Update to 1.1.8 release

This release is compatible with DeepStream SDK 6.3 Ubuntu 20.04 Python 3.8 DeepStream SDK 6.3 Features: - New interactive Jupyter notebook for LaunchPad demo - New binding added: configure_source_for_ntp_sync() - Updated deepstream-rtsp-in-rtsp-out app with new command line argument demonstrating above binding - Updated apps that use tracker for deprecated configs
NVIDIA-AI-IOT · Aug 8, 2023 · 8178b5e · 8178b5e
1 parent 441b50d
commit 8178b5e
Show file tree

Hide file tree

Showing 62 changed files with 2,223 additions and 2,584 deletions.
diff --git a/FAQ.md b/FAQ.md
@@ -152,5 +152,5 @@ The pyds wheel installs the pyds.so library where all the pip packages are store
 
 Command to install the pyds wheel is:
 ```bash
-   $ pip3 install ./pyds-1.1.6-py3-none*.whl
+   $ pip3 install ./pyds-1.1.8-py3-none*.whl
 ```
diff --git a/HOWTO.md b/HOWTO.md
@@ -16,7 +16,7 @@ This guide provides resources for DeepStream application development in Python.
 ## Prerequisites
 
 * Ubuntu 20.04
-* [DeepStream SDK 6.2](https://developer.nvidia.com/deepstream-download) or later
+* [DeepStream SDK 6.3](https://developer.nvidia.com/deepstream-download) or later
 * Python 3.8
 * [Gst Python](https://gstreamer.freedesktop.org/modules/gst-python.html) v1.16.2
 
@@ -46,11 +46,11 @@ Note: Compiling bindings now also generates a pip installable python wheel for t
 <a name="run_samples"></a>
 ## Running Sample Applications
 
-Clone the deepstream_python_apps repo under <DeepStream 6.2 ROOT>/sources:
+Clone the deepstream_python_apps repo under <DeepStream ROOT>/sources:
 git clone https://github.com/NVIDIA-AI-IOT/deepstream_python_apps
 
 This will create the following directory:  
-```<DeepStream 6.2 ROOT>/sources/deepstream_python_apps```
+```<DeepStream ROOT>/sources/deepstream_python_apps```
 
 The Python apps are under the "apps" directory.  
 Go into each app directory and follow instructions in the README.  

diff --git a/README.md b/README.md
@@ -2,11 +2,11 @@
 
 This repository contains Python bindings and sample applications for the [DeepStream SDK](https://developer.nvidia.com/deepstream-sdk).  
 
-SDK version supported: 6.2
+SDK version supported: 6.3
 
 <b>The bindings sources along with build instructions are now available under [bindings](bindings)! We now include a [guide](bindings/BINDINGSGUIDE.md) for contributing to bindings and another [guide](bindings/CUSTOMUSERMETAGUIDE.md) for advanced use-cases such as writing bindings for custom data structures.</b>
 
-<b>This release only supports Ubuntu 20.04 for DeepStreamSDK 6.2 with Python 3.8 and [gst-python](3rdparty/gst-python/) 1.16.2! Ubuntu 18.04 support is now deprecrated.</b>
+<b>This release only supports Ubuntu 20.04 for DeepStreamSDK 6.3 with Python 3.8 and [gst-python](3rdparty/gst-python/) 1.16.2! Ubuntu 18.04 support is now deprecrated.</b>
 
 Download the latest release package complete with bindings and sample applications from the [release section](../../releases).  
 
