nvidia@nvidia-desktop:~$ git clone https://github.com/ultralytics/yolov5.git

nvidia@nvidia-desktop:~/yolov5$ wget https://github.com/ultralytics/yolov5/releases/download/v6.0/yolov5n.pt

git clone https://github.com/linghu8812/tensorrt_inference.git

ubuntu@ubuntu:~/yolov5$ python3 detect.py --weights yolov5n.pt --source ../tensorrt_inference/yolov5/samples/ --device 0 
detect: weights=['yolov5n.pt'], source=../tensorrt_inference/yolov5/samples/, imgsz=[640, 640], conf_thres=0.25, iou_thres=0.45, max_det=1000, device=0, view_img=False, save_txt=False, save_conf=False, save_crop=False, nosave=False, classes=None, agnostic_nms=False, augment=False, visualize=False, update=False, project=runs/detect, name=exp, exist_ok=False, line_thickness=3, hide_labels=False, hide_conf=False, half=False, dnn=False
YOLOv5 🚀 v6.0-88-g80cfaf4 torch 1.10.0+cu113 CUDA:0 (GeForce RTX 2060, 5931MiB)

Fusing layers... 
Model Summary: 213 layers, 1867405 parameters, 0 gradients
image 1/7 /home/ubuntu/tensorrt_inference/yolov5/samples/bus.jpg: 640x480 4 persons, 1 bus, 1 skateboard, Done. (0.038s)
image 2/7 /home/ubuntu/tensorrt_inference/yolov5/samples/dog.jpg: 480x640 1 bicycle, 1 car, 1 dog, Done. (0.011s)
image 3/7 /home/ubuntu/tensorrt_inference/yolov5/samples/eagle.jpg: 448x640 1 bird, Done. (0.012s)
image 4/7 /home/ubuntu/tensorrt_inference/yolov5/samples/giraffe.jpg: 640x640 1 zebra, 1 giraffe, Done. (0.013s)
image 5/7 /home/ubuntu/tensorrt_inference/yolov5/samples/horses.jpg: 448x640 3 horses, 2 cows, Done. (0.007s)
image 6/7 /home/ubuntu/tensorrt_inference/yolov5/samples/person.jpg: 448x640 1 person, 1 dog, 1 horse, 1 cow, Done. (0.008s)
image 7/7 /home/ubuntu/tensorrt_inference/yolov5/samples/zidane.jpg: 384x640 2 persons, 1 tie, Done. (0.011s)
Speed: 0.5ms pre-process, 14.2ms inference, 1.0ms NMS per image at shape (1, 3, 640, 640)
Results saved to runs/detect/exp

ubuntu@ubuntu:~$ sudo apt-get install libgstreamer1.0-0 gstreamer1.0-plugins-base gstreamer1.0-plugins-good gstreamer1.0-plugins-bad gstreamer1.0-plugins-ugly gstreamer1.0-libav gstreamer1.0-doc gstreamer1.0-tools gstreamer1.0-x gstreamer1.0-alsa gstreamer1.0-gl gstreamer1.0-gtk3 gstreamer1.0-qt5 gstreamer1.0-pulseaudio
ubuntu@ubuntu:~$ sudo aptitude install libssl-dev
ubuntu@ubuntu:~$ sudo apt install libgstrtspserver-1.0-0 libjansson4

ubuntu@ubuntu:~$ git clone https://github.com/edenhill/librdkafka.git
ubuntu@ubuntu:~$ cd librdkafka
ubuntu@ubuntu:~$ git reset --hard 7101c2310341ab3f4675fc565f64f0967e135a6a
ubuntu@ubuntu:~/librdkafka$ ./configure
ubuntu@ubuntu:~/librdkafka$ make
ubuntu@ubuntu:~/librdkafka$ sudo make install
ubuntu@ubuntu:~/librdkafka$ sudo mkdir -p /opt/nvidia/deepstream/deepstream-5.0/lib
ubuntu@ubuntu:~/librdkafka$ sudo cp /usr/local/lib/librdkafka* /opt/nvidia/deepstream/deepstream-5.0/lib

ubuntu@ubuntu:~$ tar -jxvf deepstream_sdk_v5.1.0_x86_64.tbz2 -C /

ubuntu@ubuntu:~$ cd /opt/nvidia/deepstream/deepstream-5.1
ubuntu@ubuntu:~$ sudo vim uninstall.sh
//打开后，设置PREV_DS_VER=5.1
ubuntu@ubuntu:~$ sudo ./uninstall.sh

ubuntu@ubuntu:~$ cd /opt/nvidia/deepstream/deepstream-5.0/
ubuntu@ubuntu:~$ sudo ./install.sh
ubuntu@ubuntu:~$ sudo ldconfig

ubuntu@ubuntu:~$ sudo vi /etc/ld.so.conf
/opt/nvidia/deepstream/deepstream-5.1/lib/   //在文本后边添加该路径
ubuntu@ubuntu:~$ sudo ldconfig    //执行ldconfig立即生效

