DeepStream Libraries#

DeepStream Libraries provide CVCUDA, NvImageCodec, and PyNvVideoCodec modules as Python APIs to easily integrate into custom frameworks. Developers can build complete Python applications with fully accelerated components leveraging intuitive Python APIs. Most of the DeepStream Libraries building blocks and their Python APIs are available today as standalone packages. DeepStream Libraries provide a way for Python developers to install these packages with a single installer. All these packages are built against the same CUDA version and validated with the specified driver version. Reference applications are provided to demonstrate the usage of Python APIs.

DeepStream Libraries Repository Setup#

Follow these steps to set up your environment for running sample applications:

  1. Clone Repository

$ git clone https://github.com/NVIDIA-AI-IOT/deepstream_libraries.git
$ cd deepstream_libraries

  1. Install System Dependencies

$ sudo sh scripts/install_sys_pkgs.sh

  1. Download Sample Data

$ sh scripts/download_data.sh

  1. Setup Python Virtual Environment

# Create virtual environment
$ python3 -m venv deepstream_libraries_env

# Activate virtual environment
$ source deepstream_libraries_env/bin/activate

# Verify activation
$ which python3  # Should point to virtual environment

Note: Activate the virtual environment for Python dependencies and wheel installation, and in each new terminal session.

  1. Install Python Dependencies

$ sh scripts/install_python_pkgs.sh

DeepStream Libraries Installation#

  1. Download DeepStream Libraries wheel file from NGC.

  • Download wheel file from this NGC link

  1. Install DeepStream Libraries package.

$ pip3 install deepstream_libraries-1.2-cp312-cp312-linux_x86_64.whl

Getting Started with DeepStream Libraries APIs#

We can use DeepStream Libraries API’s to create an application.

Consider the below reference example:

  • Read an image from the given file path using NvImageCodec

  • Resize the image with specified dimensions and Cubic interpolation method using CVCUDA

  • Align output dimensions to ensure compatibility with nvImageCodec

  • Save the resized image using NvImageCodec

    # Import necessary libraries
import cvcuda
from nvidia import nvimgcodec

# Create Decoder
decoder = nvimgcodec.Decoder()

# Read image with nvImageCodec
inputImage = decoder.read("path/to/image.jpg")

# Pass it to cvcuda using as_tensor
nvcvInputTensor = cvcuda.as_tensor(inputImage, "HWC")

# Align output dimensions to 32-byte boundaries for nvImageCodec compatibility
output_width, output_height, alignment = 320, 240 , 32
aligned_width, aligned_height = ((output_width + alignment - 1) // alignment) * alignment , ((output_height + alignment - 1) // alignment) * alignment

# Resize with cvcuda using aligned dimensions
cvcuda_stream = cvcuda.Stream()
with cvcuda_stream:
    nvcvResizeTensor = cvcuda.resize(nvcvInputTensor,(aligned_height, aligned_width, 3), cvcuda.Interp.CUBIC)

# Write with nvImageCodec
encoder = nvimgcodec.Encoder()
output_image_path = "output.jpg"
encoder.write(output_image_path, nvimgcodec.as_image(nvcvResizeTensor.cuda(), cuda_stream = cvcuda_stream.handle))

Sample Applications#

DeepStream Libraries Sample Apps#

Application

Description

Classification

A CUDA-accelerated image and video classification pipeline integrating PyTorch or TensorRT for efficient processing on NVIDIA GPUs

Object-Detection

GPU accelerated Object detection using CV-CUDA library with TensorFlow or TensorRT

Segmentation

GPU accelerated Semantic segmentation by utilizing the CV-CUDA library with PyTorch or TensorRT

Resize-Image

A sample app that decodes, resizes, and encodes images using the CVCUDA and NvImageCodec Python API’s

Decode-Video

Decodes encoded bitstreams using PyNvVideoCodec decode APIs

Encode-Video

Encodes a raw YUV file using PyNvVideoCodec encode APIs

Transcode-Video

Transcodes the video files using PyNvVideoCodec API’s

Additional References and Applications#

For more references and application please refer to the below link: