Xuanlin (Simon) Li

icon indicating a website link https://xuanlinli17.github.io

icon location San Diego, CA icon location Building generalist robotic and vision-language algorithms & systems that work well.

Results 2 issues of Xuanlin (Simon) Li

EfficientViT-SAM TensorRT export error due to invalid node (temp solution by monkey patching original sam repo)

When converting the EfficientViT-SAM model from torch to ONNX to TensorRT with latest torch version (2.2), I encounter the following errors while converting from ONNX to TensorRT: ``` [03/08/2024-23:29:49] [E]...

Add Owlv2; Add option to use owlvit / owlv2's image preprocessing procedure (the roi_align in current implementation processes images differently and results in distribution shifts and subpar performance)

- Factor in a bug found by https://github.com/NVIDIA-AI-IOT/nanoowl/pull/20 - Add Owlv2 - Add an option (`no_roi_align`) in the `OwlPredictor` class of `nanoowl/owl_predictor.py` to use the original owlvit / owlv2 implementation's...