ubuntu@ubuntu:~$ sudo gedit /etc/ld.so.conf

(gedit:1302304): Tepl-WARNING **: 11:29:05.109: GVfs metadata is not supported. Fallback to TeplMetadataManager. Either GVfs is not correctly installed or GVfs metadata are not supported on this platform. In the latter case, you should configure Tepl with --disable-gvfs-metadata.
ubuntu@ubuntu:~$ sudo ldconfig
ubuntu@ubuntu:~$ deepstream-app --version-all
deepstream-app version 5.1.0
DeepStreamSDK 5.1.0
CUDA Driver Version: 11.2
CUDA Runtime Version: 11.1
TensorRT Version: 7.2
cuDNN Version: 8.1
libNVWarp360 Version: 2.0.1d3
ubuntu@ubuntu:~$

ubuntu@ubuntu:~$ sudo gedit /opt/nvidia/deepstream/deepstream-5.1/samples/configs/deepstream-app/source4_1080p_dec_infer-resnet_tracker_sgie_tiled_display_int8.txt

ubuntu@ubuntu:~$ sudo deepstream-app -c /opt/nvidia/deepstream/deepstream-5.1/samples/configs/deepstream-app/source4_1080p_dec_infer-resnet_tracker_sgie_tiled_display_int8.txt

ubuntu@ubuntu:/opt/nvidia/deepstream/deepstream-5.1/sources/apps/sample_apps/deepstream-test1$ sudo make
cc -c -o deepstream_test1_app.o -I../../../includes -I /usr/local/cuda-11.1/include -pthread -I/usr/include/gstreamer-1.0 -I/usr/include/glib-2.0 -I/usr/lib/x86_64-linux-gnu/glib-2.0/include deepstream_test1_app.c
cc -o deepstream-test1-app deepstream_test1_app.o -lgstreamer-1.0 -lgobject-2.0 -lglib-2.0 -L/usr/local/cuda-11.1/lib64/ -lcudart -L/opt/nvidia/deepstream/deepstream-5.1/lib/ -lnvdsgst_meta -lnvds_meta -lcuda -Wl,-rpath,/opt/nvidia/deepstream/deepstream-5.1/lib/
ubuntu@ubuntu:/opt/nvidia/deepstream/deepstream-5.1/sources/apps/sample_apps/deepstream-test1$ ./deepstream-test1-app ../../../../samples/streams/sample_720p.h264 
Running...
Frame Number = 0 Number of objects = 6 Vehicle Count = 4 Person Count = 2
Frame Number = 1 Number of objects = 6 Vehicle Count = 4 Person Count = 2
Frame Number = 2 Number of objects = 6 Vehicle Count = 4 Person Count = 2
Frame Number = 3 Number of objects = 6 Vehicle Count = 4 Person Count = 2
Frame Number = 4 Number of objects = 5 Vehicle Count = 3 Person Count = 2
Frame Number = 5 Number of objects = 6 Vehicle Count = 4 Person Count = 2
Frame Number = 6 Number of objects = 6 Vehicle Count = 4 Person Count = 2
Frame Number = 7 Number of objects = 6 Vehicle Count = 4 Person Count = 2
Frame Number = 8 Number of objects = 6 Vehicle Count = 4 Person Count = 2
Frame Number = 9 Number of objects = 6 Vehicle Count = 4 Person Count = 2
Frame Number = 10 Number of objects = 7 Vehicle Count = 5 Person Count = 2
Frame Number = 11 Number of objects = 6 Vehicle Count = 4 Person Count = 2
Frame Number = 12 Number of objects = 7 Vehicle Count = 5 Person Count = 2
Frame Number = 13 Number of objects = 5 Vehicle Count = 3 Person Count = 2
Frame Number = 14 Number of objects = 5 Vehicle Count = 3 Person Count = 2
Frame Number = 15 Number of objects = 6 Vehicle Count = 4 Person Count = 2
Frame Number = 16 Number of objects = 6 Vehicle Count = 4 Person Count = 2
Frame Number = 17 Number of objects = 5 Vehicle Count = 3 Person Count = 2
Frame Number = 18 Number of objects = 5 Vehicle Count = 3 Person Count = 2
Frame Number = 19 Number of objects = 5 Vehicle Count = 3 Person Count = 2
Frame Number = 20 Number of objects = 8 Vehicle Count = 6 Person Count = 2
Frame Number = 21 Number of objects = 8 Vehicle Count = 6 Person Count = 2
Frame Number = 22 Number of objects = 8 Vehicle Count = 6 Person Count = 2
Frame Number = 23 Number of objects = 8 Vehicle Count = 6 Person Count = 2
Frame Number = 24 Number of objects = 8 Vehicle Count = 6 Person Count = 2
....

ubuntu@ubuntu:~/yolov5$ python3 export.py --weights yolov5n.pt --img 640 --batch 1 --device 0 
export: data=data/coco128.yaml, weights=yolov5n.pt, imgsz=[640], batch_size=1, 
ONNX: export success, saved as yolov5n.onnx (7.9 MB)
ONNX: run --dynamic ONNX model inference with: 'python detect.py --weights yolov5n.onnx'

