RepNet-Vehicle-ReID (IGIE)

Model Description

The paper "Deep Relative Distance Learning: Tell the Difference Between Similar Vehicles" introduces a model named Deep Relative Distance Learning (DRDL), specifically designed for the problem of vehicle re-identification. DRDL employs a dual-branch deep convolutional network architecture, combined with a coupled clusters loss function and a mixed difference network structure, effectively mapping vehicle images into Euclidean space for similarity measurement.

Supported Environments

Model Preparation

Prepare Resources

Pretrained model: https://github.com/CaptainEven/RepNet-MDNet-VehicleReID

Dataset: https://www.pkuml.org/resources/pku-vehicleid.html to download the VehicleID dataset.

Install Dependencies

pip3 install -r requirements.txt

Model Conversion

python3 export.py --weight epoch_14.pth --output repnet.onnx

# Use onnxsim optimize onnx model
onnxsim repnet.onnx repnet_opt.onnx

Model Inference

export DATASETS_DIR=/Path/to/VehicleID/

FP16

# Accuracy
bash scripts/infer_repnet_fp16_accuracy.sh
# Performance
bash scripts/infer_repnet_fp16_performance.sh

Model Results

References

• RepNet-MDNet-VehicleReID