[Happy New Year] TensorRT + DeepStream Support. ()

* [Happy New Years] TensorRT + DeepStream Support.

* Add deepstream config

* pre-commit fix

* Fix name

* [Happy New Years] TensorRT + DeepStream Support.

* Add deepstream config

* pre-commit fix

* Fix name

* Add config

* Add rtmdet deepstream
pull/531/head
tripleMu 2023-02-08 11:07:46 +08:00 committed by GitHub
parent 4a7228a5cc
commit 031e7450bc
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
5 changed files with 317 additions and 0 deletions

View File

@ -0,0 +1,35 @@
cmake_minimum_required(VERSION 2.8.12)
set(CMAKE_CUDA_ARCHITECTURES 60 61 62 70 72 75 86)
set(CMAKE_CUDA_COMPILER /usr/local/cuda/bin/nvcc)
project(nvdsparsebbox_mmyolo LANGUAGES CXX)
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -std=c++14 -O3 -g -Wall -Werror -shared -fPIC")
set(CMAKE_CXX_STANDARD 14)
set(CMAKE_BUILD_TYPE Release)
option(CUDA_USE_STATIC_CUDA_RUNTIME OFF)
# CUDA
find_package(CUDA REQUIRED)
# TensorRT
set(TensorRT_INCLUDE_DIRS "/usr/include/x86_64-linux-gnu" CACHE STRING "TensorRT headers path")
set(TensorRT_LIBRARIES "/usr/lib/x86_64-linux-gnu" CACHE STRING "TensorRT libs path")
# DeepStream
set(DEEPSTREAM "/opt/nvidia/deepstream/deepstream" CACHE STRING "DeepStream root path")
set(DS_LIBRARIES ${DEEPSTREAM}/lib)
set(DS_INCLUDE_DIRS ${DEEPSTREAM}/sources/includes)
include_directories(
${CUDA_INCLUDE_DIRS}
${TensorRT_INCLUDE_DIRS}
${DS_INCLUDE_DIRS})
add_library(
${PROJECT_NAME}
SHARED
custom_mmyolo_bbox_parser/nvdsparsebbox_mmyolo.cpp)
target_link_libraries(${PROJECT_NAME} PRIVATE nvinfer nvinfer_plugin)

View File

@ -0,0 +1,80 @@
person
bicycle
car
motorbike
aeroplane
bus
train
truck
boat
traffic light
fire hydrant
stop sign
parking meter
bench
bird
cat
dog
horse
sheep
cow
elephant
bear
zebra
giraffe
backpack
umbrella
handbag
tie
suitcase
frisbee
skis
snowboard
sports ball
kite
baseball bat
baseball glove
skateboard
surfboard
tennis racket
bottle
wine glass
cup
fork
knife
spoon
bowl
banana
apple
sandwich
orange
broccoli
carrot
hot dog
pizza
donut
cake
chair
sofa
pottedplant
bed
diningtable
toilet
tvmonitor
laptop
mouse
remote
keyboard
cell phone
microwave
oven
toaster
sink
refrigerator
book
clock
vase
scissors
teddy bear
hair drier
toothbrush

View File

@ -0,0 +1,22 @@
[property]
gpu-id=0
net-scale-factor=0.01735207357279195
offsets=57.375;57.12;58.395
model-color-format=1
model-engine-file=../end2end.engine
labelfile-path=../coco_labels.txt
batch-size=1
network-mode=0
num-detected-classes=80
interval=0
gie-unique-id=1
process-mode=1
network-type=0
cluster-mode=2
maintain-aspect-ratio=1
parse-bbox-func-name=NvDsInferParseCustomMMYOLO
custom-lib-path=../build/libnvdsparsebbox_mmyolo.so
[class-attrs-all]
pre-cluster-threshold=0.45
topk=100