@@ -41,7 +41,7 @@ To run the sample applications or write your own, please consult the [HOW-TO Gui
 </p>
 
 We currently provide the following sample applications:
-* <b>UPDATED</b> [deepstream-test1](apps/deepstream-test1) -- 4-class object detection pipeline - now also demonstrates support for new nvstreammux
+* [deepstream-test1](apps/deepstream-test1) -- 4-class object detection pipeline - now also demonstrates support for new nvstreammux
 * [deepstream-test2](apps/deepstream-test2) -- 4-class object detection, tracking and attribute classification pipeline
 * [deepstream-test3](apps/deepstream-test3) -- multi-stream pipeline performing 4-class object detection - now also supports triton inference server, no-display mode, file-loop and silent mode
 * [deepstream-test4](apps/deepstream-test4) -- msgbroker for sending analytics results to the cloud
@@ -54,12 +54,12 @@ We currently provide the following sample applications:
 * [deepstream-nvdsanalytics](apps/deepstream-nvdsanalytics) -- multistream pipeline with analytics plugin
 * [runtime_source_add_delete](apps/runtime_source_add_delete) -- add/delete source streams at runtime
 * [deepstream-imagedata-multistream-redaction](apps/deepstream-imagedata-multistream-redaction) -- multi-stream pipeline with face detection and redaction
-* [deepstream-rtsp-in-rtsp-out](apps/deepstream-rtsp-in-rtsp-out) -- multi-stream pipeline with RTSP input/output
+* <b>UPDATED</b> [deepstream-rtsp-in-rtsp-out](apps/deepstream-rtsp-in-rtsp-out) -- multi-stream pipeline with RTSP input/output -- now takes new command line argument "--rtsp-ts" for configuring the RTSP source to attach the timestamp rather than the streammux
 * [deepstream-preprocess-test](apps/deepstream-preprocess-test) -- multi-stream pipeline using nvdspreprocess plugin with custom ROIs
 * [deepstream-demux-multi-in-multi-out](apps/deepstream-demux-multi-in-multi-out) -- multi-stream pipeline using nvstreamdemux plugin to generated separate buffer outputs
 * [deepstream-imagedata-multistream-cupy](apps/deepstream-imagedata-multistream-cupy) -- access imagedata buffer from GPU in a multistream source as CuPy array - x86 only
-* <b>NEW</b> [deepstream-segmask](apps/deepstream-segmask) -- access and interpret segmentation mask information from NvOSD_MaskParams
-* <b>NEW</b> [deepstream-custom-binding-test](apps/deepstream-custom-binding-test) -- demonstrate usage of NvDsUserMeta for attaching custom data structure - see also the [Custom User Meta Guide](bindings/CUSTOMUSERMETAGUIDE.md)
+* [deepstream-segmask](apps/deepstream-segmask) -- access and interpret segmentation mask information from NvOSD_MaskParams
+* [deepstream-custom-binding-test](apps/deepstream-custom-binding-test) -- demonstrate usage of NvDsUserMeta for attaching custom data structure - see also the [Custom User Meta Guide](bindings/CUSTOMUSERMETAGUIDE.md)
 
 
 Detailed application information is provided in each application's subdirectory under [apps](apps).  

diff --git a/apps/README b/apps/README
@@ -20,7 +20,7 @@ DeepStream SDK Python Bindings
 ================================================================================
 Setup pre-requisites:
 - Ubuntu 20.04
-- NVIDIA DeepStream SDK 6.2
+- NVIDIA DeepStream SDK 6.3
 - Python 3.8
 - Gst-python
 
@@ -36,7 +36,7 @@ Package Contents
 Installing Pre-requisites:
 --------------------------------------------------------------------------------
 
-DeepStream SDK 6.2
+DeepStream SDK 6.3
 --------------------
 Download and install from https://developer.nvidia.com/deepstream-download
 
@@ -54,7 +54,7 @@ $ sudo apt install python3-gi python3-dev python3-gst-1.0 -y
 --------------------------------------------------------------------------------
 Running the samples
 --------------------------------------------------------------------------------
-The apps are configured to work from inside the DeepStream SDK 6.2 installation.
+The apps are configured to work from inside the DeepStream SDK 6.3 installation.
 
