pytorch_geometric
pytorch_geometric_temporal
pytorch_geometric | pytorch_geometric_temporal | |
---|---|---|
9 | 18 | |
20,154 | 2,491 | |
1.3% | - | |
9.8 | 1.8 | |
5 days ago | 20 days ago | |
Python | Python | |
MIT License | MIT License |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
pytorch_geometric
- Please help I'm suffering | RuntimeError: mat1 and mat2 must have the same dtype
-
Looking for Point Cloud deep learning, training sources
https://github.com/pyg-team/pytorch_geometric/tree/master/examples any of the scripts ending in _segmentation.py can be used for semantic segmentation of point clouds
- Why is the loss not decreasing with Pytorch Geometric GATv2Conv (and GATconv) ??
-
MetaPath2Vec from Pytorch geometric with HeteroData Dataset
Here the code I'm referring to: https://github.com/pyg-team/pytorch_geometric/blob/master/examples/hetero/metapath2vec.py
-
[N] PyG 2.3.0 released: PyTorch 2.0 support, native sparse tensor support, explainability and accelerations
Today version 2.3 got released: https://github.com/pyg-team/pytorch_geometric/releases/tag/2.3.0
-
Custom Point Cloud semantic segmentation
Here is a working example for semantic segmentation with pointnet++ using PyTorch geometric. There are equivalent scripts for dgcnn, randlanet, point transformer in the same folder https://github.com/pyg-team/pytorch_geometric/blob/master/examples/pointnet2_segmentation.py
-
RL Agent Library to use graph in spaces
I don't know if any RL library includes an already implemented agent that can process graphs. However there are a number of deep learning frameworks that can help with the implementation of graph neural networks, especially Graph Nets (based on Tensorflow) and PyTorch Geometric. You might need to modify an existing RL agent to make use of one of these frameworks. If you are not familiar with GNNs you can look up these surveys. This article may also be of interest to you: it tackles graph-based environments, and the paper's code is available (it has a custom implementation of A2C and uses PyTorch Geometric -- btw it doesn't use Gym's space.graph since this feature is very recent in Gym).
-
TensorFlow Graph Neural Networks
Meanwhile, PyTorch-Geometric is 3 years old and 13K stars on Github.
https://github.com/pyg-team/pytorch_geometric
-
[D] Asking for ideas on Matrix of only 0/1 values as inputs and real value outputs
A pytorch implementation: https://github.com/rusty1s/pytorch_geometric
pytorch_geometric_temporal
-
Ask HN: ML Papers to Implement
I have done this a few times now. Alone (e.g. https://github.com/paulmorio/geo2dr) and in collaboration with others (e.g. https://github.com/benedekrozemberczki/pytorch_geometric_tem...) primarily as a way to learn about the methods I was interested in from a research perspective whilst improving my skills in software engineering. I am still learning.
Starting out I would recommend implementing fundamental building blocks within whatever 'subculture' of ML you are interested in whether that be DL, kernel methods, probabilistic models, etc.
Let's say you are interested in deep learning methods (as that's something I could at least speak more confidently about). In that case build yourself an MLP layer, then an RNN layer, then a GNN layer, then a CNN layer, and an attention layer along with some full models with those layers on some case studies exhibiting different data modalities (images, graphs, signals). This should give you a feel for the assumptions driving the inductive biases in each layer and what motivates their existence (vs. an MLP). It also gives you the all the building blocks you can then extend to build every other DL layer+model out there. Another reason is that these fundamental building blocks have been implemented many times so you have a reference to look to when you get stuck.
On that note: here are some fun GNN papers to implement in order of increasing difficulty (try building using vanilla PyTorch/Jax instead of PyG).
- GitHub - benedekrozemberczki/pytorch_geometric_temporal: PyTorch Geometric Temporal: Spatiotemporal Signal Processing with Neural Machine Learning Models (CIKM 2021)
- PyTorch Geometric Temporal 0.37
- PyTorch Geometric Temporal - Spatiotemporal Signal Processing with Neural Machine Learning Models
- [P] PyTorch Geometric Temporal
- Show HN: Deep Learning for Windmill Output Forecasting with PyTorch
-
[R] PyTorch Geometric Temporal: Spatiotemporal Signal Processing with Neural Machine Learning Models
Repo: https://github.com/benedekrozemberczki/pytorch_geometric_temporal
- PyTorch Geometric Temporal 0.27
- Show HN: Machine Learning on Spatiotemporal Data – PyTorch Geometric Temporal
- PyTorch Geometric Temporal
What are some alternatives?
dgl - Python package built to ease deep learning on graph, on top of existing DL frameworks.
osmnx - OSMnx is a Python package to easily download, model, analyze, and visualize street networks and other geospatial features from OpenStreetMap.
gnn-lspe - Source code for GNN-LSPE (Graph Neural Networks with Learnable Structural and Positional Representations), ICLR 2022
GeometricFlux.jl - Geometric Deep Learning for Flux
torchdrug - A powerful and flexible machine learning platform for drug discovery
deep_gcns_torch - Pytorch Repo for DeepGCNs (ICCV'2019 Oral, TPAMI'2021), DeeperGCN (arXiv'2020) and GNN1000(ICML'2021): https://www.deepgcns.org
graphein - Protein Graph Library
pytorch_geometric - Graph Neural Network Library for PyTorch [Moved to: https://github.com/pyg-team/pytorch_geometric]
gnn - TensorFlow GNN is a library to build Graph Neural Networks on the TensorFlow platform.
sgas - SGAS: Sequential Greedy Architecture Search (CVPR'2020) https://www.deepgcns.org/auto/sgas
awesome-graph-classification - A collection of important graph embedding, classification and representation learning papers with implementations.