Update to 1.1.1 release

nv-zhliu · nv-zhliu · commit b768386c984f · 2022-03-08T22:29:20.000-08:00
Minor update:
- Support DeepStream SDK 6.0.1
- Fix memory leak in deepstream-test3 app
- Add missing binding for network_info field in NvDsInferTensorMeta
- Cross-compile dockerfile update
diff --git a/HOWTO.md b/HOWTO.md
@@ -16,7 +16,7 @@ This guide provides resources for DeepStream application development in Python.
 ## Prerequisites
 
 * Ubuntu 18.04
-* [DeepStream SDK 6.0](https://developer.nvidia.com/deepstream-download) or later
+* [DeepStream SDK 6.0.1](https://developer.nvidia.com/deepstream-download) or later
 * Python 3.6+
 * [Gst Python](https://gstreamer.freedesktop.org/modules/gst-python.html) v1.14.5
 
@@ -45,11 +45,11 @@ 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 6.0 ROOT>/sources:
+Clone the deepstream_python_apps repo under <DeepStream 6.0.1 ROOT>/sources:
 git clone https://github.com/NVIDIA-AI-IOT/deepstream_python_apps
 
 This will create the following directory:  
-```<DeepStream 6.0 ROOT>/sources/deepstream_python_apps```  
+```<DeepStream 6.0.1 ROOT>/sources/deepstream_python_apps```  
 
 The Python apps are under the "apps" directory.  
 Go into each app directory and follow instructions in the README.  
@@ -211,5 +211,5 @@ This function populates the input buffer with a timestamp generated according to
 <a name="imagedata_access"></a>
 ## Image Data Access
 
-Decoded images are accessible as NumPy arrays via the `get_nvds_buf_surface` function. This function is documented in the [API Guide](https://docs.nvidia.com/metropolis/deepstream/6.0/python-api/index.html).
+Decoded images are accessible as NumPy arrays via the `get_nvds_buf_surface` function. This function is documented in the [API Guide](https://docs.nvidia.com/metropolis/deepstream/6.0.1/python-api/index.html).
 Please see the [deepstream-imagedata-multistream](apps/deepstream-imagedata-multistream) sample application for an example of image data usage.
diff --git a/README.md b/README.md
@@ -2,7 +2,7 @@
 
 This repository contains Python bindings and sample applications for the [DeepStream SDK](https://developer.nvidia.com/deepstream-sdk).  
 
-SDK version supported: 6.0
+SDK version supported: 6.0.1
 
 <b>NEW: The bindings sources along with build instructions are now available under [bindings](bindings)!  </b>
 
diff --git a/apps/README b/apps/README
@@ -20,7 +20,7 @@ DeepStream SDK Python Bindings
 ================================================================================
 Setup pre-requisites:
 - Ubuntu 18.04
-- NVIDIA DeepStream SDK 6.0
+- NVIDIA DeepStream SDK 6.0.1
 - Python 3.6
 - Gst-python
 
@@ -58,7 +58,7 @@ The DeepStream Python package includes:
 Installing Pre-requisites:
 --------------------------------------------------------------------------------
 
-DeepStream SDK 6.0
+DeepStream SDK 6.0.1
 --------------------
 Download and install from https://developer.nvidia.com/deepstream-download
 
@@ -76,7 +76,7 @@ $ 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 6.0 installation.
+The apps are configured to work from inside the DeepStream SDK 6.0.1 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-imagedata-multistream-redaction/README b/apps/deepstream-imagedata-multistream-redaction/README
@@ -16,7 +16,7 @@
 ################################################################################
 
 Prerequisites:
-- DeepStreamSDK 6.0
+- DeepStreamSDK 6.0.1
 - Python 3.6
 - Gst-python
 - NumPy package
@@ -39,7 +39,7 @@ Yet, we need to install the introspection typelib package:
   $ sudo apt-get install gobject-introspection gir1.2-gst-rtsp-server-1.0
 
 Download Peoplenet model:
-  $ cd /opt/nvidia/deepstream/deepstream-6.0/samples/configs/tao_pretrained_models
+  $ cd /opt/nvidia/deepstream/deepstream/samples/configs/tao_pretrained_models
   $ mkdir -p ../../models/tao_pretrained_models/peoplenet && wget https://api.ngc.nvidia.com/v2/models/nvidia/tao/peoplenet/versions/pruned_v2.1/files/resnet34_peoplenet_pruned.etlt \
     -O ../../models/tao_pretrained_models/peoplenet/resnet34_peoplenet_pruned.etlt
 
diff --git a/apps/deepstream-imagedata-multistream/README b/apps/deepstream-imagedata-multistream/README
@@ -16,7 +16,7 @@
 ################################################################################
 
