Please provide complete information as applicable to your setup.
• Hardware Platform (Jetson / GPU) - GeForce RTX 2080 Ti
• DeepStream Version - 6.2
• TensorRT Version - 8.5.2
• NVIDIA GPU Driver Version (valid for GPU only) - 535.54.03
• Issue Type( questions, new requirements, bugs) - bugs
Hi,
I modified deepstream-segmask to save the image after segmentation(i dont want mask as in the example), and i get:
Error: gst-stream-error-quark: memory type configured and i/p buffer mismatch ip_surf 2 muxer 3 (1): gstnvstreammux.c(643): gst_nvstreammux_chain (): /GstPipeline:pipeline0/GstNvStreamMux:Stream-muxer
This is my code:
#!/usr/bin/env python3
import sys
from syslog import LOG_WARNING
sys.path.append('../')
import gi
import configparser
gi.require_version('Gst', '1.0')
from gi.repository import GLib, Gst
from ctypes import *
import time
import sys
import math
import platform
from common.is_aarch_64 import is_aarch64
from common.bus_call import bus_call
from common.FPS import PERF_DATA
import numpy as np
import pyds
import cv2
import os
import os.path
from os import path
import argparse
perf_data = None
MAX_DISPLAY_LEN = 64
MUXER_OUTPUT_WIDTH = 1920
MUXER_OUTPUT_HEIGHT = 1080
MUXER_BATCH_TIMEOUT_USEC = 4000000
TILED_OUTPUT_WIDTH = 1920
TILED_OUTPUT_HEIGHT = 1080
GST_CAPS_FEATURES_NVMM = "memory:NVMM"
def tiler_sink_pad_buffer_probe(pad, info, u_data):
frame_number = 0
num_rects = 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
l_obj = frame_meta.obj_meta_list
num_rects = frame_meta.num_obj_meta
is_first_obj = True
save_image = False
obj_number = 0
while l_obj is not None:
try:
obj_meta = pyds.NvDsObjectMeta.cast(l_obj.data)
except StopIteration:
break
if is_first_obj and frame_number % 30 == 0:
is_first_obj = False
rectparams = obj_meta.rect_params
maskparams = obj_meta.mask_params
mask_image = resize_mask(maskparams, math.floor(rectparams.width), math.floor(rectparams.height))
n_frame = pyds.get_nvds_buf_surface(hash(gst_buffer), frame_meta.batch_id)
frame_image = np.array(n_frame, copy=True, order='C')
frame_image = cv2.cvtColor(frame_image, cv2.COLOR_RGBA2BGR)
original_image = cv2.resize(frame_image, (mask_image.shape[1], mask_image.shape[0]))
# Create 3-channel mask image
mask_image = cv2.merge((mask_image, mask_image, mask_image))
# Apply mask to original image
segmented_image = cv2.bitwise_and(original_image, mask_image)
img_path = "{}/stream_{}/frame_{}.jpg".format(folder_name, frame_meta.pad_index, frame_number)
cv2.imwrite(img_path, segmented_image)
try:
l_obj = l_obj.next
obj_number += 1
except StopIteration:
break
print("Frame Number=", frame_number, "Number of Objects=", num_rects)
stream_index = "stream{0}".format(frame_meta.pad_index)
global perf_data
perf_data.update_fps(stream_index)
try:
l_frame = l_frame.next
except StopIteration:
break
return Gst.PadProbeReturn.OK
def clip(val, low, high):
if val < low:
return low
elif val > high:
return high
else:
return val
# Resize and binarize mask array for interpretable segmentation mask
def resize_mask(maskparams, target_width, target_height):
src = maskparams.get_mask_array() # Retrieve mask array
dst = np.empty((target_height, target_width), src.dtype) # Initialize array to store re-sized mask
original_width = maskparams.width
original_height = maskparams.height
ratio_h = float(original_height) / float(target_height)
ratio_w = float(original_width) / float(target_width)
threshold = maskparams.threshold
channel = 1
# Resize from original width/height to target width/height
for y in range(target_height):
for x in range(target_width):
x0 = float(x) * ratio_w
y0 = float(y) * ratio_h
left = int(clip(math.floor(x0), 0.0, float(original_width - 1.0)))
top = int(clip(math.floor(y0), 0.0, float(original_height - 1.0)))
right = int(clip(math.ceil(x0), 0.0, float(original_width - 1.0)))
bottom = int(clip(math.ceil(y0), 0.0, float(original_height - 1.0)))
for c in range(channel):
# H, W, C ordering
# Note: lerp is shorthand for linear interpolation
left_top_val = float(src[top * (original_width * channel) + left * (channel) + c])
right_top_val = float(src[top * (original_width * channel) + right * (channel) + c])
left_bottom_val = float(src[bottom * (original_width * channel) + left * (channel) + c])
right_bottom_val = float(src[bottom * (original_width * channel) + right * (channel) + c])
top_lerp = left_top_val + (right_top_val - left_top_val) * (x0 - left)
bottom_lerp = left_bottom_val + (right_bottom_val - left_bottom_val) * (x0 - left)
lerp = top_lerp + (bottom_lerp - top_lerp) * (y0 - top)
if (lerp < threshold): # Binarize according to threshold
dst[y,x] = 0
else:
dst[y,x] = 255
return dst
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.
