Please provide complete information as applicable to your setup.
• Hardware Platform (Jetson Nano)
• DeepStream Version 6.0.1
• JetPack Version (R32.6.1)
• TensorRT Version: 8.2.1-1+cuda10.2
• Issue Type( Bug/Question)
I (as well as a few other people in this forum) cannot access mask parameters from the GST buffer with a probe.
All other parameters are accessible (bounding box, label, confidence), but Pybind11 will throw an error when accessing the mask parameters:
TypeError: Unable to convert function return value to a Python type! The signature was
(self: pyds.NvDsObjectMeta) -> _NvOSD_MaskParams
Therefore, I believe this is a bug within the Python DeepStream bindings.
To clarify, everything works as expected except for accessing mask parameters.
I have gone deeper into the issue, and I believe it is because the _NvOSD_MaskParams object (a C struct) contains a pointer to an array of floats:
/**
*From /deepstream_sdk_v6.0.1_jetson/opt/nvidia/deepstream/deepstream-6.0/sources/includes/nvll_osd_struct.h
*/
/**
* Holds the mask parameters of the segment to be overlayed
*/
typedef struct _NvOSD_MaskParams {
float *data; /** Mask data */
unsigned int size; /** Mask size */
float threshold; /** Threshold for binarization */
unsigned int width; /** Mask width */
unsigned int height; /** Mask height */
} NvOSD_MaskParams;
Here, data is a pointer to an array of type float, and I believe Pybind11 is unable to interpret this and is thus throwing the error.
Is there any solution to this?
Thank you so much,
Adam
• How to reproduce the issue ? (This is for bugs. Including which sample app is using, the configuration files content, the command line used and other details for reproducing)
App: Modified version of python test 1 (code provided below) : /deepstream_python_apps/apps/deepstream-test1
Config file: /deepstream_tao_apps/configs/peopleSegNet_tao/pgie_peopleSegNet_tao_config.txt
Model: /deepstream_tao_apps/models/peopleSegNet
• Requirement details( This is for new requirement. Including the module name-for which plugin or for which sample application, the function description)
Install the TRT OSS plugin (libnvinfer_plugin.so.8.2.1)
Modified Sample App Test 1:
#!/usr/bin/env python3
################################################################################
# SPDX-FileCopyrightText: Copyright (c) 2019-2021 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# SPDX-License-Identifier: Apache-2.0
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
################################################################################
import sys
sys.path.append('../')
import gi
gi.require_version('Gst', '1.0')
from gi.repository import GObject, Gst
from common.is_aarch_64 import is_aarch64
from common.bus_call import bus_call
import pyds
# PGIE_CLASS_ID_VEHICLE = 0
# PGIE_CLASS_ID_BICYCLE = 1
# PGIE_CLASS_ID_PERSON = 2
# PGIE_CLASS_ID_ROADSIGN = 3
def osd_sink_pad_buffer_probe(pad,info,u_data):
frame_number=0
# #Intiallizing object counter with 0.
# obj_counter = {
# PGIE_CLASS_ID_VEHICLE:0,
# PGIE_CLASS_ID_PERSON:0,
# PGIE_CLASS_ID_BICYCLE:0,
# PGIE_CLASS_ID_ROADSIGN:0
# }
num_rects=0
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.glist_get_nvds_frame_meta()
# 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.glist_get_nvds_frame_meta(l_frame.data)
frame_meta = pyds.NvDsFrameMeta.cast(l_frame.data)
except StopIteration:
break
frame_number=frame_meta.frame_num
num_rects = frame_meta.num_obj_meta
l_obj=frame_meta.obj_meta_list
while l_obj is not None:
try:
# Casting l_obj.data to pyds.NvDsObjectMeta
#obj_meta=pyds.glist_get_nvds_object_meta(l_obj.data)
obj_meta=pyds.NvDsObjectMeta.cast(l_obj.data)
except StopIteration:
break
# obj_counter[obj_meta.class_id] += 1
obj_meta.rect_params.border_color.set(0.0, 0.0, 1.0, 0.0)
try:
l_obj=l_obj.next
except StopIteration:
