peabody124
peabody124
Currently set paths to analysis tools in: https://github.com/peabody124/PosePipeline/blob/main/pose_pipeline/env.py#L26 And path to data storage in: https://github.com/peabody124/PosePipeline/blob/main/pose_pipeline/pipeline.py#L19 The later should be set with the other DataJoint configuration settings, rather than the pipeline....
For any cases where code is changed, it would be very beneficial to store the timestamp for when rows are computed. This is easy to do using: ``` timestamp=CURRENT_TIMESTAMP :...
Making the lookup tables strings would simplify the code and using integers in the primary key provides no benefit. This would break the database layout though, or at least be...
Right now the analysis pipeline is standalone, which is somewhat of a strength. However, videos from experiments have their own organization structure that should be reflected and will benefit from...
The system would be much easier to use if there were instructions to create a Docker with Jupyter and all the analysis components. This system probably cannot be pushed to...
This is an implementation of https://arxiv.org/pdf/2204.07137.pdf Not sure if there is interest merging this into the main branch. This might be an algorithm worth supporting as it leverages the differentiable...
I was trying to extend the domain randomization examples to include changing collider shapes using the code below. However, the renderer doesn't pick up the changes. Specifically this occurs because...
I've tracked down a regression in the python bindings that causes a segafult when nimblephysics when from 0.8.77 to 0.8.78 This can be easily reproduced with: ``` import nimblephysics as...
I'm planning to make two changes to how we handle the bridging keypoints that would be a breaking change and require recomputing lots of things: - we should use the...