-
## 🚀 Feature
I'd like to add some convenience keyword args to `add_labels`, `add_points`, and `add_shapes` to make instantiating those layers with no data easier.
The use case is that someone has …
-
we need to get from the acquired markers the observation vector → **Data Labeling**
- the state space S is given by `S=[p_t, p_g, p_c]`, so we need to identify which marker is part of which object a…
-
Hi @miquelduranfrigola
As this is organised now, it basically uses three modules:
- Docking (code embedded within the repository)
- Conformer generation (either from the embedded code in the rep…
-
As discussed in #177, we should reshape the coefficient matrices (which are currently in an interleaved 2D array) into a 3D array with shape (m, m, p).
cbrnr updated
7 years ago
-
Thank you for your repo.
When I ran the example.ipynb:
---------------------------------------------------------------------------
import os
from miqsar.utils import calc_3d_pmapper
#Choose d…
-
Ideally, we should use blender to create a 3D plane of the exact eye glass shape
-
write a function for creating kernel density plots, along the lines of seaborn's kdeplot: http://seaborn.pydata.org/generated/seaborn.kdeplot.html
in 3d, each group's distribution would be plotted …
-
Hi, as far as I know, with SAM1, we cannot use both multiple boxes and multiple points at the same time to segment one image. Can we do this using SAM2? If so, can anyone please share the code? Apprec…
-
I have a time of flight camera, that is I get a depth image as raw data from my camera, after calibration, is `mrcal.unprocject` the supposed way to compute the corresponding point cloud, e.g. like th…
Baehn updated
3 months ago
-
recently I've successfully replace unet2d with [U-Dit](https://github.com/YuchuanTian/U-DiT) which claims to have less compute and better performance, and also changing the VAE to *stabilityai/sd-vae-…