break
# Acquiring a display meta object. The memory ownership remains in
# the C code so downstream plugins can still access it. Otherwise
# the garbage collector will claim it when this probe function exits.
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)
print(f"frame number: {frame_number}")
print(obj_meta.class_id)
print(obj_meta.object_id)
print(f"confidence: {obj_meta.confidence}")
# print(obj_meta.tracker_bbox_info)
# print(obj_meta.tracker_confidence)
rect_params=obj_meta.rect_params
print("rectangle: top, left, width, height")
print(int(rect_params.top), int(rect_params.left), int(rect_params.width), int(rect_params.height))
print(obj_meta.mask_params.size)
print(obj_meta.obj_label)
# # # 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
def main(args):
# Check input arguments
if len(args) != 2:
sys.stderr.write("usage: %s <media file or uri>\n" % args[0])
sys.exit(1)
# Standard GStreamer initialization
GObject.threads_init()
Gst.init(None)
# Create gstreamer elements
# Create Pipeline element that will form a connection of other elements
print("Creating Pipeline \n ")
pipeline = Gst.Pipeline()
if not pipeline:
sys.stderr.write(" Unable to create Pipeline \n")
# Source element for reading from the file
print("Creating Source \n ")
source = Gst.ElementFactory.make("filesrc", "file-source")
if not source:
sys.stderr.write(" Unable to create Source \n")
# Since the data format in the input file is elementary h264 stream,
# we need a h264parser
print("Creating H264Parser \n")
h264parser = Gst.ElementFactory.make("h264parse", "h264-parser")
if not h264parser:
sys.stderr.write(" Unable to create h264 parser \n")
# Use nvdec_h264 for hardware accelerated decode on GPU
print("Creating Decoder \n")
decoder = Gst.ElementFactory.make("nvv4l2decoder", "nvv4l2-decoder")
if not decoder:
sys.stderr.write(" Unable to create Nvv4l2 Decoder \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")
# Use nvinfer to run inferencing on decoder's output,
# behaviour of inferencing is set through config file
pgie = Gst.ElementFactory.make("nvinfer", "primary-inference")
if not pgie:
sys.stderr.write(" Unable to create pgie \n")
# Use convertor to convert from NV12 to RGBA as required by nvosd
nvvidconv = Gst.ElementFactory.make("nvvideoconvert", "convertor")
if not nvvidconv:
sys.stderr.write(" Unable to create nvvidconv \n")
# Create OSD to draw on the converted RGBA buffer
nvosd = Gst.ElementFactory.make("nvdsosd", "onscreendisplay")
# Display mask
nvosd.set_property('display-mask',1)
nvosd.set_property('process-mode',0)
nvosd.set_property("display-text", 0)
nvosd.set_property("display-bbox", 0)
if not nvosd:
sys.stderr.write(" Unable to create nvosd \n")
# Finally render the osd output
if is_aarch64():
transform = Gst.ElementFactory.make("nvegltransform", "nvegl-transform")
print("Creating EGLSink \n")
sink = Gst.ElementFactory.make("nveglglessink", "nvvideo-renderer")
if not sink:
sys.stderr.write(" Unable to create egl sink \n")
print("Playing file %s " %args[1])
source.set_property('location', args[1])
streammux.set_property('width', int(1920/2))
streammux.set_property('height', int(1080/2))
streammux.set_property('batch-size', 1)
streammux.set_property('batched-push-timeout', 4000000)
pgie.set_property('config-file-path', "pgie_peopleSegNet_tao_config.txt")
print("Adding elements to Pipeline \n")
pipeline.add(source)
pipeline.add(h264parser)
pipeline.add(decoder)
pipeline.add(streammux)
pipeline.add(pgie)
pipeline.add(nvvidconv)
pipeline.add(nvosd)
pipeline.add(sink)
if is_aarch64():
pipeline.add(transform)
# we link the elements together
# file-source -> h264-parser -> nvh264-decoder ->
# nvinfer -> nvvidconv -> nvosd -> video-renderer
print("Linking elements in the Pipeline \n")
source.link(h264parser)
h264parser.link(decoder)
sinkpad = streammux.get_request_pad("sink_0")
if not sinkpad:
sys.stderr.write(" Unable to get the sink pad of streammux \n")
srcpad = decoder.get_static_pad("src")
if not srcpad:
sys.stderr.write(" Unable to get source pad of decoder \n")
srcpad.link(sinkpad)
streammux.link(pgie)
pgie.link(nvvidconv)
nvvidconv.link(nvosd)
if is_aarch64():
nvosd.link(transform)
transform.link(sink)
else:
nvosd.link(sink)
# create an event loop and feed gstreamer bus mesages to it
loop = GObject.MainLoop()
bus = pipeline.get_bus()
bus.add_signal_watch()
bus.connect ("message", bus_call, loop)
# Lets add probe to get informed of the meta data generated, we add probe to
# the sink pad of the osd element, since by that time, the buffer would have
# had got all the metadata.
# osdsinkpad = nvosd.get_static_pad("sink")
# if not osdsinkpad:
# sys.stderr.write(" Unable to get sink pad of nvosd \n")
# osdsinkpad.add_probe(Gst.PadProbeType.BUFFER, osd_sink_pad_buffer_probe, 0)
sinkpad1 = sink.get_static_pad("sink")
if not sinkpad1:
sys.stderr.write(" Unable to get sink pad\n")
sinkpad1.add_probe(Gst.PadProbeType.BUFFER, osd_sink_pad_buffer_probe, 0)
# start play back and listen to events
print("Starting pipeline \n")
pipeline.set_state(Gst.State.PLAYING)
try:
loop.run()
except:
pass
# cleanup
pipeline.set_state(Gst.State.NULL)
if __name__ == '__main__':
sys.exit(main(sys.argv))