Export complete (4.93s)
Results saved to /home/ubuntu/yolov5
Visualize with https://netron.app
ubuntu@ubuntu:~/yolov5$ python3 -m onnxsim yolov5n.onnx yolov5n_sim.onnx
Simplifying...
Checking 0/3...
Checking 1/3...
Checking 2/3...
Ok!

ubuntu@ubuntu:~/yolov5$ python3 detect.py --weights yolov5n.onnx ../tensorrt_inference/yolov5/samples/
detect: weights=['yolov5n.onnx', '../tensorrt_inference/yolov5/samples/'], source=data/images, imgsz=[640, 640], conf_thres=0.25, iou_thres=0.45, max_det=1000, device=, view_img=False, save_txt=False, save_conf=False, save_crop=False, nosave=False, classes=None, agnostic_nms=False, augment=False, visualize=False, update=False, project=runs/detect, name=exp, exist_ok=False, line_thickness=3, hide_labels=False, hide_conf=False, half=False, dnn=False
YOLOv5 🚀 v6.0-88-g80cfaf4 torch 1.10.0+cu113 CUDA:0 (GeForce RTX 2060, 5931MiB)

Loading yolov5n.onnx for ONNX Runtime inference...
/home/ubuntu/.local/lib/python3.8/site-packages/onnxruntime/capi/onnxruntime_inference_collection.py:350: UserWarning: Deprecation warning. This ORT build has ['CUDAExecutionProvider', 'CPUExecutionProvider'] enabled. The next release (ORT 1.10) will require explicitly setting the providers parameter (as opposed to the current behavior of providers getting set/registered by default based on the build flags) when instantiating InferenceSession.For example, onnxruntime.InferenceSession(..., providers=["CUDAExecutionProvider"], ...)
  warnings.warn("Deprecation warning. This ORT build has {} enabled. ".format(available_providers) +
image 1/2 /home/ubuntu/yolov5/data/images/bus.jpg: 640x640 4 class0s, 1 class5, Done. (7.235s)
image 2/2 /home/ubuntu/yolov5/data/images/zidane.jpg: 640x640 2 class0s, 1 class27, Done. (0.016s)
Speed: 5.0ms pre-process, 3625.7ms inference, 41.3ms NMS per image at shape (1, 3, 640, 640)
Results saved to runs/detect/exp3

# TensorRT
set(TENSORRT_ROOT /home/ubuntu/NVIDIA_CUDA-11.1_Samples/TensorRT-7.2.2.3)

yolov5:
    onnx_file:     "/home/ubuntu/yolov5/yolov5s.onnx"
    engine_file:   "/home/ubuntu/yolov5/yolov5s.trt"
    labels_file:   "../coco.names"
    BATCH_SIZE:    1
    INPUT_CHANNEL: 3
    IMAGE_WIDTH:   640
    IMAGE_HEIGHT:  640
    obj_threshold: 0.4
    nms_threshold: 0.45
    strides:       [8, 16, 32]
    num_anchors:   [3,  3,  3]
    anchors:       [[10,13], [16,30], [33,23], [30,61], [62,45], [59,119], [116,90], [156,198], [373,326]]

ubuntu@ubuntu:~/tensorrt_inference/yolov5/build$ ./yolov5_trt ../config.yaml ../samples/
loading filename from:/home/ubuntu/yolov5/yolov5n.trt
[11/17/2021-17:20:31] [W] [TRT] TensorRT was linked against cuBLAS/cuBLAS LT 11.3.0 but loaded cuBLAS/cuBLAS LT 11.2.1
deserialize done
[11/17/2021-17:20:31] [W] [TRT] TensorRT was linked against cuBLAS/cuBLAS LT 11.3.0 but loaded cuBLAS/cuBLAS LT 11.2.1
engine->getNbBindings()===5
yolov5_trt: /home/ubuntu/tensorrt_inference/yolov5/yolov5.cpp:58: bool YOLOv5::InferenceFolder(const string&): Assertion `engine->getNbBindings() == 2' failed.
Aborted (core dumped)

ubuntu@ubuntu:~/tensorrt_inference/yolov5/build$ ./yolov5_trt ../config.yaml ../samples/
----------------------------------------------------------------
Input filename:   /home/ubuntu/yolov5/yolov5n.onnx
ONNX IR version:  0.0.7
Opset version:    13
Producer name:    pytorch
Producer version: 1.10
Domain:           
Model version:    0
Doc string:       
----------------------------------------------------------------
[11/15/2021-13:26:29] [W] [TRT] onnx2trt_utils.cpp:220: Your ONNX model has been generated with INT64 weights, while TensorRT does not natively support INT64. Attempting to cast down to INT32.
terminate called after throwing an instance of 'std::out_of_range'
  what():  Attribute not found: axes
Aborted (core dumped)