 Prerequisites:
-- DeepStreamSDK 6.0
+- DeepStreamSDK 6.0.1
 - Python 3.6
 - Gst-python
 - NumPy package
diff --git a/apps/deepstream-nvdsanalytics/README b/apps/deepstream-nvdsanalytics/README
@@ -16,7 +16,7 @@
 ################################################################################
 
 Prerequisites:
-- DeepStreamSDK 6.0
+- DeepStreamSDK 6.0.1
 - Python 3.6
 - Gst-python
 
diff --git a/apps/deepstream-opticalflow/README b/apps/deepstream-opticalflow/README
@@ -16,7 +16,7 @@
 ################################################################################
 
 Prerequisites:
-- DeepStreamSDK 6.0
+- DeepStreamSDK 6.0.1
 - Python 3
 - Gst-python
 - NumPy package
diff --git a/apps/deepstream-rtsp-in-rtsp-out/README b/apps/deepstream-rtsp-in-rtsp-out/README
@@ -16,7 +16,7 @@
 ################################################################################
 
 Prequisites:
-- DeepStreamSDK 6.0
+- DeepStreamSDK 6.0.1
 - Python 3.6+
 - Gst-python
 - GstRtspServer
diff --git a/apps/deepstream-segmentation/README b/apps/deepstream-segmentation/README
@@ -16,7 +16,7 @@
 ################################################################################
 
 Prerequisites:
-- DeepStreamSDK 6.0
+- DeepStreamSDK 6.0.1
 - Python 3.6
 - Gst-python
 - NumPy package
diff --git a/apps/deepstream-ssd-parser/README b/apps/deepstream-ssd-parser/README
@@ -16,7 +16,7 @@
 ################################################################################
 
 Prequisites:
-- DeepStreamSDK 6.0
+- DeepStreamSDK 6.0.1
 - NVIDIA Triton Inference Server
 - Python 3.6
 - Gst-python
diff --git a/apps/deepstream-test1-rtsp-out/README b/apps/deepstream-test1-rtsp-out/README
@@ -16,7 +16,7 @@
 ################################################################################
 
 Prequisites:
-- DeepStreamSDK 6.0
+- DeepStreamSDK 6.0.1
 - Python 3.6
 - Gst-python
 - GstRtspServer
diff --git a/apps/deepstream-test1-usbcam/README b/apps/deepstream-test1-usbcam/README
@@ -16,7 +16,7 @@
 ################################################################################
 
 Prequisites:
-- DeepStreamSDK 6.0
+- DeepStreamSDK 6.0.1
 - Python 3.6
 - Gst-python
 
diff --git a/apps/deepstream-test1/README b/apps/deepstream-test1/README
@@ -16,7 +16,7 @@
 ################################################################################
 
 Prequisites:
-- DeepStreamSDK 6.0
+- DeepStreamSDK 6.0.1
 - Python 3.6
 - Gst-python
 
diff --git a/apps/deepstream-test2/README b/apps/deepstream-test2/README
@@ -16,7 +16,7 @@
 ################################################################################
 
 Prequisites:
-- DeepStreamSDK 6.0
+- DeepStreamSDK 6.0.1
 - Python 3.6
 - Gst-python
 
diff --git a/apps/deepstream-test3/README b/apps/deepstream-test3/README
@@ -16,7 +16,7 @@
 ################################################################################
 
 Prerequisites:
-- DeepStreamSDK 6.0
+- DeepStreamSDK 6.0.1
 - Python 3.6
 - Gst-python
 
diff --git a/apps/deepstream-test3/deepstream_test_3.py b/apps/deepstream-test3/deepstream_test_3.py
@@ -140,6 +140,10 @@ 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 "source" in name:
+        Object.set_property("drop-on-latency", True)
+
+
 def create_source_bin(index,uri):
     print("Creating source bin")
 
diff --git a/apps/deepstream-test3/dstest3_pgie_config.txt b/apps/deepstream-test3/dstest3_pgie_config.txt
@@ -69,8 +69,9 @@ num-detected-classes=4
 interval=0
 gie-unique-id=1
 output-blob-names=conv2d_bbox;conv2d_cov/Sigmoid
+cluster-mode=2
 
