Daniel M. García-Ocaña Hernández
Daniel M. García-Ocaña Hernández
### Checklist - [X] Code issue ### What happened? Hi, I was reviewing `rng.py` script due to some inconsistencies in my generated images, and I came across a code snippet...
### Checklist - [X] I have searched related issues but cannot get the expected help. - [X] 2. I have read the [FAQ documentation](https://github.com/open-mmlab/mmdeploy/tree/main/docs/en/faq.md) but cannot get the expected help....
Hi! First of all, thanks a lot for this huge contribution. I've been testing Florence-2 recently and believe I've found a significant bug, specifically in the [predict() method](https://github.com/autodistill/autodistill-florence-2/blob/c984522e7ba7e61d28d361f84b81532d0779d06b/autodistill_florence_2/model.py#L100): ```python ontology_classes...
### System Info Hi, When will the new NVILA models be supported? As current example in [multimodal readme](https://github.com/NVIDIA/TensorRT-LLM/tree/main/examples/multimodal#llava-llava-next-llava-onevision-and-vila) is with VILA + Llama (and NVILA is based on Qwen2) Many...
Hi, When running Co-DINO with ViT-L backbone, there seems to be a missing dependency, einops. It is imported [here](https://github.com/Sense-X/Co-DETR/blob/main/mmdet/models/backbones/vit.py#L38). Maybe it should be added to the requirements? Regards!
Hi everyone, I was testing Grounding Dino with SwinB backbone and I found that, unexpectedly, it detects less objects than Grounding Dino SwinT. For example, when asking for "light bulb",...
## Problem Description When processing videos provided as lists of frames (instead of file paths), the implementation applies resizing **twice** with incorrect pixel constraints, causing inconsistent behavior compared to file-path...