ubuntu@ubuntu:~/tensorrt_inference/yolov5/build$ ./yolov5_trt ../config.yaml ../samples/
----------------------------------------------------------------
Input filename:   /home/ubuntu/models/yolov5/yolov5n_sim.onnx
ONNX IR version:  0.0.7
Opset version:    12
Producer name:    pytorch
Producer version: 1.10
Domain:           
Model version:    0
Doc string:       
----------------------------------------------------------------
[11/17/2021-16:56:22] [W] [TRT] onnx2trt_utils.cpp:220: Your ONNX model has been generated with INT64 weights, while TensorRT does not natively support INT64. Attempting to cast down to INT32.
start building engine
[11/17/2021-16:56:22] [W] [TRT] TensorRT was linked against cuBLAS/cuBLAS LT 11.3.0 but loaded cuBLAS/cuBLAS LT 11.2.1
[11/17/2021-16:59:21] [I] [TRT] Some tactics do not have sufficient workspace memory to run. Increasing workspace size may increase performance, please check verbose output.
[11/17/2021-17:00:29] [I] [TRT] Detected 1 inputs and 4 output network tensors.
[11/17/2021-17:00:29] [W] [TRT] TensorRT was linked against cuBLAS/cuBLAS LT 11.3.0 but loaded cuBLAS/cuBLAS LT 11.2.1
build engine done
writing engine file...
save engine file done
[11/17/2021-17:00:29] [W] [TRT] TensorRT was linked against cuBLAS/cuBLAS LT 11.3.0 but loaded cuBLAS/cuBLAS LT 11.2.1
.....
Inference take: 1.1703 ms.
execute success
device2host
post process
Post process take: 6.44929 ms.
../samples//person_.jpg
Average processing time is 12.9103ms

import tensorrt as trt
import sys
import argparse

logger = trt.Logger(trt.Logger.WARNING)

def convert():
    explicit_batch = 1 << (int)(trt.NetworkDefinitionCreationFlag.EXPLICIT_BATCH)  # trt7
    with trt.Builder(logger) as builder, builder.create_network(explicit_batch) as network, trt.OnnxParser(network, logger) as parser:
        builder.max_workspace_size = 1 << 28
        builder.max_batch_size = 1
        if args.floatingpoint == 16:
            builder.fp16_mode = True
        with open(args.model, 'rb') as f:
            print('Beginning ONNX file parsing')
            if not parser.parse(f.read()):
                for error in range(parser.num_errors):
                    print("ERROR", parser.get_error(error))
        print("num layers:", network.num_layers)
        network.get_input(0).shape = [1, 3, 640, 640]  # trt7
        # last_layer = network.get_layer(network.num_layers - 1)
        # network.mark_output(last_layer.get_output(0))
        # reshape input from 32 to 1
        engine = builder.build_cuda_engine(network)
        with open(args.output, 'wb') as f:
            f.write(engine.serialize())
        print("Completed creating Engine")
if __name__ == '__main__':
    desc = 'Compile Onnx model to TensorRT'
    parser = argparse.ArgumentParser(description=desc)
    parser.add_argument('-m', '--model', default='yolov5n.onnx', help='onnx file location')
    parser.add_argument('-fp', '--floatingpoint', type=int, default=16, help='floating point precision. 16 or 32')
    parser.add_argument('-o', '--output', default='yolov5.trt', help='name of trt output file')
    args = parser.parse_args()
    convert()

ubuntu@ubuntu:~/yolov5_tensorRT$ python3 onnx_tensorrt.py -m ~/yolov5/yolov5n_sim.onnx -o ~/yolov5/yolov5n_sim.trt
Beginning ONNX file parsing
[TensorRT] WARNING: onnx2trt_utils.cpp:220: Your ONNX model has been generated with INT64 weights, while TensorRT does not natively support INT64. Attempting to cast down to INT32.
[TensorRT] WARNING: onnx2trt_utils.cpp:246: One or more weights outside the range of INT32 was clamped
num layers: 281
[TensorRT] WARNING: TensorRT was linked against cuBLAS/cuBLAS LT 11.3.0 but loaded cuBLAS/cuBLAS LT 11.2.1
[TensorRT] WARNING: TensorRT was linked against cuBLAS/cuBLAS LT 11.3.0 but loaded cuBLAS/cuBLAS LT 11.2.1
Completed creating Engine

ubuntu@ubuntu:~$ sudo cp NVIDIA_CUDA-11.1_Samples/TensorRT-7.2.2.3/targets/x86_64-linux-gnu/lib/libnvinfer.so.7 /usr/lib
ubuntu@ubuntu:~$ sudo cp NVIDIA_CUDA-11.1_Samples/TensorRT-7.2.2.3/targets/x86_64-linux-gnu/lib/libnvonnxparser.so.7 /usr/lib
ubuntu@ubuntu:~$ sudo cp NVIDIA_CUDA-11.1_Samples/TensorRT-7.2.2.3/targets/x86_64-linux-gnu/lib/libnvparsers.so.7 /usr/lib
ubuntu@ubuntu:~$ sudo cp NVIDIA_CUDA-11.1_Samples/TensorRT-7.2.2.3/targets/x86_64-linux-gnu/lib/libnvinfer_ /usr/lib
libnvinfer_plugin.so        libnvinfer_plugin_static.a
libnvinfer_plugin.so.7      libnvinfer_static.a
libnvinfer_plugin.so.7.2.2  
ubuntu@ubuntu:~$ sudo cp NVIDIA_CUDA-11.1_Samples/TensorRT-7.2.2.3/targets/x86_64-linux-gnu/lib/libnvinfer_plugin.so.7 /usr/lib
ubuntu@ubuntu:~$ sudo cp NVIDIA_CUDA-11.1_Samples/TensorRT-7.2.2.3/targets/x86_64-linux-gnu/lib/libmyelin.so.1 /usr/lib

