Basically, i modify this repo: face detection repo by adding yolox detector as PGIE, change retina face to SGIE, change config as follow:
, main.py
'''
Author: zhouyuchong
Date: 2023-07-12 09:47:15
Description:
LastEditors: zhouyuchong
LastEditTime: 2023-07-12 15:00:36
'''
import numpy as np
import math
import sys
from common.is_aarch_64 import is_aarch64
from common.bus_call import bus_call
from common.FPS import GETFPS
from common.utils import cal_ratio
from config import *
from probe import osd_sink_pad_buffer_probe, tiler_pad_buffer_probe
import gi
gi.require_version('Gst', '1.0')
from gi.repository import GLib, Gst
import ctypes
ctypes.cdll.LoadLibrary('nvdsinfer_custom_impl_retina_face/libdecodeplugin.so')
def main(args):
if len(args) < 2:
sys.stderr.write("usage: %s <uri1> [uri2] ... [uriN]\n" % args[0])
sys.exit(1)
number_sources=len(args)-1
# Standard GStreamer initialization
Gst.init(None)
# Create gstreamer elements */
# Create Pipeline element that will form a connection of other elements
print("Creating Pipeline \n ")
pipeline = Gst.Pipeline()
is_live = False
if not pipeline:
sys.stderr.write(" Unable to create Pipeline \n")
print("Creating streamux \n ")
# Create nvstreammux instance to form batches from one or more sources.
streammux = Gst.ElementFactory.make("nvstreammux", "Stream-muxer")
if not streammux:
sys.stderr.write(" Unable to create NvStreamMux \n")
pipeline.add(streammux)
for i in range(number_sources):
print("Creating source_bin ",i," \n ")
uri_name=args[i+1]
if uri_name.find("rtsp://") == 0 :
is_live = True
source_bin=create_source_bin(i, uri_name)
if not source_bin:
sys.stderr.write("Unable to create source bin \n")
pipeline.add(source_bin)
padname="sink_%u" %i
sinkpad= streammux.request_pad_simple(padname)
if not sinkpad:
sys.stderr.write("Unable to create sink pad bin \n")
srcpad=source_bin.get_static_pad("src")
if not srcpad:
sys.stderr.write("Unable to create src pad bin \n")
srcpad.link(sinkpad)
queue1=Gst.ElementFactory.make("queue","queue1")
queue2=Gst.ElementFactory.make("queue","queue2")
queue3=Gst.ElementFactory.make("queue","queue3")
queue4=Gst.ElementFactory.make("queue","queue4")
queue5=Gst.ElementFactory.make("queue","queue5")
queue6=Gst.ElementFactory.make("queue","queue6")
queue7=Gst.ElementFactory.make("queue","queue7")
queue8=Gst.ElementFactory.make("queue","queue8")
pipeline.add(queue1)
pipeline.add(queue2)
pipeline.add(queue3)
pipeline.add(queue4)
pipeline.add(queue5)
pipeline.add(queue6)
pipeline.add(queue7)
pipeline.add(queue8)
print("Creating Pgie \n ")
pgie = Gst.ElementFactory.make("nvinfer", "primary-inference")
if not pgie:
sys.stderr.write(" Unable to create pgie \n")
sgie = Gst.ElementFactory.make("nvinfer", "secondary-inference")
if not pgie:
sys.stderr.write(" Unable to create sgie \n")
print("Creating tiler \n ")
tiler=Gst.ElementFactory.make("nvmultistreamtiler", "nvtiler")
if not tiler:
sys.stderr.write(" Unable to create tiler \n")
print("Creating nvvidconv \n ")