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.
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:
source_element = child_proxy.get_by_name("source")
if source_element.find_property('drop-on-latency') != None:
Object.set_property("drop-on-latency", True)
def create_source_bin(index, uri):
print("Creating source bin")
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")
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)
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
def main(stream_paths, output_folder):
global perf_data
perf_data = PERF_DATA(len(stream_paths))
number_sources = len(stream_paths)
global folder_name
folder_name = output_folder
if path.exists(folder_name):
sys.stderr.write("The output folder %s already exists. Please remove it first.\n" % folder_name)
sys.exit(1)
os.mkdir(folder_name)
print("Frames will be saved in ", folder_name)
# 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 streammux \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):
os.mkdir(folder_name + "/stream_" + str(i))
print("Creating source_bin ", i, " \n ")
uri_name = stream_paths[i]
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.get_request_pad(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)
print("Creating Pgie \n ")
pgie = Gst.ElementFactory.make("nvinfer", "primary-inference")
if not pgie:
sys.stderr.write(" Unable to create pgie \n")
# Add nvvidconv1 and filter1 to convert the frames to RGBA
# which is easier to work with in Python.
print("Creating nvvidconv1 \n ")
nvvidconv1 = Gst.ElementFactory.make("nvvideoconvert", "convertor1")
if not nvvidconv1:
sys.stderr.write(" Unable to create nvvidconv1 \n")
print("Creating filter1 \n ")
caps1 = Gst.Caps.from_string("video/x-raw(memory:NVMM), format=RGBA")
filter1 = Gst.ElementFactory.make("capsfilter", "filter1")
if not filter1:
sys.stderr.write(" Unable to get the caps filter1 \n")
filter1.set_property("caps", caps1)
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")
if is_aarch64():
print("Creating nv3dsink \n")
sink = Gst.ElementFactory.make("nv3dsink", "nv3d-sink")
if not sink:
sys.stderr.write(" Unable to create nv3dsink \n")
else:
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', "dstest_segmask_config.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)
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("sync", 0)
sink.set_property("qos", 0)
if not is_aarch64():
# Use CUDA unified memory in the pipeline so frames
# can be easily accessed on CPU in Python.
mem_type = int(pyds.NVBUF_MEM_CUDA_UNIFIED)
streammux.set_property("nvbuf-memory-type", mem_type)
nvvidconv.set_property("nvbuf-memory-type", mem_type)
nvvidconv1.set_property("nvbuf-memory-type", mem_type)
tiler.set_property("nvbuf-memory-type", mem_type)
print("Adding elements to Pipeline \n")
pipeline.add(pgie)
pipeline.add(tiler)
pipeline.add(nvvidconv)
pipeline.add(filter1)
pipeline.add(nvvidconv1)
pipeline.add(nvosd)
pipeline.add(sink)
print("Linking elements in the Pipeline \n")
streammux.link(pgie)
pgie.link(nvvidconv1)
nvvidconv1.link(filter1)
filter1.link(tiler)
tiler.link(nvvidconv)
nvvidconv.link(nvosd)
nvosd.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)
tiler_sink_pad = tiler.get_static_pad("sink")
if not tiler_sink_pad:
sys.stderr.write(" Unable to get src pad \n")
else:
tiler_sink_pad.add_probe(Gst.PadProbeType.BUFFER, tiler_sink_pad_buffer_probe, 0)
# perf callback function to print fps every 5 sec
GLib.timeout_add(5000, perf_data.perf_print_callback)
# List the sources
print("Now playing...")
for i, source in enumerate(stream_paths):
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 parse_args():
parser = argparse.ArgumentParser(prog="deepstream_segmask.py",
description="deepstream-segmask takes multiple URI streams as input" \
" and re-sizes and binarizes segmentation mask arrays to save to image")
parser.add_argument(
"-i",
"--input",
help="Path to input streams",
nargs="+",
metavar="URIs",
default=["a"],
required=True,
)
parser.add_argument(
"-o",
"--output",
metavar="output_folder_name",
default="out",
help="Name of folder to output mask images",
)
args = parser.parse_args()
stream_paths = args.input
output_folder = args.output
return stream_paths, output_folder
if __name__ == '__main__':
stream_paths, output_folder = parse_args()
sys.exit(main(stream_paths, output_folder))