-
## 🐛 Bug
I wanted to use aim for logging the process of the following task:
https://lightning-flash.readthedocs.io/en/stable/reference/semantic_segmentation.html
flash is built up of pytorch-l…
-
## Description
When converting ONNX model, I get an error:
[Error (Could not find any implementation for node ArgMax_260.)](https://forums.developer.nvidia.com/t/error-could-not-find-any-implementat…
-
### Checklist
- [X] I have searched for [similar issues](https://github.com/isl-org/Open3D-ML/issues).
- [X] I have tested with the [latest development wheel](http://www.open3d.org/docs/latest/get…
-
While trying to use the multi-raster source with input rasters of different type (float32 and float64), I had to write a raster transformer to make all of the sub-raster sources the same type (which …
-
I'm trying to put trees in my scene where I am detecting objects. When applying material to the trees (specifically the leaves), the transparent areas aren't actually transparent. This is because the …
-
Maybe icevision does not support classification task and SemanticSegmentation task now？Do you have any plans to add this features or can you give me some clues to do that？
-
Hello, first of all congratulations for your incredible work. Currently I have accurately reconstructed indoor scenes using Bundlefusion, obtaining similar results to Scannet's 3D dataset models. In t…
-
## 🐛 Bug
When training semantic segmentation ,the training process just hangs after a given amount of steps.
I have tried various different heads/backbones, batch sizes, finetuning strategies, …
-
## ❓ Questions and Help
#### What is your question?
I am trying to train a `SemanticSegmentation()` task. Some metrics (not the loss) such as the `torchmetrics.MeanSquaredError()` and other regres…
-
Hello, I get the following error when attempting to train a DeeplabV3 model for a simple foreground/background segmentation. 1024x1024 images are being fed to the model, annotations are as described i…