ubuntu@ubuntu:~$ git clone https://github.com/DanaHan/Yolov5-in-Deepstream-5.0.git
Cloning into 'Yolov5-in-Deepstream-5.0'...
remote: Enumerating objects: 93, done.
remote: Counting objects: 100% (93/93), done.
remote: Compressing objects: 100% (73/73), done.
remote: Total 93 (delta 26), reused 86 (delta 20), pack-reused 0
Unpacking objects: 100% (93/93), 125.54 KiB | 615.00 KiB/s, done.
ubuntu@ubuntu:~$ cd Yolov5-in-Deepstream-5.0/
ubuntu@ubuntu:~/Yolov5-in-Deepstream-5.0$ ls
 CMakeLists.txt    gen_wts.py     logging.h   yololayer.cu   yolov5_trt.py
 common.hpp        hardswish.cu   README.md   yololayer.h
'Deepstream 5.0'   hardswish.h    utils.h     yolov5.cpp
ubuntu@ubuntu:~/Yolov5-in-Deepstream-5.0$ mkdir build
ubuntu@ubuntu:~/Yolov5-in-Deepstream-5.0$ cd build/
ubuntu@ubuntu:~/Yolov5-in-Deepstream-5.0/build$ cmake .

ubuntu@ubuntu:~/Yolov5-in-Deepstream-5.0$ cp gen_wts.py ../yolov5
ubuntu@ubuntu:~/Yolov5-in-Deepstream-5.0$ cd 
ubuntu@ubuntu:~$ cd yolov5/
ubuntu@ubuntu:~/yolov5$ python3 gen_wts.py 
YOLOv5 🚀 v6.0-88-g80cfaf4 torch 1.10.0+cu113 CPU
ubuntu@ubuntu:~/yolov5$ cp yolov5n.wts ../Yolov5-in-Deepstream-5.0/

ubuntu@ubuntu:~/Yolov5-in-Deepstream-5.0$ cp ../NVIDIA_CUDA-11.1_Samples/TensorRT-7.2.2.3/include/* .

ubuntu@ubuntu:~/Yolov5-in-Deepstream-5.0/build$ make
[ 60%] Built target myplugins
[100%] Built target yolov5

#define NET x  // s m l x

ubuntu@ubuntu:~/Yolov5-in-Deepstream-5.0/build$ sudo ./yolov5 -s 
Loading weights: ../yolov5s.wts
[11/18/2021-16:14:05] [E] [TRT] Parameter check failed at: ../builder/Network.cpp::addScale::494, condition: shift.count > 0 ? (shift.values != nullptr) : (shift.values == nullptr)
yolov5: /home/ubuntu/Yolov5-in-Deepstream-5.0/common.hpp:190: nvinfer1::IScaleLayer* addBatchNorm2d(nvinfer1::INetworkDefinition*, std::map<std::__cxx11::basic_string<char>, nvinfer1::Weights>&, nvinfer1::ITensor&, std::string, float): Assertion `scale_1' failed.
Aborted

import torch
from torchsummaryX import summary

from models.experimental import attempt_load

model1_path = r'yolov5s.pt'

model = attempt_load(model1_path, map_location=torch.device('cpu'))
# model.to('cuda').eval（)
# print(model)
summary(model, torch.rand((1, 3, 640, 640)))

ubuntu@ubuntu:~/yolov5$ git checkout -b v1.7.0
Switched to a new branch 'v1.7.0'
ubuntu@ubuntu:~/yolov5$ git branch -v
  master 80cfaf4 AutoAnchor and AutoBatch `LOGGER` (#5635)
* v1.7.0 80cfaf4 AutoAnchor and AutoBatch `LOGGER` (#5635)
ubuntu@ubuntu:~/yolov5$ python3 gen_wts.py 
YOLOv5 🚀 v6.0-88-g80cfaf4 torch 1.10.0+cu113 CPU

ubuntu@ubuntu:~/Yolov5-in-Deepstream-5.0/build$ sudo ./yolov5 -s 
Loading weights: ../yolov5s.wts
Building engine, please wait for a while...
[11/18/2021-20:17:50] [W] [TRT] TensorRT was linked against cuBLAS/cuBLAS LT 11.3.0 but loaded cuBLAS/cuBLAS LT 11.2.1
[11/18/2021-20:18:36] [W] [TRT] TensorRT was linked against cuBLAS/cuBLAS LT 11.3.0 but loaded cuBLAS/cuBLAS LT 11.2.1
Build engine successfully!

