Comments (7)
Hi, the errors you are referring to are issues about MPS Apple hardware. We have seen the issue you are facing in multiVI in newer scvi-tools version. The main reason in our hands is that we have changed the default see in newer scvi-tools version. Do you fix the seed and still face the problem? Can you share the toy dataset (how large is it - ncells and file size)? It would be interesting to explore what updates in the TrainingPlan remove these errors.
from scvi-tools.
thanks for your answer! here is the toy dataset (approx 2000 cells by 4000 features)
i didn't include a seed but i will try that and let you know.
from scvi-tools.
Unfortunately, no success with explicit scvi.settings.seed
https://github.com/DendrouLab/panpipes/actions/runs/8114593332/job/22180588924?pr=201
from scvi-tools.
Hi @bio-la, sorry you're running into this issue. It looks like the issue might be slightly different than the Discourse threads you linked since the CI is running on Ubuntu, not macOS, so I'm guessing this is an issue unrelated to a PyTorch MPS build.
Could you try passing in a lower learning rate (maybe lr=1e-5
or lr=1e-6
) and see if that helps? Also, is this error occurring in the first epoch of training or later on? I wasn't able to find that info in the logs.
from scvi-tools.
thanks for your suggestions. here are my comments:
- i get the same error message on Ubuntu and Macos Intel chip. I wouldn't know why the effect is the same on M3 chips, if you speculate that the cause is not the same.
- the error appears at the first epoch of training
- changing lr from
1e-3
to1e-5
doesn't solve the issue,scvi 0.20.3
still works with the lower lr - i noticed that the conda install is now pulling
scvi 1.1.2
, still failing here.
I'm using this dataset
with the following parameters for Multivi:
MultiVI:
batch_covariate: dataset
model_args:
n_hidden : None
n_latent : None
#(bool,default: True)
region_factors : True
#{‘normal’, ‘ln’} (default: 'normal')
latent_distribution : 'normal'
#(bool,default: False)
deeply_inject_covariates : False
#(bool, default: False)
fully_paired : False
training_args:
#(default: 500)
max_epochs : 500
#float (default: 0.0001)
lr : 1.0e-05
#leave blanck for default str | int | bool | None (default: None)
use_gpu :
# float (default: 0.9)
train_size : 0.9
# leave blanck for default, float | None (default: None)
validation_size :
# int (default: 128)
batch_size : 128
#float (default: 0.001)
weight_decay : 0.001
#float (default: 1.0e-08)
eps : 1.0e-08
#bool (default: True)
early_stopping : True
#bool (default: True)
save_best : True
#leave blanck for default int | None (default: None)
check_val_every_n_epoch :
#leave blank for default int | None (default: None)
n_steps_kl_warmup :
# int | None (default: 50)
n_epochs_kl_warmup : 50
#bool (default: True)
adversarial_mixing : True
#leave blank for default dict | None (default: None)
training_plan : None
from scvi-tools.
Related Issues (20)
- Add workflow for releases HOT 1
- Consider adding tensor/array shape annotations with jaxtyping
- Remove `scvi.data.cellxgene`
- is there any way to sepcific the number of workers when using scvi in R ?
- Bug using "scvi-tools/tabula-sapiens-heart-stereoscope" hugging face scvi model - scvi-tools 1.0.4 HOT 1
- Enable custom splits in `DataSplitter` HOT 1
- Transfer mrVI to external
- ImportError: cannot import name 'sparse_csc_tensor' from 'torch' HOT 2
- Assess whether we should deprecate more `scvi.data` functions
- Enable custom dataloader usage with autotune
- Deprecate `scvi.train.SaveBestState` and `save_best` argument
- Release scvi-tools 1.1.2
- Enable checkpointing with autotune
- scvi ignoring GPU because of jax HOT 6
- Allow scArches to extend categorical covariates HOT 1
- ParserError: Error tokenizing data. C error: Expected 1 fields in line 52, saw 3 HOT 1
- Add feature to generate coordinates for `synthetic_iid` HOT 1
- Failing to train on multiple GPUs in jupyter notebook HOT 4
- TypeError with model.train() using R reticulate
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 scvi-tools.