Comments (3)
Hi @screamer, is the MemoryError happening in the correct() function? You can take a look at the whole stack trace to make sure.
You might also try decreasing the batch size. I believe 256GB should be sufficient.
You can also try sketching-based integration for additional efficiency: https://github.com/brianhie/scanorama/blob/master/scanorama/scanorama.py#L147
Will close since this doesn't appear to be a bug with Scanorama, but please feel free to ask additional questions!
from scanorama.
Hello @brianhie , thanks for your fast replying. I used BATCH_SIZE=2000. It returns the same problem. It seems that the error was happening in the integrate() function, because I didn't see the results of print('Integrated panoramas in {:.3f}s'.format(time() - t0)). Could I solved it by use a smaller BATCH_SIZE like 500? or better to use the sketch option? It costs about 18 hours to test the error everytime.
from scanorama.
If your batch size is that low and you use the integrate() function I think 256 GB should be sufficient. Maybe sketch it with a very low amount (e.g., a sketch size of 1000) and see if that works?
from scanorama.
Related Issues (20)
- Much larger element cout in output matrix
- confusion about the calculation about KNN
- Data sets must be numpy array or scipy.sparse.csr_matrix, received type <class 'scipy.sparse._csc.csc_matrix'>. HOT 1
- scanorama from this repo vs scanpy external
- scanorama with reticulate - ERROR: Data sets must be numpy array or scipy.sparse.csr_matrix, received type <class 'str'>. HOT 2
- Can scanorama.correct() be used on raw data for batch correction HOT 1
- module 'scanorama' has no attribute
- Can we use it on several daatsets for which we're not sure about the normalization
- Running Scanorama in parallel with Reticulate
- "negative dimensions are not allowed" when integrating large dataset HOT 1
- Order of Samples leads to different expression data after Scanorama normalization HOT 1
- Kernel dies with 500GB memory HOT 2
- Error when taking the union of genes
- Broken tutorial link
- Memory not mapped
- The tutorial address has changed HOT 1
- Data sets must be numpy array or scipy.sparse.csr_matrix, received type <class 'anndata._core.views.SparseCSCView'>. HOT 1
- alignment scores outpout HOT 1
- Issue
- batch correction in label transfer
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 scanorama.