ubuntu@ubuntu:~/Yolov5-in-Deepstream-5.0/build$ sudo ./yolov5 -d ~/tensorrt_inference/yolov5/samples/
[11/18/2021-20:27:00] [W] [TRT] TensorRT was linked against cuBLAS/cuBLAS LT 11.3.0 but loaded cuBLAS/cuBLAS LT 11.2.1
[11/18/2021-20:27:00] [W] [TRT] TensorRT was linked against cuBLAS/cuBLAS LT 11.3.0 but loaded cuBLAS/cuBLAS LT 11.2.1
492ms
5ms
6ms
5ms
5ms
5ms
6ms

ubuntu@ubuntu:~/Yolov5-in-Deepstream-5.0/build$ cp yolov5s.engine ../Deepstream\ 5.0/
ubuntu@ubuntu:~/Yolov5-in-Deepstream-5.0/build$ cp libmyplugins.so ../Deepstream\ 5.0/
ubuntu@ubuntu:~/Yolov5-in-Deepstream-5.0$ cd Deepstream\ 5.0/
ubuntu@ubuntu:~/Yolov5-in-Deepstream-5.0/Deepstream 5.0$ cd nvdsinfer_custom_impl_Yolo/

ubuntu@ubuntu:~/Yolov5-in-Deepstream-5.0/Deepstream 5.0$ cat config_infer_primary_yoloV5.txt
..... 
model-engine-file=yolov5s.engine
custom-lib-path=nvdsinfer_custom_impl_Yolo/libnvdsinfer_custom_impl_Yolo.so
.....

ubuntu@ubuntu:~/Yolov5-in-Deepstream-5.0/Deepstream 5.0/nvdsinfer_custom_impl_Yolo$ make
g++ -c -o nvdsinfer_yolo_engine.o -Wall -std=c++11 -shared -fPIC -Wno-error=deprecated-declarations -I../includes -I/usr/local/cuda-11.3/include nvdsinfer_yolo_engine.cpp
In file included from nvdsinfer_yolo_engine.cpp:23:
../includes/nvdsinfer_custom_impl.h:126:10: fatal error: NvCaffeParser.h: No such file or directory
  126 | #include "NvCaffeParser.h"
      |          ^~~~~~~~~~~~~~~~~
compilation terminated.
make: *** [Makefile:50: nvdsinfer_yolo_engine.o] Error 1

ubuntu@ubuntu:~/Yolov5-in-Deepstream-5.0/Deepstream 5.0/nvdsinfer_custom_impl_Yolo$ cp ~/NVIDIA_CUDA-11.1_Samples/TensorRT-7.2.2.3/include/* ../include

ubuntu@ubuntu:~/Yolov5-in-Deepstream-5.0/Deepstream 5.0/nvdsinfer_custom_impl_Yolo$ make
g++ -c -o yolo.o -Wall -std=c++11 -shared -fPIC -Wno-error=deprecated-declarations -I../includes -I/usr/local/cuda-11.1/include yolo.cpp
In file included from yolo.h:31,
                 from yolo.cpp:23:
yolo.cpp:72:12: error: ‘virtual nvinfer1::IBuilderConfig::~IBuilderConfig()’ is protected within this context
   72 |     delete config;
      |            ^~~~~~
In file included from yolo.h:31,
                 from yolo.cpp:23:
../includes/NvInfer.h:6756:13: note: declared protected here
 6756 |     virtual ~IBuilderConfig() {}
      |             ^
yolo.cpp: In member function ‘NvDsInferStatus Yolo::buildYoloNetwork(std::vector<float>&, nvinfer1::INetworkDefinition&)’:
yolo.cpp:178:81: error: invalid new-expression of abstract class type ‘YoloLayerV3’
  178 |                m_OutputTensors.at(outputTensorCount).gridSize);
      |                                                              ^

make: *** [Makefile:50: yolo.o] Error 1

ubuntu@ubuntu:~$ git clone https://github.com/wang-xinyu/tensorrtx.git
Cloning into 'tensorrtx'...
remote: Enumerating objects: 1827, done.
remote: Counting objects: 100% (184/184), done.
remote: Compressing objects: 100% (136/136), done.
remote: Total 1827 (delta 105), reused 87 (delta 48), pack-reused 1643
Receiving objects: 100% (1827/1827), 1.64 MiB | 2.96 MiB/s, done.
Resolving deltas: 100% (1162/1162), done.
ubuntu@ubuntu:~$ cd tensorrtx/
ubuntu@ubuntu:~/tensorrtx$ cd yolov
bash: cd: yolov: No such file or directory
ubuntu@ubuntu:~/tensorrtx$ cd yolov5
ubuntu@ubuntu:~/tensorrtx/yolov5/build$ make
[100%] Linking CXX executable yolov5
[100%] Built target yolov5
ubuntu@ubuntu:~/tensorrtx/yolov5/build$ ./yolov5 
arguments not right!
./yolov5 -s [.wts] [.engine] [n/s/m/l/x/n6/s6/m6/l6/x6 or c/c6 gd gw]  // serialize model to plan file
./yolov5 -d [.engine] ../samples  // deserialize plan file and run inference
ubuntu@ubuntu:~/tensorrtx/yolov5/build$ sudo ./yolov5 -s ~/yolov5/yolov5n.
yolov5n.onnx            yolov5n.torchscript.pt  yolov5n.wts
yolov5n.pt              yolov5n.trt             
ubuntu@ubuntu:~/tensorrtx/yolov5/build$ sudo ./yolov5 -s ~/yolov5/yolov5n.
yolov5n.onnx            yolov5n.torchscript.pt  yolov5n.wts
yolov5n.pt              yolov5n.trt             
ubuntu@ubuntu:~/tensorrtx/yolov5/build$ sudo ./yolov5 -s ~/yolov5/yolov5n.wts yolov5n.engine n
Loading weights: /home/ubuntu/yolov5/yolov5n.wts
Building engine, please wait for a while...
[11/19/2021-18:16:52] [W] [TRT] TensorRT was linked against cuBLAS/cuBLAS LT 11.3.0 but loaded cuBLAS/cuBLAS LT 11.2.1

