Sebastian Janampa Rojas

Hi, Could you provide some information and code on how to do the deduplication? More specifically this part ``` Considering only neighbors with a similarity >0.6, we extract the connected...

Hello, Thanks for your work. I was reading the D-FINE paper, and it is mentioned that D-FINE-L was trained for 72 epochs, but in the code, I found this https://github.com/Peterande/D-FINE/blob/4a1f73a8bcfac736a88abde9596d87f116d780a7/configs/dfine/dfine_hgnetv2_l_coco.yml#L34-L44...

trt conversion

6

Hello, Thanks for the incredible work you've done. I tried to convert the model to tensorrt fp 16, but I encountered a problem with segmentation. However, if I remove --fp16,...

Question about discrite sampling in RT-DETRv2

5

Hello, I love your work. I have a question regarding the discrete sampling. You state on the paper: ``` we propose an optional discrete_sample operator to replace the grid_sample, thus...

### What is the feature? Hi, Could you share the FLOPs information for RTMO models. I tried to install the library in colab and on my PC but it failed....

Hello MoGe team, Thanks for such great work. In the GitHub repo, you mention that MoGe can recover intrinsic camera parameters. I wonder if it can also estimate extrinsic camera...