 Clone the deepstream_python_apps repo under <DeepStream ROOT>/sources:
 $ git clone https://github.com/NVIDIA-AI-IOT/deepstream_python_apps

diff --git a/apps/deepstream-custom-binding-test/README b/apps/deepstream-custom-binding-test/README
@@ -16,7 +16,7 @@
 ################################################################################
 
 Prequisites:
-- DeepStreamSDK 6.2
+- DeepStreamSDK 6.3
 - Python 3.8
 - Gst-python
 

diff --git a/apps/deepstream-demux-multi-in-multi-out/README b/apps/deepstream-demux-multi-in-multi-out/README
@@ -16,7 +16,7 @@
 ################################################################################
 
 Prerequisites:
-- DeepStreamSDK 6.2
+- DeepStreamSDK 6.3
 - Python 3.8
 - Gst-python
 

diff --git a/apps/deepstream-imagedata-multistream-cupy/README b/apps/deepstream-imagedata-multistream-cupy/README
@@ -1,5 +1,5 @@
 ################################################################################
-# SPDX-FileCopyrightText: Copyright (c) 2022 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
+# SPDX-FileCopyrightText: Copyright (c) 2022-2023 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
 # SPDX-License-Identifier: Apache-2.0
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
@@ -16,19 +16,19 @@
 ################################################################################
 
 Prerequisites:
-- DeepStreamSDK 6.2
+- DeepStreamSDK 6.3
 - Python 3.8
 - Gst-python
 - NumPy package
 - OpenCV package
-- CuPy for Cuda 11.2 or later
+- CuPy for Cuda 12.1 or later
 
 ** This application is currently only supported on x86.
 
 To install required packages:
 $ sudo apt update
 $ sudo apt install python3-numpy python3-opencv -y
-$ pip3 install cupy-cuda11x
+$ pip3 install cupy-cuda12x
 
 To run:
   $ python3 deepstream_imagedata-multistream_cupy.py -i <uri1> [uri2] ... [uriN]
@@ -92,4 +92,4 @@ broken down into the following steps:
  4. Construction of cupy.cuda.MemoryPointer from UnownedMemory
  5. Construction of cupy.ndarray from MemoryPointer and other buffer info retrieved from bindings call
 
-When performing operations on the image array, we use a CUDA null stream to prevent access of buffer memory by other CUDA operations.
+When performing operations on the image array, we use a CUDA null stream to prevent access of buffer memory by other CUDA operations.
diff --git a/apps/deepstream-imagedata-multistream-redaction/README b/apps/deepstream-imagedata-multistream-redaction/README
@@ -16,7 +16,7 @@
 ################################################################################
 
 Prerequisites:
-- DeepStreamSDK 6.2
+- DeepStreamSDK 6.3
 - Python 3.8
 - Gst-python
 - NumPy package

diff --git a/apps/deepstream-imagedata-multistream/README b/apps/deepstream-imagedata-multistream/README
@@ -16,7 +16,7 @@
 ################################################################################
 
 Prerequisites:
-- DeepStreamSDK 6.2
+- DeepStreamSDK 6.3
 - Python 3.8
 - Gst-python
 - NumPy package

diff --git a/apps/deepstream-nvdsanalytics/README b/apps/deepstream-nvdsanalytics/README
@@ -16,7 +16,7 @@
 ################################################################################
 
 Prerequisites:
-- DeepStreamSDK 6.2
+- DeepStreamSDK 6.3
 - Python 3.8
 - Gst-python
 

diff --git a/apps/deepstream-nvdsanalytics/deepstream_nvdsanalytics.py b/apps/deepstream-nvdsanalytics/deepstream_nvdsanalytics.py
@@ -364,12 +364,6 @@ def main(args):
         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)
-        if key == 'enable-past-frame' :
-            tracker_enable_past_frame = config.getint('tracker', key)
-            tracker.set_property('enable_past_frame', tracker_enable_past_frame)
 
     print("Adding elements to Pipeline \n")
     pipeline.add(pgie)

diff --git a/apps/deepstream-nvdsanalytics/dsnvanalytics_tracker_config.txt b/apps/deepstream-nvdsanalytics/dsnvanalytics_tracker_config.txt
@@ -28,5 +28,3 @@ tracker-height=384
 gpu-id=0
 ll-lib-file=/opt/nvidia/deepstream/deepstream/lib/libnvds_nvmultiobjecttracker.so
 ll-config-file=config_tracker_NvDCF_perf.yml
-#enable-past-frame=1
-enable-batch-process=1
diff --git a/apps/deepstream-opticalflow/README b/apps/deepstream-opticalflow/README
@@ -16,7 +16,7 @@
 ################################################################################
 