[11/19/2021-18:20:31] [W] [TRT] TensorRT was linked against cuBLAS/cuBLAS LT 11.3.0 but loaded cuBLAS/cuBLAS LT 11.2.1
Build engine successfully!
ubuntu@ubuntu:~/tensorrtx/yolov5/build$ 
ubuntu@ubuntu:~/tensorrtx/yolov5/build$ sudo ./yolov5 -d yolov5n.engine ../samples
[11/19/2021-18:20:53] [W] [TRT] TensorRT was linked against cuBLAS/cuBLAS LT 11.3.0 but loaded cuBLAS/cuBLAS LT 11.2.1
[11/19/2021-18:20:53] [W] [TRT] TensorRT was linked against cuBLAS/cuBLAS LT 11.3.0 but loaded cuBLAS/cuBLAS LT 11.2.1
inference time: 1ms
inference time: 1ms

ubuntu@ubuntu:~$ git clone https://github.com/hlld/deepstream-yolov5.git
Cloning into 'deepstream-yolov5'...
remote: Enumerating objects: 33, done.
remote: Counting objects: 100% (33/33), done.
remote: Compressing objects: 100% (24/24), done.
remote: Total 33 (delta 9), reused 32 (delta 8), pack-reused 0
Unpacking objects: 100% (33/33), 25.26 KiB | 253.00 KiB/s, done.
ubuntu@ubuntu:~$ cd deepstream-yolov5/
ubuntu@ubuntu:~/deepstream-yolov5$ ls
configs  data  LICENSE  README.md  source
ubuntu@ubuntu:~/deepstream-yolov5$ cd source/
ubuntu@ubuntu:~/deepstream-yolov5/source$ ls
common.h                   nvdsparsebbox_Yolo.cpp  yolo.cpp      yololayer.h
Makefile                   trt_utils.cpp           yolo.h        yolo_utils.h
nvdsinfer_yolo_engine.cpp  trt_utils.h             yololayer.cu  yolov5.cpp
ubuntu@ubuntu:~/deepstream-yolov5/source$ sudo vim Makefile 
ubuntu@ubuntu:~/deepstream-yolov5/source$ sudo gedit Makefile 

(gedit:20487): Tepl-WARNING **: 18:25:12.660: GVfs metadata is not supported. Fallback to TeplMetadataManager. Either GVfs is not correctly installed or GVfs metadata are not supported on this platform. In the latter case, you should configure Tepl with --disable-gvfs-metadata.
ubuntu@ubuntu:~/deepstream-yolov5/source$ make
ugin -lnvinfer -lnvparsers -L/usr/local/cuda-11.1/lib64 -lcudart -lcublas -lstdc++fs -L/home/ubuntu/NVIDIA_CUDA-11.1_Samples/TensorRT-7.2.2.3/lib -Wl,--end-group
ubuntu@ubuntu:~/deepstream-yolov5/source$ ls
common.h                            trt_utils.cpp  yololayer.o
libnvdsinfer_custom_impl_yolov5.so  trt_utils.h    yolo.o
Makefile                            trt_utils.o    yolo_utils.h
nvdsinfer_yolo_engine.cpp           yolo.cpp       yolov5.cpp
nvdsinfer_yolo_engine.o             yolo.h         yolov5.o
nvdsparsebbox_Yolo.cpp              yololayer.cu
nvdsparsebbox_Yolo.o                yololayer.h

[sink0]
#enable=1
enable=0

[sink1]
#enable=0
enable=1

[primary-gie]
enable=1
gpu-id=0
#model-engine-file=../yolov5s_b1_gpu0_fp16.engine
model-engine-file=/home/ubuntu/ty/tensorrtx/yolov5/build/yolov5n.engine

[tracker]
enable=0
tracker-width=640
tracker-height=384
#ll-lib-file=/opt/nvidia/deepstream/deepstream/lib/libnvds_mot_klt.so
ll-lib-file=/opt/nvidia/deepstream/deepstream-5.1/lib/libnvds_mot_klt.so

[source0]
#enable=1
enable=2
#Type - 1=CameraV4L2 2=URI 3=MultiURI

ubuntu@ubuntu:~/deepstream-yolov5$ sudo deepstream-app -c configs/deepstream_app_config_yolov5s.txt 