nvvidconv = Gst.ElementFactory.make("nvvideoconvert", "convertor")
if not nvvidconv:
sys.stderr.write(" Unable to create nvvidconv \n")
print("Creating nvosd \n ")
nvosd = Gst.ElementFactory.make("nvdsosd", "onscreendisplay")
if not nvosd:
sys.stderr.write(" Unable to create nvosd \n")
nvosd.set_property('process-mode',OSD_PROCESS_MODE)
nvosd.set_property('display-text',OSD_DISPLAY_TEXT)
if(is_aarch64()):
print("Creating transform \n ")
transform=Gst.ElementFactory.make("nvegltransform", "nvegl-transform")
if not transform:
sys.stderr.write(" Unable to create transform \n")
print("Creating EGLSink \n")
sink = Gst.ElementFactory.make("nveglglessink", "nvvideo-renderer")
if not sink:
sys.stderr.write(" Unable to create egl sink \n")
if is_live:
print("Atleast one of the sources is live")
streammux.set_property('live-source', 1)
streammux.set_property('width', 1920)
streammux.set_property('height', 1080)
streammux.set_property('batch-size', number_sources)
streammux.set_property('batched-push-timeout', 4000000)
pgie.set_property('config-file-path', "configs/config_yolox.txt")
pgie_batch_size=pgie.get_property("batch-size")
if(pgie_batch_size != number_sources):
print("WARNING: Overriding infer-config batch-size",pgie_batch_size," with number of sources ", number_sources," \n")
pgie.set_property("batch-size",number_sources)
sgie.set_property('config-file-path', "configs/config_retinanet.txt")
tiler_rows=int(math.sqrt(number_sources))
tiler_columns=int(math.ceil((1.0*number_sources)/tiler_rows))
tiler.set_property("rows",tiler_rows)
tiler.set_property("columns",tiler_columns)
tiler.set_property("width", TILED_OUTPUT_WIDTH)
tiler.set_property("height", TILED_OUTPUT_HEIGHT)
sink.set_property("qos",0)
sink.set_property("sync",0)
print("Adding elements to Pipeline \n")
pipeline.add(pgie)
pipeline.add(sgie)
pipeline.add(tiler)
pipeline.add(nvvidconv)
pipeline.add(nvosd)
if is_aarch64():
pipeline.add(transform)
pipeline.add(sink)
print("Linking elements in the Pipeline \n")
streammux.link(queue1)
queue1.link(pgie)
pgie.link(queue2)
# queue2.link(queue8)
queue2.link(sgie)
sgie.link(queue8)
queue8.link(tiler)
# queue2.link(tiler)
tiler.link(queue5)
queue5.link(nvvidconv)
nvvidconv.link(queue6)
queue6.link(nvosd)
if is_aarch64():
nvosd.link(queue7)
queue7.link(transform)
transform.link(sink)
else:
nvosd.link(queue7)
queue7.link(sink)
# create an event loop and feed gstreamer bus mesages to it
loop = GLib.MainLoop()
bus = pipeline.get_bus()
bus.add_signal_watch()
bus.connect ("message", bus_call, loop)
# ratio for draw lmks
scale_ratio = cal_ratio(NETWORK_HEIGHT, NETWORK_WIDTH, TILED_OUTPUT_HEIGHT, TILED_OUTPUT_WIDTH)
user_data = [scale_ratio, DRAW_LMKS_SIGNAL]
tiler_src_pad=queue8.get_static_pad("sink")
if not tiler_src_pad:
print(" Unable to get src pad \n")
sys.stderr.write(" Unable to get src pad \n")
else:
tiler_src_pad.add_probe(Gst.PadProbeType.BUFFER, tiler_pad_buffer_probe, user_data)
# List the sources
print("Now playing...")