 [class-attrs-all]
 pre-cluster-threshold=0.2
-eps=0.2
-group-threshold=1
+topk=20
+nms-iou-threshold=0.5
diff --git a/apps/deepstream-test4/README b/apps/deepstream-test4/README
@@ -16,7 +16,7 @@
 ################################################################################
 
 Prerequisites:
-- DeepStreamSDK 6.0
+- DeepStreamSDK 6.0.1
 - Python 3.6
 - Gst-python
 
diff --git a/apps/runtime_source_add_delete/README b/apps/runtime_source_add_delete/README
@@ -16,7 +16,7 @@
 ################################################################################
 
 Prequisites:
-- DeepStreamSDK 6.0
+- DeepStreamSDK 6.0.1
 - Python 3.6
 - Gst-python
 
diff --git a/bindings/README.md b/bindings/README.md
@@ -27,6 +27,14 @@ apt install python3-gi python3-dev python3-gst-1.0 python-gi-dev git python-dev
 git submodule update --init
 ```
 ### 2.3 Installing Gst-python
+
+Following commands ensure we add the new certificates that gst-python git server now uses:
+```
+sudo apt-get install -y apt-transport-https ca-certificates -y
+sudo update-ca-certificates
+```
+
+Build and install gst-python:
 ```
 cd 3rdparty/gst-python/
 ./autogen.sh
@@ -38,7 +46,7 @@ Go to https://developer.nvidia.com/deepstream-sdk, download and install Deepstre
 
 ## 3 - Building the bindings
 
-### 3.1 Quick build (x86-ubuntu-18.04 | python 3.6 | Deepstream 6.0)
+### 3.1 Quick build (x86-ubuntu-18.04 | python 3.6 | Deepstream 6.0.1)
 ```
 cd deepstream_python_apps/bindings
 mkdir build
@@ -47,7 +55,7 @@ cmake ..
 make
 ```
 
-### 3.1.1 Quick build (x86-ubuntu-20.04 | python 3.8 | Deepstream 6.0)
+### 3.1.1 Quick build (x86-ubuntu-20.04 | python 3.8 | Deepstream 6.0.1)
 
 ```
 cd deepstream_python_apps/bindings
@@ -70,7 +78,7 @@ cmake [-D<var>=<value> [-D<var>=<value> [-D<var>=<value> ... ]]]
 
 | Var | Default value | Purpose | Available values
 |-----|:-------------:|---------|:----------------:
-| DS_VERSION | 6.0 | Used to determine default deepstream library path | should match to the deepstream version installed on your computer
+| DS_VERSION | 6.0.1 | Used to determine default deepstream library path | should match to the deepstream version installed on your computer
 | PYTHON_MAJOR_VERSION | 3 | Used to set the python version used for the bindings | 3
 | PYTHON_MINOR_VERSION | 6 | Used to set the python version used for the bindings | 6, 8
 | PIP_PLATFORM | linux_x86_64 | Used to select the target architecture to compile the bindings | linux_x86_64, linux_aarch64
@@ -107,21 +115,21 @@ sudo apt-get install qemu binfmt-support qemu-user-static
 docker run --rm --privileged dockerhub.nvidia.com/multiarch/qemu-user-static --reset -p yes
 
 # Verify qemu installation
-docker run --rm -t nvcr.io/nvidia/deepstream-l4t:6.0-base uname -m
+docker run --rm -t docker pull nvcr.io/nvidia/deepstream:6.0.1-samples uname -m
 #aarch64
 ```
 
-#### 3.3.2 Download the JetPack SDK 4.6
+#### 3.3.2 Download the JetPack SDK 4.6.1
 1. Download and install the [NVIDIA SDK manager](https://developer.nvidia.com/nvidia-sdk-manager)
 2. Launch the SDK Manager and login with your NVIDIA developer account.
-3. Select the platform and target OS (example: Jetson AGX Xavier, `Linux Jetpack 4.6`) and click Continue.
+3. Select the platform and target OS (example: Jetson AGX Xavier, `Linux Jetpack 4.6.1`) and click Continue.
 4. Under `Download & Install Options` change the download folder and select `Download now, Install later`. Agree to the license terms and click Continue.
 5. Go to the download folder, and run:
 
 ```bash
 # path/to/deepstream_python_apps is the path where you downloaded the deepstream_python_apps repository
 mkdir -p path/to/deepstream_python_apps/bindings/docker/jetpack_files
-mv nvidia/sdkm_downloads/* path/to/deepstream_python_apps/bindings/docker/jetpack_files
+mv ~/Downloads/nvidia/sdkm_downloads/* path/to/deepstream_python_apps/bindings/docker/jetpack_files
 ```
 