 *** DeepStream: Launched RTSP Streaming at rtsp://localhost:10154/ds-test ***

Unknown or legacy key specified 'is-classifier' for group [property]
Warn: 'threshold' parameter has been deprecated. Use 'pre-cluster-threshold' instead.
WARNING: ../nvdsinfer/nvdsinfer_func_utils.cpp:36 [TRT]: TensorRT was linked against cuBLAS/cuBLAS LT 11.3.0 but loaded cuBLAS/cuBLAS LT 11.2.1
WARNING: ../nvdsinfer/nvdsinfer_func_utils.cpp:36 [TRT]: TensorRT was linked against cuBLAS/cuBLAS LT 11.3.0 but loaded cuBLAS/cuBLAS LT 11.2.1
0:00:01.030647881 22360 0x55cfcb064090 INFO                 nvinfer gstnvinfer.cpp:619:gst_nvinfer_logger:<primary_gie> NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::deserializeEngineAndBackend() <nvdsinfer_context_impl.cpp:1702> [UID = 1]: deserialized trt engine from :/home/ubuntu/ty/tensorrtx/yolov5/build/yolov5n.engine
INFO: ../nvdsinfer/nvdsinfer_model_builder.cpp:685 [Implicit Engine Info]: layers num: 2
0   INPUT  kFLOAT data            3x640x640       
1   OUTPUT kFLOAT prob            6001x1x1        

0:00:01.030690121 22360 0x55cfcb064090 INFO                 nvinfer gstnvinfer.cpp:619:gst_nvinfer_logger:<primary_gie> NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::generateBackendContext() <nvdsinfer_context_impl.cpp:1806> [UID = 1]: Use deserialized engine model: /home/ubuntu/ty/tensorrtx/yolov5/build/yolov5n.engine
0:00:01.031251094 22360 0x55cfcb064090 INFO                 nvinfer gstnvinfer_impl.cpp:313:notifyLoadModelStatus:<primary_gie> [UID 1]: Load new model:/home/ubuntu/ty/deepstream-yolov5/configs/./config_infer_primary_yolov5s.txt sucessfully

Runtime commands:
  h: Print this help
  q: Quit

  p: Pause
  r: Resume

NOTE: To expand a source in the 2D tiled display and view object details, left-click on the source.
      To go back to the tiled display, right-click anywhere on the window.

** INFO: <bus_callback:181>: Pipeline ready

** INFO: <bus_callback:167>: Pipeline running


**PERF:  FPS 0 (Avg)  
**PERF:  460.51 (460.49)  
**PERF:  462.28 (461.40)  
**PERF:  462.21 (461.76)  
**PERF:  461.70 (461.69)  
**PERF:  464.78 (462.37)  
**PERF:  463.54 (462.57)  
**PERF:  461.85 (462.45)  
**PERF:  460.58 (462.21)  
**PERF:  460.26 (462.00)  
**PERF:  460.67 (461.85)  
**PERF:  464.37 (462.10)  
**PERF:  465.33 (462.37)  
**PERF:  466.88 (462.72)  
**PERF:  464.26 (462.83)  
**PERF:  465.44 (463.00)  
**PERF:  465.30 (463.15)  
**PERF:  465.44 (463.29)  
**PERF:  451.70 (462.62)  
**PERF:  451.87 (462.07)  
**PERF:  463.94 (462.16)  

**PERF:  FPS 0 (Avg)  
**PERF:  451.90 (461.66)  
**PERF:  455.48 (461.38)

nvidia@nvidia-desktop:~$ git clone https://github.com/ultralytics/yolov5.git

nvidia@nvidia-desktop:~/yolov5$ wget https://github.com/ultralytics/yolov5/releases/download/v6.0/yolov5n.pt

git clone https://github.com/linghu8812/tensorrt_inference.git

nvidia@nvidia-desktop:~/yolov5 sudo apt-get install python3-matplotlib
nvidia@nvidia-desktop:~/yolov5$ sudo apt-get install python3-seaborn
nvidia@nvidia-desktop:~/yolov5$ sudo apt-get install libblas-dev checkinstall
nvidia@nvidia-desktop:~/yolov5$ sudo apt-get install liblapack-dev checkinstall
nvidia@nvidia-desktop:~/yolov5$ sudo apt-get install gfortran
nvidia@nvidia-desktop:~/yolov5$ pip3 install -i https://pypi.tuna.tsinghua.edu.cn/simple scipy
Collecting scipy
  Using cached https://pypi.tuna.tsinghua.edu.cn/packages/aa/d5/dd06fe0e274e579e1dff21aa021219c039df40e39709fabe559faed072a5/scipy-1.5.4.tar.gz
Building wheels for collected packages: scipy
  Running setup.py bdist_wheel for scipy ... 
done
  Stored in directory: /home/nvidia/.cache/pip/wheels/74/91/ed/c853fd6d1f8f7f436e23b242427d9dacf967f3507e736f0637
Successfully built scipy
Installing collected packages: scipy
Successfully installed scipy-1.5.4
nvidia@nvidia-desktop:~/yolov5$ pip3 install -i https://pypi.tuna.tsinghua.edu.cn/simple Pillow-PIL

ubuntu@ubuntu:~$ pip3 install mxnet-cu111 -i https://pypi.tuna.tsinghua.edu.cn/simple