for i, source in enumerate(args):
if (i != 0):
print(i, ": ", source)
print("Starting pipeline \n")
# start play back and listed to events
pipeline.set_state(Gst.State.PLAYING)
try:
loop.run()
except:
pass
# cleanup
print("Exiting app\n")
pipeline.set_state(Gst.State.NULL)
def cb_newpad(decodebin, decoder_src_pad,data):
print("In cb_newpad\n")
caps=decoder_src_pad.get_current_caps()
gststruct=caps.get_structure(0)
gstname=gststruct.get_name()
source_bin=data
features=caps.get_features(0)
# Need to check if the pad created by the decodebin is for video and not
# audio.
print("gstname=",gstname)
if(gstname.find("video")!=-1):
# Link the decodebin pad only if decodebin has picked nvidia
# decoder plugin nvdec_*. We do this by checking if the pad caps contain
# NVMM memory features.
print("features=",features)
if features.contains("memory:NVMM"):
# Get the source bin ghost pad
bin_ghost_pad=source_bin.get_static_pad("src")
if not bin_ghost_pad.set_target(decoder_src_pad):
sys.stderr.write("Failed to link decoder src pad to source bin ghost pad\n")
else:
sys.stderr.write(" Error: Decodebin did not pick nvidia decoder plugin.\n")
def decodebin_child_added(child_proxy,Object,name,user_data):
print("Decodebin child added:", name, "\n")
if(name.find("decodebin") != -1):
Object.connect("child-added",decodebin_child_added,user_data)
if "source" in name:
obj_name = str(Object)
if 'GstRTSPSrc' in obj_name:
Object.set_property("drop-on-latency", True)
def create_source_bin(index,uri):
print("Creating source bin")
# Create a source GstBin to abstract this bin's content from the rest of the
# pipeline
bin_name="source-bin-%02d" %index
print(bin_name)
nbin=Gst.Bin.new(bin_name)
if not nbin:
sys.stderr.write(" Unable to create source bin \n")
# Source element for reading from the uri.
# We will use decodebin and let it figure out the container format of the
# stream and the codec and plug the appropriate demux and decode plugins.
uri_decode_bin=Gst.ElementFactory.make("uridecodebin", "uri-decode-bin")
if not uri_decode_bin:
sys.stderr.write(" Unable to create uri decode bin \n")
# We set the input uri to the source element
uri_decode_bin.set_property("uri",uri)
# Connect to the "pad-added" signal of the decodebin which generates a
# callback once a new pad for raw data has beed created by the decodebin
uri_decode_bin.connect("pad-added",cb_newpad,nbin)
uri_decode_bin.connect("child-added",decodebin_child_added,nbin)
# We need to create a ghost pad for the source bin which will act as a proxy
# for the video decoder src pad. The ghost pad will not have a target right
# now. Once the decode bin creates the video decoder and generates the
# cb_newpad callback, we will set the ghost pad target to the video decoder
# src pad.
Gst.Bin.add(nbin,uri_decode_bin)
bin_pad=nbin.add_pad(Gst.GhostPad.new_no_target("src",Gst.PadDirection.SRC))
if not bin_pad:
sys.stderr.write(" Failed to add ghost pad in source bin \n")
return None
return nbin
if __name__ == '__main__':
sys.exit(main(sys.argv))
probe function file
'''
Author: zhouyuchong
Date: 2023-07-12 10:26:33
Description:
LastEditors: zhouyuchong
LastEditTime: 2023-07-12 14:18:03
'''
import gi
gi.require_version('Gst', '1.0')
from gi.repository import GObject, Gst
import numpy as np
from rface_custom import parse_objects_from_tensor_meta
import pyds
def tiler_pad_buffer_probe(pad,info,u_data):
gst_buffer = info.get_buffer()
if not gst_buffer:
print("Unable to get GstBuffer ")
return
# Retrieve batch metadata from the gst_buffer
# Note that pyds.gst_buffer_get_nvds_batch_meta() expects the
# C address of gst_buffer as input, which is obtained with hash(gst_buffer)
batch_meta = pyds.gst_buffer_get_nvds_batch_meta(hash(gst_buffer))
l_frame = batch_meta.frame_meta_list
while l_frame is not None:
try:
