-
Creating a `DataArray` with a mixed binned and non-binned multi-dimensional coordinate is only possible if the binned dimension of the coordinate is last.
```python
import scipp as sc
import nump…
-
Hi! I'm trying to run the generate_point_cloud section of the code using VisSat for the Jacksonville Core3D data. But
it seems to error out in self.run_colmap_sfm_perspective() because the after_bun…
-
Hi, please add Deformed Implicit Field: Modeling 3D Shapes with Learned Dense Correspondence (https://arxiv.org/abs/2011.13650) which is a cvpr2021 poster paper.
It can be classified as 3d vision pap…
-
https://github.com/keras-team/keras/blob/aedad3986200b825d94f847d52bd6b81f0419a06/keras/layers/core.py#L776
The documentation of the dense layer claims to flatten the input if a tensor with rank > …
-
The documentation suggests that edge features (used by `ECCConv`, for instance) can be in sparse format to avoid padding large arrays with zeros. However, attempting to construct a `Graph` with `e` se…
-
I think it might be helpful if the users, on clicking the top menu tabs, get a definition of the category they have landed in.
For example, I think the word "Clavis" is not understandbale to those ex…
-
```
I think we all agree that having a means to record markers used in FACS sorting
of cells is an important and useful. But there is an ongoing issue in CL with
species specificity and these axiom…
-
#### Description
If I try and fit some data to a `ConstantModel` and then `plot` the results, I get a `TypeError`
###### A Minimal, Complete, and Verifiable example
```
import numpy as np
impor…
-
I'd like to implement a new loss for the keypoint head. For this loss, I need the xy-coordinates of the predicted keypoints. However, in `_forward_keypoint` and `keypoint_rcnn_loss`, I only have acces…
-
#### Describe the bug
VWRegressor provides very different performance for loss_function = 'quantile' , quantile_tau = 0.5 and loss_function = 'squared'
loss_function = 'squared' - provides very…