 Prerequisites:
-- DeepStreamSDK 6.2
+- DeepStreamSDK 6.3
 - Python 3.8
 - Gst-python
 - NumPy package

diff --git a/apps/deepstream-opticalflow/deepstream-opticalflow.py b/apps/deepstream-opticalflow/deepstream-opticalflow.py
@@ -62,7 +62,7 @@ def visualize_optical_flowvectors(flow):
     return bgr
 
 
-# tiler_sink_pad_buffer_probe  will extract metadata received on OSD sink pad
+# ofvisual_queue_src_pad_buffer_probe  will extract metadata received on OSD sink pad
 def ofvisual_queue_src_pad_buffer_probe(pad, info, u_data):
     got_visual = False
     frame_number = 0

diff --git a/apps/deepstream-preprocess-test/README b/apps/deepstream-preprocess-test/README
@@ -16,7 +16,7 @@
 ################################################################################
 
 Prerequisites:
-- DeepStreamSDK 6.2
+- DeepStreamSDK 6.3
 - Python 3.8
 - Gst-python
 - GstRtspServer

diff --git a/apps/deepstream-rtsp-in-rtsp-out/README b/apps/deepstream-rtsp-in-rtsp-out/README
@@ -16,7 +16,7 @@
 ################################################################################
 
 Prequisites:
-- DeepStreamSDK 6.2
+- DeepStreamSDK 6.3
 - Python 3.8
 - Gst-python
 - GstRtspServer
@@ -76,3 +76,5 @@ This sample app specifically includes following :
     4. Performs post-processing on the generated boxes with NMS (Non-maximum Suppression)
     5. Adds detected objects into the pipeline metadata for downstream processing
     6. Encodes OSD output and shows visual output over RTSP.
+
+The "--rtsp-ts" option configures the RTSP source to attach the timestamp to the frame, as opposed to the streammux. Before using this option, please make sure the RTSP source sends RTCP Sender Reports. See this documentation for more details on how to check: https://docs.nvidia.com/metropolis/deepstream/dev-guide/text/DS_NTP_Timestamp.html.
diff --git a/apps/deepstream-rtsp-in-rtsp-out/deepstream_test1_rtsp_in_rtsp_out.py b/apps/deepstream-rtsp-in-rtsp-out/deepstream_test1_rtsp_in_rtsp_out.py
@@ -30,6 +30,7 @@
 gi.require_version("GstRtspServer", "1.0")
 from gi.repository import Gst, GstRtspServer, GLib
 import configparser
+import datetime
 
 import argparse
 
@@ -48,11 +49,11 @@
 OSD_DISPLAY_TEXT = 0
 pgie_classes_str = ["Vehicle", "TwoWheeler", "Person", "RoadSign"]
 
-# tiler_sink_pad_buffer_probe  will extract metadata received on OSD sink pad
+# pgie_src_pad_buffer_probe  will extract metadata received on OSD sink pad
 # and update params for drawing rectangle, object information etc.
 
 
-def tiler_src_pad_buffer_probe(pad, info, u_data):
+def pgie_src_pad_buffer_probe(pad, info, u_data):
     frame_number = 0
     num_rects = 0
     gst_buffer = info.get_buffer()
@@ -77,36 +78,13 @@ def tiler_src_pad_buffer_probe(pad, info, u_data):
             break
 