# Note that l_frame.data needs a cast to pyds.NvDsFrameMeta
# The casting is done by pyds.NvDsFrameMeta.cast()
# The casting also keeps ownership of the underlying memory
# in the C code, so the Python garbage collector will leave
# it alone.
frame_meta = pyds.NvDsFrameMeta.cast(l_frame.data)
except StopIteration:
break
frame_number = frame_meta.frame_num
l_obj = frame_meta.obj_meta_list
while l_obj is not None:
try:
# Casting l_obj.data to pyds.NvDsObjectMeta
obj_meta = pyds.NvDsObjectMeta.cast(l_obj.data)
except StopIteration:
break
print("obj_meta.unique_component_id", obj_meta.unique_component_id)
print("l_obj.parent: ", obj_meta.class_id, obj_meta.parent)
try:
l_obj = l_obj.next
except StopIteration:
break
try:
l_frame = l_frame.next
except StopIteration:
break
return Gst.PadProbeReturn.OK
def osd_sink_pad_buffer_probe(pad, info, u_data):
if not u_data[1]:
return Gst.PadProbeReturn.OK
scale_ratio = u_data[0]
frame_number=0
gst_buffer = info.get_buffer()
if not gst_buffer:
print("Unable to get GstBuffer ")
return
batch_meta = pyds.gst_buffer_get_nvds_batch_meta(hash(gst_buffer))
l_frame = batch_meta.frame_meta_list
while l_frame is not None:
try:
frame_meta = pyds.NvDsFrameMeta.cast(l_frame.data)
except StopIteration:
break
frame_number=frame_meta.frame_num
result_landmark = []
l_user=frame_meta.frame_user_meta_list
while l_user is not None:
try:
user_meta=pyds.NvDsUserMeta.cast(l_user.data)
except StopIteration:
break
if(user_meta and user_meta.base_meta.meta_type==pyds.NvDsMetaType.NVDSINFER_TENSOR_OUTPUT_META):
try:
tensor_meta = pyds.NvDsInferTensorMeta.cast(user_meta.user_meta_data)
except StopIteration:
break
layer = pyds.get_nvds_LayerInfo(tensor_meta, 0)
result_landmark = parse_objects_from_tensor_meta(layer)
try:
l_user=l_user.next
except StopIteration:
break
num_rects = frame_meta.num_obj_meta
face_count = 0
l_obj=frame_meta.obj_meta_list
while l_obj is not None:
try:
# Casting l_obj.data to pyds.NvDsObjectMeta
obj_meta=pyds.NvDsObjectMeta.cast(l_obj.data)
except StopIteration:
break
print("obj_meta.unique_component_id: ", obj_meta.unique_component_id)
# set bbox color in rgba
obj_meta.rect_params.border_color.set(1.0, 1.0, 1.0, 0.0)
# set the border width in pixel
obj_meta.rect_params.border_width=5
obj_meta.rect_params.has_bg_color=1
obj_meta.rect_params.bg_color.set(0.0, 0.5, 0.3, 0.4)
face_count +=1
#print(face_count)
try:
l_obj=l_obj.next
except StopIteration:
break
# draw 5 landmarks for each rect
# display_meta.num_circles = len(result_landmark) * 5
display_meta=pyds.nvds_acquire_display_meta_from_pool(batch_meta)
ccount = 0
for i in range(len(result_landmark)):
# scale coordinates
landmarks = result_landmark[i] * scale_ratio
# nvosd struct can only draw MAX 16 elements once
# so acquire a new display meta for every face detected
display_meta=pyds.nvds_acquire_display_meta_from_pool(batch_meta)
display_meta.num_circles = 5
ccount = 0
for j in range(5):
py_nvosd_circle_params = display_meta.circle_params[ccount]
py_nvosd_circle_params.circle_color.set(0.0, 0.0, 1.0, 1.0)
py_nvosd_circle_params.has_bg_color = 1
py_nvosd_circle_params.bg_color.set(0.0, 0.0, 0.0, 1.0)
py_nvosd_circle_params.xc = int(landmarks[j * 2]) if int(landmarks[j * 2]) > 0 else 0
py_nvosd_circle_params.yc = int(landmarks[j * 2 + 1]) if int(landmarks[j * 2 + 1]) > 0 else 0
py_nvosd_circle_params.radius=2
ccount = ccount + 1
pyds.nvds_add_display_meta_to_frame(frame_meta, display_meta)
display_meta=pyds.nvds_acquire_display_meta_from_pool(batch_meta)
display_meta.num_labels = 1
py_nvosd_text_params = display_meta.text_params[0]
