Do you have experience with Model optimization/compression/quantization methods such as ONNX/TensorRT?  If yes, please mention the project in brief.

Yes, I have experience with model optimization, compression, and quantization methods such as ONNX and TensorRT. In a recent project, I worked on optimizing a deep learning model for deployment on edge devices with limited computational resources. The goal was to reduce the model's size and computational requirements without sacrificing too much accuracy. I used ONNX to convert the model into an intermediate representation and then applied various compression techniques to reduce its size. Finally, I used TensorRT to optimize the model's inference performance on the target edge device. The project was successful in achieving significant model size reduction and improved inference speed while maintaining acceptable accuracy levels.