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

DeepStream Libraries is hosted as a part of the NVIDIA/DeepStream GitHub mono-repo. Clone the mono-repo and change into the deepstream_libraries directory:

$ git clone https://github.com/NVIDIA/DeepStream.git
$ cd DeepStream/deepstream_libraries

2. Install System Dependencies

$ sudo sh scripts/install_sys_pkgs.sh

3. Download Sample Data

$ sh scripts/download_data.sh

4. 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.

5. Install Python Dependencies

$ sh scripts/install_python_pkgs.sh

DeepStream Libraries Installation

1. Download the DeepStream Libraries wheel file from the GitHub mono-repo release assets.

• Download the deepstream_libraries-1.4-cp312-cp312-linux_x86_64.whl wheel file from this release

2. Install DeepStream Libraries package.

$ pip3 install deepstream_libraries-1.4-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 (using CodeStream API)
  with open("path/to/image.jpg", "rb") as f:
      image_bytes = f.read()
  code_stream = nvimgcodec.CodeStream(image_bytes)
  inputImage = decoder.decode(code_stream)
  # 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

Additional References and Applications

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

• CVCUDA
• NvImageCodec
• PyNvVideoCodec