vic

Tensorrt fp32 inference slower than pytorch on tesla T4 for GroundingDINO

3

## Description I convert groundingdino from torch to tensorrt on A100, which can accelarate 50% on inference. However, when I deploy the same model on T4, after I rebuild engine,...

question in "Real-time Transformer-based Open-Vocabulary Detection with Efficient Fusion Head"

1

Hello, author, your work is excellent. I have a question about tensorrt-groundingdino on your paper "Real-time Transformer-based Open-Vocabulary Detection with Efficient Fusion Head", I can only convert gd in tensorrt-fp32...

Fix dynamical batch inference bug

1

When multi-batch detr model is converted from pytorch to onnx, if max_per_img is smaller than num_quries, there will be an incorrect index for bbox_preds. Thanks for your contribution and we...