Deepstream freezes on Jetson

I’m running my edited version of the deepstream-test3 and the machine seems to work fine for a while, but then all the sudden the application will freeze. I thought it was the memory problem, but jetson-stat shows that it is not. The GPU just stops processing the rtsp stream all of the sudden. Anybody else experienced the same?

Jetson TX2
Deepstream 5.0
Jetpack 4.4

Can you use sudo tegrastats to check CPU/GPU/MEM stats?

Shows same stats of GPU just going idle even if I didn’t stop the application, the processing just freezes and doesn’t terminate. Sometimes it jumps back, sometimes it doesn’t.

From tegrastats, seems part of your apps is CPU intensive consuming, hard to say where goes wrong.
Is that possible share one workable sample which can run in our environments to repro your issue?

import sys
sys.path.append(’…/’)
import gi
import configparser
gi.require_version(‘Gst’, ‘1.0’)
from gi.repository import GObject, Gst
from gi.repository import GLib
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 GETFPS
import numpy as np
import pyds
import cv2
import os
import os.path
from os import path
from datetime import datetime
fps_streams={}
frame_count={}
saved_count={}
global PGIE_CLASS_ID_VEHICLE
PGIE_CLASS_ID_VEHICLE=0
global PGIE_CLASS_ID_PERSON
PGIE_CLASS_ID_PERSON=2

MAX_DISPLAY_LEN=64
PGIE_CLASS_ID_VEHICLE = 0
PGIE_CLASS_ID_BICYCLE = 1
PGIE_CLASS_ID_PERSON = 2
PGIE_CLASS_ID_ROADSIGN = 3
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"
pgie_classes_str= ["Person", "Bag", "Face","RoadSign"]

obj_timer={}


# tiler_sink_pad_buffer_probe  will extract metadata received on tiler src pad
# and update params for drawing rectangle, object information etc.
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
    obj_counter = {
        PGIE_CLASS_ID_VEHICLE:0,
        PGIE_CLASS_ID_PERSON:0,
        PGIE_CLASS_ID_BICYCLE:0,
        PGIE_CLASS_ID_ROADSIGN:0
        }    
    # 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
        num_rects = frame_meta.num_obj_meta
        is_first_obj = True
        save_image = False
        
        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
            obj_counter[obj_meta.class_id] += 1
            if pyds.NvDsObjectMeta.cast(l_obj.data).object_id not in obj_timer.keys() and pyds.NvDsObjectMeta.cast(l_obj.data).class_id == 0:
                obj_timer[pyds.NvDsObjectMeta.cast(l_obj.data).object_id] = datetime.now()
            if pyds.NvDsObjectMeta.cast(l_obj.data).class_id == 0:
                print(str(pyds.NvDsObjectMeta.cast(l_obj.data).object_id) + " has been here for "+str(datetime.now()-obj_timer[pyds.NvDsObjectMeta.cast(l_obj.data).object_id]))
            # Periodically check for objects with borderline confidence value that may be false positive detections.
            # If such detections are found, annoate the frame with bboxes and confidence value.
            # Save the annotated frame to file.
            if((saved_count["stream_"+str(frame_meta.pad_index)]%30==0) and (obj_meta.confidence>0.3)):
                if is_first_obj:
                    is_first_obj = False
                    # Getting Image data using nvbufsurface
                    # the input should be address of buffer and batch_id
                    n_frame=pyds.get_nvds_buf_surface(hash(gst_buffer),frame_meta.batch_id)
                    #convert python array into numy array format.
                    frame_image=np.array(n_frame,copy=True,order='C')
                    #covert the array into cv2 default color format
                    frame_image=cv2.cvtColor(frame_image,cv2.COLOR_RGBA2BGRA)

                save_image = True
                frame_image=draw_bounding_boxes(frame_image,obj_meta,obj_meta.confidence)
            try: 
                l_obj=l_obj.next
            except StopIteration:
                break
            
        # Get frame rate through this probe
        fps_streams["stream{0}".format(frame_meta.pad_index)].get_fps()
        if save_image:
            cv2.imwrite("/media/nvidiatx2/c794e009-b2df-4e5b-9ae2-d30a913b8eee/" +folder_name+"/stream_"+str(frame_meta.pad_index)+"/frame_"+str(frame_number)+".jpg",frame_image)
        saved_count["stream_"+str(frame_meta.pad_index)]+=1        
        # 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={} Vehicle_count={} Person_count={}".format(frame_number, num_rects, obj_counter[PGIE_CLASS_ID_VEHICLE], obj_counter[PGIE_CLASS_ID_PERSON])

