Michał Tyszkiewicz
Michał Tyszkiewicz
**Describe the bug** This is more of a documentation issue than a "hard" bug, so please excuse no self-contained repro case. I can produce one if you deem it crucial...
I'm trying to understand [`divergence_approx`](https://github.com/stevenygd/PointFlow/blob/fd00fce0daa37453a1469c669a83c44bfb54c44d/models/odefunc.py#L9). I am not sure what exactly it is trying to compute, I suppose something related to the trace of the Jacobian, that is equation 7...
When I upload phone -> PC with firefox mobile and select multiple files at once, I instantly get a successful upload message but only some of the chosen files appear...
- OS: Ubuntu 16.04 - PyTorch version: 0.4.0 - How you installed PyTorch (conda, pip, source): conda - Python version: 3.6 - CUDA/cuDNN version: 9.0 - GPU models and configuration:...
To my best knowledge, you currently only accept `matches.h5` files with keys in form of `{filename1}-{filename2}`. I would request that support for `{filename1}/{filename2}` is added, which is interpreted by HDF...
* K3D version: 3.14 * Python version: 3.8 * Operating System: Linux/MacOS (reproduced on both) ### Description There is an issue with K3D alongside the latest versions of jupyterlab. Running...
## Summary I ran a script to render 4046 objects of class `02691156` from `ShapeNetCore.v2` and had the script crash on 3887th render with: ``` Assertion failed in /project/ext/drjit-core/ext/nanothread/src/queue.cpp:354: remain...
### Description of the model to be implemented My request regards not a model but rather an example of how to lift new transformations. There are [design docs](https://flax.readthedocs.io/en/latest/design_notes/lift.html) on lifted...
I tried installing and I am meeting the error below. Before I dig deeper I'd like to ask if it's maybe a known issue with M1 chips or rather something...
My question concerns [this line](https://github.com/yang-song/score_sde_pytorch/blob/cb1f359f4aadf0ff9a5e122fe8fffc9451fd6e44/controllable_generation.py#L73): ```python # Initial sample x = data * mask + sde.prior_sampling(data.shape).to(data.device) * (1. - mask) ``` Let's assume `data` is normalised to have approx `std=1`....