# Setting display text to be shown on screen
# Note that the pyds module allocates a buffer for the string, and the
# memory will not be claimed by the garbage collector.
# Reading the display_text field here will return the C address of the
# allocated string. Use pyds.get_string() to get the string content.
py_nvosd_text_params.display_text = "Frame Number={} Number of Objects={}".format(frame_number, num_rects)
# Now set the offsets where the string should appear
py_nvosd_text_params.x_offset = 10
py_nvosd_text_params.y_offset = 12
# Font , font-color and font-size
py_nvosd_text_params.font_params.font_name = "Serif"
py_nvosd_text_params.font_params.font_size = 10
# set(red, green, blue, alpha); set to White
py_nvosd_text_params.font_params.font_color.set(1.0, 1.0, 1.0, 1.0)
# Text background color
py_nvosd_text_params.set_bg_clr = 1
# set(red, green, blue, alpha); set to Black
py_nvosd_text_params.text_bg_clr.set(0.0, 0.0, 0.0, 1.0)
# Using pyds.get_string() to get display_text as string
# print(pyds.get_string(py_nvosd_text_params.display_text))
pyds.nvds_add_display_meta_to_frame(frame_meta, display_meta)
try:
l_frame=l_frame.next
except StopIteration:
break
return Gst.PadProbeReturn.OK
config_yolox.txt
[property]
gpu-id=0
net-scale-factor=1.0
# 0:RGB 1:BGR
model-color-format=0
model-engine-file=../models/yolox/yolox_s.trt
labelfile-path=labels.txt
num-detected-classes=80
interval=0
gie-unique-id=1
process-mode=1
batch-size=16
# 0=Detector, 1=Classifier, 2=Segmentation, 100=Other
network-type=0
# 0：Group Rectange 1：DBSCAN 2：NMS 3:DBSCAN+NMS 4:None
cluster-mode=4
maintain-aspect-ratio=0
parse-bbox-func-name=NvDsInferParseCustomYolox
custom-lib-path=../nvdsinfer_custom_impl_yolox/libnvdsinfer_custom_impl_yolox.so
[class-attrs-all]
pre-cluster-threshold=0.25
interval=15
Config for retina_face
[property]
gpu-id=0
net-scale-factor=1.0
offsets=104.0;117.0;123.0
# 0:RGB 1:BGR
model-color-format=1
# onnx-file=../models/retina_face/FaceDetector.onnx
model-engine-file=../models/retina_face/retina_r50.engine
labelfile-path=../models/retina_face/labels.txt
interval=0
gie-unique-id=2
process-mode=1
batch-size=16
# 0=Detector, 1=Classifier, 2=Segmentation, 100=Other
network-type=0
output-blob-names=prob
num-detected-classes=1
output-tensor-meta=1
maintain-aspect-ratio=1
operate-on-gie-id=1
operate-on-class-ids=0
# 0：Group Rectange 1：DBSCAN 2：NMS 3:DBSCAN+NMS 4:None
cluster-mode=4
maintain-aspect-ratio=0
parse-bbox-func-name=NvDsInferParseCustomRetinaface
custom-lib-path=../nvdsinfer_custom_impl_retina_face/libnvdsinfer_custom_impl_retinaface.so
[class-attrs-all]
pre-cluster-threshold=0.6
nms-iou-threshold=0.5