 #### 3.3.3 Generate the cross-compile build container
@@ -130,7 +138,7 @@ Below command generates the build container
 
 ```bash
 # Make sure you are in deepstream_python_apps/bindings directory
-docker build --tag=deepstream-6.0-ubuntu18.04-python-l4t -f qemu_docker/ubuntu-cross-aarch64.Dockerfile .
+docker build --tag=deepstream-6.0.1-ubuntu18.04-python-l4t -f qemu_docker/ubuntu-cross-aarch64.Dockerfile .
 ```
 
 #### 3.3.4 Launch the cross-compile build container
@@ -140,7 +148,7 @@ docker build --tag=deepstream-6.0-ubuntu18.04-python-l4t -f qemu_docker/ubuntu-c
 mkdir export_pyds
 
 # Make sure the tag matches the one from Generate step above
-docker run -it -v $PWD/export_pyds:/export_pyds deepstream-6.0-ubuntu18.04-python-l4t bash
+docker run -it -v $PWD/export_pyds:/export_pyds deepstream-6.0.1-ubuntu18.04-python-l4t bash
 ```
 
 #### 3.3.5 Build DeepStreamSDK python bindings
@@ -178,6 +186,7 @@ Build output is generated in the created export_pyds directory (deepstream_pytho
 
 ### 4.1 Installing the pip wheel
 ```
+apt install libgirepository1.0-dev
 pip3 install ./pyds-1.1.0-py3-none*.whl
 ```
 
diff --git a/bindings/qemu_docker/ubuntu-cross-aarch64.Dockerfile b/bindings/qemu_docker/ubuntu-cross-aarch64.Dockerfile
@@ -13,7 +13,7 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-FROM nvcr.io/nvidia/deepstream-l4t:6.0-samples
+FROM nvcr.io/nvidia/deepstream:6.0.1-samples
 LABEL maintainer="NVIDIA CORPORATION"
 
 # Set timezone.
@@ -73,11 +73,11 @@ RUN cd /usr/local/bin &&\
 RUN pip3 install --upgrade pip
 RUN pip3 install setuptools>=41.0.0
 
-COPY docker/jetpack_files/Jetson_Linux_R32*aarch64.tbz2 /bsp_files/
+COPY docker/jetpack_files/Jetson*Linux_R32*aarch64.tbz2 /bsp_files/
 
 # Copy libs from BSP
 RUN cd /bsp_files \
-    && tar -jxpf Jetson_Linux_R32*aarch64.tbz2 \
+    && tar -jxpf Jetson*Linux_R32*aarch64.tbz2 \
     && cd Linux_for_Tegra/nv_tegra \
     && tar -jxpf nvidia_drivers.tbz2 \
     && cp -aprf usr/lib/aarch64-linux-gnu/tegra/libnvbuf*.so.1.0.0 /opt/nvidia/deepstream/deepstream/lib/ \
diff --git a/bindings/src/bindnvdsinfer.cpp b/bindings/src/bindnvdsinfer.cpp
@@ -199,6 +199,7 @@ namespace pydeepstream {
         py::class_<NvDsInferTensorMeta>(m, "NvDsInferTensorMeta",
                                         pydsdoc::NvInferDoc::NvDsInferTensorMetaDoc::descr)
                 .def(py::init<>())
+                .def_readonly("network_info", &NvDsInferTensorMeta::network_info)
                 .def_readonly("unique_id", &NvDsInferTensorMeta::unique_id)
                 .def_readonly("num_output_layers",
                               &NvDsInferTensorMeta::num_output_layers)
@@ -255,4 +256,4 @@ namespace pydeepstream {
 
     }
 
-}
+}
diff --git a/docs/conf.py b/docs/conf.py
@@ -36,9 +36,9 @@
 import pyds
 
 project = 'Deepstream'
-copyright = '2019-2021, NVIDIA.'
+copyright = '2019-2022, NVIDIA.'
 author = 'NVIDIA'
-version = 'Deepstream Version: 6.0 GA'
+version = 'Deepstream Version: 6.0.1'
 release = version
 
 