View File

@ -0,0 +1,118 @@
#include "nvdsinfer_custom_impl.h"
#include <cassert>
#include <iostream>
/**
* Function expected by DeepStream for decoding the MMYOLO output.
*
* C-linkage [extern "C"] was written to prevent name-mangling. This function must return true after
* adding all bounding boxes to the objectList vector.
*
* @param [outputLayersInfo] std::vector of NvDsInferLayerInfo objects with information about the output layer.
* @param [networkInfo] NvDsInferNetworkInfo object with information about the MMYOLO network.
* @param [detectionParams] NvDsInferParseDetectionParams with information about some config params.
* @param [objectList] std::vector of NvDsInferParseObjectInfo objects to which bounding box information must
* be stored.
*
* @return true
*/
// This is just the function prototype. The definition is written at the end of the file.
extern "C" bool NvDsInferParseCustomMMYOLO(
std::vector<NvDsInferLayerInfo> const& outputLayersInfo,
NvDsInferNetworkInfo const& networkInfo,
NvDsInferParseDetectionParams const& detectionParams,
std::vector<NvDsInferParseObjectInfo>& objectList);
static __inline__ float clamp(float& val, float min, float max)
{
return val > min ? (val < max ? val : max) : min;
}
static std::vector<NvDsInferParseObjectInfo> decodeMMYoloTensor(
const int* num_dets,
const float* bboxes,
const float* scores,
const int* labels,
const float& conf_thres,
const unsigned int& img_w,
const unsigned int& img_h
)
{
std::vector<NvDsInferParseObjectInfo> bboxInfo;
size_t nums = num_dets[0];
for (size_t i = 0; i < nums; i++)
{
float score = scores[i];
if (score < conf_thres)continue;
float x0 = (bboxes[i * 4]);
float y0 = (bboxes[i * 4 + 1]);
float x1 = (bboxes[i * 4 + 2]);
float y1 = (bboxes[i * 4 + 3]);
x0 = clamp(x0, 0.f, img_w);
y0 = clamp(y0, 0.f, img_h);
x1 = clamp(x1, 0.f, img_w);
y1 = clamp(y1, 0.f, img_h);
NvDsInferParseObjectInfo obj;
obj.left = x0;
obj.top = y0;
obj.width = x1 - x0;
obj.height = y1 - y0;
obj.detectionConfidence = score;
obj.classId = labels[i];
bboxInfo.push_back(obj);
}
return bboxInfo;
}
/* C-linkage to prevent name-mangling */
extern "C" bool NvDsInferParseCustomMMYOLO(
std::vector<NvDsInferLayerInfo> const& outputLayersInfo,
NvDsInferNetworkInfo const& networkInfo,
NvDsInferParseDetectionParams const& detectionParams,
std::vector<NvDsInferParseObjectInfo>& objectList)
{
// Some assertions and error checking.
if (outputLayersInfo.empty() || outputLayersInfo.size() != 4)
{
std::cerr << "Could not find output layer in bbox parsing" << std::endl;
return false;
}
// Score threshold of bboxes.
const float conf_thres = detectionParams.perClassThreshold[0];
// Obtaining the output layer.
const NvDsInferLayerInfo& num_dets = outputLayersInfo[0];
const NvDsInferLayerInfo& bboxes = outputLayersInfo[1];
const NvDsInferLayerInfo& scores = outputLayersInfo[2];
const NvDsInferLayerInfo& labels = outputLayersInfo[3];
// num_dets(int) bboxes(float) scores(float) labels(int)
assert (num_dets.dims.numDims == 2);
assert (bboxes.dims.numDims == 3);
assert (scores.dims.numDims == 2);
assert (labels.dims.numDims == 2);
// Decoding the output tensor of MMYOLO to the NvDsInferParseObjectInfo format.
std::vector<NvDsInferParseObjectInfo> objects =
decodeMMYoloTensor(
(const int*)(num_dets.buffer),
(const float*)(bboxes.buffer),
(const float*)(scores.buffer),
(const int*)(labels.buffer),
conf_thres,
networkInfo.width,
networkInfo.height
);
objectList.clear();
objectList = objects;
return true;
}
/* Check that the custom function has been defined correctly */
CHECK_CUSTOM_PARSE_FUNC_PROTOTYPE(NvDsInferParseCustomMMYOLO);

View File

@ -0,0 +1,62 @@
[application]
enable-perf-measurement=1
perf-measurement-interval-sec=5
[tiled-display]
enable=1
rows=1
columns=1
width=1280
height=720
gpu-id=0
nvbuf-memory-type=0
[source0]
enable=1
type=3
uri=file:///opt/nvidia/deepstream/deepstream/samples/streams/sample_1080p_h264.mp4
num-sources=1
gpu-id=0
cudadec-memtype=0
[sink0]
enable=1
type=2
sync=0
gpu-id=0
nvbuf-memory-type=0
[osd]
enable=1
gpu-id=0
border-width=5
text-size=15
text-color=1;1;1;1;
text-bg-color=0.3;0.3;0.3;1
font=Serif
show-clock=0
clock-x-offset=800
clock-y-offset=820
clock-text-size=12
clock-color=1;0;0;0
nvbuf-memory-type=0
[streammux]
gpu-id=0
live-source=0
batch-size=1
batched-push-timeout=40000
width=1920
height=1080
enable-padding=0
nvbuf-memory-type=0
[primary-gie]
enable=1
gpu-id=0
gie-unique-id=1
nvbuf-memory-type=0
config-file=configs/config_infer_rtmdet.txt
[tests]
file-loop=0