-
Hi,
I am trying to do a version of example_gan.py in which both generator and discriminator admit a label that tells which number to generate/identify. This requires the the label to be untouched w…
-
When we use multiple gpus to do sampling with quiver in the mode of gpu sampling(graph stored in gpu memory), we found that the scalability is poor.
To be specific, we run the example code on redd…
-
## 🚀 Feature
We should integrate cugraph local storage into DGL to allow DGL to use faster single and multi-gpu cugraph sampling we are developing in cugraph.
This class will be a thin wrapper…
-
## 🚀 Feature
I would appreciate a feature that implements smart minibatching algorithms like https://arxiv.org/pdf/1905.07953.pdf for node level tasks.
## Motivation
I see currently batch_siz…
-
Hi Meng, thanks for sharing this repo - very nice work!
Could you add the code related to the Graph Generation experiments (section 5.2 in the paper)?
In particular I suppose you had to adapt the […
-
- [x] Implement a function that does Typed Sampling using graph Schema
- [x] Implement RESCAL https://icml.cc/2011/papers/438_icmlpaper.pdf
-
Hi @MalikTeng,
There is a potential issue with the F.grid_sample as it receives a ZYX ordered coordinate system instead of XYZ.
This was discussed here: https://discuss.pytorch.org/t/surprising-c…
-
For localization on a frozen map of 400 submaps, for instance on a map generated with default config from https://storage.googleapis.com/cartographer-public-data/bags/backpack_2d/b2-2015-02-16-1…
-
This issue is to implement DGI for graph classification. The original DGI paper (https://arxiv.org/pdf/1809.10341.pdf) proposes a method of doing this by randomly sampling a negative graph instead of …
-
i can use odom, but i can not use imu when i run cartographer 2D
OR when i use imu, it is disable for the TRAJECTORY_BUILDER_2D.use_online_correlative_scan_matching = true
thanks for every one's …