:00.097947449 207122 0x55bdf194dc10 WARN                 nvinfer gstnvinfer.cpp:616:gst_nvinfer_logger:<secondary_gie_0> NvDsInferContext[UID 2]: Warning from NvDsInferContextImpl::deserializeEngineAndBackend() <nvdsinfer_context_impl.cpp:1690> [UID = 2]: deserialize engine from file :/opt/nvidia/deepstream/deepstream-5.0/sources/apps/face-recognition-deepstream/ir50_asia-l2norm-db.engine failed
0:00:00.097974348 207122 0x55bdf194dc10 WARN                 nvinfer gstnvinfer.cpp:616:gst_nvinfer_logger:<secondary_gie_0> NvDsInferContext[UID 2]: Warning from NvDsInferContextImpl::generateBackendContext() <nvdsinfer_context_impl.cpp:1797> [UID = 2]: deserialize backend context from engine from file :/opt/nvidia/deepstream/deepstream-5.0/sources/apps/face-recognition-deepstream/ir50_asia-l2norm-db.engine failed, try rebuild
0:00:00.097982746 207122 0x55bdf194dc10 INFO                 nvinfer gstnvinfer.cpp:619:gst_nvinfer_logger:<secondary_gie_0> NvDsInferContext[UID 2]: Info from NvDsInferContextImpl::buildModel() <nvdsinfer_context_impl.cpp:1715> [UID = 2]: Trying to create engine from model files
ERROR: ../nvdsinfer/nvdsinfer_model_builder.cpp:934 failed to build network since there is no model file matched.
ERROR: ../nvdsinfer/nvdsinfer_model_builder.cpp:872 failed to build network.
0:00:00.098110610 207122 0x55bdf194dc10 ERROR                nvinfer gstnvinfer.cpp:613:gst_nvinfer_logger:<secondary_gie_0> NvDsInferContext[UID 2]: Error in NvDsInferContextImpl::buildModel() <nvdsinfer_context_impl.cpp:1735> [UID = 2]: build engine file failed
0:00:00.098122536 207122 0x55bdf194dc10 ERROR                nvinfer gstnvinfer.cpp:613:gst_nvinfer_logger:<secondary_gie_0> NvDsInferContext[UID 2]: Error in NvDsInferContextImpl::generateBackendContext() <nvdsinfer_context_impl.cpp:1821> [UID = 2]: build backend context failed
0:00:00.098129880 207122 0x55bdf194dc10 ERROR                nvinfer gstnvinfer.cpp:613:gst_nvinfer_logger:<secondary_gie_0> NvDsInferContext[UID 2]: Error in NvDsInferContextImpl::initialize() <nvdsinfer_context_impl.cpp:1148> [UID = 2]: generate backend failed, check config file settings
0:00:00.098155543 207122 0x55bdf194dc10 WARN                 nvinfer gstnvinfer.cpp:809:gst_nvinfer_start:<secondary_gie_0> error: Failed to create NvDsInferContext instance
0:00:00.098160885 207122 0x55bdf194dc10 WARN                 nvinfer gstnvinfer.cpp:809:gst_nvinfer_start:<secondary_gie_0> error: Config file path: /opt/nvidia/deepstream/deepstream-5.0/sources/apps/face-recognition-deepstream/config_recognition.txt, NvDsInfer Error: NVDSINFER_CONFIG_FAILED
** ERROR: <main:712>: Failed to set pipeline to PAUSED
Quitting
ERROR from secondary_gie_0: Failed to create NvDsInferContext instance
Debug info: gstnvinfer.cpp(809): gst_nvinfer_start (): /GstPipeline:pipeline/GstBin:secondary_gie_bin/GstNvInfer:secondary_gie_0:
Config file path: /opt/nvidia/deepstream/deepstream-5.0/sources/apps/face-recognition-deepstream/config_recognition.txt, NvDsInfer Error: NVDSINFER_CONFIG_FAILED
App run failed