Andrea Panizza
Andrea Panizza
I would like to understand how metrics are computed in MMSegmentation.v In particular, I would like to understand the logic behind these two functions: https://github.com/open-mmlab/mmsegmentation/blob/144dc3919e53d51921837e5a2a6d5ee656dccd7d/mmseg/core/evaluation/metrics.py#L26 https://github.com/open-mmlab/mmsegmentation/blob/144dc3919e53d51921837e5a2a6d5ee656dccd7d/mmseg/core/evaluation/metrics.py#L89 Is there a reference...
# Description This PR fixes an error in the documentation. Assuming the scores are ranked from highest to lowest until the conformity score of the true label is found, then...
Could you please update the MacOS wheels? The last one was released nearly 18 months ago, and it has Tensorflow 1.4 (!): https://github.com/mind/wheels/releases/tag/tf1.4-cpu-mac Thanks & regards
Hi, big fan of `visdat` and `naniar` here. I've been making a couple benchmarks for the new, very useful functions introduced in `naniar` 0.2.0. It seeems to me that `replace_with_na_all`...
Hi! Thanks for the great package, my work EDAs are better because of `naniar` & `visdat` :-D I like the lollypop plot generated by `gg_miss_var()` **a lot**, especially the faceting...
The [PyTorch Lightning example](https://github.com/benedekrozemberczki/pytorch_geometric_temporal/blob/master/examples/recurrent/lightning_example.py) uses a DCRNN, but I want to use a GConvLSTM. However, this layer doesn't return a single tensor, but three. How should I modify the `training_step`...
PyTorch Geometric Temporal supports a lot of Recurrent Graph Convolution layers. I have a static graph dataset, with ∼ 2000 timesteps and ∼ 500 nodes. Which Recurrent Graph Convolution should...
Hi, I have a small dataset (_N_ ~ 2000) of samples (**x**, y) where **x** ∈ ℝ²⁰, with very little noise. The 2000 samples are not completely independent, in the...
## Problem The documentation has a typo: the key bindings reference is empty https://markdown-all-in-one.github.io/docs/guide/key-binding.html#key-binding-reference ## How to reproduce Navigate to the page above and look for key bindings.
## Proposal **Visual Studio Code for the Web** is the web-based editor that powers `github.dev`. Being compatible with it can help the Markdown editing experience on GitHub in web browser....