Comments (3)
Hi @HANSANGJUN,
Thank you for the question! There should be some degree of RAM usage increase during inference since we are creating a list that holds the results across all batches of the test set on which inference is being performed. However, the memory usage should not be very large. What sort of RAM usage numbers are you seeing? Also just to clarify, is this during inference on the validation or test set in train.py
or is this when running predict.py
?
Thanks,
Kyle
from chemprop.
I modified your code to combined with my algorithms, and I found caching mechanism
if cache: SMILES_TO_GRAPH[d.smiles] = mol_graph
filled my RAM.
I disallowed that mechanism. Thank you.
from chemprop.
Okay great, I'm glad you found that!
from chemprop.
Related Issues (20)
- [v2 QUESTION]: How to train model with two smiles inputs HOT 4
- convergence in hyperparameter optimization HOT 1
- [TODO]: push new tagged images to Docker Hub automatically for new releases
- [v2 BUG]: Bug in calculating the initial and final learning rates while using hpopt HOT 4
- combining "domain adaptation" technique and chemprop
- [v2 better design?]: Function override can cause unexpected and unclear featurization behavior HOT 10
- mat1 and mat2 shapes cannot be multiplied (64x2348 and 300x300) HOT 4
- How do I implement V_d into a trainer? HOT 6
- [v2 BUG]: no features generators in predict.py HOT 3
- [v2 QUESTION]: Getting D-MPNN Embedding without target values HOT 2
- [v1 QUESTION]: Conformal prediction in and out sets HOT 9
- [v2 BUG]: Binary-mcc not working as a --loss-function and --metrics HOT 9
- [v2 BUG]: The extra metrics calcualtions don't work for `MveFFN` and `EvidentialFFN`
- [v2 QUESTION]: Why does chemprop convert produce a ckpt file? HOT 1
- Question about interpretation HOT 8
- [v2 FEATURE]: Automatic device handling for loading trained models HOT 1
- transfer learning with Chemprop HOT 3
- [v2 BUG]: "RuntimeError: Detected the following values in `target`" during binary classification HOT 4
- [v2 BUG]: HOT 1
- [v2 BUG]: NaN target values set to 0.0 rather than being masked. HOT 1
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 chemprop.