         frame_number = frame_meta.frame_num
-        l_obj = frame_meta.obj_meta_list
-        num_rects = frame_meta.num_obj_meta
-        obj_counter = {
-            PGIE_CLASS_ID_VEHICLE: 0,
-            PGIE_CLASS_ID_PERSON: 0,
-            PGIE_CLASS_ID_BICYCLE: 0,
-            PGIE_CLASS_ID_ROADSIGN: 0,
-        }
-        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
-            try:
-                l_obj = l_obj.next
-            except StopIteration:
-                break
-
         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],
+            frame_number
         )
+        if ts_from_rtsp:
+            ts = frame_meta.ntp_timestamp/1000000000 # Retrieve timestamp, put decimal in proper position for Unix format
+            print("RTSP Timestamp:",datetime.datetime.utcfromtimestamp(ts).strftime('%Y-%m-%d %H:%M:%S')) # Convert timestamp to UTC
 
         try:
             l_frame = l_frame.next
@@ -149,6 +127,10 @@ def decodebin_child_added(child_proxy, Object, name, user_data):
     if name.find("decodebin") != -1:
         Object.connect("child-added", decodebin_child_added, user_data)
 
+    if ts_from_rtsp:
+        if name.find("source") != -1:
+            pyds.configure_source_for_ntp_sync(hash(Object))
+
 
 def create_source_bin(index, uri):
     print("Creating source bin")
@@ -298,8 +280,11 @@ def main(args):
 
     streammux.set_property("width", 1920)
     streammux.set_property("height", 1080)
-    streammux.set_property("batch-size", 1)
+    streammux.set_property("batch-size", number_sources)
     streammux.set_property("batched-push-timeout", 4000000)
+
+    if ts_from_rtsp:
+        streammux.set_property("attach-sys-ts", 0)
 
     if gie=="nvinfer":
         pgie.set_property("config-file-path", "dstest1_pgie_config.txt")
@@ -353,6 +338,12 @@ def main(args):
     bus.add_signal_watch()
     bus.connect("message", bus_call, loop)
 
+    pgie_src_pad=pgie.get_static_pad("src")
+    if not pgie_src_pad:
+        sys.stderr.write(" Unable to get src pad \n")
+    else:
+        pgie_src_pad.add_probe(Gst.PadProbeType.BUFFER, pgie_src_pad_buffer_probe, 0)
+
     # Start streaming
     rtsp_port_num = 8554
 
@@ -394,6 +385,8 @@ def parse_args():
                   help="RTSP Streaming Codec H264/H265 , default=H264", choices=['H264','H265'])
     parser.add_argument("-b", "--bitrate", default=4000000,
                   help="Set the encoding bitrate ", type=int)
+    parser.add_argument("--rtsp-ts", action="store_true", default=False, dest='rtsp_ts', help="Attach NTP timestamp from RTSP source",
+    )
     # Check input arguments
     if len(sys.argv)==1:
         parser.print_help(sys.stderr)
@@ -403,10 +396,12 @@ def parse_args():
     global bitrate
     global stream_path
     global gie
+    global ts_from_rtsp
     gie = args.gie
     codec = args.codec
     bitrate = args.bitrate
     stream_path = args.input
+    ts_from_rtsp = args.rtsp_ts
     return stream_path
 
 if __name__ == '__main__':

diff --git a/apps/deepstream-segmask/README b/apps/deepstream-segmask/README
@@ -16,8 +16,7 @@
 ################################################################################
 
 Prerequisites:
-- DeepStreamSDK 6.2
-- Python 3.8
+- DeepStreamSDK 6.3
 - Gst-python
 - NumPy package
 - OpenCV package

diff --git a/apps/deepstream-segmentation/README b/apps/deepstream-segmentation/README
@@ -16,7 +16,7 @@
 ################################################################################
 
 Prerequisites:
-- DeepStreamSDK 6.2
+- DeepStreamSDK 6.3
 - Python 3.8
 - Gst-python
 - NumPy package

diff --git a/apps/deepstream-ssd-parser/README b/apps/deepstream-ssd-parser/README
@@ -16,7 +16,7 @@
 ################################################################################
 
 Prequisites:
-- DeepStreamSDK 6.2
+- DeepStreamSDK 6.3
 - NVIDIA Triton Inference Server
 - Python 3.8
 - Gst-python