-
Hello,
I would like to contribute to a tutorial on [Hyperbolic Vision Transformers](https://arxiv.org/abs/2203.10833) by Ermolov, A. et al (2022).
The paper describes a vision transformer with …
-
It's probably worth thinking about some of the most common plots users might want to make related to manifolds and see if we can identify a small subset of utility plotting recipes we could provide th…
-
I wonder which topic is studied on Facebook.
Let's Go.
https://research.fb.com/
h…
-
Post a link for a "possibility" reading of your own on the topic of Network & Table Learning [for week 6], accompanied by a 300-400 word reflection that: 1) briefly summarizes the article (e.g., as we…
lkcao updated
2 years ago
-
Hello, I am interested in exploring the concept of periodicity in art and mathematics, and I have a specific idea that I would like to formalize and express mathematically. My idea is based on the con…
-
The document says `workers` (int, optional) – Number of threads to use for training the model.
https://radimrehurek.com/gensim/models/poincare.html
But there is no implementation for multi-threads i…
-
I'm trying to use my own data in tsv format but I have a problem:
The console returns me this message:
"./poincare-embeddings/model.py", line 156, in __init__ assert len(objects) == nents, 'Num…
-
Hello! First, great package! It has been a delight to use. One thing I have noticed is that the performance on GPU seems a bit off. To embed a graph of 15k nodes (~100k edges) and modest parameters (d…
-
-
Batch size is 2048. Getting the training data from the q I see
x_train, y_train = train_q.get()
print('X.. ' + str(x_train.shape) + ' Y.. ' + str(y_train.shape))
X.. (2048, 2980) Y.…