-
As per the title, was wondering if there is a way of using different pad values for different masks? My use case is, for example, to pad a segmentation mask with one value and a depth mask with a diff…
-
**Is your feature request related to a problem? Please describe.**
We have the following to port:
- [x] 2d_autoencoderkl --> #1823
- [x] 2d_controlnet --> #1815
- [x] 2d_ddpm --> #1814
- [ ] …
-
@NielsRogge Thanks a lot for your tutorial on how to fientune SAM!
I am trying to finetune SAM for multiclass segmentation following your notebook.
Everything went fine until I create the dataload…
-
I have searched related issues but cannot get the expected help.
I want to train my custom dataset for instance segmentation using Improved HTC with DB-Swin-L as backbone. But I am facing the above…
-
With `get_segmentation_learner(architecture_name='hrnet', backbone_name='hrnet_w18')`.
Using the following callback to save the models during training:
`SaveModelCallback(monitor='dice_multi', fna…
-
Related: https://github.com/iterative/dvc/issues/10198, https://github.com/iterative/vscode-dvc/issues/4917
We need a way to log bounding boxes (and maybe later other annotations like segmentation …
-
I trying to train some DAPI nucleus images (22 images/masks with about 100 of objects labelled) with Startdist 3D using modified jupiter-notebook scripts examples(images folders). The masks have been …
-
Hi, thank you for the excellent work! Xtreme is the most powerful open-source LiDAR annotation tool available online. I am curious if there is any ongoing effort to support per-point LiDAR annotation …
-
https://arxiv.org/abs/2206.02777
-
I noticed that when I change the reshape from
https://github.com/TianzhongSong/Person-Segmentation-Keras/blob/master/models/unet.py#L71
into:
conv11 = Reshape((input_height * input_width, nClasse…