richardrl

Solving problems in batch

1

Does this library support solving qps in batch? E.g. see this post: https://stackoverflow.com/questions/73076452/solving-many-convex-programs-in-parallel

[Feature]: Mass delete runs

13

### Description It is very common while debugging code to perform many runs, which may be a few seconds long, but which ultimately fail due to code bugs. ### Suggested...

What's the recommended way to setup realnvp flow?

Asychronous multiple GPU multiple model training with shared replay buffer

1

Let's say we have multiple diffusion models, as in the Cascading diffusion model paper. Is there an easy way to setup training such that each conditional model is trained simultaneously...

New modalities

6

One of the stated design decisions from the readme was to support arbitrary modalities, not just images. I'm in the process of trying to adapt the code for 1D vectors...

How to fix mount permission issues

1

I am using maestral latest docker image with Ubuntu 18 host system. This is the recommended way to fix mount permission issues: `chown -R 1000 /mnt/dropbox` However, chowning a directory...

Manually set learning rate

2

Is there any way to manually set the learning rate instead of finding the LR using automatic search in steepest descent?

Installation error

10

``` >>> import torch Traceback (most recent call last): File "", line 1, in File "/home/richard/improbable/mctorch/torch/__init__.py", line 23, in from .version import __version__ ModuleNotFoundError: No module named 'torch.version' ``` Hi,...

Support for Sphere/SO(3)/SE(3)

6

Hi, is there support for these manifolds?

Default GPU Yaml file fails

4

In "linux-env-gpu.yml", it is trying to install: `- python=3.5.2 ` We need at least python3.6 to sucessfully install