Collin McCarthy

I ran into this problem and ended up creating a function to convert strings to tuples so when `parser.parse_args()` is called it passes the tuples onto the `__parse_args()` and `__whitelist_cluster_commands()`...

Can we also handle the case for segmentation with datasets like PASCAL VOC, which has a "void" label of 255 but the number of classes is 21? I tried passing...

After reviewing the code it would make sense to leave it at whatever value was used when the "log-spaced continuous position bias method" was trained from scratch, so that would...

This is indirectly because `loss_by_feat()` isn't implemented for the instance segmentation head. That is, instance segmentation is only supported currently for inference. I don't think it is that difficult to...

Does mmdetection support instance segmentation training with rtmdet? Or just inference like mmyolo? -CollinOn Feb 6, 2024, at 6:19 PM, jlok ***@***.***> wrote: No update on this? Am I correct...

Hi @ryouchinsa, I noticed you are approximating the contour in a different way than this answer here - https://github.com/cocodataset/cocoapi/issues/476#issuecomment-871804850 Why are you using this: ``` contours, _ = cv2.findContours(m, cv2.RETR_EXTERNAL,...

Is this still a planned feature or WIP? Would love to be able to train the RTMDet-Ins model but I'm not 100% sure what changes I need to make. It...

@rose-jinyang Were you able to train rtmdet-ins-s or just perform inference? It appears only inference is implemented, but if I'm wrong please let me know!

I'm having the same issue. I use slurm to launch `wandb agent ` via the CLI interface and I noticed if a job gets pre-empted, when it resumes with the...

@dannygoldstein I can give you access to [this sweep](https://wandb.ai/sparse-dnn/sparse-dnn/sweeps/v5kt6bh3) if it helps, but I can't make it public. At the moment my workflow is Slurm -> Elastic launch (DDP) ->...