Comments (2)
I try to use this hyper-param to save the memory:
model = Equiformer(
dim=32,
depth=6,
l2_dist_attention=True,
reduce_dim_out=True,
dim_head=4,
heads=4,
single_headed_kv=True,
radial_hidden_dim=32,
num_neighbors=128,
)
But it still takes up much more memory than equifold.
from equiformer-pytorch.
Hi, I met with the same issue. My experiments show that the number of neighbors, the input length and the number of degrees influence a lot on GPU usages. I have been keeping track of this issue but see now it is closed. Any successful trick that you would kindly share to reduce the GPU usage? Thanks.
from equiformer-pytorch.
Related Issues (8)
- Specifying edge index / adjacency HOT 13
- TypeError: 'type' object is not subscriptable HOT 3
- Adapting Equiformer for Efficient Handling of Graphs with Sparse Matrix in COO format? HOT 4
- Dependency Conflict HOT 5
- Question About Graph Sparsity/Edges HOT 1
- Error when use equiformer-pytorch HOT 2
- equiformer v2 is out! HOT 9
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from equiformer-pytorch.