cimp-impl/README.md

C++ Tracker Implementation

This project implements a C++ version of the DiMP tracker, focusing on the bounding box regressor and classifier components.

Overview

The project consists of two main components:

1. BBRegressor: Implements the IoU (Intersection over Union) network for bounding box regression
2. Classifier: Implements the feature extraction for target classification

Requirements

• CMake (3.18 or higher)
• C++17 compatible compiler
• LibTorch (PyTorch C++ API)
• CUDA (optional, for GPU acceleration)

Building the Project

Automatic Build

The easiest way to build the project is to use the provided build script:

chmod +x build.sh
./build.sh

This will:

1. Check for CUDA availability
2. Download LibTorch if not already installed
3. Configure the project with CMake
4. Build the project
5. Install the executable to the bin/ directory

Manual Build

If you prefer to build manually:

mkdir -p build
cd build
cmake .. -DCMAKE_BUILD_TYPE=Release
cmake --build . --config Release

Running the Demo

To run the demo application:

# Set the library path to include LibTorch
LD_LIBRARY_PATH=$HOME/libtorch/lib:$LD_LIBRARY_PATH ./bin/tracking_demo

Or use the provided script:

./run_demo.sh

Project Structure

• cimp/: Main C++ implementation
  • bb_regressor/: Bounding box regressor implementation
  • classifier/: Feature extractor implementation
  • demo.cpp: Demo application
• exported_weights/: Directory containing exported PyTorch weights
  • backbone/: Backbone network weights
  • bb_regressor/: Bounding box regressor weights
  • classifier/: Classifier weights
• ltr/: Reference Python implementation
• bin/: Built executables

Known Issues

• The PrRoIPooling implementation requires CUDA, but there's a fallback CPU implementation
• Some CUDA operations may fail on certain GPU configurations; the code includes fallbacks

Comparing Python and C++ Implementations

To compare the outputs between Python and C++ implementations:

1. Run the Python implementation to generate reference outputs:

python demo.py

2. Run the C++ implementation:

./run_demo.sh

3. Compare the output statistics in the generated files:
   • bb_regressor_stats.txt
   • classifier_stats.txt

License

This project is licensed under the MIT License - see the LICENSE file for details.