        # 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)
        print("Frame Number=", frame_number, "Number of Objects=",num_rects,"Vehicle_count=",obj_counter[PGIE_CLASS_ID_VEHICLE],"Person_count=",obj_counter[PGIE_CLASS_ID_PERSON])
        try:
            l_frame=l_frame.next
        except StopIteration:
            break

    return Gst.PadProbeReturn.OK

def draw_bounding_boxes(image,obj_meta,confidence):
    confidence='{0:.2f}'.format(confidence)
    rect_params=obj_meta.rect_params
    top=int(rect_params.top)
    left=int(rect_params.left)
    width=int(rect_params.width)
    height=int(rect_params.height)
    obj_name=pgie_classes_str[obj_meta.class_id]
    image=cv2.rectangle(image,(left,top),(left+width,top+height),(0,0,255,0),2)
    # Note that on some systems cv2.putText erroneously draws horizontal lines across the image
    image=cv2.putText(image,"This is " +obj_name+',C='+str(confidence),(left-10,top-10),cv2.FONT_HERSHEY_SIMPLEX,0.5,(0,0,255,0),2)
    return image

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(is_aarch64() and name.find("nvv4l2decoder") != -1):
        print("Seting bufapi_version\n")
        Object.set_property("bufapi-version",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

def main(args):
    # Check input arguments
    if len(args) < 2:
        sys.stderr.write("usage: %s <uri1> [uri2] ... [uriN] <folder to save frames>\n" % args[0])
        sys.exit(1)

    for i in range(0,len(args)-2):
        fps_streams["stream{0}".format(i)]=GETFPS(i)
    number_sources=len(args)-2

    global folder_name
    folder_name=args[-1]
    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("/media/nvidiatx2/c794e009-b2df-4e5b-9ae2-d30a913b8eee/" + folder_name)
    print("Frames will be saved in ",folder_name)
    # 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()
    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):
        os.mkdir("/media/nvidiatx2/c794e009-b2df-4e5b-9ae2-d30a913b8eee/" + folder_name+"/stream_"+str(i))
        frame_count["stream_"+str(i)]=0
        saved_count["stream_"+str(i)]=0
        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.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")

    tracker = Gst.ElementFactory.make("nvtracker", "tracker")
    if not tracker:
        sys.stderr.write(" Unable to create tracker \n")
    #Set properties of tracker
    config = configparser.ConfigParser()
    config.read('dstest2_tracker_config.txt')
    config.sections()

    for key in config['tracker']:
        if key == 'tracker-width' :
            tracker_width = config.getint('tracker', key)
            tracker.set_property('tracker-width', tracker_width)
        if key == 'tracker-height' :
            tracker_height = config.getint('tracker', key)
            tracker.set_property('tracker-height', tracker_height)
        if key == 'gpu-id' :
            tracker_gpu_id = config.getint('tracker', key)
            tracker.set_property('gpu_id', tracker_gpu_id)
        if key == 'll-lib-file' :
            tracker_ll_lib_file = config.get('tracker', key)
            tracker.set_property('ll-lib-file', tracker_ll_lib_file)
        if key == 'll-config-file' :
            tracker_ll_config_file = config.get('tracker', key)
            tracker.set_property('ll-config-file', tracker_ll_config_file)
        if key == 'enable-batch-process' :
            tracker_enable_batch_process = config.getint('tracker', key)
            tracker.set_property('enable_batch_process', tracker_enable_batch_process)

    # 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 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', "config_infer_primary_peoplenet.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)

    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(tracker)
    pipeline.add(tiler)
    pipeline.add(nvvidconv)
    pipeline.add(filter1)
    pipeline.add(nvvidconv1)
    pipeline.add(nvosd)
    if is_aarch64():
        pipeline.add(transform)
    pipeline.add(sink)

    print("Linking elements in the Pipeline \n")
    streammux.link(pgie)
    pgie.link(tracker)    
    tracker.link(nvvidconv1)
    nvvidconv1.link(filter1)
    filter1.link(tiler)
    tiler.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)

    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)

    # List the sources
    print("Now playing...")
    for i, source in enumerate(args[:-1]):
        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)

if __name__ == '__main__':
    sys.exit(main(sys.argv))

This is my python code

I’m not sure if each instance has a limited amount of memory it can consume? I am running both an instance of the above code and a deepstream-test3 in parallel on separate console and only the edited version freezes. I know that there is a declared list, obj_timer, that is ever expanding; but since the memory doesn’t seem to be filled in the tegrastats I’m not sure if there are other codes limiting it

Hi,
I can not repro your issue, from picture you can see both your sample and test3 python sample running into ends. no freeze of your sample.
will look into further.

The error occurs like 40 minutes in. And now theres a new error:

Warning: gst-resource-error-quark: Could not read from resource. (9): gstrtspsrc.c(5280): gst_rtspsrc_loop_udp (): /GstPipeline:pipeline0/GstBin:source-bin-00/GstURIDecodeBin:uri-decode-bin/GstRTSPSrc:source:

Do you run with a long video file?

I’m running it on a live rtsp stream, it just randomly freezes on me maybe an hour in to the stream where as the deepstream-3 running along side does not.

I am using live rtsp stream and try again, run about 4 hours, never run into your issue.
Have you got any findings?